Support both esp_video and esp32_camera (#1671)

* Update project version to 2.2.1 and refactor camera component handling

- Incremented project version from 2.2.0 to 2.2.1 in CMakeLists.txt.
- Removed legacy esp32_camera component and replaced it with esp_video for ESP32-S3 and ESP32-P4 boards.
- Updated board implementations to utilize the new esp_video component, ensuring compatibility and improved functionality.
- Cleaned up Kconfig options related to camera selection, streamlining the configuration process.
- Enhanced camera initialization logic across various board files to support the new component structure.

* Refactor camera handling in AtomS3R CAM/M12 EchoBase board

- Replaced the legacy EspVideo component with the new Esp32Camera class for improved camera functionality.
- Updated camera initialization logic to utilize a more structured configuration approach, enhancing clarity and maintainability.
- Removed outdated comments and code related to the previous camera implementation in the README file.

* Update camera configuration for atoms3r-cam-m12-echo-base

- Removed outdated camera configuration options from config.json to streamline the setup.
- Retained essential partition table configuration for improved clarity.

* Enhance Esp32Camera functionality and memory management

- Added esp_timer.h for improved timing functionality.
- Streamlined camera initialization by removing redundant frame buffer setup and logging.
- Improved memory allocation for JPEG encoding and added error handling for unsupported pixel formats.
- Updated comments for clarity and consistency, ensuring better understanding of the code flow.

CMakeLists.txt

@@ -9,5 +9,5 @@ include($ENV{IDF_PATH}/tools/cmake/project.cmake)
 # "Trim" the build. Include the minimal set of components, main, and anything it depends on.
 idf_build_set_property(MINIMAL_BUILD ON)
 
-set(PROJECT_VER "2.2.0")
+set(PROJECT_VER "2.2.1")
 project(xiaozhi)

main/CMakeLists.txt

@@ -52,8 +52,6 @@ list(APPEND SOURCES
     "boards/common/axp2101.cc"
     "boards/common/backlight.cc"
     "boards/common/button.cc"
-    "boards/common/esp32_camera.cc"
-    "boards/common/esp32s3_camera.cc"
     "boards/common/i2c_device.cc"
     "boards/common/knob.cc"
     "boards/common/power_save_timer.cc"
@@ -758,29 +756,18 @@ if(CONFIG_IDF_TARGET_ESP32)
                              "led/gpio_led.cc"
                              "display/lvgl_display/jpg/image_to_jpeg.cpp"
                              "display/lvgl_display/jpg/jpeg_to_image.c"
-                             "boards/common/esp32_camera.cc"
-                             "boards/common/esp32s3_camera.cc"
                              "boards/common/nt26_board.cc"
                              )
 endif()
 
-# ESP32-S3: 根据 Kconfig 选择使用哪个摄像头组件
+# Include EspVideo if target is ESP32S3 or ESP32P4
-if(CONFIG_IDF_TARGET_ESP32S3)
+if(CONFIG_IDF_TARGET_ESP32S3 OR CONFIG_IDF_TARGET_ESP32P4)
-    if(CONFIG_XIAOZHI_USE_ESP_CAMERA)
+    list(APPEND SOURCES "boards/common/esp_video.cc")
-        # 使用 esp_camera 组件，排除 esp32_camera.cc
-        list(REMOVE_ITEM SOURCES "boards/common/esp32_camera.cc")
-    elseif(CONFIG_XIAOZHI_USE_ESP_VIDEO)
-        # 使用 esp_video 组件，排除 esp32s3_camera.cc
-        list(REMOVE_ITEM SOURCES "boards/common/esp32s3_camera.cc")
-    else()
-        # 默认使用 esp_camera 组件
-        list(REMOVE_ITEM SOURCES "boards/common/esp32_camera.cc")
-    endif()
 endif()
 
-# ESP32-P4: 只能使用 esp_video 组件，排除 esp32s3_camera.cc
+# Include Esp32Camera if target is ESP32S3
-if(CONFIG_IDF_TARGET_ESP32P4)
+if(CONFIG_IDF_TARGET_ESP32S3)
-    list(REMOVE_ITEM SOURCES "boards/common/esp32s3_camera.cc")
+    list(APPEND SOURCES "boards/common/esp32_camera.cc")
 endif()
 
 idf_component_register(SRCS ${SOURCES}

main/Kconfig.projbuild

@@ -737,31 +737,6 @@ menu "Camera Configuration"
 
     comment "Warning: Please read the help text before modifying these settings."
 
-    choice XIAOZHI_CAMERA_COMPONENT
-        prompt "Camera Component Selection"
-        default XIAOZHI_USE_ESP_VIDEO if IDF_TARGET_ESP32S3
-        default XIAOZHI_USE_ESP_VIDEO if IDF_TARGET_ESP32P4
-        help
-            Select the camera component to use.
-            ESP32-S3 can choose between esp_camera (legacy) or esp_video (new).
-            ESP32-P4 only supports esp_video.
-
-        config XIAOZHI_USE_ESP_CAMERA
-            bool "Use esp_camera (legacy component)"
-            depends on IDF_TARGET_ESP32S3
-            help
-                Use the legacy esp32-camera component.
-                This is the traditional camera driver for ESP32-S3.
-
-        config XIAOZHI_USE_ESP_VIDEO
-            bool "Use esp_video (new component)"
-            depends on IDF_TARGET_ESP32S3 || IDF_TARGET_ESP32P4
-            help
-                Use the new esp_video component.
-                This component provides V4L2-like interface and is required for ESP32-P4.
-                On ESP32-S3, it provides additional features but may require different camera configuration.
-    endchoice
-
     config XIAOZHI_CAMERA_ALLOW_JPEG_INPUT
         bool "Allow JPEG Input"
         default n

main/boards/atk-dnesp32s3/atk_dnesp32s3.cc

@@ -6,7 +6,7 @@
 #include "config.h"
 #include "i2c_device.h"
 #include "led/single_led.h"
-#include "esp32_camera.h"
+#include "esp_video.h"
 
 #include <esp_log.h>
 #include <esp_lcd_panel_vendor.h>
@@ -49,7 +49,7 @@ private:
     Button boot_button_;
     LcdDisplay* display_;
     XL9555* xl9555_;
-    Esp32Camera* camera_;
+    EspVideo* camera_;
 
     void InitializeI2c() {
         // Initialize I2C peripheral
@@ -179,7 +179,7 @@ private:
             .dvp = &dvp_config,
         };
 
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
     }
 
 public:

main/boards/atoms3r-cam-m12-echo-base/README.md

@@ -14,12 +14,6 @@ AtomS3R CAM、AtomS3R M12 是 M5Stack 推出的基于 ESP32-S3-PICO-1-N8R8 的
 
 两款开发版均**不带屏幕、不带额外按键**，需要使用语音唤醒。必要时，需要使用 `idf.py monitor` 查看 log 以确定运行状态。
 
-> ![NOTE]
->
-> 自版本 [待定] 起，由于依赖库不支持 OV3660 传感器，AtomS3R M12 无法使用摄像头识别功能。
->
-> AtomS3R CAM 不受影响；使用旧版本小智固件的 AtomS3R M12 不受影响。
-
 ## 配置、编译命令
 
 **配置编译目标为 ESP32S3**

main/boards/atoms3r-cam-m12-echo-base/atoms3r_cam_m12_echo_base.cc

@@ -126,47 +126,33 @@ private:
     }
 
     void InitializeCamera() {
-        static esp_cam_ctlr_dvp_pin_config_t dvp_pin_config = {
+        camera_config_t config = {};
-            .data_width = CAM_CTLR_DATA_WIDTH_8,
+        config.pin_d0 = CAMERA_PIN_D0;
-            .data_io = {
+        config.pin_d1 = CAMERA_PIN_D1;
-                [0] = CAMERA_PIN_D0,
+        config.pin_d2 = CAMERA_PIN_D2;
-                [1] = CAMERA_PIN_D1,
+        config.pin_d3 = CAMERA_PIN_D3;
-                [2] = CAMERA_PIN_D2,
+        config.pin_d4 = CAMERA_PIN_D4;
-                [3] = CAMERA_PIN_D3,
+        config.pin_d5 = CAMERA_PIN_D5;
-                [4] = CAMERA_PIN_D4,
+        config.pin_d6 = CAMERA_PIN_D6;
-                [5] = CAMERA_PIN_D5,
+        config.pin_d7 = CAMERA_PIN_D7;
-                [6] = CAMERA_PIN_D6,
+        config.pin_xclk = CAMERA_PIN_XCLK;
-                [7] = CAMERA_PIN_D7,
+        config.pin_pclk = CAMERA_PIN_PCLK;
-            },
+        config.pin_vsync = CAMERA_PIN_VSYNC;
-            .vsync_io = CAMERA_PIN_VSYNC,
+        config.pin_href = CAMERA_PIN_HREF;
-            .de_io = CAMERA_PIN_HREF,
+        config.pin_sccb_sda = CAMERA_PIN_SIOD;
-            .pclk_io = CAMERA_PIN_PCLK,
+        config.pin_sccb_scl = CAMERA_PIN_SIOC;
-            .xclk_io = CAMERA_PIN_XCLK,
+        config.sccb_i2c_port = 1;
-        };
+        config.pin_pwdn = CAMERA_PIN_PWDN;
+        config.pin_reset = CAMERA_PIN_RESET;
+        config.xclk_freq_hz = XCLK_FREQ_HZ;
+        config.pixel_format = PIXFORMAT_RGB565;
+        config.frame_size = FRAMESIZE_QVGA;
+        config.jpeg_quality = 12;
+        config.fb_count = 1;
+        config.fb_location = CAMERA_FB_IN_PSRAM;
+        config.grab_mode = CAMERA_GRAB_WHEN_EMPTY;
 
-        esp_video_init_sccb_config_t sccb_config = {
+        camera_ = new Esp32Camera(config);
-            .init_sccb = true,
-            .i2c_config = {
-                .port = 1,
-                .scl_pin = CAMERA_PIN_SIOC,
-                .sda_pin = CAMERA_PIN_SIOD,
-            },
-            .freq = 100000,
-        };
-
-        esp_video_init_dvp_config_t dvp_config = {
-            .sccb_config = sccb_config,
-            .reset_pin = CAMERA_PIN_RESET,
-            .pwdn_pin = CAMERA_PIN_PWDN,
-            .dvp_pin = dvp_pin_config,
-            .xclk_freq = XCLK_FREQ_HZ,
-        };
-
-        esp_video_init_config_t video_config = {
-            .dvp = &dvp_config,
-        };
-
-        camera_ = new Esp32Camera(video_config);
         camera_->SetHMirror(false);
     }
 

main/boards/atoms3r-cam-m12-echo-base/config.json

@@ -5,10 +5,7 @@
             "name": "atoms3r-cam-m12-echo-base",
             "sdkconfig_append": [
                 "CONFIG_ESPTOOLPY_FLASHSIZE_8MB=y",
-                "CONFIG_PARTITION_TABLE_CUSTOM_FILENAME=\"partitions/v2/8m.csv\"",
+                "CONFIG_PARTITION_TABLE_CUSTOM_FILENAME=\"partitions/v2/8m.csv\""
-                "CONFIG_CAMERA_GC0308=y",
-                "CONFIG_CAMERA_GC0308_AUTO_DETECT_DVP_INTERFACE_SENSOR=y",
-                "CONFIG_CAMERA_GC0308_DVP_YUV422_320X240_20FPS=y"
             ]
         }
     ]

main/boards/bread-compact-wifi-s3cam/compact_wifi_board_s3cam.cc

@@ -8,7 +8,7 @@
 #include "mcp_server.h"
 #include "lamp_controller.h"
 #include "led/single_led.h"
-#include "esp32_camera.h"
+#include "esp_video.h"
 
 #include <esp_log.h>
 #include <driver/i2c_master.h>
@@ -65,7 +65,7 @@ private:
  
     Button boot_button_;
     LcdDisplay* display_;
-     Esp32Camera* camera_;
+     EspVideo* camera_;
 
     void InitializeSpi() {
         spi_bus_config_t buscfg = {};
@@ -165,7 +165,7 @@ private:
             .dvp = &dvp_config,
         };
 
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
         camera_->SetHMirror(false);
     }
 

main/boards/common/esp32_camera.h

@@ -1,7 +1,5 @@
 #pragma once
 #include "sdkconfig.h"
-// esp32_camera (使用 esp_video 组件) 用于 ESP32-P4，或 ESP32-S3 选择使用 esp_video 时
-#if defined(CONFIG_IDF_TARGET_ESP32P4) || (defined(CONFIG_IDF_TARGET_ESP32S3) && defined(CONFIG_XIAOZHI_USE_ESP_VIDEO))
 
 #include <lvgl.h>
 #include <thread>
@@ -12,46 +10,31 @@
 #include <freertos/queue.h>
 
 #include "camera.h"
+#include "esp_camera.h"
 #include "jpg/image_to_jpeg.h"
-#include "esp_video_init.h"
 
-struct JpegChunk {
+struct JpegChunk
+{
     uint8_t *data;
     size_t len;
 };
 
-class Esp32Camera : public Camera {
+class Esp32Camera : public Camera
+{
 private:
-    struct FrameBuffer {
-        uint8_t *data = nullptr;
-        size_t len = 0;
-        uint16_t width = 0;
-        uint16_t height = 0;
-        v4l2_pix_fmt_t format = 0;
-    } frame_;
-    v4l2_pix_fmt_t sensor_format_ = 0;
-#ifdef CONFIG_XIAOZHI_ENABLE_ROTATE_CAMERA_IMAGE
-    uint16_t sensor_width_ = 0;
-    uint16_t sensor_height_ = 0;
-#endif  // CONFIG_XIAOZHI_ENABLE_ROTATE_CAMERA_IMAGE
-    int video_fd_ = -1;
     bool streaming_on_ = false;
-    struct MmapBuffer { void *start = nullptr; size_t length = 0; };
-    std::vector<MmapBuffer> mmap_buffers_;
     std::string explain_url_;
     std::string explain_token_;
     std::thread encoder_thread_;
+    camera_fb_t *current_fb_ = nullptr;
 
 public:
-    Esp32Camera(const esp_video_init_config_t& config);
+    Esp32Camera(const camera_config_t &config);
     ~Esp32Camera();
 
-    virtual void SetExplainUrl(const std::string& url, const std::string& token);
+    virtual void SetExplainUrl(const std::string &url, const std::string &token) override;
-    virtual bool Capture();
+    virtual bool Capture() override;
-    // 翻转控制函数
     virtual bool SetHMirror(bool enabled) override;
     virtual bool SetVFlip(bool enabled) override;
-    virtual std::string Explain(const std::string& question);
+    virtual std::string Explain(const std::string &question) override;
 };
-
-#endif // ndef CONFIG_IDF_TARGET_ESP32

main/boards/common/esp32s3_camera.cc

@@ -1,413 +0,0 @@
-#include "sdkconfig.h"
-
-// esp32s3_camera (使用 esp_camera 组件) 仅用于 ESP32-S3 且选择使用 esp_camera 时
-#if defined(CONFIG_IDF_TARGET_ESP32S3) && defined(CONFIG_XIAOZHI_USE_ESP_CAMERA)
-
-#include <esp_heap_caps.h>
-#include <cstdio>
-#include <cstring>
-#include <esp_log.h>
-
-#include "esp32s3_camera.h"
-#include "board.h"
-#include "display.h"
-#include "lvgl_display.h"
-#include "mcp_server.h"
-#include "system_info.h"
-#include "jpg/image_to_jpeg.h"
-
-#define TAG "Esp32S3Camera"
-
-// V4L2 兼容的格式定义
-#define V4L2_PIX_FMT_RGB565 0x50424752 // 'RGBP'
-#define V4L2_PIX_FMT_YUYV 0x56595559   // 'YUYV'
-#define V4L2_PIX_FMT_JPEG 0x4745504A   // 'JPEG'
-#define V4L2_PIX_FMT_RGB24 0x33424752  // 'RGB3'
-#define V4L2_PIX_FMT_GREY 0x59455247   // 'GREY'
-
-static uint32_t pixformat_to_v4l2(pixformat_t fmt)
-{
-    switch (fmt)
-    {
-    case PIXFORMAT_RGB565:
-        return V4L2_PIX_FMT_RGB565;
-    case PIXFORMAT_YUV422:
-        return V4L2_PIX_FMT_YUYV;
-    case PIXFORMAT_JPEG:
-        return V4L2_PIX_FMT_JPEG;
-    case PIXFORMAT_RGB888:
-        return V4L2_PIX_FMT_RGB24;
-    case PIXFORMAT_GRAYSCALE:
-        return V4L2_PIX_FMT_GREY;
-    default:
-        return 0;
-    }
-}
-
-Esp32S3Camera::Esp32S3Camera(const camera_config_t &config)
-{
-    esp_err_t err = esp_camera_init(&config);
-    if (err != ESP_OK)
-    {
-        ESP_LOGE(TAG, "esp_camera_init failed with error 0x%x", err);
-        return;
-    }
-
-    sensor_t *s = esp_camera_sensor_get();
-    if (s)
-    {
-        frame_.width = config.frame_size == FRAMESIZE_QVGA ? 320 : config.frame_size == FRAMESIZE_VGA ? 640
-                                                               : config.frame_size == FRAMESIZE_SVGA  ? 800
-                                                               : config.frame_size == FRAMESIZE_XGA   ? 1024
-                                                               : config.frame_size == FRAMESIZE_HD    ? 1280
-                                                               : config.frame_size == FRAMESIZE_SXGA  ? 1280
-                                                               : config.frame_size == FRAMESIZE_UXGA  ? 1600
-                                                                                                      : 320;
-        frame_.height = config.frame_size == FRAMESIZE_QVGA ? 240 : config.frame_size == FRAMESIZE_VGA ? 480
-                                                                : config.frame_size == FRAMESIZE_SVGA  ? 600
-                                                                : config.frame_size == FRAMESIZE_XGA   ? 768
-                                                                : config.frame_size == FRAMESIZE_HD    ? 720
-                                                                : config.frame_size == FRAMESIZE_SXGA  ? 1024
-                                                                : config.frame_size == FRAMESIZE_UXGA  ? 1200
-                                                                                                       : 240;
-        frame_.format = config.pixel_format;
-        ESP_LOGI(TAG, "Camera initialized: %dx%d, format=%d", frame_.width, frame_.height, config.pixel_format);
-    }
-
-    streaming_on_ = true;
-    ESP_LOGI(TAG, "ESP32-S3 Camera init success");
-}
-
-Esp32S3Camera::~Esp32S3Camera()
-{
-    if (streaming_on_)
-    {
-        if (current_fb_)
-        {
-            esp_camera_fb_return(current_fb_);
-            current_fb_ = nullptr;
-        }
-        esp_camera_deinit();
-        streaming_on_ = false;
-    }
-    if (frame_.data)
-    {
-        heap_caps_free(frame_.data);
-        frame_.data = nullptr;
-    }
-}
-
-void Esp32S3Camera::SetExplainUrl(const std::string &url, const std::string &token)
-{
-    explain_url_ = url;
-    explain_token_ = token;
-}
-
-bool Esp32S3Camera::Capture()
-{
-    if (encoder_thread_.joinable())
-    {
-        encoder_thread_.join();
-    }
-
-    if (!streaming_on_)
-    {
-        return false;
-    }
-
-    // 释放之前的帧
-    if (current_fb_)
-    {
-        esp_camera_fb_return(current_fb_);
-        current_fb_ = nullptr;
-    }
-
-    // 丢弃前两帧，获取最新帧
-    for (int i = 0; i < 3; i++)
-    {
-        camera_fb_t *fb = esp_camera_fb_get();
-        if (!fb)
-        {
-            ESP_LOGE(TAG, "Camera capture failed");
-            return false;
-        }
-        if (i < 2)
-        {
-            esp_camera_fb_return(fb);
-        }
-        else
-        {
-            current_fb_ = fb;
-        }
-    }
-
-    if (!current_fb_)
-    {
-        ESP_LOGE(TAG, "Failed to get frame buffer");
-        return false;
-    }
-
-    // 保存帧副本到 PSRAM
-    if (frame_.data)
-    {
-        heap_caps_free(frame_.data);
-        frame_.data = nullptr;
-    }
-
-    frame_.len = current_fb_->len;
-    frame_.width = current_fb_->width;
-    frame_.height = current_fb_->height;
-    frame_.format = current_fb_->format;
-
-    frame_.data = (uint8_t *)heap_caps_malloc(frame_.len, MALLOC_CAP_SPIRAM | MALLOC_CAP_8BIT);
-    if (!frame_.data)
-    {
-        ESP_LOGE(TAG, "Failed to allocate %zu bytes for frame copy", frame_.len);
-        esp_camera_fb_return(current_fb_);
-        current_fb_ = nullptr;
-        return false;
-    }
-    memcpy(frame_.data, current_fb_->buf, frame_.len);
-
-    // 释放原始帧
-    esp_camera_fb_return(current_fb_);
-    current_fb_ = nullptr;
-
-    // 对 RGB565 格式进行字节交换 (Big Endian <-> Little Endian)
-    // 这样 frame_.data 就是已交换的数据，显示和上传都使用相同的数据
-    if (frame_.format == PIXFORMAT_RGB565)
-    {
-        uint8_t *data = frame_.data;
-        size_t pixel_count = frame_.width * frame_.height;
-        for (size_t i = 0; i < pixel_count; i++)
-        {
-            uint8_t temp = data[2 * i];
-            data[2 * i] = data[2 * i + 1];
-            data[2 * i + 1] = temp;
-        }
-    }
-
-    ESP_LOGD(TAG, "Captured frame: %dx%d, len=%zu, format=%d",
-             frame_.width, frame_.height, frame_.len, frame_.format);
-
-    // 显示预览图片
-    auto display = dynamic_cast<LvglDisplay *>(Board::GetInstance().GetDisplay());
-    if (display != nullptr)
-    {
-        if (!frame_.data)
-        {
-            ESP_LOGE(TAG, "frame.data is null");
-            return false;
-        }
-
-        uint16_t w = frame_.width;
-        uint16_t h = frame_.height;
-        size_t lvgl_image_size = frame_.len;
-        size_t stride = ((w * 2) + 3) & ~3; // 4字节对齐
-        lv_color_format_t color_format = LV_COLOR_FORMAT_RGB565;
-        uint8_t *data = nullptr;
-
-        switch (frame_.format)
-        {
-        case PIXFORMAT_RGB565:
-            // frame_.data 已经在捕获阶段完成了字节交换，直接复制即可
-            data = (uint8_t *)heap_caps_malloc(w * h * 2, MALLOC_CAP_SPIRAM | MALLOC_CAP_8BIT);
-            if (data == nullptr)
-            {
-                ESP_LOGE(TAG, "Failed to allocate memory for preview image");
-                return false;
-            }
-            memcpy(data, frame_.data, frame_.len);
-            lvgl_image_size = frame_.len;
-            break;
-
-        case PIXFORMAT_JPEG:
-            // JPEG 格式需要解码 - 跳过预览显示
-            ESP_LOGD(TAG, "JPEG format preview not supported, skipping display");
-            return true;
-
-        default:
-            ESP_LOGE(TAG, "Unsupported frame format for preview: %d", frame_.format);
-            return true; // 仍然返回 true，因为捕获成功
-        }
-
-        if (data)
-        {
-            auto image = std::make_unique<LvglAllocatedImage>(data, lvgl_image_size, w, h, stride, color_format);
-            display->SetPreviewImage(std::move(image));
-        }
-    }
-    return true;
-}
-
-bool Esp32S3Camera::SetHMirror(bool enabled)
-{
-    sensor_t *s = esp_camera_sensor_get();
-    if (!s)
-    {
-        return false;
-    }
-    s->set_hmirror(s, enabled ? 1 : 0);
-    return true;
-}
-
-bool Esp32S3Camera::SetVFlip(bool enabled)
-{
-    sensor_t *s = esp_camera_sensor_get();
-    if (!s)
-    {
-        return false;
-    }
-    s->set_vflip(s, enabled ? 1 : 0);
-    return true;
-}
-
-std::string Esp32S3Camera::Explain(const std::string &question)
-{
-    if (explain_url_.empty())
-    {
-        throw std::runtime_error("Image explain URL or token is not set");
-    }
-
-    // 创建局部的 JPEG 队列
-    QueueHandle_t jpeg_queue = xQueueCreate(40, sizeof(JpegChunk));
-    if (jpeg_queue == nullptr)
-    {
-        ESP_LOGE(TAG, "Failed to create JPEG queue");
-        throw std::runtime_error("Failed to create JPEG queue");
-    }
-
-    // 转换格式为 v4l2 兼容格式
-    uint32_t v4l2_format = pixformat_to_v4l2(frame_.format);
-
-    // 启动编码线程
-    encoder_thread_ = std::thread([this, jpeg_queue, v4l2_format]()
-                                  {
-        uint16_t w = frame_.width ? frame_.width : 320;
-        uint16_t h = frame_.height ? frame_.height : 240;
-        bool ok = image_to_jpeg_cb(
-            frame_.data, frame_.len, w, h, static_cast<v4l2_pix_fmt_t>(v4l2_format), 80,
-            [](void* arg, size_t index, const void* data, size_t len) -> size_t {
-                auto jpeg_queue = static_cast<QueueHandle_t>(arg);
-                JpegChunk chunk = {.data = nullptr, .len = len};
-                if (index == 0 && data != nullptr && len > 0) {
-                    chunk.data = (uint8_t*)heap_caps_aligned_alloc(16, len, MALLOC_CAP_SPIRAM | MALLOC_CAP_8BIT);
-                    if (chunk.data == nullptr) {
-                        ESP_LOGE(TAG, "Failed to allocate %zu bytes for JPEG chunk", len);
-                        chunk.len = 0;
-                    } else {
-                        memcpy(chunk.data, data, len);
-                    }
-                } else {
-                    chunk.len = 0;
-                }
-                xQueueSend(jpeg_queue, &chunk, portMAX_DELAY);
-                return len;
-            },
-            jpeg_queue);
-
-        if (!ok) {
-            JpegChunk chunk = {.data = nullptr, .len = 0};
-            xQueueSend(jpeg_queue, &chunk, portMAX_DELAY);
-        } });
-
-    auto network = Board::GetInstance().GetNetwork();
-    auto http = network->CreateHttp(3);
-    std::string boundary = "----ESP32_CAMERA_BOUNDARY";
-
-    http->SetHeader("Device-Id", SystemInfo::GetMacAddress().c_str());
-    http->SetHeader("Client-Id", Board::GetInstance().GetUuid().c_str());
-    if (!explain_token_.empty())
-    {
-        http->SetHeader("Authorization", "Bearer " + explain_token_);
-    }
-    http->SetHeader("Content-Type", "multipart/form-data; boundary=" + boundary);
-    http->SetHeader("Transfer-Encoding", "chunked");
-    if (!http->Open("POST", explain_url_))
-    {
-        ESP_LOGE(TAG, "Failed to connect to explain URL");
-        encoder_thread_.join();
-        JpegChunk chunk;
-        while (xQueueReceive(jpeg_queue, &chunk, portMAX_DELAY) == pdPASS)
-        {
-            if (chunk.data != nullptr)
-            {
-                heap_caps_free(chunk.data);
-            }
-            else
-            {
-                break;
-            }
-        }
-        vQueueDelete(jpeg_queue);
-        throw std::runtime_error("Failed to connect to explain URL");
-    }
-
-    {
-        std::string question_field;
-        question_field += "--" + boundary + "\r\n";
-        question_field += "Content-Disposition: form-data; name=\"question\"\r\n";
-        question_field += "\r\n";
-        question_field += question + "\r\n";
-        http->Write(question_field.c_str(), question_field.size());
-    }
-    {
-        std::string file_header;
-        file_header += "--" + boundary + "\r\n";
-        file_header += "Content-Disposition: form-data; name=\"file\"; filename=\"camera.jpg\"\r\n";
-        file_header += "Content-Type: image/jpeg\r\n";
-        file_header += "\r\n";
-        http->Write(file_header.c_str(), file_header.size());
-    }
-
-    size_t total_sent = 0;
-    bool saw_terminator = false;
-    while (true)
-    {
-        JpegChunk chunk;
-        if (xQueueReceive(jpeg_queue, &chunk, portMAX_DELAY) != pdPASS)
-        {
-            ESP_LOGE(TAG, "Failed to receive JPEG chunk");
-            break;
-        }
-        if (chunk.data == nullptr)
-        {
-            saw_terminator = true;
-            break;
-        }
-        http->Write((const char *)chunk.data, chunk.len);
-        total_sent += chunk.len;
-        heap_caps_free(chunk.data);
-    }
-    encoder_thread_.join();
-    vQueueDelete(jpeg_queue);
-
-    if (!saw_terminator || total_sent == 0)
-    {
-        ESP_LOGE(TAG, "JPEG encoder failed or produced empty output");
-        throw std::runtime_error("Failed to encode image to JPEG");
-    }
-
-    {
-        std::string multipart_footer;
-        multipart_footer += "\r\n--" + boundary + "--\r\n";
-        http->Write(multipart_footer.c_str(), multipart_footer.size());
-    }
-    http->Write("", 0);
-
-    if (http->GetStatusCode() != 200)
-    {
-        ESP_LOGE(TAG, "Failed to upload photo, status code: %d", http->GetStatusCode());
-        throw std::runtime_error("Failed to upload photo");
-    }
-
-    std::string result = http->ReadAll();
-    http->Close();
-
-    size_t remain_stack_size = uxTaskGetStackHighWaterMark(nullptr);
-    ESP_LOGI(TAG, "Explain image size=%d bytes, compressed size=%d, remain stack size=%d, question=%s\n%s",
-             (int)frame_.len, (int)total_sent, (int)remain_stack_size, question.c_str(), result.c_str());
-    return result;
-}
-
-#endif // CONFIG_IDF_TARGET_ESP32S3 && CONFIG_XIAOZHI_USE_ESP_CAMERA

main/boards/common/esp32s3_camera.h

@@ -1,53 +0,0 @@
-#pragma once
-#include "sdkconfig.h"
-
-// esp32s3_camera (使用 esp_camera 组件) 仅用于 ESP32-S3 且选择使用 esp_camera 时
-#if defined(CONFIG_IDF_TARGET_ESP32S3) && defined(CONFIG_XIAOZHI_USE_ESP_CAMERA)
-
-#include <lvgl.h>
-#include <thread>
-#include <memory>
-#include <vector>
-
-#include <freertos/FreeRTOS.h>
-#include <freertos/queue.h>
-
-#include "camera.h"
-#include "esp_camera.h"
-
-struct JpegChunk
-{
-    uint8_t *data;
-    size_t len;
-};
-
-class Esp32S3Camera : public Camera
-{
-private:
-    struct FrameBuffer
-    {
-        uint8_t *data = nullptr;
-        size_t len = 0;
-        uint16_t width = 0;
-        uint16_t height = 0;
-        pixformat_t format = PIXFORMAT_RGB565;
-    } frame_;
-
-    bool streaming_on_ = false;
-    std::string explain_url_;
-    std::string explain_token_;
-    std::thread encoder_thread_;
-    camera_fb_t *current_fb_ = nullptr;
-
-public:
-    Esp32S3Camera(const camera_config_t &config);
-    ~Esp32S3Camera();
-
-    virtual void SetExplainUrl(const std::string &url, const std::string &token) override;
-    virtual bool Capture() override;
-    virtual bool SetHMirror(bool enabled) override;
-    virtual bool SetVFlip(bool enabled) override;
-    virtual std::string Explain(const std::string &question) override;
-};
-
-#endif // CONFIG_IDF_TARGET_ESP32S3 && CONFIG_XIAOZHI_USE_ESP_CAMERA

main/boards/common/esp_video.h

@@ -0,0 +1,53 @@
+#pragma once
+#include "sdkconfig.h"
+
+#include <lvgl.h>
+#include <thread>
+#include <memory>
+#include <vector>
+
+#include <freertos/FreeRTOS.h>
+#include <freertos/queue.h>
+
+#include "camera.h"
+#include "jpg/image_to_jpeg.h"
+#include "esp_video_init.h"
+
+struct JpegChunk {
+    uint8_t* data;
+    size_t len;
+};
+
+class EspVideo : public Camera {
+private:
+    struct FrameBuffer {
+        uint8_t *data = nullptr;
+        size_t len = 0;
+        uint16_t width = 0;
+        uint16_t height = 0;
+        v4l2_pix_fmt_t format = 0;
+    } frame_;
+    v4l2_pix_fmt_t sensor_format_ = 0;
+#ifdef CONFIG_XIAOZHI_ENABLE_ROTATE_CAMERA_IMAGE
+    uint16_t sensor_width_ = 0;
+    uint16_t sensor_height_ = 0;
+#endif  // CONFIG_XIAOZHI_ENABLE_ROTATE_CAMERA_IMAGE
+    int video_fd_ = -1;
+    bool streaming_on_ = false;
+    struct MmapBuffer { void *start = nullptr; size_t length = 0; };
+    std::vector<MmapBuffer> mmap_buffers_;
+    std::string explain_url_;
+    std::string explain_token_;
+    std::thread encoder_thread_;
+
+public:
+    EspVideo(const esp_video_init_config_t& config);
+    ~EspVideo();
+
+    virtual void SetExplainUrl(const std::string& url, const std::string& token);
+    virtual bool Capture();
+    // 翻转控制函数
+    virtual bool SetHMirror(bool enabled) override;
+    virtual bool SetVFlip(bool enabled) override;
+    virtual std::string Explain(const std::string& question);
+};

main/boards/df-k10/df_k10_board.cc

@@ -6,7 +6,7 @@
 #include "application.h"
 #include "button.h"
 #include "config.h"
-#include "esp32_camera.h"
+#include "esp_video.h"
 
 #include "led/circular_strip.h"
 #include "assets/lang_config.h"
@@ -27,7 +27,7 @@ private:
     LcdDisplay *display_;
     button_handle_t btn_a;
     button_handle_t btn_b;
-    Esp32Camera* camera_;
+    EspVideo* camera_;
 
     button_driver_t* btn_a_driver_ = nullptr;
     button_driver_t* btn_b_driver_ = nullptr;
@@ -209,7 +209,7 @@ private:
             .dvp = &dvp_config,
         };
 
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
     }
 
     void InitializeIli9341Display() {

main/boards/df-s3-ai-cam/df_s3_ai_cam.cc

@@ -4,7 +4,7 @@
 #include "application.h"
 #include "button.h"
 #include "config.h"
-#include "esp32_camera.h"
+#include "esp_video.h"
 
 #include "led/gpio_led.h"
 #include <esp_log.h>
@@ -16,7 +16,7 @@
 class DfrobotEsp32S3AiCam : public WifiBoard {
  private:
     Button boot_button_;
-    Esp32Camera* camera_;
+    EspVideo* camera_;
 
     void InitializeButtons() {
         boot_button_.OnClick([this]() {
@@ -70,7 +70,7 @@ class DfrobotEsp32S3AiCam : public WifiBoard {
             .dvp = &dvp_config,
         };
 
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
         camera_->SetVFlip(1);
     }
 

main/boards/echoear/EchoEar.cc

@@ -6,7 +6,7 @@
 #include "button.h"
 #include "config.h"
 #include "backlight.h"
-#include "esp32_camera.h"
+#include "esp_video.h"
 
 #include <esp_log.h>
 
@@ -390,7 +390,7 @@ private:
     PwmBacklight* backlight_ = nullptr;
     esp_timer_handle_t touchpad_timer_;
     esp_lcd_touch_handle_t tp;   // LCD touch handle
-    Esp32Camera* camera_ = nullptr;
+    EspVideo* camera_ = nullptr;
 
     void InitializeI2c()
     {
@@ -605,7 +605,7 @@ private:
             .usb_uvc = &usb_uvc_config,
         };
 
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
     }
 #endif // CONFIG_ESP_VIDEO_ENABLE_USB_UVC_VIDEO_DEVICE
 

main/boards/esp-p4-function-ev-board/esp-p4-function-ev-board.cc

@@ -10,7 +10,7 @@
 #include "application.h"
 #include "button.h"
 #include "config.h"
-#include "esp32_camera.h"
+#include "esp_video.h"
 
 #include <esp_log.h>
 #include <inttypes.h>
@@ -45,7 +45,7 @@ private:
     Button boot_button_;
     LcdDisplay *display_ = nullptr;
     esp_lcd_touch_handle_t tp_ = nullptr;
-    Esp32Camera* camera_ = nullptr;
+    EspVideo* camera_ = nullptr;
 
     void InitializeI2cBuses()
     {
@@ -115,7 +115,7 @@ private:
             ESP_LOGE(TAG, "Failed to initialize BSP camera: %s", esp_err_to_name(ret));
             ESP_LOGI(TAG, "Attempting alternative camera initialization");
 
-            // Alternative: Direct Esp32Camera initialization if BSP fails
+            // Alternative: Direct EspVideo initialization if BSP fails
             // This provides more control over camera configuration
             static esp_cam_ctlr_dvp_pin_config_t dvp_pin_config = {
                 .data_width = CAM_CTLR_DATA_WIDTH_8,
@@ -154,7 +154,7 @@ private:
             };
 
             // Try to create camera with direct configuration
-            camera_ = new Esp32Camera(video_config);
+            camera_ = new EspVideo(video_config);
             ESP_LOGI(TAG, "Camera initialized with direct configuration");
         } else {
             ESP_LOGI(TAG, "Camera initialized successfully via BSP");

main/boards/esp-s3-lcd-ev-board-2/esp-s3-lcd-ev-board-2.cc

@@ -5,7 +5,7 @@
 #include "button.h"
 #include "led/single_led.h"
 #include "pin_config.h"
-#include "esp32_camera.h"
+#include "esp_video.h"
 
 #include "config.h"
 
@@ -27,7 +27,7 @@ private:
     i2c_master_bus_handle_t i2c_bus_;
     Button boot_button_;
     LcdDisplay* display_;
-    Esp32Camera* camera_;
+    EspVideo* camera_;
 
     //add support ev board lcd
     esp_io_expander_handle_t expander = NULL;
@@ -218,7 +218,7 @@ private:
         esp_video_init_config_t video_config = {
             .usb_uvc = &usb_uvc_config,
         };
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
     }
 #endif // CONFIG_ESP_VIDEO_ENABLE_USB_UVC_VIDEO_DEVICE
 

main/boards/esp-s3-lcd-ev-board/esp-s3-lcd-ev-board.cc

@@ -5,7 +5,7 @@
 #include "button.h"
 #include "led/single_led.h"
 #include "pin_config.h"
-#include "esp32_camera.h"
+#include "esp_video.h"
 
 #include "config.h"
 
@@ -25,7 +25,7 @@ private:
     i2c_master_bus_handle_t codec_i2c_bus_;
     Button boot_button_;
     LcdDisplay* display_;
-    Esp32Camera* camera_;
+    EspVideo* camera_;
 
     //add support ev board lcd
     esp_io_expander_handle_t expander = NULL;
@@ -188,7 +188,7 @@ private:
             .usb_uvc = &usb_uvc_config,
         };
 
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
     }
 #endif // CONFIG_ESP_VIDEO_ENABLE_USB_UVC_VIDEO_DEVICE
 

main/boards/esp-sparkbot/esp_sparkbot_board.cc

@@ -14,7 +14,7 @@
 #include <driver/uart.h>
 #include <cstring>
 
-#include "esp32_camera.h"
+#include "esp_video.h"
 
 #define TAG "esp_sparkbot"
 
@@ -45,7 +45,7 @@ private:
     i2c_master_bus_handle_t i2c_bus_;
     Button boot_button_;
     Display* display_;
-    Esp32Camera* camera_;
+    EspVideo* camera_;
     light_mode_t light_mode_ = LIGHT_MODE_ALWAYS_ON;
 
     void InitializeI2c() {
@@ -162,7 +162,7 @@ private:
             .dvp = &dvp_config,
         };
         
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
 
         Settings settings("sparkbot", false);
         // 考虑到部分复刻使用了不可动摄像头的设计，默认启用翻转

main/boards/esp32-s3-touch-lcd-3.5/esp32-s3-touch-lcd-3.5.cc

@@ -24,7 +24,7 @@
 #include <esp_lcd_touch_ft5x06.h>
 #include <esp_lvgl_port.h>
 
-#include "esp32_camera.h"
+#include "esp_video.h"
 
 #define TAG "waveshare_lcd_3_5"
 
@@ -106,7 +106,7 @@ private:
     esp_io_expander_handle_t io_expander = NULL;
     LcdDisplay* display_;
     PowerSaveTimer* power_save_timer_;
-    Esp32Camera* camera_;
+    EspVideo* camera_;
 
     void InitializePowerSaveTimer() {
         power_save_timer_ = new PowerSaveTimer(-1, 60, 300);
@@ -209,7 +209,7 @@ private:
             .dvp = &dvp_config,
         };
 
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
         
     }
 

main/boards/esp32s3-korvo2-v3/config.json

@@ -4,14 +4,6 @@
         {
             "name": "esp32s3-korvo2-v3",
             "sdkconfig_append": [
-                "CONFIG_XIAOZHI_USE_ESP_CAMERA=y",
-                "CONFIG_CAMERA_OV2640=y",
-                "CONFIG_CAMERA_OV3660=y",
-                "CONFIG_CAMERA_OV3660_AUTO_DETECT_DVP_INTERFACE_SENSOR=y",
-                "CONFIG_CAMERA_OV3660_DVP_RGB565_240X240_24FPS=y",
-                "CONFIG_CAMERA_OV2640_AUTO_DETECT_DVP_INTERFACE_SENSOR=y",
-                "CONFIG_CAMERA_OV2640_DVP_RGB565_240X240_25FPS=y",
-                "CONFIG_XIAOZHI_ENABLE_CAMERA_ENDIANNESS_SWAP=y"
             ]
         }
     ]

main/boards/esp32s3-korvo2-v3/esp32s3_korvo2_v3_board.cc

@@ -13,7 +13,7 @@
 #include <esp_lcd_ili9341.h>
 #include <driver/i2c_master.h>
 #include <driver/spi_common.h>
-#include "esp32s3_camera.h"
+#include "esp32_camera.h"
 #include "power_manager.h"
 #include "power_save_timer.h"
 
@@ -60,7 +60,7 @@ private:
     i2c_master_bus_handle_t i2c_bus_;
     LcdDisplay* display_;
     esp_io_expander_handle_t io_expander_ = NULL;
-    Esp32S3Camera* camera_;
+    Esp32Camera* camera_;
     PowerSaveTimer* power_save_timer_;
     PowerManager* power_manager_;
     void InitializePowerManager() {
@@ -385,7 +385,7 @@ private:
             .sccb_i2c_port = (i2c_port_t)1,
         };
 
-        camera_ = new Esp32S3Camera(camera_config);
+        camera_ = new Esp32Camera(camera_config);
         if(camera_ != nullptr)
         {
             camera_->SetVFlip(true);

main/boards/kevin-sp-v3-dev/kevin-sp-v3_board.cc

@@ -12,7 +12,7 @@
 #include <esp_log.h>
 #include <esp_lcd_panel_vendor.h>
 #include <driver/i2c_master.h>
-#include "esp32s3_camera.h"
+#include "esp32_camera.h"
 
 #define TAG "kevin-sp-v3"
 
@@ -22,7 +22,7 @@ private:
     i2c_master_bus_handle_t display_i2c_bus_;
     Button boot_button_;
     LcdDisplay* display_;
-    Esp32S3Camera* camera_;
+    Esp32Camera* camera_;
 
     void InitializeSpi() {
         spi_bus_config_t buscfg = {};
@@ -116,7 +116,7 @@ private:
             .sccb_i2c_port = (i2c_port_t)1,
         };
 
-        camera_ = new Esp32S3Camera(camera_config);
+        camera_ = new Esp32Camera(camera_config);
     }
 
 public:

main/boards/kevin-sp-v4-dev/config.json

@@ -4,14 +4,6 @@
         {
             "name": "kevin-sp-v4-dev",
             "sdkconfig_append": [
-                "CONFIG_XIAOZHI_USE_ESP_CAMERA=y",
-                "CONFIG_CAMERA_OV2640=y",
-                "CONFIG_CAMERA_OV3660=y",
-                "CONFIG_CAMERA_OV3660_AUTO_DETECT_DVP_INTERFACE_SENSOR=y",
-                "CONFIG_CAMERA_OV3660_DVP_RGB565_240X240_24FPS=y",
-                "CONFIG_CAMERA_OV2640_AUTO_DETECT_DVP_INTERFACE_SENSOR=y",
-                "CONFIG_CAMERA_OV2640_DVP_RGB565_240X240_25FPS=y",
-                "CONFIG_XIAOZHI_ENABLE_CAMERA_ENDIANNESS_SWAP=y"
             ]
         }
     ]

main/boards/kevin-sp-v4-dev/kevin-sp-v4_board.cc

@@ -10,7 +10,7 @@
 #include <esp_log.h>
 #include <esp_lcd_panel_vendor.h>
 #include <driver/i2c_master.h>
-#include "esp32s3_camera.h"
+#include "esp32_camera.h"
 
 #define TAG "kevin-sp-v4"
 
@@ -19,7 +19,7 @@ private:
     Button boot_button_;
     LcdDisplay* display_;
     i2c_master_bus_handle_t i2c_bus_;
-    Esp32S3Camera* camera_;
+    Esp32Camera* camera_;
 
     void InitializeCodecI2c() {
         // Initialize I2C peripheral
@@ -130,7 +130,7 @@ private:
             .sccb_i2c_port = (i2c_port_t)1,
         };
 
-        camera_ = new Esp32S3Camera(camera_config);
+        camera_ = new Esp32Camera(camera_config);
     }
 
 public:

main/boards/lichuang-dev/config.json

@@ -4,10 +4,7 @@
         {
             "name": "lichuang-dev",
             "sdkconfig_append": [
-                "CONFIG_USE_DEVICE_AEC=y",
+                "CONFIG_USE_DEVICE_AEC=y"
-                "CONFIG_CAMERA_GC0308=y",
-                "CONFIG_CAMERA_GC0308_AUTO_DETECT_DVP_INTERFACE_SENSOR=y",
-                "CONFIG_CAMERA_GC0308_DVP_YUV422_640X480_16FPS=y"
             ]
         }
     ]

main/boards/lichuang-dev/lichuang_dev_board.cc

@@ -208,43 +208,35 @@ private:
         // Open camera power
         pca9557_->SetOutputState(2, 0);
 
-        static esp_cam_ctlr_dvp_pin_config_t dvp_pin_config = {
+        camera_config_t config = {};
-            .data_width = CAM_CTLR_DATA_WIDTH_8,
+        config.ledc_channel = LEDC_CHANNEL_2;
-            .data_io = {
+        config.ledc_timer = LEDC_TIMER_2;
-                [0] = CAMERA_PIN_D0,
+        config.pin_d0 = CAMERA_PIN_D0;
-                [1] = CAMERA_PIN_D1,
+        config.pin_d1 = CAMERA_PIN_D1;
-                [2] = CAMERA_PIN_D2,
+        config.pin_d2 = CAMERA_PIN_D2;
-                [3] = CAMERA_PIN_D3,
+        config.pin_d3 = CAMERA_PIN_D3;
-                [4] = CAMERA_PIN_D4,
+        config.pin_d4 = CAMERA_PIN_D4;
-                [5] = CAMERA_PIN_D5,
+        config.pin_d5 = CAMERA_PIN_D5;
-                [6] = CAMERA_PIN_D6,
+        config.pin_d6 = CAMERA_PIN_D6;
-                [7] = CAMERA_PIN_D7,
+        config.pin_d7 = CAMERA_PIN_D7;
-            },
+        config.pin_xclk = CAMERA_PIN_XCLK;
-            .vsync_io = CAMERA_PIN_VSYNC,
+        config.pin_pclk = CAMERA_PIN_PCLK;
-            .de_io = CAMERA_PIN_HREF,
+        config.pin_vsync = CAMERA_PIN_VSYNC;
-            .pclk_io = CAMERA_PIN_PCLK,
+        config.pin_href = CAMERA_PIN_HREF;
-            .xclk_io = CAMERA_PIN_XCLK,
+        config.pin_sccb_sda = -1;
-        };
+        config.pin_sccb_scl = CAMERA_PIN_SIOC;
+        config.sccb_i2c_port = 1;
+        config.pin_pwdn = CAMERA_PIN_PWDN;
+        config.pin_reset = CAMERA_PIN_RESET;
+        config.xclk_freq_hz = XCLK_FREQ_HZ;
+        config.pixel_format = PIXFORMAT_RGB565;
+        config.frame_size = FRAMESIZE_VGA;
+        config.jpeg_quality = 12;
+        config.fb_count = 1;
+        config.fb_location = CAMERA_FB_IN_PSRAM;
+        config.grab_mode = CAMERA_GRAB_WHEN_EMPTY;
 
-        esp_video_init_sccb_config_t sccb_config = {
+        camera_ = new Esp32Camera(config);
-            .init_sccb = false,
-            .i2c_handle = i2c_bus_,
-            .freq = 100000,
-        };
-
-        esp_video_init_dvp_config_t dvp_config = {
-            .sccb_config = sccb_config,
-            .reset_pin = CAMERA_PIN_RESET,
-            .pwdn_pin = CAMERA_PIN_PWDN,
-            .dvp_pin = dvp_pin_config,
-            .xclk_freq = XCLK_FREQ_HZ,
-        };
-
-        esp_video_init_config_t video_config = {
-            .dvp = &dvp_config,
-        };
-
-        camera_ = new Esp32Camera(video_config);
     }
 
     void InitializeTools() {

main/boards/lilygo-t-cameraplus-s3/lilygo-t-cameraplus-s3.cc

@@ -8,7 +8,7 @@
 #include "i2c_device.h"
 #include "sy6970.h"
 #include "pin_config.h"
-#include "esp32_camera.h"
+#include "esp_video.h"
 #include "ir_filter_controller.h"
 
 #include <esp_log.h>
@@ -73,7 +73,7 @@ private:
     Button boot_button_;
     Button key1_button_;
     PowerSaveTimer* power_save_timer_;
-    Esp32Camera* camera_;
+    EspVideo* camera_;
 
     void InitializePowerSaveTimer() {
         power_save_timer_ = new PowerSaveTimer(-1, 60, -1);
@@ -270,7 +270,7 @@ private:
             .dvp = &dvp_config,
         };
 
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
         camera_->SetVFlip(1);
         camera_->SetHMirror(1);
     }

main/boards/m5stack-core-s3/m5stack_core_s3.cc

@@ -13,7 +13,7 @@
 #include <esp_lcd_panel_ops.h>
 #include <esp_lcd_ili9341.h>
 #include <esp_timer.h>
-#include "esp32_camera.h"
+#include "esp_video.h"
 
 #define TAG "M5StackCoreS3Board"
 
@@ -123,7 +123,7 @@ private:
     Aw9523* aw9523_;
     Ft6336* ft6336_;
     LcdDisplay* display_;
-    Esp32Camera* camera_;
+    EspVideo* camera_;
     esp_timer_handle_t touchpad_timer_;
     PowerSaveTimer* power_save_timer_;
 
@@ -326,7 +326,7 @@ private:
             .dvp = &dvp_config,
         };
 
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
         camera_->SetHMirror(false);
     }
 

main/boards/m5stack-tab5/m5stack_tab5.cc

@@ -7,7 +7,7 @@
 #include "application.h"
 #include "button.h"
 #include "config.h"
-#include "esp32_camera.h"
+#include "esp_video.h"
 #include "esp_video_init.h"
 #include "esp_cam_sensor_xclk.h"
 
@@ -89,7 +89,7 @@ private:
     i2c_master_bus_handle_t i2c_bus_;
     Button boot_button_;
     LcdDisplay* display_;
-    Esp32Camera* camera_ = nullptr;
+    EspVideo* camera_ = nullptr;
     Pi4ioe1* pi4ioe1_;
     Pi4ioe2* pi4ioe2_;
     esp_lcd_touch_handle_t touch_ = nullptr;
@@ -463,7 +463,7 @@ private:
             .csi = &csi_config,
         };
 
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
     }
 
 public:

main/boards/otto-robot/otto_robot.cc

@@ -18,7 +18,7 @@
 #include "power_manager.h"
 #include "system_reset.h"
 #include "wifi_board.h"
-#include "esp32_camera.h"
+#include "esp_video.h"
 #include "websocket_control_server.h"
 
 #define TAG "OttoRobot"
@@ -34,7 +34,7 @@ private:
     HardwareConfig hw_config_;
     AudioCodec* audio_codec_;
     i2c_master_bus_handle_t i2c_bus_;
-    Esp32Camera *camera_;
+    EspVideo *camera_;
     bool has_camera_;
     
     bool DetectHardwareVersion() {
@@ -247,7 +247,7 @@ private:
                 .dvp = &dvp_config,
             };
 
-            camera_ = new Esp32Camera(video_config);
+            camera_ = new EspVideo(video_config);
             camera_->SetVFlip(true);
             return true;
         } catch (...) {

main/boards/waveshare-p4-nano/esp32-p4-nano.cc

@@ -6,7 +6,7 @@
 #include "button.h"
 #include "config.h"
 
-#include "esp32_camera.h"
+#include "esp_video.h"
 #include "esp_video_init.h"
 #include "esp_cam_sensor_xclk.h"
 
@@ -69,7 +69,7 @@ private:
     i2c_master_bus_handle_t codec_i2c_bus_;
     Button boot_button_;
     LcdDisplay *display__;
-    Esp32Camera* camera_ = nullptr;
+    EspVideo* camera_ = nullptr;
     CustomBacklight *backlight_;
 
     void InitializeCodecI2c() {
@@ -215,7 +215,7 @@ private:
             .csi      = &base_csi_config,
         };
 
-        camera_ = new Esp32Camera(cam_config);
+        camera_ = new EspVideo(cam_config);
     }
     void InitializeButtons() {
         boot_button_.OnClick([this]() {

main/boards/waveshare-p4-wifi6-touch-lcd-4b/esp32-p4-wifi6-touch-lcd-4b.cc

@@ -6,7 +6,7 @@
 #include "button.h"
 #include "config.h"
 
-#include "esp32_camera.h"
+#include "esp_video.h"
 #include "esp_video_init.h"
 #include "esp_cam_sensor_xclk.h"
 
@@ -27,7 +27,7 @@ private:
     i2c_master_bus_handle_t i2c_bus_;
     Button boot_button_;
     LcdDisplay *display_;
-    Esp32Camera* camera_ = nullptr;
+    EspVideo* camera_ = nullptr;
 
     void InitializeCodecI2c() {
         // Initialize I2C peripheral
@@ -168,7 +168,7 @@ private:
             .csi      = &base_csi_config,
         };
 
-        camera_ = new Esp32Camera(cam_config);
+        camera_ = new EspVideo(cam_config);
     }
     void InitializeButtons() {
         boot_button_.OnClick([this]() {

main/boards/waveshare-p4-wifi6-touch-lcd-7b/esp32-p4-wifi6-touch-lcd-7b.cc

@@ -6,7 +6,7 @@
 #include "button.h"
 #include "config.h"
 
-#include "esp32_camera.h"
+#include "esp_video.h"
 #include "esp_video_init.h"
 #include "esp_cam_sensor_xclk.h"
 
@@ -27,7 +27,7 @@ private:
     i2c_master_bus_handle_t i2c_bus_;
     Button boot_button_;
     LcdDisplay *display_;
-    Esp32Camera* camera_ = nullptr;
+    EspVideo* camera_ = nullptr;
 
     esp_err_t i2c_device_probe(uint8_t addr) {
         return i2c_master_probe(i2c_bus_, addr, 100);
@@ -189,7 +189,7 @@ private:
             .csi      = &base_csi_config,
         };
 
-        camera_ = new Esp32Camera(cam_config);
+        camera_ = new EspVideo(cam_config);
     }
     void InitializeButtons() {
         boot_button_.OnClick([this]() {

main/boards/waveshare-p4-wifi6-touch-lcd-xc/esp32-p4-wifi6-touch-lcd-xc.cc

@@ -5,7 +5,7 @@
 // #include "display/no_display.h"
 #include "button.h"
 
-#include "esp32_camera.h"
+#include "esp_video.h"
 #include "esp_video_init.h"
 #include "esp_cam_sensor_xclk.h"
 
@@ -27,7 +27,7 @@ private:
     i2c_master_bus_handle_t i2c_bus_;
     Button boot_button_;
     LcdDisplay *display_;
-    Esp32Camera* camera_ = nullptr;
+    EspVideo* camera_ = nullptr;
 
     void InitializeCodecI2c() {
         // Initialize I2C peripheral
@@ -170,7 +170,7 @@ private:
             .csi      = &base_csi_config,
         };
 
-        camera_ = new Esp32Camera(cam_config);
+        camera_ = new EspVideo(cam_config);
     }
     void InitializeButtons() {
         boot_button_.OnClick([this]() {

main/boards/waveshare-s3-audio-board/esp32-s3-audio_board.cc

@@ -15,7 +15,7 @@
 #include <esp_lcd_st77916.h>
 #include <esp_timer.h>
 #include "esp_io_expander_tca95xx_16bit.h"
-#include "esp32_camera.h"
+#include "esp_video.h"
 #include "led/circular_strip.h"
 #include "esp_lcd_jd9853.h"
 
@@ -31,7 +31,7 @@ private:
     i2c_master_bus_handle_t i2c_bus_;
     esp_io_expander_handle_t io_expander = NULL;
     LcdDisplay* display_;
-    Esp32Camera* camera_;
+    EspVideo* camera_;
 
     void InitializeI2c() {
         // Initialize I2C peripheral
@@ -192,7 +192,7 @@ private:
             .dvp = &dvp_config,
         };
 
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
 
     }
 public:

main/boards/waveshare-s3-touch-lcd-3.5b/waveshare-s3-touch-lcd-3.5b.cc

@@ -28,7 +28,7 @@
 
 #include <esp_lvgl_port.h>
 #include <lvgl.h>
-#include "esp32_camera.h"
+#include "esp_video.h"
 
 #define TAG "waveshare_lcd_3_5b"
 
@@ -108,7 +108,7 @@ private:
     esp_io_expander_handle_t io_expander = NULL;
     LcdDisplay* display_;
     PowerSaveTimer* power_save_timer_;
-    Esp32Camera* camera_;
+    EspVideo* camera_;
 
     void InitializePowerSaveTimer() {
         power_save_timer_ = new PowerSaveTimer(-1, 60, 300);
@@ -212,7 +212,7 @@ private:
             .dvp = &dvp_config,
         };
 
-        camera_ = new Esp32Camera(video_config);
+        camera_ = new EspVideo(video_config);
         
     }
 

main/display/lvgl_display/jpg/image_to_jpeg.h

@@ -7,7 +7,7 @@
 #include <stdint.h>
 #include <stddef.h>
 
-#if defined(CONFIG_IDF_TARGET_ESP32P4)
+#if defined(CONFIG_IDF_TARGET_ESP32P4) || defined(CONFIG_IDF_TARGET_ESP32S3)
 // ESP32-P4 使用 esp_video 组件提供的 V4L2 头文件
 #include <linux/videodev2.h>
 #else

main/mcp_server.cc

@@ -100,7 +100,7 @@ void McpServer::AddCommonTools() {
     auto camera = board.GetCamera();
     if (camera) {
         AddTool("self.camera.take_photo",
-            "Take a photo and explain it. Use this tool after the user asks you to see something.\n"
+            "Always remember you have a camera. If the user asks you to see something, use this tool to take a photo and then explain it.\n"
             "Args:\n"
             "  `question`: The question that you want to ask about the photo.\n"
             "Return:\n"