github.com/espressif/esp32-camera

ESP32 Camera Driver

General Information

This repository hosts ESP32 series Soc compatible driver for image sensors. Additionally it provides a few tools, which allow converting the captured frame data to the more common BMP and JPEG formats.

Supported Soc

• ESP32
• ESP32-S2
• ESP32-S3

Supported Sensor

model	max resolution	color type	output format	Len Size
OV2640	1600 x 1200	color	YUV(422/420)/YCbCr422 RGB565/555 8-bit compressed data 8/10-bit Raw RGB data	1/4"
OV3660	2048 x 1536	color	raw RGB data RGB565/555/444 CCIR656 YCbCr422 compression	1/5"
OV5640	2592 x 1944	color	RAW RGB RGB565/555/444 CCIR656 YUV422/420 YCbCr422 compression	1/4"
OV7670	640 x 480	color	Raw Bayer RGB Processed Bayer RGB YUV/YCbCr422 GRB422 RGB565/555	1/6"
OV7725	640 x 480	color	Raw RGB GRB 422 RGB565/555/444 YCbCr 422	1/4"
NT99141	1280 x 720	color	YCbCr 422 RGB565/555/444 Raw CCIR656 JPEG compression	1/4"
GC032A	640 x 480	color	YUV/YCbCr422 RAW Bayer RGB565	1/10"
GC0308	640 x 480	color	YUV/YCbCr422 RAW Bayer RGB565 Grayscale	1/6.5"
GC2145	1600 x 1200	color	YUV/YCbCr422 RAW Bayer RGB565	1/5"
BF3005	640 x 480	color	YUV/YCbCr422 RAW Bayer RGB565	1/4"
BF20A6	640 x 480	color	YUV/YCbCr422 RAW Bayer Only Y	1/10"
SC101IOT	1280 x 720	color	YUV/YCbCr422 Raw RGB	1/4.2"
SC030IOT	640 x 480	color	YUV/YCbCr422 RAW Bayer	1/6.5"
SC031GS	640 x 480	monochrome	RAW MONO Grayscale	1/6"

Important to Remember

• Except when using CIF or lower resolution with JPEG, the driver requires PSRAM to be installed and activated.
• Using YUV or RGB puts a lot of strain on the chip because writing to PSRAM is not particularly fast. The result is that image data might be missing. This is particularly true if WiFi is enabled. If you need RGB data, it is recommended that JPEG is captured and then turned into RGB using fmt2rgb888 or fmt2bmp/frame2bmp.
• When 1 frame buffer is used, the driver will wait for the current frame to finish (VSYNC) and start I2S DMA. After the frame is acquired, I2S will be stopped and the frame buffer returned to the application. This approach gives more control over the system, but results in longer time to get the frame.
• When 2 or more frame bufers are used, I2S is running in continuous mode and each frame is pushed to a queue that the application can access. This approach puts more strain on the CPU/Memory, but allows for double the frame rate. Please use only with JPEG.

Installation Instructions

Using with ESP-IDF

• Add a dependency on espressif/esp32-camera component:

  idf.py add-dependency "espressif/esp32-camera"
  

  (or add it manually in idf_component.yml of your project)
• Enable PSRAM in menuconfig (also set Flash and PSRAM frequiencies to 80MHz)
• Include esp_camera.h in your code

These instructions also work for PlatformIO, if you are using framework=espidf.

Using with Arduino

Arduino IDE

If you are using the arduino-esp32 core in Arduino IDE, no installation is needed! You can use esp32-camera right away.

PlatformIO

The easy way -- on the env section of platformio.ini, add the following:

[env]
lib_deps =
  esp32-camera

Now the esp_camera.h is available to be included:

#include "esp_camera.h"

Enable PSRAM on menuconfig or type it direclty on sdkconfig. Check the official doc for more info.

CONFIG_ESP32_SPIRAM_SUPPORT=y

Examples

This component comes with a basic example illustrating how to get frames from the camera. You can try out the example using the following command:

idf.py create-project-from-example "espressif/esp32-camera:camera_example"

This command will download the example into camera_example directory. It comes already pre-configured with the correct settings in menuconfig.

Initialization

#include "esp_camera.h"

//WROVER-KIT PIN Map
#define CAM_PIN_PWDN    -1 //power down is not used
#define CAM_PIN_RESET   -1 //software reset will be performed
#define CAM_PIN_XCLK    21
#define CAM_PIN_SIOD    26
#define CAM_PIN_SIOC    27

#define CAM_PIN_D7      35
#define CAM_PIN_D6      34
#define CAM_PIN_D5      39
#define CAM_PIN_D4      36
#define CAM_PIN_D3      19
#define CAM_PIN_D2      18
#define CAM_PIN_D1       5
#define CAM_PIN_D0       4
#define CAM_PIN_VSYNC   25
#define CAM_PIN_HREF    23
#define CAM_PIN_PCLK    22

static camera_config_t camera_config = {
    .pin_pwdn  = CAM_PIN_PWDN,
    .pin_reset = CAM_PIN_RESET,
    .pin_xclk = CAM_PIN_XCLK,
    .pin_sccb_sda = CAM_PIN_SIOD,
    .pin_sccb_scl = CAM_PIN_SIOC,

    .pin_d7 = CAM_PIN_D7,
    .pin_d6 = CAM_PIN_D6,
    .pin_d5 = CAM_PIN_D5,
    .pin_d4 = CAM_PIN_D4,
    .pin_d3 = CAM_PIN_D3,
    .pin_d2 = CAM_PIN_D2,
    .pin_d1 = CAM_PIN_D1,
    .pin_d0 = CAM_PIN_D0,
    .pin_vsync = CAM_PIN_VSYNC,
    .pin_href = CAM_PIN_HREF,
    .pin_pclk = CAM_PIN_PCLK,

    .xclk_freq_hz = 20000000,//EXPERIMENTAL: Set to 16MHz on ESP32-S2 or ESP32-S3 to enable EDMA mode
    .ledc_timer = LEDC_TIMER_0,
    .ledc_channel = LEDC_CHANNEL_0,

    .pixel_format = PIXFORMAT_JPEG,//YUV422,GRAYSCALE,RGB565,JPEG
    .frame_size = FRAMESIZE_UXGA,//QQVGA-UXGA, For ESP32, do not use sizes above QVGA when not JPEG. The performance of the ESP32-S series has improved a lot, but JPEG mode always gives better frame rates.

    .jpeg_quality = 12, //0-63, for OV series camera sensors, lower number means higher quality
    .fb_count = 1, //When jpeg mode is used, if fb_count more than one, the driver will work in continuous mode.
    .grab_mode = CAMERA_GRAB_WHEN_EMPTY//CAMERA_GRAB_LATEST. Sets when buffers should be filled
};

esp_err_t camera_init(){
    //power up the camera if PWDN pin is defined
    if(CAM_PIN_PWDN != -1){
        pinMode(CAM_PIN_PWDN, OUTPUT);
        digitalWrite(CAM_PIN_PWDN, LOW);
    }

    //initialize the camera
    esp_err_t err = esp_camera_init(&camera_config);
    if (err != ESP_OK) {
        ESP_LOGE(TAG, "Camera Init Failed");
        return err;
    }

    return ESP_OK;
}

esp_err_t camera_capture(){
    //acquire a frame
    camera_fb_t * fb = esp_camera_fb_get();
    if (!fb) {
        ESP_LOGE(TAG, "Camera Capture Failed");
        return ESP_FAIL;
    }
    //replace this with your own function
    process_image(fb->width, fb->height, fb->format, fb->buf, fb->len);
  
    //return the frame buffer back to the driver for reuse
    esp_camera_fb_return(fb);
    return ESP_OK;
}

JPEG HTTP Capture

#include "esp_camera.h"
#include "esp_http_server.h"
#include "esp_timer.h"

typedef struct {
        httpd_req_t *req;
        size_t len;
} jpg_chunking_t;

static size_t jpg_encode_stream(void * arg, size_t index, const void* data, size_t len){
    jpg_chunking_t *j = (jpg_chunking_t *)arg;
    if(!index){
        j->len = 0;
    }
    if(httpd_resp_send_chunk(j->req, (const char *)data, len) != ESP_OK){
        return 0;
    }
    j->len += len;
    return len;
}

esp_err_t jpg_httpd_handler(httpd_req_t *req){
    camera_fb_t * fb = NULL;
    esp_err_t res = ESP_OK;
    size_t fb_len = 0;
    int64_t fr_start = esp_timer_get_time();

    fb = esp_camera_fb_get();
    if (!fb) {
        ESP_LOGE(TAG, "Camera capture failed");
        httpd_resp_send_500(req);
        return ESP_FAIL;
    }
    res = httpd_resp_set_type(req, "image/jpeg");
    if(res == ESP_OK){
        res = httpd_resp_set_hdr(req, "Content-Disposition", "inline; filename=capture.jpg");
    }

    if(res == ESP_OK){
        if(fb->format == PIXFORMAT_JPEG){
            fb_len = fb->len;
            res = httpd_resp_send(req, (const char *)fb->buf, fb->len);
        } else {
            jpg_chunking_t jchunk = {req, 0};
            res = frame2jpg_cb(fb, 80, jpg_encode_stream, &jchunk)?ESP_OK:ESP_FAIL;
            httpd_resp_send_chunk(req, NULL, 0);
            fb_len = jchunk.len;
        }
    }
    esp_camera_fb_return(fb);
    int64_t fr_end = esp_timer_get_time();
    ESP_LOGI(TAG, "JPG: %uKB %ums", (uint32_t)(fb_len/1024), (uint32_t)((fr_end - fr_start)/1000));
    return res;
}

JPEG HTTP Stream

#include "esp_camera.h"
#include "esp_http_server.h"
#include "esp_timer.h"

#define PART_BOUNDARY "123456789000000000000987654321"
static const char* _STREAM_CONTENT_TYPE = "multipart/x-mixed-replace;boundary=" PART_BOUNDARY;
static const char* _STREAM_BOUNDARY = "\r\n--" PART_BOUNDARY "\r\n";
static const char* _STREAM_PART = "Content-Type: image/jpeg\r\nContent-Length: %u\r\n\r\n";

esp_err_t jpg_stream_httpd_handler(httpd_req_t *req){
    camera_fb_t * fb = NULL;
    esp_err_t res = ESP_OK;
    size_t _jpg_buf_len;
    uint8_t * _jpg_buf;
    char * part_buf[64];
    static int64_t last_frame = 0;
    if(!last_frame) {
        last_frame = esp_timer_get_time();
    }

    res = httpd_resp_set_type(req, _STREAM_CONTENT_TYPE);
    if(res != ESP_OK){
        return res;
    }

    while(true){
        fb = esp_camera_fb_get();
        if (!fb) {
            ESP_LOGE(TAG, "Camera capture failed");
            res = ESP_FAIL;
            break;
        }
        if(fb->format != PIXFORMAT_JPEG){
            bool jpeg_converted = frame2jpg(fb, 80, &_jpg_buf, &_jpg_buf_len);
            if(!jpeg_converted){
                ESP_LOGE(TAG, "JPEG compression failed");
                esp_camera_fb_return(fb);
                res = ESP_FAIL;
            }
        } else {
            _jpg_buf_len = fb->len;
            _jpg_buf = fb->buf;
        }

        if(res == ESP_OK){
            res = httpd_resp_send_chunk(req, _STREAM_BOUNDARY, strlen(_STREAM_BOUNDARY));
        }
        if(res == ESP_OK){
            size_t hlen = snprintf((char *)part_buf, 64, _STREAM_PART, _jpg_buf_len);

            res = httpd_resp_send_chunk(req, (const char *)part_buf, hlen);
        }
        if(res == ESP_OK){
            res = httpd_resp_send_chunk(req, (const char *)_jpg_buf, _jpg_buf_len);
        }
        if(fb->format != PIXFORMAT_JPEG){
            free(_jpg_buf);
        }
        esp_camera_fb_return(fb);
        if(res != ESP_OK){
            break;
        }
        int64_t fr_end = esp_timer_get_time();
        int64_t frame_time = fr_end - last_frame;
        last_frame = fr_end;
        frame_time /= 1000;
        ESP_LOGI(TAG, "MJPG: %uKB %ums (%.1ffps)",
            (uint32_t)(_jpg_buf_len/1024),
            (uint32_t)frame_time, 1000.0 / (uint32_t)frame_time);
    }

    last_frame = 0;
    return res;
}

BMP HTTP Capture

#include "esp_camera.h"
#include "esp_http_server.h"
#include "esp_timer.h"

esp_err_t bmp_httpd_handler(httpd_req_t *req){
    camera_fb_t * fb = NULL;
    esp_err_t res = ESP_OK;
    int64_t fr_start = esp_timer_get_time();

    fb = esp_camera_fb_get();
    if (!fb) {
        ESP_LOGE(TAG, "Camera capture failed");
        httpd_resp_send_500(req);
        return ESP_FAIL;
    }

    uint8_t * buf = NULL;
    size_t buf_len = 0;
    bool converted = frame2bmp(fb, &buf, &buf_len);
    esp_camera_fb_return(fb);
    if(!converted){
        ESP_LOGE(TAG, "BMP conversion failed");
        httpd_resp_send_500(req);
        return ESP_FAIL;
    }

    res = httpd_resp_set_type(req, "image/x-windows-bmp")
       || httpd_resp_set_hdr(req, "Content-Disposition", "inline; filename=capture.bmp")
       || httpd_resp_send(req, (const char *)buf, buf_len);
    free(buf);
    int64_t fr_end = esp_timer_get_time();
    ESP_LOGI(TAG, "BMP: %uKB %ums", (uint32_t)(buf_len/1024), (uint32_t)((fr_end - fr_start)/1000));
    return res;
}