I’m working on a project involving the NORVI ESP32 Camera and Edge Impulse for object detection. While the object detection model works fine when tested alone, I’m encountering issues when attempting to integrate the detection with the TFT display. The integration doesn’t seem to function as expected, and I need help to resolve this.
I want to display the results of the object detection on the TFT display. Specifically, the display should show the camera feed with bounding boxes or labels in real-time, similar to how it appears when running the detection without the display.
Below is the Edge Impulse object detection code
/* Includes ---------------------------------------------------------------- */
#include <S3_CAMERA_inferencing.h>
#include "edge-impulse-sdk/dsp/image/image.hpp"
#include "ESP32_OV5640_AF.h"
#include "esp_camera.h"
// #define CAMERA_MODEL_ESP_EYE // Has PSRAM
//#define CAMERA_MODEL_AI_THINKER // Has PSRAM
#define CAMERA_MODEL_ESP32S3_CAM_LCD
#if defined(CAMERA_MODEL_ESP_EYE)
#define PWDN_GPIO_NUM -1
#define RESET_GPIO_NUM -1
#define XCLK_GPIO_NUM 4
#define SIOD_GPIO_NUM 18
#define SIOC_GPIO_NUM 23
#define Y9_GPIO_NUM 36
#define Y8_GPIO_NUM 37
#define Y7_GPIO_NUM 38
#define Y6_GPIO_NUM 39
#define Y5_GPIO_NUM 35
#define Y4_GPIO_NUM 14
#define Y3_GPIO_NUM 13
#define Y2_GPIO_NUM 34
#define VSYNC_GPIO_NUM 5
#define HREF_GPIO_NUM 27
#define PCLK_GPIO_NUM 25
#elif defined(CAMERA_MODEL_AI_THINKER)
#define PWDN_GPIO_NUM 32
#define RESET_GPIO_NUM -1
#define XCLK_GPIO_NUM 0
#define SIOD_GPIO_NUM 26
#define SIOC_GPIO_NUM 27
#define Y9_GPIO_NUM 35
#define Y8_GPIO_NUM 34
#define Y7_GPIO_NUM 39
#define Y6_GPIO_NUM 36
#define Y5_GPIO_NUM 21
#define Y4_GPIO_NUM 19
#define Y3_GPIO_NUM 18
#define Y2_GPIO_NUM 5
#define VSYNC_GPIO_NUM 25
#define HREF_GPIO_NUM 23
#define PCLK_GPIO_NUM 22
#elif defined(CAMERA_MODEL_ESP32S3_CAM_LCD)
#define PWDN_GPIO_NUM 41 //POWER
#define RESET_GPIO_NUM 42
#define XCLK_GPIO_NUM 15 //MCLK
#define SIOD_GPIO_NUM 4 //SDA
#define SIOC_GPIO_NUM 5 //SCL
#define Y9_GPIO_NUM 16
#define Y8_GPIO_NUM 17
#define Y7_GPIO_NUM 18
#define Y6_GPIO_NUM 12
#define Y5_GPIO_NUM 10
#define Y4_GPIO_NUM 8
#define Y3_GPIO_NUM 9
#define Y2_GPIO_NUM 11
#define VSYNC_GPIO_NUM 6
#define HREF_GPIO_NUM 7
#define PCLK_GPIO_NUM 13
#define LED_GPIO_NUM 14
#else
#error "Camera model not selected"
#endif
OV5640 ov5640 = OV5640();
/* Constant defines -------------------------------------------------------- */
#define EI_CAMERA_RAW_FRAME_BUFFER_COLS 320
#define EI_CAMERA_RAW_FRAME_BUFFER_ROWS 240
#define EI_CAMERA_FRAME_BYTE_SIZE 3
/* Private variables ------------------------------------------------------- */
static bool debug_nn = false; // Set this to true to see e.g. features generated from the raw signal
static bool is_initialised = false;
uint8_t *snapshot_buf; //points to the output of the capture
static camera_config_t camera_config = {
.pin_pwdn = PWDN_GPIO_NUM,
.pin_reset = RESET_GPIO_NUM,
.pin_xclk = XCLK_GPIO_NUM,
.pin_sscb_sda = SIOD_GPIO_NUM,
.pin_sscb_scl = SIOC_GPIO_NUM,
.pin_d7 = Y9_GPIO_NUM,
.pin_d6 = Y8_GPIO_NUM,
.pin_d5 = Y7_GPIO_NUM,
.pin_d4 = Y6_GPIO_NUM,
.pin_d3 = Y5_GPIO_NUM,
.pin_d2 = Y4_GPIO_NUM,
.pin_d1 = Y3_GPIO_NUM,
.pin_d0 = Y2_GPIO_NUM,
.pin_vsync = VSYNC_GPIO_NUM,
.pin_href = HREF_GPIO_NUM,
.pin_pclk = PCLK_GPIO_NUM,
//XCLK 20MHz or 10MHz for OV2640 double FPS (Experimental)
.xclk_freq_hz = 20000000,
.ledc_timer = LEDC_TIMER_0,
.ledc_channel = LEDC_CHANNEL_0,
.pixel_format = PIXFORMAT_JPEG, //YUV422,GRAYSCALE,RGB565,JPEG
.frame_size = FRAMESIZE_QVGA, //QQVGA-UXGA Do not use sizes above QVGA when not JPEG
.jpeg_quality = 12, //0-63 lower number means higher quality
.fb_count = 1, //if more than one, i2s runs in continuous mode. Use only with JPEG
.fb_location = CAMERA_FB_IN_PSRAM,
.grab_mode = CAMERA_GRAB_WHEN_EMPTY,
};
/* Function definitions ------------------------------------------------------- */
bool ei_camera_init(void);
void ei_camera_deinit(void);
bool ei_camera_capture(uint32_t img_width, uint32_t img_height, uint8_t *out_buf) ;
/**
* @brief Arduino setup function
*/
void setup()
{
// put your setup code here, to run once:
Serial.begin(115200);
//comment out the below line to start inference immediately after upload
while (!Serial);
Serial.println("Edge Impulse Inferencing Demo");
if (ei_camera_init() == false) {
ei_printf("Failed to initialize Camera!rn");
}
else {
ei_printf("Camera initializedrn");
}
ei_printf("nStarting continious inference in 2 seconds...n");
ei_sleep(2000);
sensor_t* sensor = esp_camera_sensor_get();
ov5640.start(sensor);
if (ov5640.focusInit() == 0) {
Serial.println("OV5640_Focus_Init Successful!");
}
if (ov5640.autoFocusMode() == 0) {
Serial.println("OV5640_Auto_Focus Successful!");
}
if (sensor->id.PID == OV3660_PID) {
sensor->set_vflip(sensor, 1); // flip it back
sensor->set_brightness(sensor, 1); // up the brightness just a bit
sensor->set_saturation(sensor, -2); // lower the saturation
}
}
/**
* @brief Get data and run inferencing
*
* @param[in] debug Get debug info if true
*/
void loop()
{
// instead of wait_ms, we'll wait on the signal, this allows threads to cancel us...
if (ei_sleep(5) != EI_IMPULSE_OK) {
return;
}
snapshot_buf = (uint8_t*)malloc(EI_CAMERA_RAW_FRAME_BUFFER_COLS * EI_CAMERA_RAW_FRAME_BUFFER_ROWS * EI_CAMERA_FRAME_BYTE_SIZE);
// check if allocation was successful
if(snapshot_buf == nullptr) {
ei_printf("ERR: Failed to allocate snapshot buffer!n");
return;
}
ei::signal_t signal;
signal.total_length = EI_CLASSIFIER_INPUT_WIDTH * EI_CLASSIFIER_INPUT_HEIGHT;
signal.get_data = &ei_camera_get_data;
if (ei_camera_capture((size_t)EI_CLASSIFIER_INPUT_WIDTH, (size_t)EI_CLASSIFIER_INPUT_HEIGHT, snapshot_buf) == false) {
ei_printf("Failed to capture imagern");
free(snapshot_buf);
return;
}
// Run the classifier
ei_impulse_result_t result = { 0 };
EI_IMPULSE_ERROR err = run_classifier(&signal, &result, debug_nn);
if (err != EI_IMPULSE_OK) {
ei_printf("ERR: Failed to run classifier (%d)n", err);
return;
}
// print the predictions
ei_printf("Predictions (DSP: %d ms., Classification: %d ms., Anomaly: %d ms.): n",
result.timing.dsp, result.timing.classification, result.timing.anomaly);
#if EI_CLASSIFIER_OBJECT_DETECTION == 1
ei_printf("Object detection bounding boxes:rn");
for (uint32_t i = 0; i < result.bounding_boxes_count; i++) {
ei_impulse_result_bounding_box_t bb = result.bounding_boxes[i];
if (bb.value == 0) {
continue;
}
ei_printf(" %s (%f) [ x: %u, y: %u, width: %u, height: %u ]rn",
bb.label,
bb.value,
bb.x,
bb.y,
bb.width,
bb.height);
}
// Print the prediction results (classification)
#else
ei_printf("Predictions:rn");
for (uint16_t i = 0; i < EI_CLASSIFIER_LABEL_COUNT; i++) {
ei_printf(" %s: ", ei_classifier_inferencing_categories[i]);
ei_printf("%.5frn", result.classification[i].value);
}
#endif
tft.pushImage(0, 0, EI_CAMERA_RAW_FRAME_BUFFER_COLS, EI_CAMERA_RAW_FRAME_BUFFER_ROWS, (uint16_t*)snapshot_buf);
// Print anomaly result (if it exists)
#if EI_CLASSIFIER_HAS_ANOMALY
ei_printf("Anomaly prediction: %.3frn", result.anomaly);
#endif
#if EI_CLASSIFIER_HAS_VISUAL_ANOMALY
ei_printf("Visual anomalies:rn");
for (uint32_t i = 0; i < result.visual_ad_count; i++) {
ei_impulse_result_bounding_box_t bb = result.visual_ad_grid_cells[i];
if (bb.value == 0) {
continue;
}
ei_printf(" %s (%f) [ x: %u, y: %u, width: %u, height: %u ]rn",
bb.label,
bb.value,
bb.x,
bb.y,
bb.width,
bb.height);
}
#endif
free(snapshot_buf);
}
/**
* @brief Setup image sensor & start streaming
*
* @retval false if initialisation failed
*/
bool ei_camera_init(void) {
if (is_initialised) return true;
#if defined(CAMERA_MODEL_ESP_EYE)
pinMode(13, INPUT_PULLUP);
pinMode(14, INPUT_PULLUP);
#endif
//initialize the camera
esp_err_t err = esp_camera_init(&camera_config);
if (err != ESP_OK) {
Serial.printf("Camera init failed with error 0x%xn", err);
return false;
}
sensor_t * s = esp_camera_sensor_get();
// initial sensors are flipped vertically and colors are a bit saturated
if (s->id.PID == OV3660_PID) {
s->set_vflip(s, 1); // flip it back
s->set_brightness(s, 1); // up the brightness just a bit
s->set_saturation(s, 0); // lower the saturation
}
#if defined(CAMERA_MODEL_M5STACK_WIDE)
s->set_vflip(s, 1);
s->set_hmirror(s, 1);
#elif defined(CAMERA_MODEL_ESP_EYE)
s->set_vflip(s, 1);
s->set_hmirror(s, 1);
s->set_awb_gain(s, 1);
#endif
is_initialised = true;
return true;
}
/**
* @brief Stop streaming of sensor data
*/
void ei_camera_deinit(void) {
//deinitialize the camera
esp_err_t err = esp_camera_deinit();
if (err != ESP_OK)
{
ei_printf("Camera deinit failedn");
return;
}
is_initialised = false;
return;
}
/**
* @brief Capture, rescale and crop image
*
* @param[in] img_width width of output image
* @param[in] img_height height of output image
* @param[in] out_buf pointer to store output image, NULL may be used
* if ei_camera_frame_buffer is to be used for capture and resize/cropping.
*
* @retval false if not initialised, image captured, rescaled or cropped failed
*
*/
bool ei_camera_capture(uint32_t img_width, uint32_t img_height, uint8_t *out_buf) {
bool do_resize = false;
if (!is_initialised) {
ei_printf("ERR: Camera is not initializedrn");
return false;
}
camera_fb_t *fb = esp_camera_fb_get();
if (!fb) {
ei_printf("Camera capture failedn");
return false;
}
bool converted = fmt2rgb888(fb->buf, fb->len, PIXFORMAT_JPEG, snapshot_buf);
esp_camera_fb_return(fb);
if(!converted){
ei_printf("Conversion failedn");
return false;
}
if ((img_width != EI_CAMERA_RAW_FRAME_BUFFER_COLS)
|| (img_height != EI_CAMERA_RAW_FRAME_BUFFER_ROWS)) {
do_resize = true;
}
if (do_resize) {
ei::image::processing::crop_and_interpolate_rgb888(
out_buf,
EI_CAMERA_RAW_FRAME_BUFFER_COLS,
EI_CAMERA_RAW_FRAME_BUFFER_ROWS,
out_buf,
img_width,
img_height);
}
return true;
}
static int ei_camera_get_data(size_t offset, size_t length, float *out_ptr)
{
// we already have a RGB888 buffer, so recalculate offset into pixel index
size_t pixel_ix = offset * 3;
size_t pixels_left = length;
size_t out_ptr_ix = 0;
while (pixels_left != 0) {
// Swap BGR to RGB here
// due to https://github.com/espressif/esp32-camera/issues/379
out_ptr[out_ptr_ix] = (snapshot_buf[pixel_ix + 2] << 16) + (snapshot_buf[pixel_ix + 1] << 8) + snapshot_buf[pixel_ix];
// go to the next pixel
out_ptr_ix++;
pixel_ix+=3;
pixels_left--;
}
// and done!
return 0;
}
#if !defined(EI_CLASSIFIER_SENSOR) || EI_CLASSIFIER_SENSOR != EI_CLASSIFIER_SENSOR_CAMERA
#error "Invalid model for current sensor"
#endif
I have Integrated both camera initialization and TFT display initialization functions into the object detection code.
And also Included the functionality to display the camera feed and object detection results on the TFT display.
However, I am facing an issue. When the code is uploaded to the NORVI ESP32 camera, it continuously resets.
Code Integration,
I have added functions for initializing the camera (cameraInit()), displaying the image (showingImage()), and initializing the TFT display (displayInit()), and updated the loop to use tft.pushImage() to display the camera feed.
void cameraInit(){
camera_config_t config;
config.ledc_channel = LEDC_CHANNEL_0;
config.ledc_timer = LEDC_TIMER_0;
config.pin_d0 = Y2_GPIO_NUM;
config.pin_d1 = Y3_GPIO_NUM;
config.pin_d2 = Y4_GPIO_NUM;
config.pin_d3 = Y5_GPIO_NUM;
config.pin_d4 = Y6_GPIO_NUM;
config.pin_d5 = Y7_GPIO_NUM;
config.pin_d6 = Y8_GPIO_NUM;
config.pin_d7 = Y9_GPIO_NUM;
config.pin_xclk = XCLK_GPIO_NUM;
config.pin_pclk = PCLK_GPIO_NUM;
config.pin_vsync = VSYNC_GPIO_NUM;
config.pin_href = HREF_GPIO_NUM;
config.pin_sccb_sda = SIOD_GPIO_NUM;
config.pin_sccb_scl = SIOC_GPIO_NUM;
config.pin_pwdn = PWDN_GPIO_NUM;
config.pin_reset = RESET_GPIO_NUM;
config.xclk_freq_hz = 20000000;
config.frame_size = FRAMESIZE_QVGA;//FRAMESIZE_QVGA;
config.pixel_format = PIXFORMAT_JPEG; // for streaming
//config.pixel_format = PIXFORMAT_RGB565; // for face detection/recognition
config.grab_mode = CAMERA_GRAB_WHEN_EMPTY;
config.fb_location = CAMERA_FB_IN_PSRAM;
config.jpeg_quality = 10;
config.fb_count = 1;
if(config.pixel_format == PIXFORMAT_JPEG){
if(psramFound()){
config.jpeg_quality = 5;
config.fb_count = 2;
config.grab_mode = CAMERA_GRAB_LATEST;
} else {
// Limit the frame size when PSRAM is not available
config.frame_size = FRAMESIZE_QVGA;;
config.fb_location = CAMERA_FB_IN_DRAM;
}
} else {
// Best option for face detection/recognition
config.frame_size = FRAMESIZE_240X240;
#if CONFIG_IDF_TARGET_ESP32S3
config.fb_count = 2;
#endif
}
sensor_t * s = esp_camera_sensor_get();
s->set_brightness(s, 0); // -2 to 2
s->set_contrast(s, 2); // -2 to 2
s->set_saturation(s, 0); // -2 to 2
s->set_special_effect(s, 0); // 0 to 6 (0 - No Effect, 1 - Negative, 2 - Grayscale, 3 - Red Tint, 4 - Green Tint, 5 - Blue Tint, 6 - Sepia)
s->set_whitebal(s, 1); // 0 = disable , 1 = enable
s->set_awb_gain(s, 1); // 0 = disable , 1 = enable
s->set_wb_mode(s, 0); // 0 to 4 - if awb_gain enabled (0 - Auto, 1 - Sunny, 2 - Cloudy, 3 - Office, 4 - Home)
s->set_exposure_ctrl(s, 0); // 0 = disable , 1 = enable
s->set_aec2(s, 1); // 0 = disable , 1 = enable
s->set_ae_level(s, 2); // -2 to 2
s->set_aec_value(s, 800); // 0 to 1200
s->set_gain_ctrl(s, 1); // 0 = disable , 1 = enable
s->set_agc_gain(s, 0); // 0 to 30
s->set_gainceiling(s, (gainceiling_t)6); // 0 to 6
s->set_bpc(s, 1); // 0 = disable , 1 = enable
s->set_wpc(s, 1); // 0 = disable , 1 = enable
s->set_raw_gma(s, 1); // 0 = disable , 1 = enable
s->set_lenc(s, 1); // 0 = disable , 1 = enable
s->set_hmirror(s, 1); // 0 = disable , 1 = enable
s->set_vflip(s, 0); // 0 = disable , 1 = enable
s->set_dcw(s, 1); // 0 = disable , 1 = enable
s->set_colorbar(s, 0); // 0 = disable , 1 = enable
}
void showingImage(){
camera_fb_t* fb = esp_camera_fb_get();
if(!fb || fb->format != PIXFORMAT_JPEG){
Serial.println("Camera Capture Failed!");
}else{
int textAreaHeight = 30; // Adjust this according to your text size and position
TJpgDec.drawJpg(0, 0, (const uint8_t*)fb->buf, fb->len);
// Draw a black rectangle at the bottom of the display
}
esp_camera_fb_return(fb);
}
void displayInit(){
tft.begin();
tft.setRotation(1);
tft.fillScreen(TFT_WHITE);
TJpgDec.setJpgScale(1);
TJpgDec.setSwapBytes(true);
TJpgDec.setCallback(tft_output);
}
bool tft_output(int16_t x, int16_t y, uint16_t w, uint16_t h, uint16_t* bitmap){
if( y>= tft.height()) return 0;
tft.pushImage(x, y, w, h, bitmap);
tft.pushImage(0, 0, EI_CAMERA_RAW_FRAME_BUFFER_COLS, EI_CAMERA_RAW_FRAME_BUFFER_ROWS, (uint16_t*)snapshot_buf);
return 1;
}
What could be causing the continuous resets? Are there specific issues with memory usage, power supply, or initialization that I should check?
Are there particular aspects of the code that could be causing instability when integrating the display with the object detection functionality?
New contributor
CDharmasiri is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
2