ESP32-S3搭建外网可访问的网络摄像头（内网穿透）

      // Copyright 2015-2016 Espressif Systems (Shanghai) PTE LTD
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//     http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
#include "esp_http_server.h"
#include "esp_timer.h"
#include "esp_camera.h"
#include "img_converters.h"
#include "fb_gfx.h"
#include "esp32-hal-ledc.h"
#include "sdkconfig.h"
#include "camera_index.h"

#if defined(ARDUINO_ARCH_ESP32) && defined(CONFIG_ARDUHAL_ESP_LOG)
#include "esp32-hal-log.h"
#endif

// Face Detection will not work on boards without (or with disabled) PSRAM
#ifdef BOARD_HAS_PSRAM
#define CONFIG_ESP_FACE_DETECT_ENABLED 1
// Face Recognition takes upward from 15 seconds per frame on chips other than ESP32S3
// Makes no sense to have it enabled for them
#if CONFIG_IDF_TARGET_ESP32S3
#define CONFIG_ESP_FACE_RECOGNITION_ENABLED 1
#else
#define CONFIG_ESP_FACE_RECOGNITION_ENABLED 0
#endif
#else
#define CONFIG_ESP_FACE_DETECT_ENABLED 0
#define CONFIG_ESP_FACE_RECOGNITION_ENABLED 0
#endif

#if CONFIG_ESP_FACE_DETECT_ENABLED

#include <vector>
#include "human_face_detect_msr01.hpp"
#include "human_face_detect_mnp01.hpp"

#define TWO_STAGE 1 /*<! 1: detect by two-stage which is more accurate but slower(with keypoints). */
                    /*<! 0: detect by one-stage which is less accurate but faster(without keypoints). */

#if CONFIG_ESP_FACE_RECOGNITION_ENABLED
#include "face_recognition_tool.hpp"
#include "face_recognition_112_v1_s16.hpp"
#include "face_recognition_112_v1_s8.hpp"

#define QUANT_TYPE 0 //if set to 1 => very large firmware, very slow, reboots when streaming...

#define FACE_ID_SAVE_NUMBER 7
#endif

#define FACE_COLOR_WHITE 0x00FFFFFF
#define FACE_COLOR_BLACK 0x00000000
#define FACE_COLOR_RED 0x000000FF
#define FACE_COLOR_GREEN 0x0000FF00
#define FACE_COLOR_BLUE 0x00FF0000
#define FACE_COLOR_YELLOW (FACE_COLOR_RED | FACE_COLOR_GREEN)
#define FACE_COLOR_CYAN (FACE_COLOR_BLUE | FACE_COLOR_GREEN)
#define FACE_COLOR_PURPLE (FACE_COLOR_BLUE | FACE_COLOR_RED)
#endif

// Enable LED FLASH setting
#define CONFIG_LED_ILLUMINATOR_ENABLED 1

// LED FLASH setup
#if CONFIG_LED_ILLUMINATOR_ENABLED

#define LED_LEDC_CHANNEL 2 //Using different ledc channel/timer than camera
#define CONFIG_LED_MAX_INTENSITY 255

int led_duty = 0;
bool isStreaming = false;

#endif

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

#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\nX-Timestamp: %d.%06d\r\n\r\n";

httpd_handle_t stream_httpd = NULL;
httpd_handle_t camera_httpd = NULL;

#if CONFIG_ESP_FACE_DETECT_ENABLED

static int8_t detection_enabled = 0;

// #if TWO_STAGE
// static HumanFaceDetectMSR01 s1(0.1F, 0.5F, 10, 0.2F);
// static HumanFaceDetectMNP01 s2(0.5F, 0.3F, 5);
// #else
// static HumanFaceDetectMSR01 s1(0.3F, 0.5F, 10, 0.2F);
// #endif

#if CONFIG_ESP_FACE_RECOGNITION_ENABLED
static int8_t recognition_enabled = 0;
static int8_t is_enrolling = 0;

#if QUANT_TYPE
    // S16 model
    FaceRecognition112V1S16 recognizer;
#else
    // S8 model
    FaceRecognition112V1S8 recognizer;
#endif
#endif

#endif

typedef struct
{
    size_t size;  //number of values used for filtering
    size_t index; //current value index
    size_t count; //value count
    int sum;
    int *values; //array to be filled with values
} ra_filter_t;

static ra_filter_t ra_filter;

static ra_filter_t *ra_filter_init(ra_filter_t *filter, size_t sample_size)
{
    memset(filter, 0, sizeof(ra_filter_t));

    filter->values = (int *)malloc(sample_size * sizeof(int));
    if (!filter->values)
    {
        return NULL;
    }
    memset(filter->values, 0, sample_size * sizeof(int));

    filter->size = sample_size;
    return filter;
}

#if ARDUHAL_LOG_LEVEL >= ARDUHAL_LOG_LEVEL_INFO
static int ra_filter_run(ra_filter_t *filter, int value)
{
    if (!filter->values)
    {
        return value;
    }
    filter->sum -= filter->values[filter->index];
    filter->values[filter->index] = value;
    filter->sum += filter->values[filter->index];
    filter->index++;
    filter->index = filter->index % filter->size;
    if (filter->count < filter->size)
    {
        filter->count++;
    }
    return filter->sum / filter->count;
}
#endif

#if CONFIG_ESP_FACE_DETECT_ENABLED
#if CONFIG_ESP_FACE_RECOGNITION_ENABLED
static void rgb_print(fb_data_t *fb, uint32_t color, const char *str)
{
    fb_gfx_print(fb, (fb->width - (strlen(str) * 14)) / 2, 10, color, str);
}

static int rgb_printf(fb_data_t *fb, uint32_t color, const char *format, ...)
{
    char loc_buf[64];
    char *temp = loc_buf;
    int len;
    va_list arg;
    va_list copy;
    va_start(arg, format);
    va_copy(copy, arg);
    len = vsnprintf(loc_buf, sizeof(loc_buf), format, arg);
    va_end(copy);
    if (len >= sizeof(loc_buf))
    {
        temp = (char *)malloc(len + 1);
        if (temp == NULL)
        {
            return 0;
        }
    }
    vsnprintf(temp, len + 1, format, arg);
    va_end(arg);
    rgb_print(fb, color, temp);
    if (len > 64)
    {
        free(temp);
    }
    return len;
}
#endif
static void draw_face_boxes(fb_data_t *fb, std::list<dl::detect::result_t> *results, int face_id)
{
    int x, y, w, h;
    uint32_t color = FACE_COLOR_YELLOW;
    if (face_id < 0)
    {
        color = FACE_COLOR_RED;
    }
    else if (face_id > 0)
    {
        color = FACE_COLOR_GREEN;
    }
    if(fb->bytes_per_pixel == 2){
        //color = ((color >> 8) & 0xF800) | ((color >> 3) & 0x07E0) | (color & 0x001F);
        color = ((color >> 16) & 0x001F) | ((color >> 3) & 0x07E0) | ((color << 8) & 0xF800);
    }
    int i = 0;
    for (std::list<dl::detect::result_t>::iterator prediction = results->begin(); prediction != results->end(); prediction++, i++)
    {
        // rectangle box
        x = (int)prediction->box[0];
        y = (int)prediction->box[1];
        w = (int)prediction->box[2] - x + 1;
        h = (int)prediction->box[3] - y + 1;
        if((x + w) > fb->width){
            w = fb->width - x;
        }
        if((y + h) > fb->height){
            h = fb->height - y;
        }
        fb_gfx_drawFastHLine(fb, x, y, w, color);
        fb_gfx_drawFastHLine(fb, x, y + h - 1, w, color);
        fb_gfx_drawFastVLine(fb, x, y, h, color);
        fb_gfx_drawFastVLine(fb, x + w - 1, y, h, color);
#if TWO_STAGE
        // landmarks (left eye, mouth left, nose, right eye, mouth right)
        int x0, y0, j;
        for (j = 0; j < 10; j+=2) {
            x0 = (int)prediction->keypoint[j];
            y0 = (int)prediction->keypoint[j+1];
            fb_gfx_fillRect(fb, x0, y0, 3, 3, color);
        }
#endif
    }
}

#if CONFIG_ESP_FACE_RECOGNITION_ENABLED
static int run_face_recognition(fb_data_t *fb, std::list<dl::detect::result_t> *results)
{
    std::vector<int> landmarks = results->front().keypoint;
    int id = -1;

    Tensor<uint8_t> tensor;
    tensor.set_element((uint8_t *)fb->data).set_shape({fb->height, fb->width, 3}).set_auto_free(false);

    int enrolled_count = recognizer.get_enrolled_id_num();

    if (enrolled_count < FACE_ID_SAVE_NUMBER && is_enrolling){
        id = recognizer.enroll_id(tensor, landmarks, "", true);
        log_i("Enrolled ID: %d", id);
        rgb_printf(fb, FACE_COLOR_CYAN, "ID[%u]", id);
    }

    face_info_t recognize = recognizer.recognize(tensor, landmarks);
    if(recognize.id >= 0){