# 在MQTT 下的影像傳輸與物件檢測
## 本次實驗使用 ESP32-CAM 來做影像傳輸與 YOLOv5 模型對保存的圖片進行物件檢測
YOLOv5 是一個物件偵測方法，可直接從輸入圖像生成邊界框和分類結果，適合對速度有高要求的應用，如即時檢測。
arduino(使用C)
```c
#include <esp_camera.h> // 引入ESP32相機功能庫
#include <WiFi.h> // 引入WiFi功能庫
#include <PubSubClient.h> // 引入MQTT功能庫
// ------ WiFi帳號密碼 ------
const char* ssid = "HPC_1"; // 定義WiFi名稱
const char* password = "HPC200-1"; // 定義WiFi密碼
// ------ MQTT設定 ------
const char* mqtt_server = "mqtt.eclipseprojects.io"; // 定義MQTT伺服器位址
const unsigned int mqtt_port = 1883; // 定義MQTT伺服器的通訊埠
#define MQTT_PUBLISH_Monitor "ESP32CAM_hpcLab/esp32cam/pic" // 定義發布圖片的Topic名稱
// ------ OV2640相機設定 ------------
#define CAMERA_MODEL_AI_THINKER // 指定相機模組為AI-THINKER
#define PWDN_GPIO_NUM 32 // 定義相機的電源控制引腳
#define RESET_GPIO_NUM -1 // 定義相機的重置引腳 (未使用)
#define XCLK_GPIO_NUM 0 // 定義相機的時鐘信號引腳
#define SIOD_GPIO_NUM 26 // 定義SCCB的資料引腳
#define SIOC_GPIO_NUM 27 // 定義SCCB的時鐘引腳
#define Y9_GPIO_NUM 35 // 定義影像數據引腳Y9
#define Y8_GPIO_NUM 34 // 定義影像數據引腳Y8
#define Y7_GPIO_NUM 39 // 定義影像數據引腳Y7
#define Y6_GPIO_NUM 36 // 定義影像數據引腳Y6
#define Y5_GPIO_NUM 21 // 定義影像數據引腳Y5
#define Y4_GPIO_NUM 19 // 定義影像數據引腳Y4
#define Y3_GPIO_NUM 18 // 定義影像數據引腳Y3
#define Y2_GPIO_NUM 5 // 定義影像數據引腳Y2
#define VSYNC_GPIO_NUM 25 // 定義垂直同步引腳
#define HREF_GPIO_NUM 23 // 定義水平同步引腳
#define PCLK_GPIO_NUM 22 // 定義像素時鐘引腳
char clientId[50]; // 定義MQTT客戶端ID字串緩衝區
WiFiClient wifiClient; // 定義WiFi客戶端
PubSubClient mqttClient(mqtt_server, mqtt_port, mqtt_callback, wifiClient); // 定義MQTT客戶端
// 啟動WiFi連線
void setup_wifi() {
Serial.printf("\nConnecting to %s", ssid); // 顯示連接的WiFi名稱
WiFi.begin(ssid, password); // 開始連接WiFi
while (WiFi.status() != WL_CONNECTED) { // 持續檢查連線狀態
delay(500);
Serial.print("."); // 顯示連接過程的提示
}
Serial.print("\nWiFi Connected. IP Address: "); // 顯示WiFi連線成功訊息
Serial.println(WiFi.localIP()); // 顯示取得的IP位址
}
// 重新連線到MQTT伺服器
boolean mqtt_nonblock_reconnect() {
boolean doConn = false; // 定義連線狀態標誌
if (! mqttClient.connected()) { // 檢查是否已連線
boolean isConn = mqttClient.connect(clientId); // 嘗試連線到MQTT伺服器
char logConnected[100]; // 定義記錄訊息的字串緩衝區
sprintf(logConnected, "MQTT Client [%s] Connect %s !", clientId, (isConn ? "Successful" : "Failed")); // 格式化連線訊息
Serial.println(logConnected); // 顯示連線結果
}
return doConn; // 返回連線狀態
}
// MQTT傳遞照片
void MQTT_picture() {
camera_fb_t * fb = NULL; // 定義相機緩衝區
fb = esp_camera_fb_get(); // 從相機取得圖片
if (!fb) { // 如果獲取圖片失敗
delay(100);
Serial.println("Camera capture failed, Reset"); // 顯示錯誤訊息
ESP.restart(); // 重新啟動ESP32
}
char* logIsPublished; // 定義傳輸結果訊息的指標
if (! mqttClient.connected()) { // 如果MQTT連線中斷
Serial.printf("MQTT Client [%s] Connection LOST !\n", clientId); // 顯示錯誤訊息
mqtt_nonblock_reconnect(); // 嘗試重新連線
}
if (! mqttClient.connected())
logIsPublished = " No MQTT Connection, Photo NOT Published !"; // 顯示傳輸失敗訊息
else {
int imgSize = fb->len; // 獲取圖片大小
int ps = MQTT_MAX_PACKET_SIZE; // 定義MQTT封包大小
mqttClient.beginPublish(MQTT_PUBLISH_Monitor, imgSize, false); // 開始傳輸圖片
for (int i = 0; i < imgSize; i += ps) { // 將圖片分段傳輸
int s = (imgSize - i < s) ? (imgSize - i) : ps; // 計算每段大小
mqttClient.write((uint8_t *)(fb->buf) + i, s); // 傳輸圖片數據
}
boolean isPublished = mqttClient.endPublish(); // 結束圖片傳輸
if (isPublished)
logIsPublished = " Publishing Photo to MQTT Successfully !"; // 顯示成功訊息
else
logIsPublished = " Publishing Photo to MQTT Failed !"; // 顯示失敗訊息
}
Serial.println(logIsPublished); // 顯示傳輸結果
esp_camera_fb_return(fb); // 清空相機緩衝區
}
// 初始化函數
void setup() {
Serial.begin(115200); // 初始化序列埠
// 相機設定
camera_config_t config; // 定義相機配置結構體
config.ledc_channel = LEDC_CHANNEL_0; // 設定LED控制通道
config.ledc_timer = LEDC_TIMER_0; // 設定LED控制計時器
config.pin_d0 = Y2_GPIO_NUM; // 設定數據引腳
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; // 設定時鐘信號引腳
config.pin_pclk = PCLK_GPIO_NUM; // 設定像素時鐘引腳
config.pin_vsync = VSYNC_GPIO_NUM; // 設定垂直同步引腳
config.pin_href = HREF_GPIO_NUM; // 設定水平同步引腳
config.pin_sscb_sda = SIOD_GPIO_NUM; // 設定SCCB資料引腳
config.pin_sscb_scl = SIOC_GPIO_NUM; // 設定SCCB時鐘引腳
config.pin_pwdn = PWDN_GPIO_NUM; // 設定電源控制引腳
config.pin_reset = RESET_GPIO_NUM; // 設定重置引腳
config.xclk_freq_hz = 20000000; // 設定時鐘頻率
config.pixel_format = PIXFORMAT_JPEG; // 設定像素格式為JPEG
config.jpeg_quality = 10; // 設定JPEG品質 (數字越小品質越高)
config.fb_count = 2; // 設定幀緩衝數量
// 設定照片解析度
config.frame_size = FRAMESIZE_QVGA; // 設定照片大小為QVGA
esp_err_t err = esp_camera_init(&config); // 初始化相機
delay(500); // 延遲500ms
// 啟動WiFi連線
setup_wifi();
sprintf(clientId, "ESP32CAM_shiaw87"); // 設定MQTT客戶端ID
// 啟動MQTT連線
mqtt_nonblock_reconnect();
}
// 主循環函數
void loop() {
mqtt_nonblock_reconnect(); // 確保MQTT連線
MQTT_picture(); // 透過MQTT傳輸照片
delay(500); // 延遲300ms
}
```
detect.py
```python
# YOLOv5 by Ultralytics, GPL-3.0 license
"""
Run inference on images, videos, directories, streams, etc.
Usage - sources:
$ python path/to/detect.py --weights yolov5s.pt --source 0 # webcam
img.jpg # image
vid.mp4 # video
path/ # directory
path/*.jpg # glob
'https://youtu.be/Zgi9g1ksQHc' # YouTube
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
Usage - formats:
$ python path/to/detect.py --weights yolov5s.pt # PyTorch
yolov5s.torchscript # TorchScript
yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn
yolov5s.xml # OpenVINO
yolov5s.engine # TensorRT
yolov5s.mlmodel # CoreML (macOS-only)
yolov5s_saved_model # TensorFlow SavedModel
yolov5s.pb # TensorFlow GraphDef
yolov5s.tflite # TensorFlow Lite
yolov5s_edgetpu.tflite # TensorFlow Edge TPU
"""
import argparse
import os
from re import S
import sys
from pathlib import Path
import requests
import time
import torch
import torch.backends.cudnn as cudnn
import logging
logging.getLogger().setLevel(logging.ERROR) # 設定全局日誌層級為 ERROR，只顯示錯誤訊息
import warnings
warnings.filterwarnings("ignore", category=UserWarning)
warnings.filterwarnings("ignore", category=FutureWarning)
import paho.mqtt.client as mqtt
# MQTT 設定
MQTT_BROKER = "mqtt.eclipseprojects.io" # 替換為你的 MQTT Broker 地址
MQTT_PORT = 1883 # MQTT 埠號（默認為 1883）
MQTT_TOPIC_SUB = "ESP32CAM_hpcLab/esp32cam/pic" # 要訂閱的主題
MQTT_TOPIC_PUB = "ESP32CAM_hpcLab/esp32cam/detect" # 發佈檢測結果的主題
mqtt_client = mqtt.Client()
FILE = Path(__file__).resolve()
ROOT = FILE.parents[0] # YOLOv5 root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
from models.common import DetectMultiBackend
from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import select_device, time_sync
@torch.no_grad()
def run(
weights=ROOT / 'yolov5s.pt', # model.pt path(s)
source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam
data=ROOT / 'data/coco128.yaml', # dataset.yaml path
imgsz=(640, 640), # inference size (height, width)
conf_thres=0.25, # confidence threshold
iou_thres=0.45, # NMS IOU threshold
max_det=1000, # maximum detections per image
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
view_img=False, # show results
save_txt=False, # save results to *.txt
save_conf=False, # save confidences in --save-txt labels
save_crop=False, # save cropped prediction boxes
nosave=False, # do not save images/videos
classes=None, # filter by class: --class 0, or --class 0 2 3
agnostic_nms=False, # class-agnostic NMS
augment=False, # augmented inference
visualize=False, # visualize features
update=False, # update all models
project=ROOT / 'runs/detect', # save results to project/name
name='exp', # save results to project/name
exist_ok=False, # existing project/name ok, do not increment
line_thickness=3, # bounding box thickness (pixels)
hide_labels=False, # hide labels
hide_conf=False, # hide confidences
half=False, # use FP16 half-precision inference
dnn=False, # use OpenCV DNN for ONNX inference
):
source = str(source)
save_img = not nosave and not source.endswith('.txt') # save inference images
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
if is_url and is_file:
source = check_file(source) # download
# Directories
#save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
#(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
# Fixed Directory
save_dir = Path(project) / name # 固定輸出到同一資料夾
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # 建立資料夾
# Load model
device = select_device(device)
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
stride, names, pt = model.stride, model.names, model.pt
imgsz = check_img_size(imgsz, s=stride) # check image size
# Dataloader
if webcam:
view_img = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# Run inference
model.warmup(imgsz=(1 if pt else bs, 3, *imgsz)) # warmup
dt, seen = [0.0, 0.0, 0.0], 0
t=0
for path, im, im0s, vid_cap, s in dataset:
t1 = time_sync()
im = torch.from_numpy(im).to(device)
im = im.half() if model.fp16 else im.float() # uint8 to fp16/32
im /= 255 # 0 - 255 to 0.0 - 1.0
if len(im.shape) == 3:
im = im[None] # expand for batch dim
t2 = time_sync()
dt[0] += t2 - t1
# Inference
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
pred = model(im, augment=augment, visualize=visualize)
t3 = time_sync()
dt[1] += t3 - t2
# NMS
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
dt[2] += time_sync() - t3
# Second-stage classifier (optional)
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
# Process predictions
for i, det in enumerate(pred): # per image
seen += 1
if webcam: # batch_size >= 1
p, im0, frame = path[i], im0s[i].copy(), dataset.count
#s += f'{i}: '
else:
p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
p = Path(p) # to Path
#save_path = str(save_dir / p.name) # im.jpg
save_path = str(save_dir / "detect.jpg") # 統一命名為 detect.jpg
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt
#s += '%gx%g ' % im.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
imc = im0.copy() if save_crop else im0 # for save_crop
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
# Print results
for c in det[:, -1].unique():
s += f"{names[int(c)]} " # add to string
mqtt_message=f"{names[int(c)]}"
if (mqtt_message != "backgrounds"):
mqtt_client.publish(MQTT_TOPIC_PUB, mqtt_message) # 發送訊息到 MQTT
print("辨識結果 :",mqtt_message)
# Write results
for *xyxy, conf, cls in reversed(det):
if save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
with open(f'{txt_path}.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if save_img or save_crop or view_img: # Add bbox to image
c = int(cls) # integer class
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
annotator.box_label(xyxy, label, color=colors(c, True))
if save_crop:
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
# Stream results
im0 = annotator.result()
if view_img:
cv2.imshow(str(p), im0)
cv2.waitKey(1) # 1 millisecond
# Save results (image with detections)
if save_img:
if dataset.mode == 'image':
cv2.imwrite(save_path, im0)
else: # 'video' or 'stream'
if vid_path[i] != save_path: # new video
vid_path[i] = save_path
if isinstance(vid_writer[i], cv2.VideoWriter):
vid_writer[i].release() # release previous video writer
if vid_cap: # video
fps = vid_cap.get(cv2.CAP_PROP_FPS)
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
else: # stream
fps, w, h = 30, im0.shape[1], im0.shape[0]
save_path = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer[i].write(im0)
#LOGGER.info(f'{s}')#印出 重製s
# Print results
#t = tuple(x / seen * 1E3 for x in dt) # speeds per image
#LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
#if save_txt or save_img:
# s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
# LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
# #print(s)
# #r = requests.post('http://192.168.1.143/test?yolo='+s)
#if update:
# strip_optimizer(weights) # update model (to fix SourceChangeWarning)
def parse_opt():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'D:/test/yolo-detect/last.pt', help='model path(s)')
parser.add_argument('--source', type=str, default=ROOT / 'D:/test/yolo-detect/img/received_image.jpg', help='file/dir/URL/glob, 0 for webcam')
parser.add_argument('--data', type=str, default=ROOT / 'D:/test/yolo-detect/mydata.yaml', help='(optional) dataset.yaml path')
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--view-img', action='store_true', help='show results')
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
parser.add_argument('--augment', action='store_true', help='augmented inference')
parser.add_argument('--visualize', action='store_true', help='visualize features')
parser.add_argument('--update', action='store_true', help='update all models')
parser.add_argument('--project', default=ROOT / 'img', help='save results to project/name')
parser.add_argument('--name', default='', help='save results to project/name')
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
opt = parser.parse_args()
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
# print_args(vars(opt)) 啟動參數
return opt
# MQTT 回調函數
def on_connect(client, userdata, flags, rc):
if rc == 0:
print("MQTT 成功連線")
mqtt_client.subscribe(MQTT_TOPIC_SUB)
print(f"訂閱主題: {MQTT_TOPIC_SUB}")
else:
print(f"連線失敗，錯誤碼: {rc}")
def on_message(client, userdata, msg):
print(f"接收到 MQTT 訊息，主題: {msg.topic}")
try:
# 假設接收到的是圖片二進位數據
output_file = "D:/test/yolo-detect/img/received_image.jpg" # 儲存圖片的檔案名稱
with open(output_file, "wb") as file:
file.write(msg.payload)
print(f"圖片已保存為 {output_file}")
# 執行 YOLOv5 檢測
print(f"開始執行 YOLOv5 檢測，圖片路徑: {output_file}")
run(**vars(opt))
except Exception as e:
print(f"處理訊息時發生錯誤: {e}")
def main(opt):
mqtt_client.on_connect = on_connect
mqtt_client.on_message = on_message
mqtt_client.connect(MQTT_BROKER, MQTT_PORT, 60)
print("啟動 MQTT 客戶端...")
mqtt_client.loop_forever()
check_requirements(exclude=('tensorboard', 'thop'))
run(**vars(opt))
if __name__ == "__main__":
opt = parse_opt()
main(opt)
```
Sign in with Wallet
Connect another wallet