# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license """ Run YOLOv5 detection inference on images, videos, directories, globs, YouTube, webcam, streams, etc. Usage - sources: $ python detect.py --weights yolov5s.pt --source 0 # webcam img.jpg # image vid.mp4 # video screen # screenshot path/ # directory list.txt # list of images list.streams # list of streams 'path/*.jpg' # glob 'https://youtu.be/Zgi9g1ksQHc' # YouTube 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream Usage - formats: $ python detect.py --weights yolov5s.pt # PyTorch yolov5s.torchscript # TorchScript yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn yolov5s_openvino_model # 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 yolov5s_paddle_model # PaddlePaddle """ from datetime import datetime from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor from qwen_vl_utils import process_vision_info import matplotlib.path as mat import requests import argparse import os import platform import sqlite3 import sys import threading import time from pathlib import Path import signal import torch from concurrent.futures import ThreadPoolExecutor from concurrent.futures import ProcessPoolExecutor from multiprocessing import Process,Manager,Value from multiprocessing import Queue from multiprocessing import set_start_method import multiprocessing import multiprocessing as mp import numpy as np import platform import pathlib from collections import defaultdict, deque #import websockets import asyncio 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 import math from models.common import DetectMultiBackend from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages,LoadStreams, LoadStreamsSQLNEWN,LoadStreamsSQL,LoadStreamsSQLNRERT,LoadStreamsVEight,LoadStreamsSQLTN from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2, increment_path, non_max_suppression, print_args, scale_boxes, strip_optimizer, xyxy2xywh,strtolst,strtolstl,apply_classifier1,task) from utils.plots import Annotator, colors, save_one_box from utils.torch_utils import select_device, smart_inference_mode #from testpool import func1,TestA from ultralytics import YOLO from ultralytics.trackers.bot_sort import BOTSORT from ultralytics.utils.checks import check_yaml from ultralytics.utils import IterableSimpleNamespace, yaml_load, ops from ultralytics.nn.autobackend import AutoBackend from ultralytics.utils.ops import non_max_suppression from ultralytics.engine.results import Results # def my_handler(signum, frame): # exit(0) #url = "http://36.7.84.146:18802/ai-service/open/api/operate/upload" plt = platform.system() if plt != 'Windows': pathlib.WindowsPath = pathlib.PosixPath urlhead = "http://172.19.152.231" url = f"{urlhead}/open/api/operate/upload" urlele = f"{urlhead}/open/api/operate/fence" urlperson = f"{urlhead}/open/api/operate/getPersonLimitNum" urlt = f"{urlhead}/open/api/operate/taskList" urla = f"{urlhead}/open/api/operate/algorithmList" weburl = f"ws://36.7.84.146:28801/websocket/device" urlrtsp = f"{urlhead}/open/api/operate/previewURLs" personcountdir = {} algdir = {'0':'helmet','8':'danager','10':'uniform','14':'smoke','16':'fire','21':'cross','25':'fall','29':'occupancy','30':'liquid','31':'pressure','32':'sleep','33':'conveyor','34':'personcount','35':'gloves','36':'sit','37':'other','38':'duty','98':'face','51':'run'} modellabeldir = {'0':'head','8':'person','10':'other','14':'smoke','16':'fire','21':'cross','25':'fall','29':'car','30':'liquid','31':'pressure','32':'sleep','33':'conveyor','34':'personcount','35':'gloves','36':'sit','37':'other','38':'person','98':'face','51':'person'} modelalgdir = {'helmet': '0','danager': '8','uniform': '10','smoke': '14','fire': '16','cross': '21','fall': '25','occupancy': '29','liquid': '30','pressure': '31','sleep': '32','conveyor': '33','personcount': '34','gloves': '35','sit': '36','other': '37','duty': '38','face': '98','run': '51'} algmodel = {} for key,value in algdir.items(): algmodel[value] = key def map_to_ellipse(position): x, y = position center_x = 640 center_y = 360 a = 580 b = 280 x_norm = x / 1280 y_norm = y / 720 d_norm = math.sqrt((x_norm - 0.5) ** 2 + (y_norm - 0.5) ** 2) theta_norm = math.atan2(y_norm - 0.5, x_norm - 0.5) f = d_norm a_new = a * f b_new = b * f bias_x = center_x + a_new * math.cos(theta_norm) bias_y = center_y + b_new * math.sin(theta_norm) return np.array([bias_x, bias_y]) def parse_opt(): parser = argparse.ArgumentParser() parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path or triton URL') opt = parser.parse_args() return opt def runtracker(modelname,channel,source,videoqueue): track_history = defaultdict(lambda: []) # 用于存储每个 track_id 最近的时间戳 time_stamps = defaultdict(lambda: deque(maxlen=50)) # 固定长度为 50 # 用于存储瞬时速度 instantaneous_velocities = defaultdict(lambda: deque(maxlen=10)) speed_threshold = 10 # 速度阈值 high_velocity_count_threshold = 30 # 高速度计数阈值 dirmodel = {"channel":channel,"postpretime":0,"classIndex":'',"VideoUrl":source} dirvideo = {} framelist = [] cap = cv2.VideoCapture(source) print(f'source = {source} cap = {cap.isOpened()}') model = YOLO(modelname) ida = 0 while cap.isOpened(): # 记录当前时间 flag = False current_time = time.time() # Read a frame from the video success, frame = cap.read() if success: oriimg = frame.copy() if len(framelist) >= 100: framelist.pop(0) framelist.append(oriimg) else: framelist.append(oriimg) idtmp = list(dirvideo.keys()) for ida in idtmp: if dirvideo[ida]['count']<=100: dirvideo[ida]['framel'].append(oriimg) dirvideo[ida]['count'] += 1 print('addimg') if dirvideo[ida]['count'] ==100: print("appendvideo") videoqueue.put([dirvideo[ida]['framel'],dirvideo[ida]['postim'],dirvideo[ida]['oriim'],dirvideo[ida]['posttime'],channel]) dirvideo.pop(ida) if success: # Run YOLO11 tracking on the frame, persisting tracks between frames results = model.track(frame, persist=True, classes=0, conf=0.6) if results[0].boxes and results[0].boxes.id is not None: # Get the boxes and track IDs boxes = results[0].boxes.xywh.cpu() track_ids = results[0].boxes.id.int().cpu().tolist() for box, track_id in zip(boxes, track_ids): x, y, w, h = box # 绘制边界框 cv2.rectangle(frame, (int(x - w / 2), int(y - h / 2)), (int(x + w / 2), int(y + h / 2)), (0, 255, 0), 2) # 计算左下角坐标 bottom_left_x = int(x - w / 2) bottom_left_y = int(y + h / 2) # 计算中心点 center_x = int(x) center_y = int(y) # 绘制中心点 cv2.circle(frame, (center_x, center_y), 5, (255, 0, 0), -1) # 红色中心点，半径为 5 # 记录位置 track_history[track_id].append((bottom_left_x, bottom_left_y)) if len(track_history[track_id]) > 100: del track_history[track_id][:-50] # 维持历史长度 # 记录每一帧的时间 time_stamps[track_id].append(current_time) # 计算时间间隔 if len(time_stamps[track_id]) > 1: delta_time = time_stamps[track_id][-1] - time_stamps[track_id][-2] # 最近两帧的时间差 else: delta_time = 0 instantaneous_velocity = 0 # 计算二维瞬时速度 if len(track_history[track_id]) >= 2: pos1 = np.array(track_history[track_id][-1]) # 最新位置 pos2 = np.array(track_history[track_id][-2]) # 前一个位置 pos1 = map_to_ellipse(pos1) pos2 = map_to_ellipse(pos2) distance = np.linalg.norm(pos1 - pos2) # 使用时间间隔进行速度计算 instantaneous_velocity = distance / delta_time if delta_time > 0 else np.zeros(2) instantaneous_velocity_magnitude = round(np.linalg.norm(instantaneous_velocity), 1) instantaneous_velocities[track_id].append(instantaneous_velocity_magnitude) else: instantaneous_velocity_magnitude = 0 # 判断是否有足够数量的高速度 high_velocity_count = sum( 1 for velocity in instantaneous_velocities[track_id] if velocity > speed_threshold) if high_velocity_count >= high_velocity_count_threshold and time.time()-dirmodel["postpretime"]>30: cv2.putText(frame, str(instantaneous_velocity_magnitude), (int(x), int(y)), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2) flag = True dirvideo.setdefault(ida,{}) dirvideo[ida]['framel'] = framelist.copy() dirvideo[ida]['count'] = 0 dirvideo[ida]["postpretime"] = time.time() dirvideo[ida]['postim'] = frame dirvideo[ida]['oriim'] = oriimg #dirmodel['channel'] = channel dirvideo[ida]['posttime'] = time.localtime(time.time()) ida = ida+1 #if flag and time.time()-dirmodel["postpretime"]>30: # timesave = time.strftime('%Y-%m-%d-%H:%M:%S', time.localtime(time.time())) # year = time.strftime('%Y', time.localtime(time.time())) # month = time.strftime('%m', time.localtime(time.time())) # day = time.strftime('%d', time.localtime(time.time())) # savefold = f'/mnt/project/images/run/{year}/{month}/{day}' # savefold = Path(savefold) # savefold.mkdir(parents=True, exist_ok=True) # detsavefold = f'/mnt/project/detimages/run/{year}/{month}/{day}' # detsavefold = Path(detsavefold) # detsavefold.mkdir(parents=True, exist_ok=True) # cv2.imwrite(f'{savefold}/{timesave}.jpg', oriimg) # cv2.imwrite(f'{detsavefold}/{timesave}det.jpg', frame) # success, encoded_image = cv2.imencode('.jpg', frame) # content = encoded_image.tobytes() # successori, encoded_imageori = cv2.imencode('.jpg', oriimg) # contentori = encoded_imageori.tobytes() # filename = f'{channel}_{int(time.time())}.jpg' # filenameori = f'ori{channel}_{int(time.time())}.jpg' # payload = {'channel': dirmodel['channel'], # 'classIndex': dirmodel['classindex'], # 'ip': dirmodel['algip'], # 'videoTime': time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time())), # 'videoUrl': dirmodel["VideoUrl"]} # files = [ # ('file', (filename, content, 'image/jpeg')), # ('oldFile', (filenameori, contentori, 'image/jpeg')), # ] # try: # result = requests.post(url, data=payload, files=files) # print(result) # except Exception: # print('posterror') def postvideo(videoqueue): model = Qwen2_5_VLForConditionalGeneration.from_pretrained( "/root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct-AWQ", # "/liq/liq_weight/Qwen2.5vl7b/", torch_dtype=torch.bfloat16, attn_implementation="flash_attention_2", device_map="auto", ) processor = AutoProcessor.from_pretrained("/root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct-AWQ") fourcc = cv2.VideoWriter_fourcc(*'XVID') while True: timesave = time.strftime('%Y-%m-%d-%H:%M:%S', time.localtime(time.time())) year = time.strftime('%Y', time.localtime(time.time())) month = time.strftime('%m', time.localtime(time.time())) day = time.strftime('%d', time.localtime(time.time())) savefold = f'/mnt/project/images/run/{year}/{month}/{day}' savefold = Path(savefold) savefold.mkdir(parents=True, exist_ok=True) detsavefold = f'/mnt/project/detimages/run/{year}/{month}/{day}' detsavefold = Path(detsavefold) detsavefold.mkdir(parents=True, exist_ok=True) vidsavefold = f'/mnt/project/video/run/{year}/{month}/{day}' vidsavefold = Path(vidsavefold) vidsavefold.mkdir(parents=True, exist_ok=True) if videoqueue.qsize() > 0: print('---------------------------------') framelist,postim,oriim,posttime,channel = videoqueue.get() fps = 25 # 帧率 frame_height,frame_width,_ = oriim.shape out = cv2.VideoWriter(f'{vidsavefold}/{time.strftime("%Y-%m-%d-%H:%M:%S",posttime)}.mp4', fourcc, fps, (frame_width, frame_height)) for frame in framelist: out.write(frame) out.release() cv2.imwrite(f'{savefold}/{posttime}.jpg', oriim) cv2.imwrite(f'{detsavefold}/{posttime}det.jpg', postim) success, encoded_image = cv2.imencode('.jpg', postim) content = encoded_image.tobytes() successori, encoded_imageori = cv2.imencode('.jpg', oriim) contentori = encoded_imageori.tobytes() filename = f'{channel}_{posttime}.jpg' filenameori = f'ori{channel}_{posttime}.jpg' messages = [ { "role": "user", "content": [ { "type": "video", "video": f'{vidsavefold}/{time.strftime("%Y-%m-%d-%H:%M:%S",posttime)}.mp4', "max_pixels": 360 * 420, "fps": 1.0, }, {"type": "text", "text": "Please help me determine whether the person in the video is running or walking. If they are running, reply 'running'; if they are walking, reply 'walking'"}, ], } ] text = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) image_inputs, video_inputs = process_vision_info(messages) inputs = processor( text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt", ) inputs = inputs.to("cuda") generated_ids = model.generate(**inputs, max_new_tokens=15) generated_ids_trimmed = [ out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) ] output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False ) #assistant_response = output_text[0].split("Assistant:")[-1].strip() print(f'output_text = {output_text[0].lower()}') if 'run' in output_text[0].lower(): payload = {'channel': channel, 'classIndex': '51', 'ip': "172.19.152.231", 'videoTime': time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time())), 'videoUrl': f'{posttime}.mp4'} files = [ ('file', (filename, content, 'image/jpeg')), ('oldFile', (filenameori, contentori, 'image/jpeg')), ] try: result = requests.post(url, data=payload, files=files) print(f'result = {result.json()}') except Exception: print('posterror') else: print('videozero') time.sleep(3) if __name__ == '__main__': torch.multiprocessing.set_start_method('spawn') #set_start_method('spawn') #multiprocessing.set_start_method('spawn') torch.cuda.set_per_process_memory_fraction(0.6) opt = parse_opt() dbpath = 'project.db' conn = sqlite3.connect(dbpath) # # print ("数据库打开成功") c = conn.cursor() task(c,conn,urlt,urla) cursor = c.execute('select channel,algip from stream where modelname = "run"') result = cursor.fetchall() for channel ,algip in result: data = { "channel": channel, "ip":algip } #personcountdir[channel] = num address = requests.post(url=urlrtsp,data=data).json()['msg'] c.execute('UPDATE STREAM set address= (?) where channel =(?)',(address,channel)) conn.commit() cursor = c.execute("SELECT modelname from CHANGESTREAM where modelname = 'run'") #cursor = c.execute("SELECT modelname from CHANGESTREAM where modelname = 'helmet'") content = cursor.fetchall() contentlist = [] for con in content: contentlist.append(con[0]) #cursor = c.execute("SELECT address,modelname,channel from STREAM where modelname='helmet' or modelname = 'sleep' or modelname = 'smoke' or modelname = 'danager'or modelname = 'gloves' or modelname = 'other'") cursor = c.execute("SELECT address,modelname,channel from STREAM where modelname = 'run'") contenta = cursor.fetchall() source = [] modellist = [] addcha = [] channellist = [] for i in contenta: addcha.append((i[0],i[2])) modellist.append(i[1]) addcha = set(addcha) addcha = sorted(addcha,key=lambda x:x[1]) for a,cha in addcha: source.append(a) channellist.append(cha) print(addcha) #source = set(source) source = list(source) #source.sort() modellist = set(modellist) n = len(content) print(f'modelname={n}') print(content) #content.reverse() print(content) # main(opt) #processes = [] streamqueue = Queue(maxsize=4) numworkv = Value('i', 0) manager = Manager() lock = multiprocessing.Lock() streamlist = manager.list() numworks = 2 #queuelist = getmutpro(channellist,source, streamlist, numworkv, lock, numworks) #thread.start() #videoqueue = Queue(maxsize=20) #thread1 = threading.Thread(target=postvideo, args=(videoqueue,)) #thread1.start() #pool = ThreadPoolExecutor(max_workers=n) #runmodel = manager.dict() modeladir = {} for modelname in modellist: if modelname in contentlist: #if modelname not in runmodel: #print(i) #detectdemo=Detect(weights=f'/mnt/project/yolodemo/yolov5-master/{i[0]}.pt') #if modelname in ['fall','helmet','bag','arm']: print(f'weights ={modelname}.pt') c.execute('select conf,cla from changestream where modelname = (?)',(modelname,)) rea = c.fetchall() #print(f'rea') modeladir.setdefault(modelname,{}) modeladir[modelname]['conf'] = rea[0][0] modeladir[modelname]['cla'] = rea[0][1] tracker_threads = [] videoqueue = Queue(maxsize=20) thread1 = threading.Thread(target=postvideo,args=(videoqueue,)) thread1.start() for channel,address in zip(channellist,source): thread = Process(target=runtracker,args=("run.pt",channel,address,videoqueue)) tracker_threads.append(thread) thread.start() for thread in tracker_threads: thread.join()