Upload 6 files

app.py

@@ -0,0 +1,177 @@
+from ultralytics import YOLO #行人识别，采用YoloV8模型
+import math #用于四舍五入取整
+import cv2 #opencv图像处理库
+import cvzone #在图像上绘画
+#import numpy as np #忘记取消注释了...
+import gradio as gr #GUI界面
+from sort import * #运动检测，采用sort算法
+#from deep_sort_realtime.deepsort_tracker import DeepSort #不会用QAQ
+import tempfile #创建输出临时文件夹
+import os
+from detectMotion import * #单独的运动检测
+
+#导入YoloV8模型,第一次使用会下载模型到当前文件夹当中
+model=YOLO("yolov8n.pt")
+
+#YoloV8标签数据，本次项目只使用了'person'
+classNames=['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
+    'fire hydrant',
+    'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra',
+    'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball',
+    'kite',
+    'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork',
+    'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza',
+    'donut',
+    'cake', 'chair', 'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote',
+    'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase',
+    'scissors',
+    'teddy bear', 'hair drier', 'toothbrush']
+
+#运动检测算法参数
+tracker=Sort(max_age=20,min_hits=3,iou_threshold=0.3)
+
+# 彩色图像进行自适应直方图均衡化
+def hisEqulColor(img):
+    ## 将RGB图像转换到YCrCb空间中
+    ycrcb = cv2.cvtColor(img, cv2.COLOR_BGR2YCR_CB)
+    # 将YCrCb图像通道分离
+    channels = cv2.split(ycrcb)
+    # 以下代码详细注释见官网：
+    # https://docs.opencv.org/4.1.0/d5/daf/tutorial_py_histogram_equalization.html
+    clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
+    clahe.apply(channels[0], channels[0])
+    cv2.merge(channels, ycrcb)
+    cv2.cvtColor(ycrcb, cv2.COLOR_YCR_CB2BGR, img)
+    return img
+
+#添加高斯噪声，并使用中值滤波降噪
+def AddGaussNoise(img,sigma):
+    gauss=np.random.normal(0,sigma,img.shape)
+    img=np.uint8(img + gauss)#将高斯噪声与原始图像叠加
+    img=cv2.medianBlur(img,5)
+    return img
+
+#图像处理
+def processImg(img,sigma):
+    img=cv2.cvtColor(img,cv2.COLOR_RGB2BGR)
+    res1 = AddGaussNoise(img,sigma)
+    res1 = hisEqulColor(res1)
+    res1=cv2.cvtColor(res1,cv2.COLOR_BGR2RGB)
+    return res1
+
+#视频处理
+def processVideo(inputPath,codec):
+    number_of_people=0
+    cap = cv2.VideoCapture(inputPath)#从inputPath读入视频
+    fps = cap.get(cv2.CAP_PROP_FPS) #获取视频的帧率
+    size = (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)),
+        int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)))#获取视频的大小
+    output_viedo = cv2.VideoWriter()#初始化视频写入
+    outputPath=tempfile.mkdtemp()#创建输出视频的临时文件夹的路径
+
+    #输出格式
+    if codec == "mp4":
+        fourcc = cv2.VideoWriter_fourcc('a','v','c','1')#视频编码：h264,只有h264格式的mp4文件才能在浏览器直接播放
+        video_save_path = os.path.join(outputPath,"output.mp4")#创建输出视频路径
+    elif codec == "avi":
+        fourcc = cv2.VideoWriter_fourcc('h','2','6','4')#视频编码：h264,只能保存为avi格式且不能在浏览器直接播放
+        video_save_path = os.path.join(outputPath,"output.avi")#创建输出视频路径
+    elif codec == "mkv":
+        fourcc = cv2.VideoWriter_fourcc('X','V','I','D')#视频编码：XVID,此编码不需要openh264-1.8.0-win64.dll
+        video_save_path = os.path.join(outputPath,"output.mkv")#创建输出视频路径
+
+    output_viedo.open(video_save_path , fourcc, fps, size, True)
+    #对每一帧图片进行读取和处理
+    while True:
+        ret, img = cap.read()#将每一帧图片读取到img当中
+        results=model(img,stream=True)#使用YoloV8模型进行推理，stream=True提高流式处理速度
+        detections=np.empty((0, 5))#初始化运动检测
+        if not(ret):#当视频全部读完，ret返回false，终止循环，视频帧读取和写入结束
+            break
+        img = hisEqulColor(img)#视频增强
+        #读取推理的数据
+        for r in results:
+            boxes=r.boxes
+            for box in boxes:
+                #读取每一帧识别出的边界信息，并显示
+                x1,y1,x2,y2=box.xyxy[0]
+                x1,y1,x2,y2=int(x1),int(y1),int(x2),int(y2)#将tensor类型转变为整型
+                conf=math.ceil(box.conf[0]*100)/100#对conf取2位小数
+                cls=int(box.cls[0])#获取物体类别标签
+                #当标签为人，且可信度大于0.3的时候，将人标识出来
+                if cls==0 and conf > 0.3:
+                    cv2.rectangle(img,(x1,y1),(x2,y2),(255,0,255),3)
+                    print(conf)
+                    #cvzone.putTextRect(img,f'{classNames[cls]}{conf}',(max(0,x1),max(30,y1)),scale=0.7,thickness=1)
+                    currentArray=np.array([x1,y1,x2,y2,conf])
+                    detections=np.vstack((detections,currentArray))#按行堆叠数据
+        #运动检测
+        resultsTracker=tracker.update(detections)
+        for result in resultsTracker:
+            x1,y1,x2,y2,Id=result
+            number_of_people=max(str(int(Id)),str(number_of_people))
+            x1,y1,x2,y2=int(x1),int(y1),int(x2),int(y2)#将浮点数转变为整型
+            #print(result)
+            cvzone.putTextRect(img,f'{int(Id)}',(max(0,x1),max(30,y1)),scale=0.7,thickness=1)
+        #image_np = np.squeeze(img.render())#用np.squeeze将输出结果降维
+        output_viedo.write(img)#将处理后的图像写入视频
+    output_viedo.release()#释放
+    cap.release()#释放
+    return video_save_path,video_save_path
+
+
+
+#WebUi图形界面（interface）
+#demo = gr.Interface(
+#    fn=processVideo,
+#    inputs=["text","text"],
+#    outputs=["text"],
+#    examples=[["D:\\[WPF]JJDown\\Download\\walker.mp4","C:\\Users\\sino\\Downloads\\output.mkv"],["C:\\Users\\sino\\Videos\\test.mp4","C:\\Users\\sino\\Downloads\\output.mkv"]],
+#    title="运动检测与行人跟踪",
+#    description="请输入绝对路径"
+#)
+
+#WebUi图形界面（block）
+with gr.Blocks() as demo:
+    gr.Markdown("""
+    # 运动检测与行人跟踪
+    基于opencv + yoloV8 + sort，请输入绝对路径
+    """)
+    with gr.Tab("视频识别"):
+        with gr.Row():
+            with gr.Column():
+                text_inputPath = gr.Video()
+                codec = gr.Radio(["mp4","avi","mkv"], label="输出视频格式")
+                videoProcess_button = gr.Button("处理")
+            with gr.Column():
+                text_output = gr.Video()
+                text_output_path = gr.Text(label="输出路径")
+    with gr.Tab("图像增强"):
+        with gr.Row():
+            with gr.Column():
+                image_input = gr.Image()
+                image_sigma = gr.Slider(0,40,label="高斯噪声sigma")
+            image_output = gr.Image()
+        image_button = gr.Button("处理")
+    with gr.Tab("运动检测"):
+        with gr.Column():
+            with gr.Row():
+                with gr.Column():
+                    motion_inputPath = gr.Video()
+                    motionProcess_button = gr.Button("处理")
+                motion_output_frame = gr.Video()
+                motion_output_fmask = gr.Video()
+                frame_output_path = gr.Text(label="frame输出路径")
+                fmask_output_path = gr.Text(label="mask输出路径")
+            with gr.Accordion("算法："):
+                gr.Markdown("高斯混合模型（GMM）")
+
+    
+
+    videoProcess_button.click(processVideo, inputs=[text_inputPath,codec], outputs=[text_output,text_output_path])
+    image_button.click(processImg, inputs=[image_input,image_sigma], outputs=image_output)
+    motionProcess_button.click(motionDetection, inputs=[motion_inputPath], outputs=[motion_output_frame,motion_output_fmask,
+                                                                                frame_output_path,fmask_output_path])
+
+demo.queue()#当有多个请求时，排队
+demo.launch()#生成内网链接，如需要公网链接，括号内输入share=True

detectMotion.py

@@ -0,0 +1,60 @@
+#修改自https://blog.csdn.net/qq_29367075/article/details/122933407
+import cv2
+import numpy as np
+import tempfile
+import os
+
+kernel1 = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))
+mog = cv2.createBackgroundSubtractorMOG2()  # 创建混合高斯模型来用于北京建模
+
+def motionDetection(inputPath):
+    cap = cv2.VideoCapture(inputPath)#从inputPath读入视频
+    fps = cap.get(cv2.CAP_PROP_FPS) #获取视频的帧率
+    size = (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)),
+        int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)))#获取视频的大小
+    output_viedo_frame = cv2.VideoWriter()#初始化视频写入
+    output_viedo_fmask = cv2.VideoWriter()#初始化视频写入
+    outputPath=tempfile.mkdtemp()#创建输出视频的临时文件夹的路径
+    fourcc = cv2.VideoWriter_fourcc('a','v','c','1')#视频编码：h264,只有h264格式的mp4文件才能在浏览器直接播放
+    video_save_path_frame = os.path.join(outputPath,"frame.mp4")#创建输出视频路径
+    video_save_path_fmask = os.path.join(outputPath,"fmask.mp4")#创建输出视频路径
+    output_viedo_frame.open(video_save_path_frame , fourcc, fps, size, True)
+    output_viedo_fmask.open(video_save_path_fmask , fourcc, fps, size, True)
+    #对每一帧图片进行读取和处理
+    while True:
+        ret, frame = cap.read()#将每一帧图片读取到img当中
+        if frame is None:
+            print("camera is over...")
+            break
+
+        fmask = mog.apply(frame)  # 判断哪些是前景和背景
+        
+
+        MORPH_OPEN_1 = cv2.morphologyEx(fmask, cv2.MORPH_OPEN, kernel1)  # 开运算，去除噪声和毛刺
+
+        contours, _ = cv2.findContours(fmask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)  # 只检测外边框
+
+        for cont in contours:
+            # 计算各个轮廓的面积
+            len = cv2.arcLength(cont, True)
+            if len > 300:  # 去除一些小的噪声点
+                # 找到一个轮廓
+                x,y,w,h = cv2.boundingRect(cont)
+                # 画出这个矩形
+                cv2.rectangle(frame, (x,y), (x+w, y+h), color=(0,255,0), thickness=3)
+        fmask=cv2.cvtColor(fmask,cv2.COLOR_BGR2RGB)
+        #print(fmask)
+            #image_np = np.squeeze(img.render())#用np.squeeze将输出结果降维
+        output_viedo_frame.write(frame)#将处理后的图像写入视频
+        output_viedo_fmask.write(fmask)#将处理后的图像写入视频
+    output_viedo_frame.release()#释放
+    output_viedo_fmask.release()#释放
+    cap.release()#释放
+    return video_save_path_frame,video_save_path_fmask,video_save_path_frame,video_save_path_fmask
+
+
+
+
+
+
+

requirements.txt

@@ -0,0 +1,4 @@
+ultralytics
+opencv-python
+cvzone
+torch

sort.py

@@ -0,0 +1,330 @@
+"""
+    SORT: A Simple, Online and Realtime Tracker
+    Copyright (C) 2016-2020 Alex Bewley alex@bewley.ai
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+"""
+from __future__ import print_function
+
+import os
+import numpy as np
+import matplotlib
+matplotlib.use('TkAgg')
+import matplotlib.pyplot as plt
+import matplotlib.patches as patches
+from skimage import io
+
+import glob
+import time
+import argparse
+from filterpy.kalman import KalmanFilter
+
+np.random.seed(0)
+
+
+def linear_assignment(cost_matrix):
+  try:
+    import lap
+    _, x, y = lap.lapjv(cost_matrix, extend_cost=True)
+    return np.array([[y[i],i] for i in x if i >= 0]) #
+  except ImportError:
+    from scipy.optimize import linear_sum_assignment
+    x, y = linear_sum_assignment(cost_matrix)
+    return np.array(list(zip(x, y)))
+
+
+def iou_batch(bb_test, bb_gt):
+  """
+  From SORT: Computes IOU between two bboxes in the form [x1,y1,x2,y2]
+  """
+  bb_gt = np.expand_dims(bb_gt, 0)
+  bb_test = np.expand_dims(bb_test, 1)
+  
+  xx1 = np.maximum(bb_test[..., 0], bb_gt[..., 0])
+  yy1 = np.maximum(bb_test[..., 1], bb_gt[..., 1])
+  xx2 = np.minimum(bb_test[..., 2], bb_gt[..., 2])
+  yy2 = np.minimum(bb_test[..., 3], bb_gt[..., 3])
+  w = np.maximum(0., xx2 - xx1)
+  h = np.maximum(0., yy2 - yy1)
+  wh = w * h
+  o = wh / ((bb_test[..., 2] - bb_test[..., 0]) * (bb_test[..., 3] - bb_test[..., 1])                                      
+    + (bb_gt[..., 2] - bb_gt[..., 0]) * (bb_gt[..., 3] - bb_gt[..., 1]) - wh)                                              
+  return(o)  
+
+
+def convert_bbox_to_z(bbox):
+  """
+  Takes a bounding box in the form [x1,y1,x2,y2] and returns z in the form
+    [x,y,s,r] where x,y is the centre of the box and s is the scale/area and r is
+    the aspect ratio
+  """
+  w = bbox[2] - bbox[0]
+  h = bbox[3] - bbox[1]
+  x = bbox[0] + w/2.
+  y = bbox[1] + h/2.
+  s = w * h    #scale is just area
+  r = w / float(h)
+  return np.array([x, y, s, r]).reshape((4, 1))
+
+
+def convert_x_to_bbox(x,score=None):
+  """
+  Takes a bounding box in the centre form [x,y,s,r] and returns it in the form
+    [x1,y1,x2,y2] where x1,y1 is the top left and x2,y2 is the bottom right
+  """
+  w = np.sqrt(x[2] * x[3])
+  h = x[2] / w
+  if(score==None):
+    return np.array([x[0]-w/2.,x[1]-h/2.,x[0]+w/2.,x[1]+h/2.]).reshape((1,4))
+  else:
+    return np.array([x[0]-w/2.,x[1]-h/2.,x[0]+w/2.,x[1]+h/2.,score]).reshape((1,5))
+
+
+class KalmanBoxTracker(object):
+  """
+  This class represents the internal state of individual tracked objects observed as bbox.
+  """
+  count = 0
+  def __init__(self,bbox):
+    """
+    Initialises a tracker using initial bounding box.
+    """
+    #define constant velocity model
+    self.kf = KalmanFilter(dim_x=7, dim_z=4) 
+    self.kf.F = np.array([[1,0,0,0,1,0,0],[0,1,0,0,0,1,0],[0,0,1,0,0,0,1],[0,0,0,1,0,0,0],  [0,0,0,0,1,0,0],[0,0,0,0,0,1,0],[0,0,0,0,0,0,1]])
+    self.kf.H = np.array([[1,0,0,0,0,0,0],[0,1,0,0,0,0,0],[0,0,1,0,0,0,0],[0,0,0,1,0,0,0]])
+
+    self.kf.R[2:,2:] *= 10.
+    self.kf.P[4:,4:] *= 1000. #give high uncertainty to the unobservable initial velocities
+    self.kf.P *= 10.
+    self.kf.Q[-1,-1] *= 0.01
+    self.kf.Q[4:,4:] *= 0.01
+
+    self.kf.x[:4] = convert_bbox_to_z(bbox)
+    self.time_since_update = 0
+    self.id = KalmanBoxTracker.count
+    KalmanBoxTracker.count += 1
+    self.history = []
+    self.hits = 0
+    self.hit_streak = 0
+    self.age = 0
+
+  def update(self,bbox):
+    """
+    Updates the state vector with observed bbox.
+    """
+    self.time_since_update = 0
+    self.history = []
+    self.hits += 1
+    self.hit_streak += 1
+    self.kf.update(convert_bbox_to_z(bbox))
+
+  def predict(self):
+    """
+    Advances the state vector and returns the predicted bounding box estimate.
+    """
+    if((self.kf.x[6]+self.kf.x[2])<=0):
+      self.kf.x[6] *= 0.0
+    self.kf.predict()
+    self.age += 1
+    if(self.time_since_update>0):
+      self.hit_streak = 0
+    self.time_since_update += 1
+    self.history.append(convert_x_to_bbox(self.kf.x))
+    return self.history[-1]
+
+  def get_state(self):
+    """
+    Returns the current bounding box estimate.
+    """
+    return convert_x_to_bbox(self.kf.x)
+
+
+def associate_detections_to_trackers(detections,trackers,iou_threshold = 0.3):
+  """
+  Assigns detections to tracked object (both represented as bounding boxes)
+
+  Returns 3 lists of matches, unmatched_detections and unmatched_trackers
+  """
+  if(len(trackers)==0):
+    return np.empty((0,2),dtype=int), np.arange(len(detections)), np.empty((0,5),dtype=int)
+
+  iou_matrix = iou_batch(detections, trackers)
+
+  if min(iou_matrix.shape) > 0:
+    a = (iou_matrix > iou_threshold).astype(np.int32)
+    if a.sum(1).max() == 1 and a.sum(0).max() == 1:
+        matched_indices = np.stack(np.where(a), axis=1)
+    else:
+      matched_indices = linear_assignment(-iou_matrix)
+  else:
+    matched_indices = np.empty(shape=(0,2))
+
+  unmatched_detections = []
+  for d, det in enumerate(detections):
+    if(d not in matched_indices[:,0]):
+      unmatched_detections.append(d)
+  unmatched_trackers = []
+  for t, trk in enumerate(trackers):
+    if(t not in matched_indices[:,1]):
+      unmatched_trackers.append(t)
+
+  #filter out matched with low IOU
+  matches = []
+  for m in matched_indices:
+    if(iou_matrix[m[0], m[1]]<iou_threshold):
+      unmatched_detections.append(m[0])
+      unmatched_trackers.append(m[1])
+    else:
+      matches.append(m.reshape(1,2))
+  if(len(matches)==0):
+    matches = np.empty((0,2),dtype=int)
+  else:
+    matches = np.concatenate(matches,axis=0)
+
+  return matches, np.array(unmatched_detections), np.array(unmatched_trackers)
+
+
+class Sort(object):
+  def __init__(self, max_age=1, min_hits=3, iou_threshold=0.3):
+    """
+    Sets key parameters for SORT
+    """
+    self.max_age = max_age
+    self.min_hits = min_hits
+    self.iou_threshold = iou_threshold
+    self.trackers = []
+    self.frame_count = 0
+
+  def update(self, dets=np.empty((0, 5))):
+    """
+    Params:
+      dets - a numpy array of detections in the format [[x1,y1,x2,y2,score],[x1,y1,x2,y2,score],...]
+    Requires: this method must be called once for each frame even with empty detections (use np.empty((0, 5)) for frames without detections).
+    Returns the a similar array, where the last column is the object ID.
+
+    NOTE: The number of objects returned may differ from the number of detections provided.
+    """
+    self.frame_count += 1
+    # get predicted locations from existing trackers.
+    trks = np.zeros((len(self.trackers), 5))
+    to_del = []
+    ret = []
+    for t, trk in enumerate(trks):
+      pos = self.trackers[t].predict()[0]
+      trk[:] = [pos[0], pos[1], pos[2], pos[3], 0]
+      if np.any(np.isnan(pos)):
+        to_del.append(t)
+    trks = np.ma.compress_rows(np.ma.masked_invalid(trks))
+    for t in reversed(to_del):
+      self.trackers.pop(t)
+    matched, unmatched_dets, unmatched_trks = associate_detections_to_trackers(dets,trks, self.iou_threshold)
+
+    # update matched trackers with assigned detections
+    for m in matched:
+      self.trackers[m[1]].update(dets[m[0], :])
+
+    # create and initialise new trackers for unmatched detections
+    for i in unmatched_dets:
+        trk = KalmanBoxTracker(dets[i,:])
+        self.trackers.append(trk)
+    i = len(self.trackers)
+    for trk in reversed(self.trackers):
+        d = trk.get_state()[0]
+        if (trk.time_since_update < 1) and (trk.hit_streak >= self.min_hits or self.frame_count <= self.min_hits):
+          ret.append(np.concatenate((d,[trk.id+1])).reshape(1,-1)) # +1 as MOT benchmark requires positive
+        i -= 1
+        # remove dead tracklet
+        if(trk.time_since_update > self.max_age):
+          self.trackers.pop(i)
+    if(len(ret)>0):
+      return np.concatenate(ret)
+    return np.empty((0,5))
+
+def parse_args():
+    """Parse input arguments."""
+    parser = argparse.ArgumentParser(description='SORT demo')
+    parser.add_argument('--display', dest='display', help='Display online tracker output (slow) [False]',action='store_true')
+    parser.add_argument("--seq_path", help="Path to detections.", type=str, default='data')
+    parser.add_argument("--phase", help="Subdirectory in seq_path.", type=str, default='train')
+    parser.add_argument("--max_age", 
+                        help="Maximum number of frames to keep alive a track without associated detections.", 
+                        type=int, default=1)
+    parser.add_argument("--min_hits", 
+                        help="Minimum number of associated detections before track is initialised.", 
+                        type=int, default=3)
+    parser.add_argument("--iou_threshold", help="Minimum IOU for match.", type=float, default=0.3)
+    args = parser.parse_args()
+    return args
+
+if __name__ == '__main__':
+  # all train
+  args = parse_args()
+  display = args.display
+  phase = args.phase
+  total_time = 0.0
+  total_frames = 0
+  colours = np.random.rand(32, 3) #used only for display
+  if(display):
+    if not os.path.exists('mot_benchmark'):
+      print('\n\tERROR: mot_benchmark link not found!\n\n    Create a symbolic link to the MOT benchmark\n    (https://motchallenge.net/data/2D_MOT_2015/#download). E.g.:\n\n    $ ln -s /path/to/MOT2015_challenge/2DMOT2015 mot_benchmark\n\n')
+      exit()
+    plt.ion()
+    fig = plt.figure()
+    ax1 = fig.add_subplot(111, aspect='equal')
+
+  if not os.path.exists('output'):
+    os.makedirs('output')
+  pattern = os.path.join(args.seq_path, phase, '*', 'det', 'det.txt')
+  for seq_dets_fn in glob.glob(pattern):
+    mot_tracker = Sort(max_age=args.max_age, 
+                       min_hits=args.min_hits,
+                       iou_threshold=args.iou_threshold) #create instance of the SORT tracker
+    seq_dets = np.loadtxt(seq_dets_fn, delimiter=',')
+    seq = seq_dets_fn[pattern.find('*'):].split(os.path.sep)[0]
+    
+    with open(os.path.join('output', '%s.txt'%(seq)),'w') as out_file:
+      print("Processing %s."%(seq))
+      for frame in range(int(seq_dets[:,0].max())):
+        frame += 1 #detection and frame numbers begin at 1
+        dets = seq_dets[seq_dets[:, 0]==frame, 2:7]
+        dets[:, 2:4] += dets[:, 0:2] #convert to [x1,y1,w,h] to [x1,y1,x2,y2]
+        total_frames += 1
+
+        if(display):
+          fn = os.path.join('mot_benchmark', phase, seq, 'img1', '%06d.jpg'%(frame))
+          im =io.imread(fn)
+          ax1.imshow(im)
+          plt.title(seq + ' Tracked Targets')
+
+        start_time = time.time()
+        trackers = mot_tracker.update(dets)
+        cycle_time = time.time() - start_time
+        total_time += cycle_time
+
+        for d in trackers:
+          print('%d,%d,%.2f,%.2f,%.2f,%.2f,1,-1,-1,-1'%(frame,d[4],d[0],d[1],d[2]-d[0],d[3]-d[1]),file=out_file)
+          if(display):
+            d = d.astype(np.int32)
+            ax1.add_patch(patches.Rectangle((d[0],d[1]),d[2]-d[0],d[3]-d[1],fill=False,lw=3,ec=colours[d[4]%32,:]))
+
+        if(display):
+          fig.canvas.flush_events()
+          plt.draw()
+          ax1.cla()
+
+  print("Total Tracking took: %.3f seconds for %d frames or %.1f FPS" % (total_time, total_frames, total_frames / total_time))
+
+  if(display):
+    print("Note: to get real runtime results run without the option: --display")

yolov8n.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31e20dde3def09e2cf938c7be6fe23d9150bbbe503982af13345706515f2ef95
+size 6534387