环境：

python3.6.4

opencv3.4.1.15

运行目标跟踪object_tracking文件夹中的mean函数时报错且不显示视频结果

Traceback (most recent call last):
  File "F:\pycharm_python\projects\project_python_test\object_tracking\main.py", line 15, in <module>
    height, width, _ = frame.shape
AttributeError: 'NoneType' object has no attribute 'shape'

查找原因基本上看见三个

1.图片不存在（路径不存在， 路径包含中文无法识别） 2.读取的图片内容和默认读取时参数匹配不匹配。（默认读取的是3通道的彩色图）例如读取到的图片是灰度图，就会返回None。3.也可能是路径中有中文(59条消息) AttributeError: 'NoneType' object has no attribute 'shape'_旅人_Eric的博客-CSDN博客

自己分析了一下，肯因为程序中是相对路径，

cap =cv2.VideoCapture("highway.mp4")

改成绝对路径

cap = cv2.VideoCapture("F:\pycharm_python\projects\project_python_test\object_tracking\highway.mp4")

再次尝试运行main函数，可以显示视频窗口和结果，单依旧报错：

 结果大概这样

再继续找别人踩过的坑：

图片路径前加 r ,可以解决部分问题——对我没用。

看到这篇文章写了一个解决办法，但是是针对图片的，俺纯小白不知道视频的能不能这么改。（主要是不知道怎么改）这坑先留着以后再说吧。

(59条消息) 解决easyocr不识别中文路径问题AttributeError: ‘NoneType‘ object has no attribute ‘shape‘_江河的江的博客-CSDN博客

附上有结果的main.py文件

import cv2
from tracker import *

# Create tracker object
tracker = EuclideanDistTracker()

cap = cv2.VideoCapture("F:\pycharm_python\projects\project_python_test\object_tracking\highway.mp4")

# Object detection from Stable camera 来自稳定相机的物体检测
object_detector = cv2.createBackgroundSubtractorMOG2(history=100, varThreshold=40)
# 函数cv2.createBackgroundSubtractorMOG2返回背景比率（background ratio），
#因为相机是固定的所以history=100，varthreshold的值越低，误报的可行就越大
while True:
    ret, frame = cap.read()
    height, width, _ = frame.shape

    # Extract Region of interest提取感兴趣区域
    roi = frame[340: 720, 500: 800]

    # 1. Object Detection 物体检测
    mask = object_detector.apply(roi)
    _, mask = cv2.threshold(mask, 254, 255, cv2.THRESH_BINARY)
    #245.255表示只想显示254和255之间的值，即只想显示白色或黑色值
    image, contours, _ = cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    detections = []
    for cnt in contours:
        # Calculate area and remove small elements 计算面积，去除小元素
        area = cv2.contourArea(cnt)
        if area > 1000:
            #cv2.drawContours(roi, [cnt], -1, (0, 255, 0), 2)    #绘制轮廓
            x, y, w, h = cv2.boundingRect(cnt)                   #找到对象的坐标


            detections.append([x, y, w, h])
            #一旦创建了对象，我们必须获得边界框的每个位置并将他们插入到单个数组中

    # 2. Object Tracking目标跟踪
    #将唯一ID关联到对象
    boxes_ids = tracker.update(detections)#将带有位置的数组传递给tracker.update（）
    for box_id in boxes_ids:  #为每个对象分配一个唯一的ID
        x, y, w, h, id = box_id
        cv2.putText(roi, str(id), (x, y - 15), cv2.FONT_HERSHEY_PLAIN, 2, (255, 0, 0), 2)
        cv2.rectangle(roi, (x, y), (x + w, y + h), (0, 255, 0), 3) #绘制矩形框

    cv2.imshow("roi", roi)
    cv2.imshow("Frame", frame)
    cv2.imshow("Mask", mask)

    key = cv2.waitKey(30)
    if key == 27:
        break

cap.release()
cv2.destroyAllWindows()

和tracker.py文件

import math


class EuclideanDistTracker:
    def __init__(self):
        # Store the center positions of the objects存储对象的中心位置
        self.center_points = {}
        # Keep the count of the IDs保持ID计数
        # each time a new object id detected, the count will increase by one每检测到新的对象ID是我技术加1
        self.id_count = 0


    def update(self, objects_rect):
        # Objects boxes and ids对象框和ID
        objects_bbs_ids = []

        # Get center point of new object获取新对象的中心点
        for rect in objects_rect:
            x, y, w, h = rect
            cx = (x + x + w) // 2
            cy = (y + y + h) // 2

            # Find out if that object was detected already查明是否已经检测到该对象
            same_object_detected = False
            for id, pt in self.center_points.items():
                #计算中心点之间的欧式距离
                dist = math.hypot(cx - pt[0], cy - pt[1])
                #如果欧式距离小于25则表明是同一个目标
                if dist < 25:
                    self.center_points[id] = (cx, cy)
                    print(self.center_points)
                    objects_bbs_ids.append([x, y, w, h, id])
                    same_object_detected = True
                    break

            # New object is detected we assign the ID to that object检测到新对象时我们将ID分配该该对象
            if same_object_detected is False:
                self.center_points[self.id_count] = (cx, cy)
                objects_bbs_ids.append([x, y, w, h, self.id_count])
                self.id_count += 1

        # Clean the dictionary by center points to remove IDS not used anymore按中心点清理字典以删除不再使用的IDS
        new_center_points = {}
        for obj_bb_id in objects_bbs_ids:
            _, _, _, _, object_id = obj_bb_id
            center = self.center_points[object_id]
            new_center_points[object_id] = center

        # Update dictionary with IDs not used removed更新字典
        self.center_points = new_center_points.copy()
        return objects_bbs_ids

以及原视频：

highway