1.下载相关文件

链接：https://pan.baidu.com/s/1xW6HXGxYaDzcWH3HMG9REA
提取码：tv4q

2.代码

下面代码的详细注释见上个博客，有少许改动。
https://blog.csdn.net/qq_45445740/article/details/106544802

import cv2
import numpy as np
import time

# 下载权重文件、配置文件
net = cv2.dnn.readNet("yolov3-tiny.weights", "cfg/yolov3-tiny.cfg")
classes = []

with open("coco.names", "r") as f:
    classes = [line.strip() for line in f.readlines()]
layer_names = net.getLayerNames()
output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]
colors = np.random.uniform(0, 255, size=(len(classes), 3))

# 输入待检测视频、或打开摄像头实时检测
# cap = cv2.VideoCapture(0) # 参数为0是打开摄像头，用摄像头实时检测
cap = cv2.VideoCapture("walking.mp4")  # 参数为文件名表示打开视频

font = cv2.FONT_HERSHEY_PLAIN
starting_time = time.time()
frame_id = 0
while True:
    _, frame = cap.read()
    frame_id += 1

    height, width, channels = frame.shape

    # 检测对象
    blob = cv2.dnn.blobFromImage(frame, 0.00392, (416, 416), (0, 0, 0), True, crop=False)

    net.setInput(blob)
    outs = net.forward(output_layers)

    # 在屏幕上显示信息
    class_ids = []
    confidences = []
    boxes = []
    for out in outs:
        for detection in out:
            scores = detection[5:]
            class_id = np.argmax(scores)
            confidence = scores[class_id]
            if confidence > 0.2:
                # 目标检测
                center_x = int(detection[0] * width)
                center_y = int(detection[1] * height)
                w = int(detection[2] * width)
                h = int(detection[3] * height)

                # 绘制矩形框
                x = int(center_x - w / 2)
                y = int(center_y - h / 2)

                boxes.append([x, y, w, h])
                confidences.append(float(confidence))
                class_ids.append(class_id)

    indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.8, 0.3)

    for i in range(len(boxes)):
        if i in indexes:
            x, y, w, h = boxes[i]
            label = str(classes[class_ids[i]])
            confidence = confidences[i]
            color = colors[class_ids[i]]
            cv2.rectangle(frame, (x, y), (x + w, y + h), color, 2)
            cv2.putText(frame, label + " " + str(round(confidence, 2)), (x, y + 30), font, 3, color, 3)

    elapsed_time = time.time() - starting_time
    fps = frame_id / elapsed_time
    cv2.putText(frame, "FPS: " + str(round(fps, 2)), (10, 50), font, 4, (0, 0, 0), 3)
    cv2.imshow("Image", frame)
    key = cv2.waitKey(1)
    if key == 27:
        break

cap.release()
cv2.destroyAllWindows()