Python YOLO视频目标识别

Python YOLO（You Only Look Once）是一种实时目标检测算法，可以用于视频目标识别。下面是一个简单的Python YOLO视频目标识别的示例代码：

首先，需要安装必要的库，包括opencv和darknet。可以使用以下命令安装：

!pip install opencv-python
!pip install darknet

然后，需要下载YOLO预训练模型和配置文件。可以从darknet官方网站下载，或者使用以下命令：

!wget https://pjreddie.com/media/files/yolov3.weights
!wget https://raw.githubusercontent.com/pjreddie/darknet/master/cfg/yolov3.cfg
!wget https://raw.githubusercontent.com/pjreddie/darknet/master/data/coco.names

接下来，可以使用以下代码进行视频目标识别：

import cv2
import numpy as np

# load YOLO model and configurations
net = cv2.dnn.readNet("yolov3.weights", "yolov3.cfg")

# load class names
classes = []
with open("coco.names", "r") as f:
    classes = [line.strip() for line in f.readlines()]

# set input size
input_size = (416, 416)

# open video stream
cap = cv2.VideoCapture("video.mp4")

while True:
    # read frame
    ret, frame = cap.read()
    if not ret:
        break

    # preprocess frame
    blob = cv2.dnn.blobFromImage(frame, 1/255, input_size, swapRB=True)
    net.setInput(blob)

    # forward pass
    outs = net.forward(net.getUnconnectedOutLayersNames())

    # postprocess detections
    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 > 0.5:
                center_x = int(detection[0] * frame.shape[1])
                center_y = int(detection[1] * frame.shape[0])
                width = int(detection[2] * frame.shape[1])
                height = int(detection[3] * frame.shape[0])
                left = center_x - width // 2
                top = center_y - height // 2
                class_ids.append(class_id)
                confidences.append(float(confidence))
                boxes.append([left, top, width, height])

    # apply non-maximum suppression
    indices = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)

    # draw detections
    for i in indices:
        i = i[0]
        box = boxes[i]
        left = box[0]
        top = box[1]
        width = box[2]
        height = box[3]
        class_id = class_ids[i]
        label = classes[class_id]
        confidence = confidences[i]
        color = (0, 255, 0)
        cv2.rectangle(frame, (left, top), (left+width, top+height), color, 2)
        cv2.putText(frame, f"{label}: {confidence:.2f}", (left, top-10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)

    # show frame
    cv2.imshow("Video", frame)
    if cv2.waitKey(1) == ord('q'):
        break

# release resources
cap.release()
cv2.destroyAllWindows()

这个示例代码会打开名为“video.mp4”的视频文件，并对其中的每个帧进行目标检测和识别，并在每个检测到的目标周围绘制一个矩形框，并在矩形框上方显示目标类别和置信度。可以使用“q”键退出程序。