Python和OpenCV实现摄像头实时目标检测的应用场景代码

案例：

import cv2
import numpy as np

# 加载预训练的YOLOv3模型
def load_yolo():
    net = cv2.dnn.readNet("yolov3.weights", "yolov3.cfg")
    classes = []
    with open("coco.names", "r") as f:
        classes = [line.strip() for line in f.readlines()]
    return net, classes

# 检测函数
def detect_objects(img, net, classes):
    height, width, _ = img.shape
    blob = cv2.dnn.blobFromImage(img, 1/255.0, (416, 416), swapRB=True, crop=False)
    net.setInput(blob)
    output_layers_names = net.getUnconnectedOutLayersNames()
    layer_outputs = net.forward(output_layers_names)

    boxes = []
    confidences = []
    class_ids = []

    for output in layer_outputs:
        for detection in output:
            scores = detection[5:]
            class_id = np.argmax(scores)
            confidence = scores[class_id]
            if confidence > 0.5:  # 置信度阈值
                center_x = int(detection[0] * width)
                center_y = int(detection[1] * height)
                w = int(detection[2] * width)
                h = int(detection[3] * height)

                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, 0.5, 0.4)  # 非极大值抑制

    return boxes, confidences, class_ids, indexes

# 主函数
def main():
    net, classes = load_yolo()
    cap = cv2.VideoCapture(0)  # 打开默认摄像头

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

        boxes, confidences, class_ids, indexes = detect_objects(frame, net, classes)

        for i in indexes.flatten():
            x, y, w, h = boxes[i]
            label = str(classes[class_ids[i]])
            confidence = confidences[i]
            color = (0, 255, 0)  # 绿色边框
            cv2.rectangle(frame, (x, y), (x + w, y + h), color, 2)
            text = f"{label}: {confidence:.2f}"
            cv2.putText(frame, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)

        cv2.imshow("Real-Time Object Detection", frame)

        if cv2.waitKey(1) & 0xFF == ord('q'):
            break

    cap.release()
    cv2.destroyAllWindows()

if __name__ == "__main__":
    main()