01 使用OpenCV的dnn模块实现YOLO模型的搭建

1、导入库

import cv2
import numpy as np

2、加载模型

# 加载模型
print("LOADING YOLO")
net = cv2.dnn.readNet("yolov3.weights", "yolov3.cfg")
# 加载类别
classes = []
with open("coco.names", "r") as f:
    classes = [line.strip() for line in f.readlines()]
# get layers of the network
layer_names = net.getLayerNames()

# 确定 YOLO 模型的输出层名称
output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]
print("YOLO LOADED")

3、读取视频流，检测

video_capture = cv2.VideoCapture(0)
while True:
    # Capture frame-by-frame
    re, img = video_capture.read()
    img = cv2.resize(img, None, fx=0.4, fy=0.4)
    height, width, channels = img.shape

    # 使用opencv的blob函数对图像进行预处理
    blob = cv2.dnn.blobFromImage(img, 1 / 255.0, (416, 416),
                                 swapRB=True, crop=False)
    # Detecting objects
    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 > 0.5:
                # Object detected
                center_x = int(detection[0] * width)
                center_y = int(detection[1] * height)
                w = int(detection[2] * width)
                h = int(detection[3] * height)

                # Rectangle coordinates
                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)

    # 使用NMS功能来执行非最大值抑制
    # 我们给出 IT 分数阈值和 NMS 阈值作为参数。7
    indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
    font = cv2.FONT_HERSHEY_PLAIN
    colors = np.random.uniform(0, 255, size=(len(classes), 3))
    for i in range(len(boxes)):
        if i in indexes:
            x, y, w, h = boxes[i]
            label = str(classes[class_ids[i]])
            color = colors[class_ids[i]]
            cv2.rectangle(img, (x, y), (x + w, y + h), color, 2)
            cv2.putText(img, label, (x, y + 30), font, 2, color, 3)

    cv2.imshow("Image", cv2.resize(img, (800, 600)))
    if cv2.waitKey(25) & 0xFF == ord('q'):
        break

4、释放摄像头和窗口

video_capture.release()
cv2.destroyAllWindows()