Python中如何使用YOLO2实现实时目标检测？附视频教程、Android Demo及开源项目

实时目标检测和分类

GIF 图：

视频截图：

论文： https://arxiv.org/pdf/1506.02640.pdf https://arxiv.org/pdf/1612.08242.pdf

了解更多 YOLO，并且下载权重文件：

https://pjreddie.com/darknet/yolo/

视频教程（视频分享到群文件了）： https://www.youtube.com/watch?v=4eIBisqx9_g&feature=youtu.be

Android Demo:https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/android/src/org/tensorflow/demo/TensorFlowYoloDetector.java

TensorFlow 更多资源： http://www.tensorflownews.com/

QQ 群（视频分享到群文件了）：522785813


Python中如何使用YOLO2实现实时目标检测？附视频教程、Android Demo及开源项目

1 回复

要搞YOLOv2实时检测，得先装好环境。核心是Darknet框架，用C写的但Python能调。我习惯用OpenCV的DNN模块来跑，这样部署起来方便。

先装依赖：

pip install opencv-python numpy

下载YOLOv2的配置和权重：

  • 配置文件：yolov2.cfg
  • 权重文件：yolov2.weights
  • 类别文件：coco.names

然后上代码：

import cv2
import numpy as np

# 加载模型
net = cv2.dnn.readNet("yolov2.weights", "yolov2.cfg")
with open("coco.names", "r") as f:
    classes = [line.strip() for line in f.readlines()]

# 获取输出层
layer_names = net.getLayerNames()
output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]

# 实时检测
cap = cv2.VideoCapture(0)  # 用摄像头
while True:
    ret, frame = cap.read()
    if not ret:
        break
    
    height, width = frame.shape[:2]
    
    # 预处理
    blob = cv2.dnn.blobFromImage(frame, 0.00392, (416, 416), (0, 0, 0), True, crop=False)
    net.setInput(blob)
    outs = net.forward(output_layers)
    
    # 解析结果
    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:  # 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)
    
    # NMS去重
    indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
    
    # 画框
    for i in range(len(boxes)):
        if i in indexes:
            x, y, w, h = boxes[i]
            label = f"{classes[class_ids[i]]}: {confidences[i]:.2f}"
            cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
            cv2.putText(frame, label, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
    
    cv2.imshow("YOLOv2 Detection", frame)
    if cv2.waitKey(1) == 27:  # 按ESC退出
        break

cap.release()
cv2.destroyAllWindows()

视频教程推荐Joseph Redmon的原版讲解，Android Demo可以看Darknet的官方移植，开源项目首推AlexeyAB的Darknet改进版。

总结：用OpenCV的DNN模块调用YOLOv2最快。

回到顶部