使用Python + YOLO+opencv进行目标检测

完整源码：https://download.csdn.net/download/bibinGee/12278566

 

YOLO相关原理及数据集可以通过这个链接查看：https://pjreddie.com/darknet/yolo/

本博文将介绍使用YOLO结合opencv进行目标检测，需要用到的的资源有coco.names/yolov3.cfg/yolov3.weights，这些文件都可以从darknet或者github上找到。GitHub资源通过这个链接找到：https://github.com/pjreddie/darknet

coco.names
yolov3.cfg
yolov3.weight

需要用的python库有： 

import numpy as np
import argparse
import imutils
import time
import cv2
import os

项目的文件结构如下：

首先加载yolov3.weight和yolov3.cfg文件

# derive the paths to the YOLO weights and model configuration
weightsPath = os.path.sep.join([args["yolo"], "yolov3.weights"])
configPath = os.path.sep.join([args["yolo"], "yolov3.cfg"])

# load our YOLO object detector trained on COCO dataset (80 classes)
print("[INFO] loading YOLO from disk...")
net = cv2.dnn.readNetFromDarknet(configPath, weightsPath)

这里用到了opencv中的 dnn.readNetFromDarknet()，这个是opencv提供的深度神经网络学习的函数，有意思的是它似乎专门给darknet框架写的，如下关于这个函数的注释。

""
    readNetFromDarknet(cfgFile[, darknetModel]) -> retval
    .   @brief Reads a network model stored in Darknet model files.
    .   *  @param cfgFile      path to the .cfg file with text description of the network architecture.
    .   *  @param darknetModel path to the .weights file with learned network.
    .   *  @returns Network object that ready to do forward, throw an exception in failure cases.
    .   *  @returns Net object.
""

 接着对输入的图像进行预处理：

blob = cv2.dnn.blobFromImage(image, 1 / 255.0, (416, 416), swapRB=True, crop=False)
net.setInput(blob)

这里用到blogFormImage()这个函数，这个函数主要执行下面3个功能：

1. 均值减法 
2. 缩放
3. 频道交换

 

下面就可以对输入的图像进行分类识别了：

# loop over each of the layer outputs
for output in layerOutputs:
    # loop over each of the detections
    for detection in output:
        # extract the class ID and confidence (i.e., probability) of
        # the current object detection
        scores = detection[5:]
        classID = np.argmax(scores)
        confidence = scores[classID]

        # filter out weak predictions by ensuring the detected
        # probability is greater than the minimum probability
        if confidence > args["confidence"]:
            # scale the bounding box coordinates back relative to the
            # size of the image, keeping in mind that YOLO actually
            # returns the center (x, y)-coordinates of the bounding
            # box followed by the boxes' width and height
            box = detection[0:4] * np.array([W, H, W, H])
            (centerX, centerY, width, height) = box.astype("int")

            # use the center (x, y)-coordinates to derive the top and
            # and left corner of the bounding box
            x = int(centerX - (width / 2))
            y = int(centerY - (height / 2))

            # update our list of bounding box coordinates, confidences,
            # and class IDs
            boxes.append([x, y, int(width), int(height)])
            confidences.append(float(confidence))
            classIDs.append(classID)

 完成后就可以将目标标注出来了：

# ensure at least one detection exists
if len(idxs) > 0:
    # loop over the indexes we are keeping
    for i in idxs.flatten():
        # extract the bounding box coordinates
        (x, y) = (boxes[i][0], boxes[i][1])
        (w, h) = (boxes[i][2], boxes[i][3])

        # draw a bounding box rectangle and label on the image
        color = [int(c) for c in COLORS[classIDs[i]]]
        print(color)
        cv2.rectangle(image, (x, y), (x + w, y + h), color, 2)
        text = "{}: {:.4f}".format(LABELS[classIDs[i]], confidences[i])
        cv2.putText(image, text, (x, y - 5), cv2.FONT_ITALIC, 0.5, [0, 0, 0], 2)

 下面是利用yolo提供的数据集和图像例子识别出来的目标，准确率还很高。

然而事情也不是一帆风顺，当输入不在训练好的数据的目标的时，就会识别出错，比如下面两位仁兄就很搞笑了，关键时给出的准确度去到了99%和88%，不得不说有一个专用的训练集真的很重要。