12.基于opencv-python+yolov3实现图片目标检测

import cv2
import numpy as np

# 读取图片
# 读取神经网络cv2.dnn.readNetFromDarknet(cfg,weight)
# 把图片送入网络并输出分类结果

imgPath = 'G:/1.png'  # 测试图像
coco='F:/coco.names'
# 读取模型和权重
configPath='F:/yolo.cfg'
weightPath='F:yolov3.weights'
net=cv2.dnn.readNetFromDarknet(configPath,weightPath)
CONFIDENCE = 0.2  # 过滤弱检测的最小概率
THRESHOLD = 0.4  # 非最大值抑制阈值

# 加载图片、转为blob格式、送入网络输入层
imgResize = cv2.imread(imgPath)
img = cv2.resize(imgResize, (800,600))
blobImg = cv2.dnn.blobFromImage(img, 1.0/255.0, (416, 416), None, True, False)   # # net需要的输入是blob格式的,用blobFromImage这个函数来转格式
net.setInput(blobImg)  # # 调用setInput函数将图片送入输入层
 
# 获取网络输出层信息(所有输出层的名字),设定并前向传播
outInfo = net.getUnconnectedOutLayersNames()  # # 前面的yolov3架构也讲了,yolo在每个scale都有输出,outInfo是每个scale的名字信息,供net.forward使用
layerOutputs = net.forward(outInfo)  # 得到各个输出层的、各个检测框等信息,是二维结构。
 
# 拿到图片尺寸
(H, W) = img.shape[:2]
# 过滤layerOutputs
# layerOutputs的第1维的元素内容: [center_x, center_y, width, height, objectness, N-class score data]
# 过滤后的结果放入:
boxes = [] # 所有边界框(各层结果放一起)
confidences = [] # 所有置信度
classIDs = [] # 所有分类ID
 
# # 1)过滤掉置信度低的框框
for out in layerOutputs:  # 各个输出层
    for detection in out:  # 各个框框
        # 拿到置信度
        scores = detection[5:]  # 各个类别的置信度
        classID = np.argmax(scores)  # 最高置信度的id即为分类id
        confidence = scores[classID]  # 拿到置信度
 
        # 根据置信度筛查
        if confidence > CONFIDENCE:
            box = detection[0:4] * np.array([W, H, W, H])  # 将边界框放会图片尺寸
            (centerX, centerY, width, height) = box.astype("int")
            x = int(centerX - (width / 2))
            y = int(centerY - (height / 2))
            boxes.append([x, y, int(width), int(height)])
            confidences.append(float(confidence))
            classIDs.append(classID)
 
# # 2)应用非最大值抑制(non-maxima suppression,nms)进一步筛掉
idxs = cv2.dnn.NMSBoxes(boxes, confidences, CONFIDENCE, THRESHOLD) # boxes中,保留的box的索引index存入idxs
# 得到labels列表
with open(coco, 'rt') as f:
    labels = f.read().rstrip('\n').split('\n')
# 应用检测结果
np.random.seed(42)
COLORS = np.random.randint(0, 255, size=(len(labels), 3), dtype="uint8")  # 框框显示颜色,每一类有不同的颜色,每种颜色都是由RGB三个值组成的,所以size为(len(labels), 3)
if len(idxs) > 0:
    for i in idxs.flatten():  # indxs是二维的,第0维是输出层,所以这里把它展平成1维
        (x, y) = (boxes[i][0], boxes[i][1])
        (w, h) = (boxes[i][2], boxes[i][3])
 
        color = [int(c) for c in COLORS[classIDs[i]]]
        cv2.rectangle(img, (x, y), (x+w, y+h), color, 2)  # 线条粗细为2px
        text = "{}: {:.4f}".format(labels[classIDs[i]], confidences[i])
        cv2.putText(img, text, (x, y-5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)  # cv.FONT_HERSHEY_SIMPLEX字体风格、0.5字体大小、粗细2px
cv2.imshow('img', img)
cv2.waitKey(0)

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-lZ8FhGrz-1662134356646)(https://git.poker/quinhua/pics/blob/main/markdown/fgbvrdffcftdfsc.webp?raw=true)]

你可能感兴趣的:(计算机视觉,python,opencv,目标检测)