【OpenCV】124 OpenCV DNN 基于SSD实现对象检测

124 OpenCV DNN 基于SSD实现对象检测

代码

import cv2 as cv

model_bin = "../models/ssd/MobileNetSSD_deploy.caffemodel";
config_text = "../models/ssd/MobileNetSSD_deploy.prototxt";
objName = ["background",
"aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair",
"cow", "diningtable", "dog", "horse",
"motorbike", "person", "pottedplant",
"sheep", "sofa", "train", "tvmonitor"];

# load caffe model
net = cv.dnn.readNetFromCaffe(config_text, model_bin)
image = cv.imread("../images/dog.jpg")
h = image.shape[0]
w = image.shape[1]

# 获得所有层名称与索引
layerNames = net.getLayerNames()
lastLayerId = net.getLayerId(layerNames[-1])
lastLayer = net.getLayer(lastLayerId)
print(lastLayer.type)

# 检测
blobImage = cv.dnn.blobFromImage(image, 0.007843, (300, 300), (127.5, 127.5, 127.5), True, False);
net.setInput(blobImage)
cvOut = net.forward()
print(cvOut)
for detection in cvOut[0,0,:,:]:
    score = float(detection[2])
    objIndex = int(detection[1])
    if score > 0.5:
        left = detection[3]*w
        top = detection[4]*h
        right = detection[5]*w
        bottom = detection[6]*h

        # 绘制
        cv.rectangle(image, (int(left), int(top)), (int(right), int(bottom)), (255, 0, 0), thickness=2)
        cv.putText(image, "score:%.2f, %s"%(score, objName[objIndex]),
                (int(left) - 10, int(top) - 5), cv.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2, 8);

cv.imshow('mobilenet-ssd-demo', image)
cv.waitKey(0)
cv.destroyAllWindows()

实验结果

解释

OpenCV DNN模块支持常见得对象检测模型SSD， 以及它的移动版Mobile Net-SSD，特别是后者在端侧边缘设备上可以实时计算，基于Caffe训练好的mobile-net SSD支持20类别对象检测。

加载网络之后，推断调用的关键API如下：

retval = cv.dnn_Net.forward([, outputName])

参数缺省值为空

对对象检测网络来说：
该API会返回一个四维的tensor，前两个维度是1，后面的两个维度，分别表示检测到BOX数量，以及每个BOX的坐标，对象类别，得分等信息。这里需要特别注意的是，这个坐标是浮点数的比率，不是像素值，所以必须转换为像素坐标才可以绘制BOX/矩形。

---

所有内容均来源于贾志刚老师的知识星球——OpenCV研习社，本文为个人整理学习，已获得贾老师授权，有兴趣、有能力的可以加入贾老师的知识星球进行深入学习。