opencv-124-DNN 基于SSD实现对象检测

发表于 | 分类于

知识点

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。

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。

代码（c++,python）

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
#include <opencv2/opencv.hpp>
#include <opencv2/dnn.hpp>
#include <iostream>

using namespace cv;
using namespace cv::dnn;
using namespace std;

const size_t width = 300;
const size_t height = 300;
String labelFile = "D:/projects/opencv_tutorial/data/models/ssd/labelmap_det.txt";
String modelFile = "D:/projects/opencv_tutorial/data/models/ssd/MobileNetSSD_deploy.caffemodel";
String model_text_file = "D:/projects/opencv_tutorial/data/models/ssd/MobileNetSSD_deploy.prototxt";

String objNames[] = { "background",
"aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair",
"cow", "diningtable", "dog", "horse",
"motorbike", "person", "pottedplant",
"sheep", "sofa", "train", "tvmonitor" };

int main(int argc, char** argv) {
	Mat frame = imread("D:/images/dog.jpg");
	if (frame.empty()) {
		printf("could not load image...\n");
		return -1;
	}
	namedWindow("input image", WINDOW_AUTOSIZE);
	imshow("input image", frame);

	Net net = readNetFromCaffe(model_text_file, modelFile);
	net.setPreferableBackend(DNN_BACKEND_INFERENCE_ENGINE);
	net.setPreferableTarget(DNN_TARGET_CPU);
	Mat blobImage = blobFromImage(frame, 0.007843,
		Size(300, 300),
		Scalar(127.5, 127.5, 127.5), true, false);
	printf("blobImage width : %d, height: %d\n", blobImage.cols, blobImage.rows);

	net.setInput(blobImage, "data");
	Mat detection = net.forward("detection_out");
	vector<double> layersTimings;
	double freq = getTickFrequency() / 1000;
	double time = net.getPerfProfile(layersTimings) / freq;
	printf("execute time : %.2f ms\n", time);


	Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>());
	float confidence_threshold = 0.5;
	for (int i = 0; i < detectionMat.rows; i++) {
		float confidence = detectionMat.at<float>(i, 2);
		if (confidence > confidence_threshold) {
			size_t objIndex = (size_t)(detectionMat.at<float>(i, 1));
			float tl_x = detectionMat.at<float>(i, 3) * frame.cols;
			float tl_y = detectionMat.at<float>(i, 4) * frame.rows;
			float br_x = detectionMat.at<float>(i, 5) * frame.cols;
			float br_y = detectionMat.at<float>(i, 6) * frame.rows;

			Rect object_box((int)tl_x, (int)tl_y, (int)(br_x - tl_x), (int)(br_y - tl_y));
			rectangle(frame, object_box, Scalar(0, 0, 255), 2, 8, 0);
			putText(frame, format(" confidence %.2f, %s", confidence, objNames[objIndex].c_str()), Point(tl_x - 10, tl_y - 5), FONT_HERSHEY_SIMPLEX, 0.7, Scalar(255, 0, 0), 2, 8);
		}
	}
	imshow("ssd-demo", frame);

	waitKey(0);
	return 0;
}
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
"""
DNN 基于SSD实现对象检测
"""

import cv2 as cv

model_bin = "MobileNetSSD_deploy.caffemodel"
config_text = "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 and read test iamge
net = cv.dnn.readNetFromCaffe(config_text, model_bin)
image = cv.imread("images/dog.jpg")
h = image.shape[0]
w = image.shape[1]

# 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("ssd-demo", image)
cv.waitKey(0)
cv.destroyAllWindows()

结果

代码地址

github