Object detection with deep learning and OpenCV

目录

• Single Shot Detectors for Object Detection
• Deep learning-based object detection with OpenCV

---

  这篇文章只是基于OpenCV使用SSD算法执行目标检测；不涉及到SSD的理论原理、不涉及训练过程；也就是说仅仅使用训练好的模型文件基于OpenCV做测试；包括图片和视频；

  只用作笔记，原教程地址：Object detection with deep learning and OpenCV

---

Single Shot Detectors for Object Detection

  当提到基于深度学习的目标检测算法，大家都多多少少的听说过这三种算法：

• Faster R-CNNs (Girshick et al., 2015)
• You Only Look Once (YOLO) (Redmon and Farhadi, 2015)
• Single Shot Detectors (SSDs) (Liu et al., 2015)

 当然了，现在已经是19年了，上面三种算法也已经更新换代了；那之所以还列举出来，想要表达的是这三类算法是相当good,...(完了，装不下去了....)

R-CNN系列检测算法，精确度高，速度慢；

YOLO系列检测算法，速度快，精确度有些欠缺；

SSD取了两者的优点吧。。。。

Deep learning-based object detection with OpenCV

#!/usr/bin/env python
#-*- coding:utf-8 -*-
# @Time    : 19-4-24 下午3:52
# @Author  : chen

"""
利用MobileNet SSD + OpenCV中的dnn执行目标检测

python deep_learning_object_detection_cz.py --image images/face_1.jpg 
--prototxt MobileNetSSD_deploy.prototxt.txt 
 --model MobileNetSSD_deploy.caffemodel
"""
# 依赖包
import numpy as np
import argparse
import cv2
import time
import pdb

# 解析命令行参数
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True, help="path to input image")
ap.add_argument("-p", "--prototxt", required=True, help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", required=True, help="path to Caffe pre-trained model")
ap.add_argument("-c", "--confidence", type=float, default=0.2, help="minimum probability to filter weak detections")
args = vars(ap.parse_args())

# 初始化类标签，然后为每一个类别设置一个颜色值
# 该颜色值是为了在图像中画出矩形框的时候使用
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
           "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
           "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
           "sofa", "train", "tvmonitor"]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))

# 加载训练好的Caffe模型
# OpenCV的dnn方法中，可以加载由Caffe，TensorFLow，Darknet，Torch训练得到的模型文件的方法
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])

# 加载测试图片，并转换成blob(OpenCV需要这样做)
image = cv2.imread(args["image"])
(h, w) = image.shape[:2]
# cv2.dnn.blobFromImage返回一个四维的blob
# 可以对image执行缩放，剪切，交换RB通道，减均值操作
blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 0.007843, (300, 300), 127.5)

# 输入到网络中，执行Inference
print("[INFO] computing object detections...")
net.setInput(blob)
start = time.time()
detections = net.forward()
end = time.time()
print("[INFO] SSD took {:6} seconds.".format(end - start))
# pdb.set_trace()

for i in range(detections.shape[2]):
    # 类别概率
    confidence = detections[0, 0, i, 2]

    # 过滤掉confidence小于人为设定的阈值的detection
    if confidence > args["confidence"]:
        idx = int(detections[0, 0, i, 1])  # 类别索引
        box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
        (startX, startY, endX, endY) = box.astype("int")  # SSD的输出直接就是框的左上角和右下角的点的坐标位置

        # 在图片展示检测的object
        label = "{}: {:.2f}%".format(CLASSES[idx], confidence*100)
        print("[INFO] {}".format(label))
        cv2.rectangle(image, (startX, startY), (endX, endY), COLORS[idx], 2)
        y = startY -15 if startY - 15 > 15 else startY + 15
        cv2.putText(image, label, (startX, y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)

# 显示
cv2.imshow("Object Detection", image)
cv2.waitKey(0)
cv2.imwrite("lab_2_ssd.jpg", image)

---

 这样有没有用？？？？？用处不大

  还是需要看论文的。。。。。