基於深度學習和OpenCV實現目標檢測

import numpy as np
import cv2
if __name__=="__main__":
	image_name = '11.jpg'
	prototxt = 'MobileNetSSD_deploy.prototxt.txt'
	model_path = 'MobileNetSSD_deploy.caffemodel'
	confidence_ta = 0.2
	# 初始化MobileNet SSD訓練的類標簽列表
	# 檢測，然後為每個類生成一組邊界框顏色
	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))

	# load our serialized model from disk
	print("[INFO] loading model...")
	net = cv2.dnn.readNetFromCaffe(prototxt, model_path)
	# 加載輸入圖像並為圖像構造一個輸入blob
	# 將大小調整為固定的300x300像素。
	# （註意：SSD模型的輸入是300x300像素）
	image = cv2.imread(image_name)
	(h, w) = image.shape[:2]
	blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 0.007843,
								 (300, 300), 127.5)
	# 通過網絡傳遞blob並獲得檢測結果和
	# 預測
	print("[INFO] computing object detections...")
	net.setInput(blob)
	detections = net.forward()

	# 循環檢測結果
	for i in np.arange(0, detections.shape[2]):
		# 提取與數據相關的置信度（即概率）
		# 預測
		confidence = detections[0, 0, i, 2]
		# 通過確保“置信度”來過濾掉弱檢測
		# 大於最小置信度
		if confidence > confidence_ta:
			# 從`detections`中提取類標簽的索引，
			# 然後計算物體邊界框的 (x, y) 坐標
			idx = int(detections[0, 0, i, 1])
			box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
			(startX, startY, endX, endY) = box.astype("int")
			# 顯示預測
			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)
	# show the output image
	cv2.imshow("Output", image)
	cv2.imwrite("output.jpg", image)
	cv2.waitKey(0)

video_name = '12.mkv'
prototxt = 'MobileNetSSD_deploy.prototxt.txt'
model_path = 'MobileNetSSD_deploy.caffemodel'
confidence_ta = 0.2

# initialize the list of class labels MobileNet SSD was trained to
# detect, then generate a set of bounding box colors for each class
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))

# load our serialized model from disk
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(prototxt, model_path)

# initialze the video stream, allow the camera to sensor to warmup,
# and initlaize the FPS counter
print('[INFO] starting video stream...')
vs = cv2.VideoCapture(video_name)
fps = 30    #保存視頻的FPS，可以適當調整
size=(600,325)
fourcc=cv2.VideoWriter_fourcc(*'XVID')
videowrite=cv2.VideoWriter('output.avi',fourcc,fps,size)
time.sleep(2.0)

# loop over the frames from the video stream
while True:
    ret_val, frame = vs.read()
    if ret_val is False:
        break
    frame = imutils.resize(frame, width=1080)
    print(frame.shape)
    # grab the frame dimentions and convert it to a blob
    (h, w) = frame.shape[:2]
    blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)), 0.007843, (300, 300), 127.5)

    # pass the blob through the network and obtain the detections and predictions
    net.setInput(blob)
    detections = net.forward()

    # loop over the detections
    for i in np.arange(0, detections.shape[2]):
        # extract the confidence (i.e., probability) associated with
        # the prediction
        confidence = detections[0, 0, i, 2]

        # filter out weak detections by ensuring the `confidence` is
        # greater than the minimum confidence
        if confidence > confidence_ta:
            # extract the index of the class label from the
            # `detections`, then compute the (x, y)-coordinates of
            # the bounding box for the object
            idx = int(detections[0, 0, i, 1])
            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
            (startX, startY, endX, endY) = box.astype("int")

            # draw the prediction on the frame
            label = "{}: {:.2f}%".format(CLASSES[idx],
                                         confidence * 100)
            cv2.rectangle(frame, (startX, startY), (endX, endY),
                          COLORS[idx], 2)
            y = startY - 15 if startY - 15 > 15 else startY + 15
            cv2.putText(frame, label, (startX, y),
                        cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)
    # show the output frame
    cv2.imshow("Frame", frame)
    videowrite.write(frame)
    key = cv2.waitKey(1) & 0xFF

    # if the `q` key was pressed, break from the loop
    if key == ord("q"):
        break
videowrite.release()
# do a bit of cleanup
cv2.destroyAllWindows()
vs.release()