卷积神经网络预测实例

# USAGE # python real_time_object_detection.py --prototxt MobileNetSSD_deploy.prototxt.txt --model MobileNetSSD_deploy.caffemodel # import the necessary packages from imutils.video import VideoStream from imutils.video import FPS import numpy as np import argparse import imutils import time import cv2 # construct the argument parse and parse the arguments ap = argparse.ArgumentParser() ap.add_argument("-p", "--prototxt",default="MobileNetSSD_deploy_0.prototxt", help="path to Caffe 'deploy' prototxt file") ap.add_argument("-m", "--model",default="MobileNetSSD_deploy_0.caffemodel", 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()) # 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...") net2 = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"]) # net2=cv2.dnn.readNetFromCaffe("VGG_SSD_300.prototxt","VGG_SSD_300.caffemodel") # net2=cv2.dnn.readNetFromTensorflow("face.pb") # initialize the video stream, allow the cammera sensor to warmup, # and initialize the FPS counter print("[INFO] starting video stream...") #vs = VideoStream(src=0).start() # vs =cv2.VideoCapture('C:\\Users\\voidking\\Desktop\\real-time-object-detection\\test_video.flv') # vs =cv2.VideoCapture('./test_video.flv') # vs =cv2.VideoCapture("video1.mp4") vs =cv2.VideoCapture('timg.jpg') time.sleep(2.0) fps = FPS().start() # loop over the frames from the video stream while True: # grab the frame from the threaded video stream and resize it # to have a maximum width of 400 pixels #frame = vs.read() #frame = imutils.resize(frame, width=400) # grab the frame from the threaded video file stream (grabbed,frame) = vs.read() # if the frame was not grabbed, then we have reached the end # of the stream if not grabbed: break frame = imutils.resize(frame, width=800) # grab the frame dimensions 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 net2.setInput(blob) detections = net2.forward() # print(np.max(detections[0])) # print(detections) # 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 idx = int(detections[0, 0, i, 1]) label = "{}: {:.2f}%".format(CLASSES[idx], confidence * 100) if confidence > args["confidence"]: if True: #if CLASSES[idx]=="person": # 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 cv2.rectangle(frame, (startX, startY), (endX, endY), COLORS[idx], 2) y = startY - 15 if startY - 15 > 15 else startY + 15 pix_person_height = endY - startY print ('pix_person_height = ', pix_person_height) print ('distance = ' , 174724 / pix_person_height) cv2.putText(frame, label, (startX, y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2) # # 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 # # 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) key = cv2.waitKey(1) & 0xFF # if the `q` key was pressed, break from the loop if key == ord("q"): break # update the FPS counter fps.update() # stop the timer and display FPS information fps.stop() print("[INFO] elapsed time: {:.2f}".format(fps.elapsed())) print("[INFO] approx. FPS: {:.2f}".format(fps.fps())) # do a bit of cleanup #销毁窗口 #cv2.destroyAllWindows()