< #!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Fri Apr 5 21:16:34 2019 @author: enigm4 """ import argparse import numpy as np import cv2 import imutils from imutils import paths from imutils.object_detection import non_max_suppression import time import os # construct the argument parse and parse the arguments ap = argparse.ArgumentParser() ap.add_argument("-i", "--images", required=True, help="path to images directory") ap.add_argument("-v", "--video", help="path to the (optional) video file") args = vars(ap.parse_args()) # initialize the HOG descriptor/person detector hog = cv2.HOGDescriptor() hog.setSVMDetector(cv2.HOGDescriptor_getDefaultPeopleDetector()) # if a video path was not supplied, process images if not args.get("video", False): # loop over the image paths imagePaths = list(paths.list_images(args["images"])) for imagePath in imagePaths: # load the image and resize it to (1) reduce detection time # and (2) improve detection accuracy image = cv2.imread(imagePath) image = imutils.resize(image, width=min(400, image.shape[1])) orig = image.copy() # detect people in the image (rects, weights) = hog.detectMultiScale(image, winStride=(4, 4), padding=(8, 8), scale=1.05) # draw the original bounding boxes for (x, y, w, h) in rects: cv2.rectangle(orig, (x, y), (x + w, y + h), (0, 0, 255), 2) # apply non-maxima suppression to the bounding boxes using a # fairly large overlap threshold to try to maintain overlapping # boxes that are still people rects = np.array([[x, y, x + w, y + h] for (x, y, w, h) in rects]) pick = non_max_suppression(rects, probs=None, overlapThresh=0.65) # draw the final bounding boxes for (xA, yA, xB, yB) in pick: cv2.rectangle(image, (xA, yA), (xB, yB), (0, 255, 0), 2) # show some information on the number of bounding boxes filename = imagePath[imagePath.rfind("/") + 1:] print("[INFO] {}: {} original boxes, {} after suppression".format( filename, len(rects), len(pick))) # show the output images cv2.imshow("Before NMS", orig) cv2.imshow("After NMS", image) cv2.waitKey(0) # otherwise, process a video file else: # open the video file cap = cv2.VideoCapture(args["video"]) # initialize the video writer fourcc = cv2.VideoWriter_fourcc(*"MJPG") writer = None # loop over frames from the video stream while True: # grab the next frame from the video grabbed, frame = cap.read() # if the frame was not grabbed, then we have reached the end # of the video if not grabbed: break # resize the frame to have a maximum width of 400 pixels frame = imutils.resize(frame, width=min(400, frame.shape[1])) # if the video writer is None, initialize it if writer is None: writer = cv2.VideoWriter("output.avi", fourcc, 30, (frame.shape[1], frame.shape[0]), True) # detect people in the frame (rects, weights) = hog.detectMultiScale(frame, winStride=(4, 4), padding=(8, 8), scale=1.05) # draw the original bounding boxes for (x, y, w, h) in rects: cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 0, 255), 2) # apply non-maxima suppression to the bounding boxes using a # fairly large overlap threshold to try to maintain overlapping # boxes that are still people rects = np.array([[x, y, x + w, y + h] for (x, y, w, h) in rects]) pick = non_max_suppression(rects, probs=None, overlapThresh=0.65) # draw the final bounding boxes for (xA, yA, xB, yB) in pick: cv2.rectangle(frame, (xA, yA), (xB, yB), (0, 255, 0), 2) # show some information on the number of bounding boxes print("[INFO] {} original boxes, {} after suppression".format( len(rects), len(pick))) # write the output frame to disk writer.write(frame) # 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 # release the video capture and video writer objects cap.release() writer.release() # close any open windows cv2.destroyAllWindows()