numpy - Counting Cars OpenCV + Python Issue

Question

I have been trying to count cars when crossing the line and it works, but the problem is it counts one car many times which is ridiculous because it should only be counted once.

Here is the code I am using:

import cv2
import numpy as np

bgsMOG = cv2.BackgroundSubtractorMOG()
cap    = cv2.VideoCapture("traffic.avi")
counter = 0

if cap:
    while True:
        ret, frame = cap.read()

        if ret:
            fgmask = bgsMOG.apply(frame, None, 0.01)
            cv2.line(frame, (0,60), (160,60), (255,255,0), 1)
            # To find the countours of the Cars
            contours, hierarchy = cv2.findContours(fgmask,
                                    cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)

            try:
                hierarchy = hierarchy[0]

            except:
                hierarchy = []

            for contour, hier in zip(contours, hierarchy):
                (x, y, w, h) = cv2.boundingRect(contour)

                if w > 20 and h > 20:
                    cv2.rectangle(frame, (x,y), (x+w,y+h), (255, 0, 0), 1)

                    # To find the centroid of the car
                    x1 = w/2
                    y1 = h/2

                    cx = x+x1
                    cy = y+y1
##                    print "cy=", cy
##                    print "cx=", cx
                    centroid = (cx,cy)
##                    print "centoid=", centroid
                    # Draw the circle of Centroid
                    cv2.circle(frame,(int(cx),int(cy)),2,(0,0,255),-1)

                    # To make sure the Car crosses the line
##                    dy = cy-108
##                    print "dy", dy
                    if centroid > (27, 38) and centroid < (134, 108):
##                        if (cx <= 132)and(cx >= 20):
                        counter +=1
##                            print "counter=", counter
##                    if cy > 10 and cy < 160:
                    cv2.putText(frame, str(counter), (x,y-5),
                                        cv2.FONT_HERSHEY_SIMPLEX,
                                        0.5, (255, 0, 255), 2)
##            cv2.namedWindow('Output',cv2.cv.CV_WINDOW_NORMAL)
            cv2.imshow('Output', frame)
##          cv2.imshow('FGMASK', fgmask)


            key = cv2.waitKey(60)
            if key == 27:
                break

cap.release()
cv2.destroyAllWindows()

And the video is on my GitHub page @ https://github.com/Tes3awy/MATLAB-Tutorials/blob/f24b680f2215c1b1bb96c76f5ba81df533552983/traffic.avi (and it's also a built-in video in Matlab library)

How can make it so that each car is only counted once?

---

The individual frames of the video look as follows:

Answer 1

Preparation

In order to understand what is happening, and eventually solve our problem, we first need to improve the script a little.

I've added logging of the important steps of your algorithm, refactored the code a little, and added saving of the mask and processed images, added ability to run the script using the individual frame images, along with some other modifications.

This is what the script looks like at this point:

import logging
import logging.handlers
import os
import time
import sys

import cv2
import numpy as np

from vehicle_counter import VehicleCounter

# ============================================================================

IMAGE_DIR = "images"
IMAGE_FILENAME_FORMAT = IMAGE_DIR + "/frame_%04d.png"

# Support either video file or individual frames
CAPTURE_FROM_VIDEO = False
if CAPTURE_FROM_VIDEO:
    IMAGE_SOURCE = "traffic.avi" # Video file
else:
    IMAGE_SOURCE = IMAGE_FILENAME_FORMAT # Image sequence

# Time to wait between frames, 0=forever
WAIT_TIME = 1 # 250 # ms

LOG_TO_FILE = True

# Colours for drawing on processed frames    
DIVIDER_COLOUR = (255, 255, 0)
BOUNDING_BOX_COLOUR = (255, 0, 0)
CENTROID_COLOUR = (0, 0, 255)

# ============================================================================

def init_logging():
    main_logger = logging.getLogger()

    formatter = logging.Formatter(
        fmt='%(asctime)s.%(msecs)03d %(levelname)-8s [%(name)s] %(message)s'
        , datefmt='%Y-%m-%d %H:%M:%S')

    handler_stream = logging.StreamHandler(sys.stdout)
    handler_stream.setFormatter(formatter)
    main_logger.addHandler(handler_stream)

    if LOG_TO_FILE:
        handler_file = logging.handlers.RotatingFileHandler("debug.log"
            , maxBytes = 2**24
            , backupCount = 10)
        handler_file.setFormatter(formatter)
        main_logger.addHandler(handler_file)

    main_logger.setLevel(logging.DEBUG)

    return main_logger

# ============================================================================

def save_frame(file_name_format, frame_number, frame, label_format):
    file_name = file_name_format % frame_number
    label = label_format % frame_number

    log.debug("Saving %s as '%s'", label, file_name)
    cv2.imwrite(file_name, frame)

# ============================================================================

def get_centroid(x, y, w, h):
    x1 = int(w / 2)
    y1 = int(h / 2)

    cx = x + x1
    cy = y + y1

    return (cx, cy)

# ============================================================================

def detect_vehicles(fg_mask):
    log = logging.getLogger("detect_vehicles")

    MIN_CONTOUR_WIDTH = 21
    MIN_CONTOUR_HEIGHT = 21

    # Find the contours of any vehicles in the image
    contours, hierarchy = cv2.findContours(fg_mask
        , cv2.RETR_EXTERNAL
        , cv2.CHAIN_APPROX_SIMPLE)

    log.debug("Found %d vehicle contours.", len(contours))

    matches = []
    for (i, contour) in enumerate(contours):
        (x, y, w, h) = cv2.boundingRect(contour)
        contour_valid = (w >= MIN_CONTOUR_WIDTH) and (h >= MIN_CONTOUR_HEIGHT)

        log.debug("Contour #%d: pos=(x=%d, y=%d) size=(w=%d, h=%d) valid=%s"
            , i, x, y, w, h, contour_valid)

        if not contour_valid:
            continue

        centroid = get_centroid(x, y, w, h)

        matches.append(((x, y, w, h), centroid))

    return matches

# ============================================================================

def filter_mask(fg_mask):
    kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3))

    # Fill any small holes
    closing = cv2.morphologyEx(fg_mask, cv2.MORPH_CLOSE, kernel)
    # Remove noise
    opening = cv2.morphologyEx(closing, cv2.MORPH_OPEN, kernel)

    # Dilate to merge adjacent blobs
    dilation = cv2.dilate(opening, kernel, iterations = 2)

    return dilation

# ============================================================================

def process_frame(frame_number, frame, bg_subtractor, car_counter):
    log = logging.getLogger("process_frame")

    # Create a copy of source frame to draw into
    processed = frame.copy()

    # Draw dividing line -- we count cars as they cross this line.
    cv2.line(processed, (0, car_counter.divider), (frame.shape[1], car_counter.divider), DIVIDER_COLOUR, 1)

    # Remove the background
    fg_mask = bg_subtractor.apply(frame, None, 0.01)
    fg_mask = filter_mask(fg_mask)

    save_frame(IMAGE_DIR + "/mask_%04d.png"
        , frame_number, fg_mask, "foreground mask for frame #%d")

    matches = detect_vehicles(fg_mask)

    log.debug("Found %d valid vehicle contours.", len(matches))
    for (i, match) in enumerate(matches):
        contour, centroid = match

        log.debug("Valid vehicle contour #%d: centroid=%s, bounding_box=%s", i, centroid, contour)

        x, y, w, h = contour

        # Mark the bounding box and the centroid on the processed frame
        # NB: Fixed the off-by one in the bottom right corner
        cv2.rectangle(processed, (x, y), (x + w - 1, y + h - 1), BOUNDING_BOX_COLOUR, 1)
        cv2.circle(processed, centroid, 2, CENTROID_COLOUR, -1)

    log.debug("Updating vehicle count...")
    car_counter.update_count(matches, processed)

    return processed

# ============================================================================

def main():
    log = logging.getLogger("main")

    log.debug("Creating background subtractor...")
    bg_subtractor = cv2.BackgroundSubtractorMOG()

    log.debug("Pre-training the background subtractor...")
    default_bg = cv2.imread(IMAGE_FILENAME_FORMAT % 119)
    bg_subtractor.apply(default_bg, None, 1.0)

    car_counter = None # Will be created after first frame is captured

    # Set up image source
    log.debug("Initializing video capture device #%s...", IMAGE_SOURCE)
    cap = cv2.VideoCapture(IMAGE_SOURCE)

    frame_width = cap.get(cv2.cv.CV_CAP_PROP_FRAME_WIDTH)
    frame_height = cap.get(cv2.cv.CV_CAP_PROP_FRAME_HEIGHT)
    log.debug("Video capture frame size=(w=%d, h=%d)", frame_width, frame_height)

    log.debug("Starting capture loop...")
    frame_number = -1
    while True:
        frame_number += 1
        log.debug("Capturing frame #%d...", frame_number)
        ret, frame = cap.read()
        if not ret:
            log.error("Frame capture failed, stopping...")
            break

        log.debug("Got frame #%d: shape=%s", frame_number, frame.shape)

        if car_counter is None:
            # We do this here, so that we can initialize with actual frame size
            log.debug("Creating vehicle counter...")
            car_counter = VehicleCounter(frame.shape[:2], frame.shape[0] / 2)

        # Archive raw frames from video to disk for later inspection/testing
        if CAPTURE_FROM_VIDEO:
            save_frame(IMAGE_FILENAME_FORMAT
                , frame_number, frame, "source frame #%d")

        log.debug("Processing frame #%d...", frame_number)
        processed = process_frame(frame_number, frame, bg_subtractor, car_counter)

        save_frame(IMAGE_DIR + "/processed_%04d.png"
            , frame_number, processed, "processed frame #%d")

        cv2.imshow('Source Image', frame)
        cv2.imshow('Processed Image', processed)

        log.debug("Frame #%d processed.", frame_number)

        c = cv2.waitKey(WAIT_TIME)
        if c == 27:
            log.debug("ESC detected, stopping...")
            break

    log.debug("Closing video capture device...")
    cap.release()
    cv2.destroyAllWindows()
    log.debug("Done.")

# ============================================================================

if __name__ == "__main__":
    log = init_logging()

    if not os.path.exists(IMAGE_DIR):
        log.debug("Creating image directory `%s`...", IMAGE_DIR)
        os.makedirs(IMAGE_DIR)

    main()

This script is responsible for processing of the stream of images, and identifying all the vehicles in each frame -- I refer to them as matches in the code.

---

The task of counting the detected vehicles is delegated to class VehicleCounter. The reason why I chose to make this a class will become evident as we progress. I did not implement your vehicle counting algorithm, because it will not work for reasons that will again become evident as we dig into this deeper.

File vehicle_counter.py contains the following code:

import logging

# ============================================================================

class VehicleCounter(object):
    def __init__(self, shape, divider):
        self.log = logging.getLogger("vehicle_counter")

        self.height, self.width = shape
        self.divider = divider

        self.vehicle_count = 0


    def update_count(self, matches, output_image = None):
        self.log.debug("Updating count using %d matches...", len(matches))

# ============================================================================

---

Finally, I wrote a script that will stitch all the generated images together, so it's easier to inspect them:

import cv2
import numpy as np

# ============================================================================

INPUT_WIDTH = 160
INPUT_HEIGHT = 120

OUTPUT_TILE_WIDTH = 10
OUTPUT_TILE_HEIGHT = 12

TILE_COUNT = OUTPUT_TILE_WIDTH * OUTPUT_TILE_HEIGHT

# ============================================================================

def stitch_images(input_format, output_filename):
    output_shape = (INPUT_HEIGHT * OUTPUT_TILE_HEIGHT
        , INPUT_WIDTH * OUTPUT_TILE_WIDTH
        , 3)
    output = np.zeros(output_shape, np.uint8)

    for i in range(TILE_COUNT):
        img = cv2.imread(input_format % i)
        cv2.rectangle(img, (0, 0), (INPUT_WIDTH - 1, INPUT_HEIGHT - 1), (0, 0, 255), 1)
        # Draw the frame number
        cv2.putText(img, str(i), (2, 10)
            , cv2.FONT_HERSHEY_PLAIN, 0.7, (255, 255, 255), 1)
        x = i % OUTPUT_TILE_WIDTH * INPUT_WIDTH
        y = i / OUTPUT_TILE_WIDTH * INPUT_HEIGHT
        output[y:y+INPUT_HEIGHT, x:x+INPUT_WIDTH,:] = img

    cv2.imwrite(output_filename, output)

# ============================================================================

stitch_images("images/frame_%04d.png", "stitched_frames.png")
stitch_images("images/mask_%04d.png", "stitched_masks.png")
stitch_images("images/processed_%04d.png", "stitched_processed.png")

---

Analysis

In order to solve this problem, we should have some idea about what results we expect to get. We should also label all the distinct cars in the video, so it's easier to talk about them.

If we run our script, and stitch the images together, we get the a number of useful files to help us analyze the problem:

• Image containing a mosaic of input frames
• Image containing a mosaic of foreground masks:

• Image containing a mosaic of processed frames

• The debug log for the run.

Upon inspecting those, a number