Detecting objects position via video

Question

So, I did object detection based on colour using openCV and I'm running it on raspberry pi 3. It's working, as it tracks tennis ball in real time (though it has some delay, as I'm using kinect v1 (freenect library)). Now I want to determine the position where the found object is. I want to know if it's in the middle, or more to the left or more to the right. I was thinking to split camera frame to 3 parts. I would have 3 booleans, one for middle, one for left and one for right, and then all 3 variables would be sent via usb communication. How ever, I have been trying for a week now to determine where the object is, but am unable to do so. I'm asking here for help.

Current working code for object detection using openCV (I detect object by colour)

# USAGE
# python ball_tracking.py --video ball_tracking_example.mp4
# python ball_tracking.py

# import the necessary packages
from collections import deque
import numpy as np
import argparse
import imutils
import cv2

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-v", "--video",
    help="path to the (optional) video file")
ap.add_argument("-b", "--buffer", type=int, default=64,
    help="max buffer size")
args = vars(ap.parse_args())

# define the lower and upper boundaries of the "green"
# ball in the HSV color space, then initialize the
# list of tracked points
greenLower = (29, 86, 6)
greenUpper = (64, 255, 255)
pts = deque(maxlen=args["buffer"])

# if a video path was not supplied, grab the reference
# to the webcam
if not args.get("video", False):
    camera = cv2.VideoCapture(0)

# otherwise, grab a reference to the video file
else:
    camera = cv2.VideoCapture(args["video"])

# keep looping
while True:
    # grab the current frame
    (grabbed, frame) = camera.read()

    # if we are viewing a video and we did not grab a frame,
    # then we have reached the end of the video
    if args.get("video") and not grabbed:
        break

    # resize the frame, blur it, and convert it to the HSV
    # color space
    frame = imutils.resize(frame, width=600)
    # blurred = cv2.GaussianBlur(frame, (11, 11), 0)
    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)

    # construct a mask for the color "green", then perform
    # a series of dilations and erosions to remove any small
    # blobs left in the mask
    mask = cv2.inRange(hsv, greenLower, greenUpper)
    mask = cv2.erode(mask, None, iterations=2)
    mask = cv2.dilate(mask, None, iterations=2)

    # find contours in the mask and initialize the current
    # (x, y) center of the ball
    cnts = cv2.findContours(mask.copy(), cv2.RETR_EXTERNAL,
        cv2.CHAIN_APPROX_SIMPLE)[-2]
    center = None

    # only proceed if at least one contour was found
    if len(cnts) > 0:
        # find the largest contour in the mask, then use
        # it to compute the minimum enclosing circle and
        # centroid
        c = max(cnts, key=cv2.contourArea)
        ((x, y), radius) = cv2.minEnclosingCircle(c)
        M = cv2.moments(c)
        center = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))

        # only proceed if the radius meets a minimum size
        if radius > 10:
            # draw the circle and centroid on the frame,
            # then update the list of tracked points
            cv2.circle(frame, (int(x), int(y)), int(radius),
                (0, 255, 255), 2)
            cv2.circle(frame, center, 5, (0, 0, 255), -1)
        #EDIT:
        if int(x) > int(200) & int(x) < int(400):
            middle = True
            left = False
            notleft = False

        if int(x) > int(1) & int(x) < int(200):
            left = True
            middle = False
            notleft = False

        if int(x) > int(400) & int(x) < int(600):
            notleft = True
            left = False
            middle = False

        print ("middle: ", middle, " left: ", left, " right: ", notleft)

    # update the points queue
    pts.appendleft(center)

    # loop over the set of tracked points
    for i in xrange(1, len(pts)):
        # if either of the tracked points are None, ignore
        # them
        if pts[i - 1] is None or pts[i] is None:
            continue

        # otherwise, compute the thickness of the line and
        # draw the connecting lines
        thickness = int(np.sqrt(args["buffer"] / float(i + 1)) * 2.5)
        cv2.line(frame, pts[i - 1], pts[i], (0, 0, 255), thickness)

    # show the frame to our screen
    cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF

    # if the 'q' key is pressed, stop the loop
    if key == ord("q"):
        break

# cleanup the camera and close any open windows
camera.release()
cv2.destroyAllWindows()

The code is properly commented. Sending information using usb port is not a problem, I just can't find out, how to detect where the ball is.

I'm running raspbian on my raspberry pi.

EDIT: I forgot to mention, I'm only interested in objects position according to X axis. I figured that as I have the current frame set at 600, that I would write 3 if's like if x > 200 && x < 400: bool middle = true. It's not working thou.

EDIT2: I think I got it to work somehow, but the "middle" will never be true. I get true for left and right, but not for middle.

Answer 1

Here is the solution for your Question,

# import the necessary packages
from collections import deque
import numpy as np
import argparse
import imutils
import cv2

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-v", "--video",
    help="path to the (optional) video file")
ap.add_argument("-b", "--buffer", type=int, default=32,
    help="max buffer size")
args = vars(ap.parse_args())

# define the lower and upper boundaries of the "green"
# ball in the HSV color space
greenLower = (29, 86, 6)
greenUpper = (64, 255, 255)

# initialize the list of tracked points, the frame counter,
# and the coordinate deltas
pts = deque(maxlen=args["buffer"])
counter = 0
(dX, dY) = (0, 0)
direction = ""

# if a video path was not supplied, grab the reference
# to the webcam
if not args.get("video", False):
    camera = cv2.VideoCapture(0)

# otherwise, grab a reference to the video file
else:
    camera = cv2.VideoCapture(args["video"])

# keep looping
while True:
    # grab the current frame
    (grabbed, frame) = camera.read()

    # if we are viewing a video and we did not grab a frame,
    # then we have reached the end of the video
    if args.get("video") and not grabbed:
        break

    # resize the frame, blur it, and convert it to the HSV
    # color space
    frame = imutils.resize(frame, width=600)
    # blurred = cv2.GaussianBlur(frame, (11, 11), 0)
    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)

    # construct a mask for the color "green", then perform
    # a series of dilations and erosions to remove any small
    # blobs left in the mask
    mask = cv2.inRange(hsv, greenLower, greenUpper)
    mask = cv2.erode(mask, None, iterations=2)
    mask = cv2.dilate(mask, None, iterations=2)

    # find contours in the mask and initialize the current
    # (x, y) center of the ball
    cnts = cv2.findContours(mask.copy(), cv2.RETR_EXTERNAL,
        cv2.CHAIN_APPROX_SIMPLE)[-2]
    center = None

    # only proceed if at least one contour was found
    if len(cnts) > 0:
        # find the largest contour in the mask, then use
        # it to compute the minimum enclosing circle and
        # centroid
        c = max(cnts, key=cv2.contourArea)
        ((x, y), radius) = cv2.minEnclosingCircle(c)
        M = cv2.moments(c)
        center = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))

        # only proceed if the radius meets a minimum size
        if radius > 10:
            # draw the circle and centroid on the frame,
            # then update the list of tracked points
            cv2.circle(frame, (int(x), int(y)), int(radius),
                (0, 255, 255), 2)
            cv2.circle(frame, center, 5, (0, 0, 255), -1)
            pts.appendleft(center)

    # loop over the set of tracked points
    for i in np.arange(1, len(pts)):
        # if either of the tracked points are None, ignore
        # them
        if pts[i - 1] is None or pts[i] is None:
            continue

        # check to see if enough points have been accumulated in
        # the buffer
        if counter >= 10 and i == 1 and pts[-10] is not None:
            # compute the difference between the x and y
            # coordinates and re-initialize the direction
            # text variables
            dX = pts[-10][0] - pts[i][0]
            dY = pts[-10][1] - pts[i][1]
            (dirX, dirY) = ("", "")

            # ensure there is significant movement in the
            # x-direction
            if np.abs(dX) > 20:
                dirX = "East" if np.sign(dX) == 1 else "West"

            # ensure there is significant movement in the
            # y-direction
            if np.abs(dY) > 20:
                dirY = "North" if np.sign(dY) == 1 else "South"

            # handle when both directions are non-empty
            if dirX != "" and dirY != "":
                direction = "{}-{}".format(dirY, dirX)

            # otherwise, only one direction is non-empty
            else:
                direction = dirX if dirX != "" else dirY

        # otherwise, compute the thickness of the line and
        # draw the connecting lines
        thickness = int(np.sqrt(args["buffer"] / float(i + 1)) * 2.5)
        cv2.line(frame, pts[i - 1], pts[i], (0, 0, 255), thickness)

    # show the movement deltas and the direction of movement on
    # the frame
    cv2.putText(frame, direction, (10, 30), cv2.FONT_HERSHEY_SIMPLEX,
        0.65, (0, 0, 255), 3)
    cv2.putText(frame, "dx: {}, dy: {}".format(dX, dY),
        (10, frame.shape[0] - 10), cv2.FONT_HERSHEY_SIMPLEX,
        0.35, (0, 0, 255), 1)

    # show the frame to our screen and increment the frame counter
    cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF
    counter += 1

    # if the 'q' key is pressed, stop the loop
    if key == ord("q"):
        break

# cleanup the camera and close any open windows
camera.release()
cv2.destroyAllWindows()

Answer 2

        if int(x) > int(200) AND int(x) < int(400):
            middle = True
            left = False
            notleft = False

        if int(x) > int(1) AND int(x) < int(200):
            left = True
            middle = False
            notleft = False

        if int(x) > int(400) AND int(x) < int(600):
            notleft = True
            left = False
            middle = False

all I had to write was "AND" insted of "&"... So much trouble, such a little fix.

Answer 3

If the object of which you are going to detect the position, then it will be better than using the cv2.findContours(), to use cv2.HoughCircles(). Since cv2.HoughCircles() returns the center position(x, y) of the circles directly.

You can find the sample of using the HoughCircles() here

If you get the center of that circle then to determine its position will be easy.

Good luck.