sorry if the title is unclear. I’m making a code in OpenCV-Python that tracks the location of my pet goldfish and outputs a keystroke depending on which quadrant of the frame she is in. I’ve already gotten the program to track my fish and output her location in coordinates, but how do I convert this into a keystroke (W, A, S, D)? Like, if the fish is in quadrant one, output W, and if the fish is in quadrant two, output A.
This is the code I have so far.
# import the necessary packages
from collections import deque
from imutils.video import VideoStream
import numpy as np
import argparse
import cv2
import imutils
import time
# 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 "orange"
# fish in the HSV color space
orangeLower = (5, 50, 50)
orangeUpper = (15, 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):
vs = VideoStream(src=0).start()
# otherwise, grab a reference to the video file
else:
vs = cv2.VideoCapture(args["video"])
# allow the camera or video file to warm up
time.sleep(2.0)
# keep looping
while True:
# grab the current frame
frame = vs.read()
# handle the frame from VideoCapture or VideoStream
frame = frame[1] if args.get("video", False) else frame
# if we are viewing a video and we did not grab a frame,
# then we have reached the end of the video
if frame is None:
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(blurred, cv2.COLOR_BGR2HSV)
# construct a mask for the color "orange", then perform
# a series of dilations and erosions to remove any small
# blobs left in the mask
mask = cv2.inRange(hsv, orangeLower, orangeUpper)
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)
cnts = imutils.grab_contours(cnts)
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 == 10 and pts[i-10] is not None:
# compute the difference between the x and y
# coordinates and re-initialize the direction
# text variables
dX = pts[i-10][0] - pts[i][0]
dY = pts[i-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 = "South" if np.sign(dY) == 1 else "North"
# 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)
cv2.line(img=frame, pt1=(300, 0), pt2=(300, 500), color=(0, 0, 0), thickness=3, lineType=8, shift=0)
cv2.line(img=frame, pt1 = (0, 225), pt2 = (600, 225), color = (0, 0, 0), thickness = 3, lineType = 8, shift = 0)
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
# if we are not using a video file, stop the camera video stream
if not args.get("video", False):
vs.stop()
# otherwise, release the camera
else:
vs.release()
# close all windows
cv2.destroyAllWindows()
Thanks for the help.
Advertisement
Answer
If I understand you correctly you want to put an image up with the frame, that image depends on what direction your fish is going. Like you’re steering it with the wasd commands right? To place an image ofe another image:
import cv2
import numpy as np
img1 = cv2.imread('Fishframe.jpg')
img2 = cv2.imread('W_button.jpg')
img3 = img1.copy()
# replace values at coordinates (300, 300) to (399, 399) of img3 with region of img2
img3[300:400,300:400,:] = img2[300:400,300:400,:]
cv2.imshow('Result1', img3)
So you just “cut” out a piece and paist your pic in the hole it left.
Let me know if it works! Have fun!