Question

我想测量被跟踪物体距离图像中心的距离，我对python并不是很好，我也不知道如何得到x，y，w，h来自roiBox对象。

正如您在下面的代码中看到的那样，算法会打印roiBox输出 - 左上角的x，y和矩形的w，h。

我需要：

将这些数字设为int＆＃39;
计算矩形的中心
然后从矩形的中心到框架的中心绘制一个箭头。

代码：

# USAGE
# python track.py --video video/sample.mov

# import the necessary packages
import numpy as np
import argparse
import cv2

# initialize the current frame of the video, along with the list of ROI points along with whether or not this is input mode
frame = None
roiPts = []
inputMode = False



def select_ROI(event, x, y, flags, param):
    # grab the reference to the current frame, list of ROI points and whether or not it is ROI selection mode
    global frame, roiPts, inputMode

    # if we are in ROI selection mode, the mouse was clicked, and we do not already have four points, then update the list of ROI points with the (x, y) location of the click and draw the circle
    if inputMode and event == cv2.EVENT_LBUTTONDOWN and len(roiPts) < 4:
        roiPts.append((x, y))
        cv2.circle(frame, (x, y), 4, (0, 255, 0), 2)
        cv2.imshow("frame", frame)



def determine_ROI_for_first_time():

    global inputMode, roiBox, roiPts, roiHist

    # indicate that we are in input mode and clone the frame
    inputMode = True
    orig = frame.copy()

    # keep looping until 4 reference ROI points have been selected; press any key to exit ROI selction mode once 4 points have been selected
    while len(roiPts) < 4:
        cv2.imshow("frame", frame)
        cv2.waitKey(0)

    # determine the top-left and bottom-right points
    roiPts = np.array(roiPts)
    s = roiPts.sum(axis = 1)
    tl = roiPts[np.argmin(s)]
    br = roiPts[np.argmax(s)]

    # grab the ROI for the bounding box and convert it to the HSV color space
    roi = orig[tl[1]:br[1], tl[0]:br[0]]
    roi = cv2.cvtColor(roi, cv2.COLOR_BGR2HSV)
    #roi = cv2.cvtColor(roi, cv2.COLOR_BGR2LAB)

    # compute a HSV histogram for the ROI and store the bounding box
    roiHist = cv2.calcHist([roi], [0], None, [16], [0, 180])
    roiHist = cv2.normalize(roiHist, roiHist, 0, 255, cv2.NORM_MINMAX)
    return (tl[0], tl[1], br[0], br[1])




def do_camshift():
    global frame, roiBox

    # convert the current frame to the HSV color space and perform mean shift
    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
    backProj = cv2.calcBackProject([hsv], [0], roiHist, [0, 180], 1)

    # apply cam shift to the back projection, convert the points to a bounding box, and then draw them
    (r, roiBox) = cv2.CamShift(backProj, roiBox, termination)
    pts = np.int0(cv2.boxPoints(r))
    cv2.polylines(frame, [pts], True, (0, 255, 0), 2)



def main():
    # construct the argument parse and parse the arguments
    ap = argparse.ArgumentParser()
    ap.add_argument("-v", "--video",
        help = "path to the (optional) video file")
    args = vars(ap.parse_args())

    # grab the reference to the current frame, list of ROI points and whether or not it is ROI selection mode
    global frame, roiPts, inputMode, roiBox, termination

    # if the video path was not supplied, grab the reference to the camera
    if not args.get("video", False):
        camera = cv2.VideoCapture(0)
    # camera = cv2.VideoCapture("/home/idan/Desktop/b.mp4")

    # otherwise, load the video
    else:
        camera = cv2.VideoCapture(args["video"])

    # setup the mouse callback
    cv2.namedWindow("frame")
    cv2.setMouseCallback("frame", select_ROI)

    # initialize the termination criteria for cam shift, indicating a maximum of ten iterations or movement by a least one pixel along with the bounding box of the ROI
    termination = (cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, 10, 1)
    roiBox = None

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

        # check to see if we have reached the end of the video
        if not grabbed:
            break

        # handle if the 'i' key is pressed, then go into ROI selection mode
        key = cv2.waitKey(1) & 0xFF
        if key == ord("i") and len(roiPts) < 4:
            roiBox = determine_ROI_for_first_time()

        # if the see if the ROI has been computed
        print roiBox
        if roiBox is not None:
            do_camshift()

        # show the frame and record if the user presses a key
        cv2.imshow("frame", frame)

        # wait, 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()


if __name__ == "__main__":
    main()

使用python在camshift算法中绘制箭头而不是矩形

0 个答案: