How to mask a video frame using contours with opencv in python -

i using opencv (cv2 module) in python recognize objects in video. in each frame, want extract particular region aka, contour. after learning opencv docs, have following code snippet:

        # np numpy module, contours expected results,         # frame each frame of video          # iterate through contours.         contour in contours:             # compute bounding box contour, draw             # on frame, , update text.             x, y, w, h = cv2.boundingrect(contour)              # find mask , build histogram object.             mask = np.zeros(frame.shape[:2], np.uint8)             mask[y:h, x:w] = 255             masked_img = cv2.bitwise_and(frame, frame, mask = mask)             obj_hist = cv2.calchist([masked_img], [0], none, [256], [0, 256]) 

however, when use matplotlib show masked_img, returns dark image. obj_hist has 1 element number greater 0, first one. wrong?

the problem way setting values in mask. line:

mask[y:h, x:w] = 255 

you trying slice each dimension of image using y:h , x:w set mask. left of colon starting row or column, , right of colon denotes end row or column. given start @ y, need offset h using same reference y... same goes x , w.

doing slicing right value of colon less left not modify array in way, , that's why aren't getting output not modifying mask when it's zeroes.

you meant do:

mask[y:y+h, x:x+w] = 255 

this set proper region given cv2.boundingrect white (255).