From 496b96b4f72164561b513eaa144b137e501ca69a Mon Sep 17 00:00:00 2001 From: blakeblackshear Date: Wed, 20 Feb 2019 06:20:52 -0600 Subject: [PATCH] make motion detection less sensitive to rain reduces the significance of fast moving objects and prioritizes objects that overlap in location across. multiple frames --- README.md | 4 ++-- detect_objects.py | 45 ++++++++++++++++++++++++++++++++------------- 2 files changed, 34 insertions(+), 15 deletions(-) diff --git a/README.md b/README.md index 70379be36..222beb22a 100644 --- a/README.md +++ b/README.md @@ -44,7 +44,7 @@ Access the mjpeg stream at http://localhost:5000 - [x] Add last will and availability for MQTT - [ ] Add ability to turn detection on and off via MQTT - [ ] Add a max size for motion and objects (height/width > 1.5, total area > 1500 and < 100,000) -- [ ] Make motion less sensitive to rain +- [x] Make motion less sensitive to rain - [x] Use Events or Conditions to signal between threads rather than polling a value - [ ] Implement a debug option to save images with detected objects - [ ] Only report if x% of the recent frames have a person to avoid single frame false positives (maybe take an average of the person scores in the past x frames?) @@ -53,7 +53,7 @@ Access the mjpeg stream at http://localhost:5000 - [ ] Merge bounding boxes that span multiple regions - [ ] Switch to a config file - [ ] Allow motion regions to be different than object detection regions -- [ ] Add motion detection masking +- [x] Add motion detection masking - [x] Change color of bounding box if motion detected - [x] Look for a subset of object types - [ ] Try and reduce CPU usage by simplifying the tensorflow model to just include the objects we care about diff --git a/detect_objects.py b/detect_objects.py index 60569614c..499884890 100644 --- a/detect_objects.py +++ b/detect_objects.py @@ -434,17 +434,11 @@ def detect_motion(shared_arr, shared_frame_time, frame_lock, frame_ready, motion arr = tonumpyarray(shared_arr).reshape(frame_shape) avg_frame = None - last_motion = -1 + avg_delta = None frame_time = 0.0 motion_frames = 0 while True: now = datetime.datetime.now().timestamp() - # if it has been long enough since the last motion, clear the flag - if last_motion > 0 and (now - last_motion) > 2: - last_motion = -1 - motion_detected.clear() - with motion_changed: - motion_changed.notify_all() with frame_ready: # if there isnt a frame ready for processing or it is old, wait for a signal @@ -459,7 +453,7 @@ def detect_motion(shared_arr, shared_frame_time, frame_lock, frame_ready, motion # convert to grayscale gray = cv2.cvtColor(cropped_frame, cv2.COLOR_BGR2GRAY) - # apply image mask + # apply image mask to remove areas from motion detection gray[mask] = [255] # apply gaussian blur @@ -470,15 +464,33 @@ def detect_motion(shared_arr, shared_frame_time, frame_lock, frame_ready, motion continue # look at the delta from the avg_frame - cv2.accumulateWeighted(gray, avg_frame, 0.01) frameDelta = cv2.absdiff(gray, cv2.convertScaleAbs(avg_frame)) - thresh = cv2.threshold(frameDelta, 25, 255, cv2.THRESH_BINARY)[1] + + if avg_delta is None: + avg_delta = frameDelta.copy().astype("float") + + # compute the average delta over the past few frames + # the alpha value can be modified to configure how sensitive the motion detection is + # higher values mean the current frame impacts the delta a lot, and a single raindrop may + # put it over the edge, too low and a fast moving person wont be detected as motion + # this also assumes that a person is in the same location across more than a single frame + cv2.accumulateWeighted(frameDelta, avg_delta, 0.2) + + # compute the threshold image for the current frame + current_thresh = cv2.threshold(frameDelta, 25, 255, cv2.THRESH_BINARY)[1] + + # black out everything in the avg_delta where there isnt motion in the current frame + avg_delta_image = cv2.convertScaleAbs(avg_delta) + avg_delta_image[np.where(current_thresh==[0])] = [0] + + # then look for deltas above the threshold, but only in areas where there is a delta + # in the current frame. this prevents deltas from previous frames from being included + thresh = cv2.threshold(avg_delta_image, 25, 255, cv2.THRESH_BINARY)[1] # dilate the thresholded image to fill in holes, then find contours # on thresholded image thresh = cv2.dilate(thresh, None, iterations=2) - cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, - cv2.CHAIN_APPROX_SIMPLE) + cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) cnts = imutils.grab_contours(cnts) # if there are no contours, there is no motion @@ -506,15 +518,22 @@ def detect_motion(shared_arr, shared_frame_time, frame_lock, frame_ready, motion motion_frames += 1 # if there have been enough consecutive motion frames, report motion if motion_frames >= 3: + # only average in the current frame if the difference persists for at least 3 frames + cv2.accumulateWeighted(gray, avg_frame, 0.01) motion_detected.set() with motion_changed: motion_changed.notify_all() - last_motion = now else: + # when no motion, just keep averaging the frames together + cv2.accumulateWeighted(gray, avg_frame, 0.01) motion_frames = 0 + motion_detected.clear() + with motion_changed: + motion_changed.notify_all() if debug and motion_frames >= 3: cv2.imwrite("/lab/debug/motion-{}-{}-{}.jpg".format(region_x_offset, region_y_offset, datetime.datetime.now().timestamp()), cropped_frame) + cv2.imwrite("/lab/debug/avg_delta-{}-{}-{}.jpg".format(region_x_offset, region_y_offset, datetime.datetime.now().timestamp()), avg_delta_image) if __name__ == '__main__': mp.freeze_support()