Last active
September 16, 2021 12:13
-
-
Save AdroitAnandAI/313243481c4db81c19b4849db426103d to your computer and use it in GitHub Desktop.
Monocular Depth Estimation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Detections contains bounding boxes using object detection model | |
boxcount = 0 | |
depths = [] | |
bboxMidXs = [] | |
bboxMidYs = [] | |
# This is computed to reflect real distance during initial camera calibration | |
scalingFactor = 1000 | |
# Depth scaling factor is based on one-time cam calibration | |
for detection in detections: | |
xmin, ymin, xmax, ymax = detection | |
depths.append(np.median(disp[ymin:ymax, xmin:xmax])) | |
bboxMidXs.append((xmin+xmax)/2) | |
bboxMidYs.append((ymin+ymax)/2) | |
size = disp.shape[:2] | |
# disp = draw_detections(disp, detection) | |
xmin = max(int(detection[0]), 0) | |
ymin = max(int(detection[1]), 0) | |
xmax = min(int(detection[2]), size[1]) | |
ymax = min(int(detection[3]), size[0]) | |
boxcount = boxcount + 1 | |
cv2.rectangle(disp, (xmin, ymin), (xmax, ymax), (0,255,0), 2) | |
cv2.putText(disp, '{} {}'.format('person', boxcount), | |
(xmin, ymin - 7), cv2.FONT_HERSHEY_COMPLEX, 0.6, (0,255,0), 1) | |
for i in range(len(bboxMidXs)): | |
for j in range(i+1, len(bboxMidXs)): | |
dist = np.square(bboxMidXs[i] - bboxMidXs[j]) + | |
np.square((depths[i]-depths[j])*scalingFactor) | |
# check whether less than 200 to detect | |
# social distance violations | |
if np.sqrt(dist) < 200: | |
color = (0, 0, 255) | |
thickness = 3 | |
else: | |
color = (0, 255, 0) | |
thickness = 1 | |
cv2.line(original_img, (int(bboxMidXs[i]), int(bboxMidYs[i])), | |
(int(bboxMidXs[j]), int(bboxMidYs[j])), color, thickness) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment