def demoVideo(image):
global count
count = count + 1
# print ('count before = {}'.format(count))
if (count % 10) > 0:
# count = 1
im = process_image(image)
return im
# count = count+1
# print ('processing image')
# print ('count = {}'.format(count))
im = process_image(image)
height, width = im.shape[:2]
mid = width / 2.5
# print('height = {} and width/2.5 = {}'.format(height, mid))
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = im_detect(default_net, im)
timer.toc()
# print ('Detection took {:.3f}s for '
# '{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = 0.8
NMS_THRESH = 0.3
for cls_ind, cls in enumerate(CLASSES[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 4 * cls_ind:4 * (cls_ind + 1)]
cls_scores = scores[:, cls_ind]
dets = np.hstack(
(cls_boxes, cls_scores[:, np.newaxis])).astype(np.float32)
keep = nms(dets, NMS_THRESH)
dets = dets[keep, :]
font = cv2.FONT_HERSHEY_SIMPLEX
color = (0, 0, 255)
inds = np.where(dets[:, -1] >= CONF_THRESH)[0]
if len(inds) > 0:
for i in inds:
bbox = dets[i, :4]
score = dets[i, -1]
cv2.rectangle(im, (bbox[0], bbox[1]), (bbox[2], bbox[3]),
color, 2)
if bbox[0] < mid:
cv2.putText(im, 'left {:s}'.format(cls), (bbox[0], (int)(
(bbox[1] - 2))), font, 0.5, (255, 0, 0), 1)
else:
cv2.putText(im, 'right {:s}'.format(cls, score),
(bbox[0], (int)(
(bbox[1] - 2))), font, 0.5, (255, 0, 0), 1)
# cv2.putText(im,'{:s} {:.3f}'.format(cls, score),(bbox[0], (int)((bbox[1]- 2))), font, 0.5, (255,255,255), 1)
return im
def process_video(image):
global heat_recent
heat = np.zeros_like(image[:, :, 0]).astype(np.float)
box_list = []
result = find_cars(image, box_list, 400, 500, 1.2, svc, X_scaler, \
orient, pix_per_cell, cell_per_block, spatial_size, hist_bins)
result = find_cars(image, box_list, 400, 550, 1.8, svc, X_scaler, \
orient, pix_per_cell, cell_per_block, spatial_size, hist_bins)
# result = find_cars(image, box_list, 400, 800, 2.3, svc, X_scaler, \
# orient, pix_per_cell, cell_per_block, spatial_size, hist_bins)
# Add heat to each box in box list
heat = add_heat(heat, box_list)
if heat_recent == []:
heat_recent = heat.reshape(1, heat.shape[0], heat.shape[1])
else:
heat = heat.reshape(1, heat.shape[0], heat.shape[1])
heat_recent = np.concatenate((heat_recent, heat), axis=0)
if len(heat_recent) > 8:
heat_recent = np.delete(heat_recent, 0, axis=0)
heat = np.sum(heat_recent, axis=0)
# Apply threshold to help remove false positives
# if visualize is on, do this based on only one frame, so lower thr
if visualize:
thr = 1
else:
thr = 12
heat = apply_threshold(heat, thr)
# Visualize the heatmap when displaying
heatmap = np.clip(heat, 0, 255)
# Find final boxes from heatmap using label function
labels = label(heatmap)
image_lanes = ld.process_image(image, calibrate=False)
result = draw_labeled_bboxes(np.copy(image_lanes), labels)
if visualize:
fig = plt.figure()
plt.subplot(121)
plt.imshow(result)
plt.title('Car Positions')
plt.subplot(122)
plt.imshow(heatmap, cmap='hot')
plt.title('Heat Map')
fig.tight_layout()
plt.savefig('output_images/heatmap.png')
plt.show()
return result
def auto_frames():
# adding path
with picamera.PiCamera() as camera:
rawCapture = PiRGBArray(camera, size=(640, 480))
# let camera warm up
camera.resolution = (640, 480)
camera.hflip = True
camera.vflip = True
time.sleep(2)
for frame in camera.capture_continuous(rawCapture, 'bgr',
use_video_port=True):
# return current frame
#img = cv2.cvtColor(frame.array, cv2.COLOR_BGR2GRAY)
img, cmd = process_image(frame.array)
status, buf = cv2.imencode('.jpeg', img)
yield (np.array(buf).tostring(), cmd)
rawCapture.truncate()
rawCapture.seek(0)
def demo(net, image_name):
"""Detect object classes in an image using pre-computed object proposals."""
# Load the demo image
img_name = os.path.basename(image_name)
# im_file = image_name
# im = cv2.imread(im_file)
im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)
im = cv2.imread(im_file)
pimg = process_image(im)
# cv2.imshow("Processed", pimg)
# cv2.waitKey(0)
im = pimg
height, width = im.shape[:2]
mid = width / 2.5
# print('height = {} and width/2.5 = {}'.format(height, mid))
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = im_detect(net, im)
timer.toc()
# print ('Detection took {:.3f}s for '
# '{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = 0.8
NMS_THRESH = 0.3
for cls_ind, cls in enumerate(CLASSES[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 4 * cls_ind:4 * (cls_ind + 1)]
cls_scores = scores[:, cls_ind]
dets = np.hstack(
(cls_boxes, cls_scores[:, np.newaxis])).astype(np.float32)
keep = nms(dets, NMS_THRESH)
dets = dets[keep, :]
# vis_detections(im, cls, dets, thresh=CONF_THRESH)
font = cv2.FONT_HERSHEY_SIMPLEX
# print 'class index is {}'.format(cls_ind)
color = (0, 0, 255)
inds = np.where(dets[:, -1] >= CONF_THRESH)[0]
if len(inds) > 0:
for i in inds:
bbox = dets[i, :4]
score = dets[i, -1]
cv2.rectangle(im, (bbox[0], bbox[1]), (bbox[2], bbox[3]),
color, 2)
if bbox[0] < mid:
cv2.putText(im, 'left {:s}'.format(cls), (bbox[0], (int)(
(bbox[1] - 2))), font, 0.5, (255, 0, 0), 1)
else:
cv2.putText(im, 'right {:s}'.format(cls, score),
(bbox[0], (int)(
(bbox[1] - 2))), font, 0.5, (255, 0, 0), 1)
# cv2.putText(im,'{:s} {:.3f}'.format(cls, score),(bbox[0], (int)((bbox[1]- 2))), font, 0.5, (255,255,255), 1)
# Write the resulting frame
# print 'Final image name is {}'.format(img_name)
splitName = os.path.splitext(img_name)[0]
# print (os.path.splitext(img_name)[0])
# print splitName
# cv2.imwrite('{:s}_output.jpg'.format(splitName), im)
## Display output frame
# cv2.imshow("output", im)
# cv2.waitKey(0)
## Write output frame
opDir = '/home/student/cmpe295-masters-project/faster-rcnn-resnet/data/output/'
cv2.imwrite(os.path.join(opDir, img_name), im)