def cvDrawBoxes(detections, img):
roi_array = []
for detection in detections:
x, y, w, h = detection[2][0],\
detection[2][1],\
detection[2][2],\
detection[2][3]
xmin, ymin, xmax, ymax = lightnet.convertBack(float(x), float(y),
float(w), float(h))
pt1 = (xmin, ymin)
pt2 = (xmax, ymax)
roi_array.append((xmin, ymin, xmax, ymax))
if args.debug:
cv.rectangle(img, pt1, pt2, (0, 255, 0), 1)
cv.putText(
img,
# detection[0] +
" [" + str(round(detection[1] * 100, 2)) + "]",
(pt1[0], pt1[1] - 5),
cv.FONT_HERSHEY_SIMPLEX,
0.5,
[0, 255, 0],
2)
return roi_array
def process(category):
image_filenames = glob.glob('%s/*.png' % (category), recursive=True)
image_filenames.extend(glob.glob('%s/*.jpg' % (category), recursive=True))
# print("Start category: %s" % (category))
for filename in image_filenames:
# load the input image
filename = pathlib.Path(filename).as_posix()
image = cv.imread(filename)
h, w, c = image.shape
# roi
if False:
x_spacing = 20
image = image[0:h, x_spacing:w - x_spacing]
h, w, c = image.shape
if args.debug:
print(w, h)
x1, y1, x2, y2 = (0, 0, w, h)
if args.yolo_cfg:
full_im, _ = darknet.array_to_image(image)
with inference_lock:
results = lightnet.detect_from_memory(
yolo_net, yolo_meta, full_im, thresh=0.75, debug=False)
if results:
detection = results[0]
x, y, w, h = detection[2][0],\
detection[2][1],\
detection[2][2],\
detection[2][3]
if w > W and h > H:
x1, y1, x2, y2 = lightnet.convertBack(
float(x), float(y), float(w), float(h))
else:
(success, saliencyMap) = saliency.computeSaliency(image)
M = cv.moments(saliencyMap.astype("uint8"))
# calculate x,y coordinate of center
cX = int(M["m10"] / M["m00"])
cY = int(M["m01"] / M["m00"])
cv.circle(saliencyMap, (cX, cY), 5, (255, 255, 255), -1)
cY = h / 2
if cX < W / 2:
cX = W / 2
if cX > w - W / 2:
cX = w - W / 2
x1 = int(cX - W / 2)
y1 = int(cY - H / 2)
x2 = int(cX + W / 2)
y2 = int(cY + H / 2)
filename = filename.replace(
args.images, 'img_roi').replace('.png', '.jpg')
# print(filename)
os.makedirs(os.path.dirname(filename), exist_ok=True)
cv.imwrite(filename, image[y1:y2, x1:x2])
if args.debug:
# show the images
cv.rectangle(saliencyMap, (x1, y1), (x2, y2), (255, 255, 255), 1)
cv.imshow("Image", image)
cv.imshow("Output", saliencyMap)
key = cv.waitKey(0)
if key == 27:
break
print("Finish category: %s" % (category))