if cls_name not in bboxes: bboxes[cls_name] = [] # probs[cls_name] = [] # (x, y, w, h) = ROIs[0, ii, :] cls_num = np.argmax(P_cls[0, ii, :]) try: (tx, ty, tw, th) = P_regr[0, ii, 4*cls_num:4*(cls_num+1)] tx /= C.classifier_regr_std[0] ty /= C.classifier_regr_std[1] tw /= C.classifier_regr_std[2] th /= C.classifier_regr_std[3] x, y, w, h = roi_helpers.apply_regr(x, y, w, h, tx, ty, tw, th) except: pass bboxes[cls_name].append([C.rpn_stride * x, C.rpn_stride * y, C.rpn_stride*(x+w), C.rpn_stride*(y+h)]) # probs[cls_name].append(np.max(P_cls[0, ii, :])) all_dets = [] for key in bboxes: if key == 'Pedestrian': bbox = np.array(bboxes[key]) new_boxes, new_probs = roi_helpers.non_max_suppression_fast(bbox, np.array(probs[key]), overlap_thresh = 0.2)
def predict_single_image(img_path, model_rpn, model_classifier_only,
class_mapping):
img = cv2.imread(img_path)
if img is None:
print('reading image failed.')
exit(0)
X, ratio = format_img(img)
if K.image_dim_ordering() == 'tf':
X = np.transpose(X, (0, 2, 3, 1))
# get the feature maps and output from the RPN
[Y1, Y2, F] = model_rpn.predict(X)
result = rpn_to_roi(Y1, Y2, K.image_dim_ordering(), overlap_thresh=0.7)
# convert from (x1,y1,x2,y2) to (x,y,w,h)
result[:, 2] -= result[:, 0]
result[:, 3] -= result[:, 1]
bbox_threshold = 0.7
# apply the spatial pyramid pooling to the proposed regions
boxes = dict()
for jk in range(result.shape[0] // 32 + 1):
rois = np.expand_dims(result[32 * jk:32 * (jk + 1), :], axis=0)
if rois.shape[1] == 0:
break
if jk == result.shape[0] // 32:
# pad R
curr_shape = rois.shape
target_shape = (curr_shape[0], 32, curr_shape[2])
rois_padded = np.zeros(target_shape).astype(rois.dtype)
rois_padded[:, :curr_shape[1], :] = rois
rois_padded[0, curr_shape[1]:, :] = rois[0, 0, :]
rois = rois_padded
[p_cls, p_regr] = model_classifier_only.predict([F, rois])
for ii in range(p_cls.shape[1]):
if np.max(p_cls[0, ii, :]) < bbox_threshold or np.argmax(
p_cls[0, ii, :]) == (p_cls.shape[2] - 1):
continue
cls_num = np.argmax(p_cls[0, ii, :])
if cls_num not in boxes.keys():
boxes[cls_num] = []
(x, y, w, h) = rois[0, ii, :]
try:
(tx, ty, tw, th) = p_regr[0, ii, 4 * cls_num:4 * (cls_num + 1)]
tx /= 8.0
ty /= 8.0
tw /= 4.0
th /= 4.0
x, y, w, h = apply_regr(x, y, w, h, tx, ty, tw, th)
except Exception as e:
print(e)
pass
boxes[cls_num].append([
16 * x, 16 * y, 16 * (x + w), 16 * (y + h),
np.max(p_cls[0, ii, :])
])
# add some nms to reduce many boxes
for cls_num, box in boxes.items():
boxes_nms = non_max_suppression_fast(box, overlap_thresh=0.5)
boxes[cls_num] = boxes_nms
#print(class_mapping[cls_num] + ":")
for b in boxes_nms:
b[0], b[1], b[2], b[3] = get_real_coordinates(
ratio, b[0], b[1], b[2], b[3])
f.write(",".join([
img_path.split("/")[-1].split(".")[0], class_mapping[cls_num],
str(b[-1]),
str(b[0]),
str(b[1]),
str(b[2]),
str(b[3])
]) + "\n")
img = draw_boxes_and_label_on_image_cv2(img, class_mapping, boxes)
result_path = './resnet_aug_results_images/{}.jpg'.format(
os.path.basename(img_path).split('.')[0])
cv2.imwrite(result_path, img)
def detect_predict(pic,
C,
model_rpn,
model_classifier,
model_classifier_only,
class_mapping,
class_to_color,
print_dets=False):
"""
Detect and predict object in the picture
:param pic: picture numpy array
:param C: config object
:params model_*: models from get_models function
:params class_*: mapping and colors, need to be loaded to keep the same colors/classes
:return: picture with bounding boxes
"""
img = pic
X, ratio = format_img(img, C)
img_scaled = np.transpose(X.copy()[0, (2, 1, 0), :, :], (1, 2, 0)).copy()
img_scaled[:, :, 0] += 123.68
img_scaled[:, :, 1] += 116.779
img_scaled[:, :, 2] += 103.939
img_scaled = img_scaled.astype(np.uint8)
if K.image_dim_ordering() == 'tf':
X = np.transpose(X, (0, 2, 3, 1))
# get the feature maps and output from the RPN
[Y1, Y2, F] = model_rpn.predict(X)
R = roi_helpers.rpn_to_roi(Y1,
Y2,
C,
K.image_dim_ordering(),
overlap_thresh=0.7)
# convert from (x1,y1,x2,y2) to (x,y,w,h)
R[:, 2] -= R[:, 0]
R[:, 3] -= R[:, 1]
# apply the spatial pyramid pooling to the proposed regions
bboxes = {}
probs = {}
# print(class_mapping)
for jk in range(R.shape[0] // C.num_rois + 1):
ROIs = np.expand_dims(R[C.num_rois * jk:C.num_rois * (jk + 1), :],
axis=0)
if ROIs.shape[1] == 0:
break
if jk == R.shape[0] // C.num_rois:
#pad R
curr_shape = ROIs.shape
target_shape = (curr_shape[0], C.num_rois, curr_shape[2])
ROIs_padded = np.zeros(target_shape).astype(ROIs.dtype)
ROIs_padded[:, :curr_shape[1], :] = ROIs
ROIs_padded[0, curr_shape[1]:, :] = ROIs[0, 0, :]
ROIs = ROIs_padded
[P_cls, P_regr] = model_classifier_only.predict([F, ROIs])
for ii in range(P_cls.shape[1]):
if np.max(P_cls[0, ii, :]) < bbox_threshold or np.argmax(
P_cls[0, ii, :]) == (P_cls.shape[2] - 1):
continue
cls_name = class_mapping[np.argmax(P_cls[0, ii, :])]
if cls_name not in bboxes:
bboxes[cls_name] = []
probs[cls_name] = []
(x, y, w, h) = ROIs[0, ii, :]
cls_num = np.argmax(P_cls[0, ii, :])
try:
(tx, ty, tw, th) = P_regr[0, ii, 4 * cls_num:4 * (cls_num + 1)]
tx /= C.classifier_regr_std[0]
ty /= C.classifier_regr_std[1]
tw /= C.classifier_regr_std[2]
th /= C.classifier_regr_std[3]
x, y, w, h = roi_helpers.apply_regr(x, y, w, h, tx, ty, tw, th)
except:
pass
bboxes[cls_name].append([
C.rpn_stride * x, C.rpn_stride * y, C.rpn_stride * (x + w),
C.rpn_stride * (y + h)
])
probs[cls_name].append(np.max(P_cls[0, ii, :]))
all_dets = []
for key in bboxes:
bbox = np.array(bboxes[key])
new_boxes, new_probs = roi_helpers.non_max_suppression_fast(
bbox, np.array(probs[key]), overlap_thresh=overlap_thresh)
jk = np.argmax(new_probs)
if new_probs[jk] > 0.55:
(x1, y1, x2, y2) = new_boxes[jk, :]
(real_x1, real_y1, real_x2,
real_y2) = get_real_coordinates(ratio, x1, y1, x2, y2)
cv2.rectangle(
img, (real_x1, real_y1), (real_x2, real_y2),
(int(class_to_color[key][0]), int(
class_to_color[key][1]), int(class_to_color[key][2])), 2)
textLabel = '{}: {}%'.format(key, int(100 * new_probs[jk]))
all_dets.append((key, 100 * new_probs[jk]))
(retval, baseLine) = cv2.getTextSize(textLabel,
cv2.FONT_HERSHEY_COMPLEX, 1,
1)
# To avoid putting text outside the frame
# replace the legende if the box is outside the image
if real_y1 < 20 and real_y2 < img.shape[0]:
textOrg = (real_x1, real_y2 + 5)
elif real_y1 < 20 and real_y2 > img.shape[0]:
textOrg = (real_x1, img.shape[0] - 10)
else:
textOrg = (real_x1, real_y1 + 5)
cv2.rectangle(
img, (textOrg[0] - 5, textOrg[1] + baseLine - 5),
(textOrg[0] + retval[0] + 5, textOrg[1] - retval[1] - 5),
(0, 0, 0), 2)
cv2.rectangle(
img, (textOrg[0] - 5, textOrg[1] + baseLine - 5),
(textOrg[0] + retval[0] + 5, textOrg[1] - retval[1] - 5),
(255, 255, 255), -1)
cv2.putText(img, textLabel, textOrg, cv2.FONT_HERSHEY_DUPLEX, 1,
(0, 0, 0), 1)
if print_dets:
print(all_dets)
return img