def _get_index(self, label):
w, h = label.size
if h != self.data_dict['input_size'][0]:
scale_f = lambda x: int(
(x * 1.0 / self.data_dict['input_size'][0]) * h)
sample_tmp = list(map(scale_f, self.row_anchor))
# 288 inx [121, 131, 141, 150, 160, 170, 180, 189, 199, 209, 219, 228, 238, 248, 258, 267, 277, 287]
# 590 inx [247, 268, 288, 307, 327, 348, 368, 387, 407, 428, 448, 467, 487, 508, 528, 546, 567, 587]
all_idx = np.zeros(
(self.data_dict['num_lanes'], len(sample_tmp),
2)) #4*18*2 第一个通道存放590 对应的anchor 第二个通道存放车道线位置。如果不存在车道线位置为-1
for i, r in enumerate(sample_tmp):
label_r = np.asarray(label)[int(round(r))]
for lane_idx in range(1, self.data_dict['num_lanes'] + 1):
# culane label 四条车道线像素分别喂1 2 3 4
pos = np.where(label_r == lane_idx)[0]
if len(pos) == 0:
all_idx[lane_idx - 1, i, 0] = r
all_idx[lane_idx - 1, i, 1] = -1
continue
pos = np.mean(pos)
all_idx[lane_idx - 1, i, 0] = r
all_idx[lane_idx - 1, i, 1] = pos
# data augmentation: extend the lane to the boundary of image
all_idx_cp = all_idx.copy()
for i in range(self.data_dict['num_lanes']):
if np.all(all_idx_cp[i, :, 1] == -1):
continue
# if there is no lane
valid = all_idx_cp[i, :, 1] != -1
# get all valid lane points' index
valid_idx = all_idx_cp[i, valid, :]
# get all valid lane points
if valid_idx[-1, 0] == all_idx_cp[0, -1, 0]:
# if the last valid lane point's y-coordinate is already the last y-coordinate of all rows
# this means this lane has reached the bottom boundary of the image
# so we skip
continue
if len(valid_idx) < 6:
continue
# if the lane is too short to extend
valid_idx_half = valid_idx[len(valid_idx) // 2:, :]
p = np.polyfit(valid_idx_half[:, 0], valid_idx_half[:, 1],
deg=1) #多项式拟合
start_line = valid_idx_half[-1, 0]
pos = find_start_pos(all_idx_cp[i, :, 0], start_line) + 1
fitted = np.polyval(p, all_idx_cp[i, pos:, 0])
fitted = np.array(
[-1 if y < 0 or y > w - 1 else y for y in fitted])
assert np.all(all_idx_cp[i, pos:, 1] == -1)
all_idx_cp[i, pos:, 1] = fitted
if -1 in all_idx[:, :, 0]:
pdb.set_trace()
return all_idx_cp
def _get_index(self, label):
w, h = label.size
if h != 288:
scale_f = lambda x: int((x * 1.0 / 288) * h)
sample_tmp = list(map(scale_f, self.row_anchor))
all_idx = np.zeros((self.num_lanes, len(sample_tmp), 2))
for i, r in enumerate(sample_tmp):
label_r = np.asarray(label)[int(round(r))]
for lane_idx in range(1, self.num_lanes + 1):
pos = np.where(label_r == lane_idx)[0]
if len(pos) == 0:
all_idx[lane_idx - 1, i, 0] = r
all_idx[lane_idx - 1, i, 1] = -1
continue
pos = np.mean(pos)
all_idx[lane_idx - 1, i, 0] = r
all_idx[lane_idx - 1, i, 1] = pos
if not self.extend:
return all_idx
# data augmentation: extend the lane to the boundary of image
all_idx_cp = all_idx.copy()
for i in range(self.num_lanes):
if np.all(all_idx_cp[i, :, 1] == -1):
continue
# if there is no lane
valid = all_idx_cp[i, :, 1] != -1
# get all valid lane points' index
valid_idx = all_idx_cp[i, valid, :]
# get all valid lane points
if valid_idx[-1, 0] == all_idx_cp[0, -1, 0]:
# if the last valid lane point's y-coordinate is already the last y-coordinate of all rows
# this means this lane has reached the bottom boundary of the image
# so we skip
continue
if len(valid_idx) < 6:
continue
# if the lane is too short to extend
valid_idx_half = valid_idx[len(valid_idx) // 2:, :]
p = np.polyfit(valid_idx_half[:, 0], valid_idx_half[:, 1], deg=1)
start_line = valid_idx_half[-1, 0]
pos = find_start_pos(all_idx_cp[i, :, 0], start_line) + 1
fitted = np.polyval(p, all_idx_cp[i, pos:, 0])
fitted = np.array(
[-1 if y < 0 or y > w - 1 else y for y in fitted])
assert np.all(all_idx_cp[i, pos:, 1] == -1)
all_idx_cp[i, pos:, 1] = fitted
if -1 in all_idx[:, :, 0]:
pdb.set_trace()
return all_idx_cp
def _get_index(self, label):
w, h = label.size
if h != 256:
scale_f = lambda x: int((x * 1.0 / 256) * h)
sample_tmp = list(map(scale_f, self.row_anchor))
all_idx = np.zeros((4, len(sample_tmp), 2))
for i, r in enumerate(sample_tmp):
label_r = np.asarray(label)[int(round(r))]
for lane_idx in range(1, 5):
pos = np.where(label_r == lane_idx)[0]
if len(pos) == 0:
all_idx[lane_idx - 1, i, 0] = r
all_idx[lane_idx - 1, i, 1] = -1
continue
pos = np.mean(pos)
all_idx[lane_idx - 1, i, 0] = r
all_idx[lane_idx - 1, i, 1] = pos
all_idx_cp = all_idx.copy()
for i in range(4):
if np.all(all_idx_cp[i, :, 1] == -1):
continue
valid = all_idx_cp[i, :, 1] != -1
valid_idx = all_idx_cp[i, valid, :]
if valid_idx[-1, 0] == all_idx_cp[0, -1, 0]:
continue
if len(valid_idx) < 6:
continue
valid_idx_half = valid_idx[len(valid_idx) // 2:, :]
p = np.polyfit(valid_idx_half[:, 0], valid_idx_half[:, 1], deg=1)
start_line = valid_idx_half[-1, 0]
pos = find_start_pos(all_idx_cp[i, :, 0], start_line) + 1
fitted = np.polyval(p, all_idx_cp[i, pos:, 0])
fitted = np.array(
[-1 if y < 0 or y > w - 1 else y for y in fitted])
assert np.all(all_idx_cp[i, pos:, 1] == -1)
all_idx_cp[i, pos:, 1] = fitted
if -1 in all_idx[:, :, 0]:
pdb.set_trace()
return all_idx_cp