def convert_detection_to_kitti_annos(self, detection):
class_names = self._class_names
det_image_idxes = [k for k in detection.keys()]
gt_image_idxes = [
str(info["image"]["image_idx"]) for info in self._kitti_infos
]
# print(f"det_image_idxes: {det_image_idxes[:10]}")
# print(f"gt_image_idxes: {gt_image_idxes[:10]}")
annos = []
# for i in range(len(detection)):
for det_idx in gt_image_idxes:
det = detection[det_idx]
info = self._kitti_infos[gt_image_idxes.index(det_idx)]
# info = self._kitti_infos[i]
calib = info["calib"]
rect = calib["R0_rect"]
Trv2c = calib["Tr_velo_to_cam"]
P2 = calib["P2"]
final_box_preds = det["box3d_lidar"].detach().cpu().numpy()
label_preds = det["label_preds"].detach().cpu().numpy()
scores = det["scores"].detach().cpu().numpy()
anno = get_start_result_anno()
num_example = 0
if final_box_preds.shape[0] != 0:
final_box_preds[:, -1] = box_np_ops.limit_period(
final_box_preds[:, -1],
offset=0.5,
period=np.pi * 2,
)
final_box_preds[:, 2] -= final_box_preds[:, 5] / 2
# aim: x, y, z, w, l, h, r -> -y, -z, x, h, w, l, r
# (x, y, z, w, l, h r) in lidar -> (x', y', z', l, h, w, r) in camera
box3d_camera = box_np_ops.box_lidar_to_camera(
final_box_preds, rect, Trv2c)
camera_box_origin = [0.5, 1.0, 0.5]
box_corners = box_np_ops.center_to_corner_box3d(
box3d_camera[:, :3],
box3d_camera[:, 3:6],
box3d_camera[:, 6],
camera_box_origin,
axis=1,
)
box_corners_in_image = box_np_ops.project_to_image(
box_corners, P2)
# box_corners_in_image: [N, 8, 2]
minxy = np.min(box_corners_in_image, axis=1)
maxxy = np.max(box_corners_in_image, axis=1)
bbox = np.concatenate([minxy, maxxy], axis=1)
for j in range(box3d_camera.shape[0]):
image_shape = info["image"]["image_shape"]
if bbox[j, 0] > image_shape[1] or bbox[j,
1] > image_shape[0]:
continue
if bbox[j, 2] < 0 or bbox[j, 3] < 0:
continue
bbox[j, 2:] = np.minimum(bbox[j, 2:], image_shape[::-1])
bbox[j, :2] = np.maximum(bbox[j, :2], [0, 0])
anno["bbox"].append(bbox[j])
anno["alpha"].append(-np.arctan2(-final_box_preds[j, 1],
final_box_preds[j, 0]) +
box3d_camera[j, 6])
# anno["dimensions"].append(box3d_camera[j, [4, 5, 3]])
anno["dimensions"].append(box3d_camera[j, 3:6])
anno["location"].append(box3d_camera[j, :3])
anno["rotation_y"].append(box3d_camera[j, 6])
anno["name"].append(class_names[int(label_preds[j])])
anno["truncated"].append(0.0)
anno["occluded"].append(0)
anno["score"].append(scores[j])
num_example += 1
if num_example != 0:
anno = {n: np.stack(v) for n, v in anno.items()}
annos.append(anno)
else:
annos.append(empty_result_anno())
num_example = annos[-1]["name"].shape[0]
annos[-1]["metadata"] = det["metadata"]
return annos
def convert_detection_to_kitti_annos(self, detection):
class_names = self._class_names
det_image_idxes = [k for k in detection.keys()]
gt_image_idxes = [
str(info["image"]["image_idx"]) for info in self._kitti_infos
]
annos = []
for det_idx in gt_image_idxes:
det = detection[det_idx]
dim = det['box3d_lidar'][:, 3:6]
l, w, h = dim[:, 0:1], dim[:, 1:2], dim[:, 2:3]
det['box3d_lidar'][:, 2] = (det['box3d_lidar'][:, 2].T +
(h / 2).T).reshape(-1)
det['box3d_lidar'][:, -1] = det['box3d_lidar'][:, -1] * -1
info = self._kitti_infos[gt_image_idxes.index(det_idx)]
# info = self._kitti_infos[i]
calib = info["calib"]
rect = calib["R0_rect"]
Trv2c = calib["Tr_velo_to_cam"]
P2 = calib["P2"]
# final_box_preds = det["box3d_lidar"].detach().cpu().numpy()
# label_preds = det["label_preds"].detach().cpu().numpy()
# scores = det["scores"].detach().cpu().numpy()
final_box_preds = det["box3d_lidar"]
label_preds = det["label_preds"]
scores = det["scores"]
anno = get_start_result_anno()
num_example = 0
if final_box_preds.shape[0] != 0:
final_box_preds[:, -1] = box_np_ops.limit_period(
final_box_preds[:, -1],
offset=0.5,
period=np.pi * 2,
)
box3d_camera = final_box_preds
camera_box_origin = [0.5, 0.5, 0.5]
box_corners = box_np_ops.center_to_corner_box3d(
box3d_camera[:, :3],
box3d_camera[:, 3:6],
box3d_camera[:, 6],
camera_box_origin,
axis=2,
)
box_corners_in_image = box_np_ops.project_to_image(
box_corners, P2)
# box_corners_in_image: [N, 8, 2]
minxy = np.min(box_corners_in_image, axis=1)
maxxy = np.max(box_corners_in_image, axis=1)
bbox = np.concatenate([minxy, maxxy], axis=1)
for j in range(box3d_camera.shape[0]):
anno["bbox"].append([-1, -1, -1, -1])
anno["alpha"].append(0)
# anno["dimensions"].append(box3d_camera[j, [4, 5, 3]])
anno["dimensions"].append(box3d_camera[j, 3:6])
anno["location"].append(box3d_camera[j, :3])
anno["rotation_y"].append(box3d_camera[j, 6])
anno["name"].append(class_names[int(label_preds[j] - 1)])
anno["truncated"].append(0.0)
anno["occluded"].append(0)
anno["score"].append(scores[j])
num_example += 1
if num_example != 0:
anno = {n: np.stack(v) for n, v in anno.items()}
annos.append(anno)
else:
annos.append(empty_result_anno())
num_example = annos[-1]["name"].shape[0]
annos[-1]["metadata"] = det["metadata"]
return annos
