ObjectDatasetTools
ObjectDatasetTools copied to clipboard
Tools to create pixel-wise object masks, bounding box labels (2D and 3D) and 3D object model (PLY triangle mesh) for object sequences filmed with an RGB-D camera. This project prepares training and te...
Hi Wang, Thank you for your great work. I got a different segmented result after running **register_segmented.py** using the default timer dataset. Could you please help me to solve it?...
when i try to get the mask of the object,it appear that: Traceback (most recent call last): File "create_label_files.py", line 155, in cnt = max(contours, key=cv2.contourArea) ValueError: max() arg is...
Hi @paperstiger @F2Wang ! Please look into this issue, ``` ``` Traceback (most recent call last): File "compute_gt_poses.py", line 351, in pose_graph = full_registration(path, max_correspondence_distance_coarse, File "compute_gt_poses.py", line 152, in...
Hi, I got a issue about the pointcloud I created after processing register_scene.py. Here is the model I got:   The rgb data I used in ./JPEGImages are like...
Thanks for @F2Wang for making this Third Party Program, which is very helpful! I have a question. In the compute_gt_poses.py file, this is how the odometer calculates: odometry = np.dot(transformation_icp,...
* Newer open3d(0.15.1) has moved some APIs under pipeline namespace. * The signature of `cv2.findCountours()` in newer OpenCV(4.6) is different from older version. I confirmed the script works well under...
Lamp is assigned class label 0. 0%| | 0/1199 [00:00
Hello, I want to run my code, but I need the RT matrix between the object and the camera. I find that the RT matrixs between all frames are saved...
   anyone can help? maybe it's related to the calibration of the camera?
How to compute matrix transformation (4x4) from two frames of object as an annotation .npy ?