filmov
tv
Object Labeling in RGB-D videos
Показать описание
In this video we demonstrate a view-based approach for labeling objects in 3D scenes reconstructed from RGB-D (Kinect) videos. On the left are the original RGB and depth video frames, with high scoring bounding box object detections plotted on the RGB image. The 3D scene labeling is shown on the right, with objects color coded by category (bowl=red, cap=green, cereal=blue, mug=yellow, soda=cyan).
For technical details and more results, see the paper:
Detection-based Object Labeling in 3D Scenes
Kevin Lai, Liefeng Bo, Xiaofeng Ren, and Dieter Fox. ICRA 2012.
For technical details and more results, see the paper:
Detection-based Object Labeling in 3D Scenes
Kevin Lai, Liefeng Bo, Xiaofeng Ren, and Dieter Fox. ICRA 2012.
0:01:01
Object Labeling in RGB-D videos
0:01:01
RevealNet: Seeing Behind Objects in RGB-D Scans
0:00:20
Unsupervised Feature Learning for 3D Scene Labeling
0:02:59
LabelFusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenes
0:02:59
LabelFusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenes
0:57:00
Saurabh Gupta: Scene Understanding from RGB-D Images
0:04:11
Detecting Temporally Consistent Objects in Videos Using Object Class Label
0:01:01
Multi-modal Unsupervised Feature Learning for RGB-D Scene Labeling
0:03:52
System Demonstration using Washington RGB-D Scene Dataset
0:00:48
RGB-D with object detection and fusion Ver 1
0:04:11
3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
0:00:50
RGB-D Segmentation & Categorization
0:01:02
Unsupervised object individuation from RGB-D image sequences
0:01:16
Real-time RGBD Object Recognition
0:14:30
3DMatch: Learning Local Geometric Descriptors From RGB-D Reconstructions
0:04:44
LabelMaker: Automatic Semantic Label Generation from RGB-D Trajectories
0:01:00
KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects
0:01:01
Real-Time RGB-D based People Detection and Tracking for Mobile Robots and Head-Worn Cameras
0:14:43
Maskfusion: real-time recognition, tracking and reconstruction of multiple moving objects.
0:03:13
Interactive Segmentation on RGBD Images via Cue Selection
0:05:11
Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation
0:01:01
Saliency Detection using RGB-D Data for Indoor Robots
0:56:57
MBZUAI Research Talks | 3D POINT CLOUD ANALYSIS AND RGBD SALIENCY DETECTION | Dr. Saeed Anwar
0:02:46
Interactive Segmentation on RGBD Images via Cue Selection
Комментарии