Abstract:
Recognition of occluded objects in unseen and unstructured indoor environments is a challenging problem for mobile robots. To address this challenge, we propose a new des...Show MoreMetadata
Abstract:
Recognition of occluded objects in unseen and unstructured indoor environments is a challenging problem for mobile robots. To address this challenge, we propose a new descriptor, Topological features Of Point cloud Slices (TOPS), for point clouds generated from depth images and an accompanying recognition framework, TOPS for Human-inspired Object Recognition (THOR), inspired by human reasoning. The descriptor employs a novel slicing-based approach to compute topological features from filtrations of simplicial complexes using persistent homology and facilitates reasoning-based recognition using object unity. Apart from a benchmark dataset, we report performance on a new dataset, the UW Indoor Scenes (UW-IS) Occluded dataset, curated using commodity hardware to reflect real-world scenarios with different environmental conditions and degrees of object occlusion. THOR outperforms state-of-the-art methods on both the datasets and achieves substantially higher recognition accuracy for all the scenarios of the UW-IS Occluded dataset. Therefore, THOR is a promising step toward robust recognition in low-cost robots, meant for everyday use in indoor settings.
Published in: IEEE Transactions on Robotics ( Volume: 40)
Funding Agency:
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Object Recognition ,
- Environmental Conditions ,
- Point Cloud ,
- Recognition Accuracy ,
- Indoor Environments ,
- Depth Images ,
- Topological Features ,
- Everyday Use ,
- Simplicial Complex ,
- Unstructured Environments ,
- Recognition Framework ,
- High Recognition Accuracy ,
- Occluded Objects ,
- Degree Of Occlusion ,
- Unseen Environments ,
- Training Data ,
- Support Vector Machine ,
- Large Amount Of Data ,
- Set Of Models ,
- Multilayer Perceptron ,
- Object Pose ,
- Bounding Box ,
- Object Point Cloud ,
- Minimum Bounding Box ,
- Domain Adaptation ,
- Occlusion Level ,
- Frontal View ,
- Objects In The Scene ,
- Target Domain ,
- Side View
- Author Keywords
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Object Recognition ,
- Environmental Conditions ,
- Point Cloud ,
- Recognition Accuracy ,
- Indoor Environments ,
- Depth Images ,
- Topological Features ,
- Everyday Use ,
- Simplicial Complex ,
- Unstructured Environments ,
- Recognition Framework ,
- High Recognition Accuracy ,
- Occluded Objects ,
- Degree Of Occlusion ,
- Unseen Environments ,
- Training Data ,
- Support Vector Machine ,
- Large Amount Of Data ,
- Set Of Models ,
- Multilayer Perceptron ,
- Object Pose ,
- Bounding Box ,
- Object Point Cloud ,
- Minimum Bounding Box ,
- Domain Adaptation ,
- Occlusion Level ,
- Frontal View ,
- Objects In The Scene ,
- Target Domain ,
- Side View
- Author Keywords