Object-Oriented Material Classification and 3D Clustering for Improved Semantic Perception and Mapping in Mobile Robots
This work addresses the need for enhanced semantic perception in mobile robots, offering incremental improvements in material recognition and mapping.
The paper tackles the problem of material classification and 3D semantic mapping for mobile robots by proposing a complementarity-aware deep learning approach using RGB-D data and integrating it with ORB-SLAM2 for 3D clustering, resulting in significant improvements in accuracy compared to state-of-the-art methods.
Classification of different object surface material types can play a significant role in the decision-making algorithms for mobile robots and autonomous vehicles. RGB-based scene-level semantic segmentation has been well-addressed in the literature. However, improving material recognition using the depth modality and its integration with SLAM algorithms for 3D semantic mapping could unlock new potential benefits in the robotics perception pipeline. To this end, we propose a complementarity-aware deep learning approach for RGB-D-based material classification built on top of an object-oriented pipeline. The approach further integrates the ORB-SLAM2 method for 3D scene mapping with multiscale clustering of the detected material semantics in the point cloud map generated by the visual SLAM algorithm. Extensive experimental results with existing public datasets and newly contributed real-world robot datasets demonstrate a significant improvement in material classification and 3D clustering accuracy compared to state-of-the-art approaches for 3D semantic scene mapping.