AirObject: A Temporally Evolving Graph Embedding for Object Identification

Object encoding and identification are vital for robotic tasks such as autonomous exploration, semantic scene understanding, and re-localization. Previous approaches have attempted to either track objects or generate descriptors for object identification. However, such systems are limited to a fixed partial object representation from a single viewpoint. In a robot exploration setup, there is a requirement for a temporally evolving global object representation built as the robot observes the object from multiple viewpoints. Furthermore, given the vast distribution of unknown novel objects in the real world, the object identification process must be class-agnostic. In this context, we propose a novel temporal 3D object encoding approach, dubbed AirObject, to obtain global keypoint graph-based embeddings of objects. Specifically, the global 3D object embeddings are generated using a temporal convolutional network across structural information of multiple frames obtained from a graph attention-based encoding method. We demonstrate that AirObject achieves the state-of-the-art performance for video object identification and is robust to severe occlusion, perceptual aliasing, viewpoint shift, deformation, and scale transform, outperforming the state-of-the-art single frame and sequential descriptors. To the best of our knowledge, AirObject is one of the first temporal object encoding methods. Source code is available at https://github. com/NIK-V9/AirObject.

Automated summary

Object encoding and identification are crucial for robotic tasks, and previous approaches have limitations in representing objects from multiple viewpoints and dealing with unknown objects. This paper proposes a novel temporal 3D object encoding method called AirObject, which generates global object embeddings using structural information and graph attention mechanism. It demonstrates superior performance in video object identification compared to existing methods.