AirObject: A Temporally Evolving Graph Embedding for Object Identification

TL;DR

AirObject introduces a novel temporal 3D object encoding method that builds evolving global representations from multiple viewpoints, enabling robust, class-agnostic object identification in robotic applications.

Contribution

It presents the first temporal object encoding approach using a graph attention-based method combined with a temporal convolutional network for robust, evolving object representations.

Findings

Achieves state-of-the-art video object identification performance.

Robust to occlusion, viewpoint shifts, and scale changes.

Outperforms existing single-frame and sequential descriptors.

Abstract

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.