AirCode: A Robust Object Encoding Method
This work addresses the challenge of precise object recall in robotics, such as for autonomous exploration and semantic relocalization, representing an incremental improvement over existing tracking-based methods.
The paper tackles the problem of robust object encoding and identification for robotic tasks by proposing AirCode, a graph-based method with feature sparse and object dense encoding, which achieves superior performance in object identification compared to state-of-the-art algorithms.
Object encoding and identification are crucial for many robotic tasks such as autonomous exploration and semantic relocalization. Existing works heavily rely on the tracking of detected objects but have difficulty recalling revisited objects precisely. In this paper, we propose a novel object encoding method, which is named as AirCode, based on a graph of key-points. To be robust to the number of key-points detected, we propose a feature sparse encoding and object dense encoding method to ensure that each key-point can only affect a small part of the object descriptors, leading it to be robust to viewpoint changes, scaling, occlusion, and even object deformation. In the experiments, we show that it achieves superior performance for object identification than the state-of-the-art algorithms and is able to provide reliable semantic relocalization. It is a plug-and-play module and we expect that it will play an important role in various applications.