To reduce the expensive labor costs of manually labeling autonomous driving datasets, an alternative is to automatically label the datasets using an offline perception system. However, objects might be temporarily occluded. Such occlusion scenarios in the datasets are common yet underexplored in offline auto labeling. In this work, we propose an offline tracking model that focuses on occluded object tracks. It leverages the concept of object permanence, which means objects continue to exist even if they are not observed anymore. The model contains three parts: a standard online tracker, a re-identification (Re-ID) module that associates tracklets before and after occlusion, and a track completion module that completes the fragmented tracks. The Re-ID module and the track completion module use the vectorized lane map as a prior to refine the tracking results with occlusion. The model can effectively recover the occluded object trajectories. It significantly improves the original online tracking result, demonstrating its potential to be applied in offline auto labeling as a useful plugin to improve tracking by recovering occlusions.
Offline Tracking with Object Permanence
2024 IEEE Intelligent Vehicles Symposium (IV) ; 1272-1279
2024-06-02
2112025 byte
Conference paper
Electronic Resource
English
British Library Online Contents | 2011
|Multi-Scale Skeletons via Permanence Ranking
British Library Conference Proceedings | 1997
|Les Américans en permanence dans l'espace.
Online Contents | 1996
Wissenschaft - Permanence in the transport sector
Online Contents | 1999
|