Detector–tracker integration framework and attention mechanism for multi–object tracking

Li, Chun-jiang; Chen, Guangzhu; Gou, Rongsong; Tang, Zaizuo

doi:10.1016/j.neucom.2021.08.107

Cited by 3 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonetheless, human beings have a remarkable ability to detect and recognize objects when they are partially visible and deformable. Some human vision mechanisms are introduced to learn appropriate attention parameters in different channels and effectively handle different occlusion and deformation patterns [45,46]. Among various human vision mechanisms, the attention mechanism has shown to be effective in many computer vision tasks, for which we will make a brief review in the next subsection.…”

Section: Related Work 21 Occlusion and Deformation Handling In Visual...mentioning

confidence: 99%

Occlusion and Deformation Handling Visual Tracking for UAV via Attention-Based Mask Generative Network

et al. 2022

View full text Add to dashboard Cite

Although the performance of unmanned aerial vehicle (UAV) tracking has benefited from the successful application of discriminative correlation filters (DCF) and convolutional neural networks (CNNs), UAV tracking under occlusion and deformation remains a challenge. The main dilemma is that challenging scenes, such as occlusion or deformation, are very complex and changeable, making it difficult to obtain training data covering all situations, resulting in trained networks that may be confused by new contexts that differ from historical information. Data-driven strategies are the main direction of current solutions, but gathering large-scale datasets with object instances under various occlusion and deformation conditions is difficult and lacks diversity. This paper proposes an attention-based mask generation network (AMGN) for UAV-specific tracking, which combines the attention mechanism and adversarial learning to improve the tracker’s ability to handle occlusion and deformation. After the base CNN extracts the deep features of the candidate region, a series of masks are determined by the spatial attention module and sent to the generator, and the generator discards some features according to these masks to simulate the occlusion and deformation of the object, producing more hard positive samples. The discriminator seeks to distinguish these hard positive samples while guiding mask generation. Such adversarial learning can effectively complement occluded and deformable positive samples in the feature space, allowing to capture more robust features to distinguish objects from backgrounds. Comparative experiments show that our AMGN-based tracker achieves the highest area under curve (AUC) of 0.490 and 0.349, and the highest precision scores of 0.742 and 0.662, on the UAV123 tracking benchmark with partial and full occlusion attributes, respectively. It also achieves the highest AUC of 0.555 and the highest precision score of 0.797 on the DTB70 tracking benchmark with the deformation attribute. On the UAVDT tracking benchmark with the large occlusion attribute, it achieves the highest AUC of 0.407 and the highest precision score of 0.582.

show abstract

Section: Related Work 21 Occlusion and Deformation Handling In Visual...mentioning

confidence: 99%