Search papers, labs, and topics across Lattice.
This paper tackles vehicle re-identification in thermal images by constructing viewpoint-conditioned feature vectors and performing area-specific feature comparisons. This approach adapts RGB-pretrained ViT feature extractors to the thermal domain, addressing challenges like high similarity and viewpoint variability. Experiments on RGBNT100 (IR) and a new maritime thermal dataset show improvements of 19.7% and 12.8% in mAP, respectively, over state-of-the-art methods.
Adapting RGB-pretrained ViTs with viewpoint-conditioned feature selection leaps ahead in thermal vehicle re-identification, outperforming existing methods by a significant margin.
Identification of less-articulated objects using single-channel images, such as thermal images, is important in many applications, such as surveillance. However, in this domain, existing methods show poor performance due to high similarity among objects of the same category in the absence of color information (overlooking shape information) and de-emphasized texture information. Furthermore, variability in viewpoint adds more complexity as the features vary from side to side. We address these issues by constructing viewpoint-conditioned feature vectors and area-specific feature comparisons in separate feature spaces. These interventions enable leveraging the advancements of existing RGB-pre-trained ViT feature extractors while effectively adapting them to address the challenges specific to the thermal domain. We test our system with RGBNT100 (IR) vehicle dataset and a thermal maritime dataset acquired by us. Our results surpass the state-of-the-art methods by 19.7% and 12.8% for the above datasets in mAP scores, respectively. We also plan to make our thermal dataset available, the first of its kind for maritime vessel identification.
