Uncertainty Aware Multitask Pyramid Vision Transformer For UAV-Based Object Re-Identification
This work addresses object re-identification for aerial surveillance systems, representing an incremental improvement in a domain-specific application.
The paper tackles the challenge of object re-identification from UAV images with varying camera parameters by proposing a multitask learning approach using a Pyramid Vision Transformer backbone and uncertainty modeling, achieving improved performance on PRAI and VRAI datasets with reported gains.
Object Re-IDentification (ReID), one of the most significant problems in biometrics and surveillance systems, has been extensively studied by image processing and computer vision communities in the past decades. Learning a robust and discriminative feature representation is a crucial challenge for object ReID. The problem is even more challenging in ReID based on Unmanned Aerial Vehicle (UAV) as the images are characterized by continuously varying camera parameters (e.g., view angle, altitude, etc.) of a flying drone. To address this challenge, multiscale feature representation has been considered to characterize images captured from UAV flying at different altitudes. In this work, we propose a multitask learning approach, which employs a new multiscale architecture without convolution, Pyramid Vision Transformer (PVT), as the backbone for UAV-based object ReID. By uncertainty modeling of intraclass variations, our proposed model can be jointly optimized using both uncertainty-aware object ID and camera ID information. Experimental results are reported on PRAI and VRAI, two ReID data sets from aerial surveillance, to verify the effectiveness of our proposed approach