TASONet: A Spatial Enhancement and Temporal Modeling Framework for UAV Small Object Tracking

Abstract

Highlights: What are the main findings? TASONet introduces a lightweight spatial–temporal enhancement framework that significantly improves the representation of ground small objects in UAV-view imagery while effectively suppressing background interference. The integrated SOE and TEM modules collaboratively enhance spatial discriminability and temporal consistency, delivering substantial performance gains on UAVDT and VisDrone-MOT with minimal computational overhead. What are the implications of the main findings? The findings demonstrate that lightweight spatial enhancement coupled with temporal modeling can overcome the common trade-off between small object amplification and false positive suppression in small object MOT. The efficiency and accuracy of TASONet make it well suited for real-time UAV-based applications such as aerial surveillance, traffic monitoring, and large-scale scene analysis. Multi object tracking (MOT) in UAV imagery is challenged by weak feature representation of small objects due to limited resolution, which leads to frequent missed detections. However, enhancing small object features often amplifies background noise and increases false positives. To address this contradiction, we propose the Temporal Aware Small Object Enhancement Network (TASONet), which integrates spatial enhancement and temporal modeling for robust tracking. The Small Object Enhancement (SOE) module combines depthwise separable convolutions with contrast-aware attention mechanisms (SimAM and LCDAttn) to improve local discriminability. It further incorporates the Small Target Enhancement Path (STEP), which uses motion-difference cues and a confidence adaptive suppression strategy to strengthen spatial features while mitigating noise. The Temporal Enhancement Module (TEM), consisting of Temporal Feature Alignment (TFA) and a Target Memory Unit (TMU), aggregates multi-frame information through adaptive inter-frame fusion and memory of high confidence historical features, improving temporal consistency and reducing false positives potentially introduced by SOE. Experiments show that TASONet achieves significant gains over state-of-the-art methods: on UAVDT, MOTA increases from 68.33 to 75.97 and IDF1 from 83.50 to 88.51; on VisDrone-MOT, MOTA rises from 61.15 to 73.52 with an IDF1 of 88.83. These results validate the effectiveness of jointly enhancing spatial features and temporal coherence for UAV small-object MOT.