COMET: Context-Aware IoU-Guided Network for Small Object Tracking
arXiv:2006.02597
Abstract
We consider the problem of tracking an unknown small target from aerial videos of medium to high altitudes. This is a challenging problem, which is even more pronounced in unavoidable scenarios of drastic camera motion and high density. To address this problem, we introduce a context-aware IoU-guided tracker (COMET) that exploits a multitask two-stream network and an offline reference proposal generation strategy. The proposed network fully exploits target-related information by multi-scale feature learning and attention modules. The proposed strategy introduces an efficient sampling strategy to generalize the network on the target and its parts without imposing extra computational complexity during online tracking. These strategies contribute considerably in handling significant occlusions and viewpoint changes. Empirically, COMET outperforms the state-of-the-arts in a range of aerial view datasets that focusing on tracking small objects. Specifically, COMET outperforms the celebrated ATOM tracker by an average margin of 6.2% (and 7%) in precision (and success) score on challenging benchmarks of UAVDT, VisDrone-2019, and Small-90.
arXiv commentAccepted manuscript in ACCV 2020
References in corpus (9)
- YOLOv3: An Incremental Improvement
- GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
- Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
- DSSD : Deconvolutional Single Shot Detector
- Deep Learning for Visual Tracking: A Comprehensive Survey
- Deeper and Wider Siamese Networks for Real-Time Visual Tracking
- MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small Objects
- Parallel Tracking and Verifying
- Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking