Research map / Detection and segmentation / Tracking
BioDrone: A Bionic Drone-Based Single Object Tracking Benchmark for Robust Vision
Xin Zhao, Shiyu Hu, Yipei Wang, Jing Zhang, Yimin Hu, Rongshuai Liu, Haibin Ling, Yin Li, Renshu Li, Kun Liu, Jiadong Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add shallow-feature candidate matching network with learned fusion weights (ablation) | KeepTrack · BioDrone test set (OPE) | precision P_score: 0.504 -> 0.513 | Improved |
| add shallow-feature candidate matching network (ablation) | KeepTrack · BioDrone test set (OPE) | success S_score: 0.424 -> 0.428 | Improved |
| add shallow-feature candidate matching network (ablation) | KeepTrack · BioDrone test set (R-OPE) | restart count R_count: 3.075 -> 2.930 | Improved |
| retrain the base tracker on LaSOT, GOT-10k and BioDrone (Strategy-1) (ablation) | KeepTrack · BioDrone test set (OPE) | precision P_score: 0.504 -> 0.538 | Improved |
| retrain the target candidate association network on BioDrone and LaSOT (Strategy-2) (ablation) | KeepTrack · BioDrone test set (OPE) | precision P_score: 0.504 -> 0.496 | Hurt |
| retrain the target candidate association network (Strategy-2) (ablation) | KeepTrack · BioDrone test set (OPE) | success S_score: 0.424 -> 0.417 | Hurt |
| combine matching network with Strategy-1 retraining (ablation) | KeepTrack* · BioDrone test set (OPE) | precision P_score: 0.538 -> 0.554 | Improved |
| combine matching network with Strategy-1 retraining (ablation) | KeepTrack* · BioDrone test set (OPE) | success S_score: 0.457 -> 0.466 | Improved |
| combine matching network with Strategy-1 retraining (ablation) | KeepTrack* · BioDrone test set (R-OPE) | success S_score: 0.703 -> 0.691 | Hurt |
| re-initialize tracker on failure (R-OPE instead of OPE) | KeepTrack · BioDrone test set | precision P_score: 0.504 -> 0.803 | Improved |
| combine correlation filter with Siamese network (SuperDiMP) instead of Siamese-only (SiamRPN++) | trackers on BioDrone · BioDrone test set (OPE) | precision P_score: 0.315 -> 0.426 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 on most shared results.
- SiamRCNN — Siam R-CNN: Visual Tracking by Re-Detection (CVPR 2020) · better on 2 of 2 shared results
- TCTrack — TCTrack: Temporal Contexts for Aerial Tracking (CVPR 2022) · better on 1 of 1 shared result
- SiamCAR — SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking (CVPR 2020) · better on 1 of 1 shared result
- GlobalTrack — GlobalTrack: A Simple and Strong Baseline for Long-Term Tracking (AAAI 2020) · better on 1 of 1 shared result
- ATOM — ATOM: Accurate Tracking by Overlap Maximization (CVPR 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Visual Object Tracking for Unmanned Aerial Vehicles: A Benchmark and New Motion Models (AAAI 2017 · similarity 0.87)
- MMOT: The First Challenging Benchmark for Drone-based Multispectral Multi-Object Tracking (NeurIPS 2025 · similarity 0.85)
- UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles (NeurIPS 2024 · similarity 0.85)
- M$^2$E-UAV: A Benchmark and Analysis for Onboard Motion-on-Motion Event-Based Tiny UAV Detection (NeurIPS 2026 · similarity 0.84)
- Open-World Drone Active Tracking with Goal-Centered Rewards (NeurIPS 2025 · similarity 0.84)
- PointSR: Self-Regularized Point Supervision for Drone-View Object Detection (CVPR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
