Re-engineering SORT-based algorithms for low-cost small object tracking from omnidirectional footage

• URL: http://arxiv.org/abs/2609.07547v1
• Date: Mon, 07 Sep 2026 14:29:21 GMT
• Title: Re-engineering SORT-based algorithms for low-cost small object tracking from omnidirectional footage
• Abstract summary: We address multi-object tracking of flying animals captured in remote environments using omnidirectional cameras.<n>We propose a lightweight framework that re-engineers SORT-based tracking for this geometry.<n>Our proposed methods improved tracking performance on OmniSmall and remained competitive on JRDB without adding appearance encoders.
• Score: 4.365505004088237
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-object tracking (MOT) has advanced rapidly in urban surveillance and autonomous driving, yet many trackers rely on ReID- and transformer-based appearance encoders and are designed for standard FoV cameras. These assumptions break down for low-cost omnidirectional deployments, where equirectangular projection introduces seam discontinuities and targets appear to be small and fast-moving. We address multi-object tracking of flying animals captured in remote environments using omnidirectional cameras. We propose a lightweight framework that re-engineers SORT-based tracking for this geometry, including (i) a Seam-Aware Motion Model that keeps the Kalman state continuous across the seam, (ii) a composite seam-aware association cost that pairs a wrapped Euclidean term with GIoU, and (iii) OmniSmall, a new benchmark of omnidirectional wildlife footage. On our new dataset, with ground-truth detections, our modifications improved over OCSORT by +8.51 HOTA, +9.41 MOTA, and +10.17 IDF1; with YOLOX detections the gain narrows to +1.95 HOTA. Our proposed methods improved tracking performance on OmniSmall and remained competitive on JRDB without adding appearance encoders while keeping the tracking stage CPU-only. Our dataset and source code are available at: https://github.com/Xin-Shu/OmniSORT.git.

Related papers

• Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis [53.67632483195509]
  We introduce StreetNVS, a video diffusion framework that conditions on all three signals through a Reference-Enhanced Camera Attention module.<n>We show capabilities of synthesizing coherent videos along extreme out-of-trajectory paths such as elevation, lane-shift, pullback, and rotation.
  arXiv  Detail & Related papers  (2026-06-01T02:37:56Z)
• Architecture and evaluation protocol for transformer-based visual object tracking in UAV applications [0.0]
  Existing visual trackers either lack robustness in complex scenarios or are too computationally demanding for real-time embedded use.<n>We propose an Modular Asynchronous Tracking Architecture (MATA) that combines a transformer-based tracker with an Extended Kalman Filter.<n>We introduce a hardware-independent, embedded oriented evaluation protocol and a new metric called Normalized time to Failure (NT2F) to quantify how long a tracker can sustain a tracking sequence without external help.
  arXiv  Detail & Related papers  (2026-03-04T10:12:12Z)
• StableTrack: Stabilizing Multi-Object Tracking on Low-Frequency Detections [0.18054741274903915]
  Multi-object tracking (MOT) is one of the most challenging tasks in computer vision.<n>Current approaches mainly focus on tracking objects in each frame of a video stream.<n>We propose StableTrack, a novel approach that stabilizes the quality of tracking on low-frequency detections.
  arXiv  Detail & Related papers  (2025-11-25T15:42:33Z)
• FutrTrack: A Camera-LiDAR Fusion Transformer for 3D Multiple Object Tracking [4.65812324892521]
  FutrTrack builds on existing 3D detectors by introducing a transformer-based smoother and a fusion-driven tracker.<n>Our fusion tracker integrates bounding boxes with multimodal bird's-eye-view (BEV) fusion features from multiple cameras and LiDAR.<n>FutrTrack achieves strong performance on 3D MOT benchmarks, reducing identity switches while maintaining competitive accuracy.
  arXiv  Detail & Related papers  (2025-10-22T19:25:01Z)
• Multi-View 3D Point Tracking [67.21282192436031]
  We introduce the first data-driven multi-view 3D point tracker, designed to track arbitrary points in dynamic scenes using multiple camera views.<n>Our model directly predicts 3D correspondences using a practical number of cameras.<n>We train on 5K synthetic multi-view Kubric sequences and evaluate on two real-world benchmarks.
  arXiv  Detail & Related papers  (2025-08-28T17:58:20Z)
• NOVA: Navigation via Object-Centric Visual Autonomy for High-Speed Target Tracking in Unstructured GPS-Denied Environments [56.35569661650558]
  We introduce NOVA, a fully onboard, object-centric framework that enables robust target tracking and collision-aware navigation.<n>Rather than constructing a global map, NOVA formulates perception, estimation, and control entirely in the target's reference frame.<n>We validate NOVA across challenging real-world scenarios, including urban mazes, forest trails, and repeated transitions through buildings with intermittent GPS loss.
  arXiv  Detail & Related papers  (2025-06-23T14:28:30Z)
• Tracking Everything Everywhere All at Once [111.00807055441028]
  We present a new test-time optimization method for estimating dense and long-range motion from a video sequence. We propose a complete and globally consistent motion representation, dubbed OmniMotion. Our approach outperforms prior state-of-the-art methods by a large margin both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2023-06-08T17:59:29Z)
• Propagate And Calibrate: Real-time Passive Non-line-of-sight Tracking [84.38335117043907]
  We propose a purely passive method to track a person walking in an invisible room by only observing a relay wall. To excavate imperceptible changes in videos of the relay wall, we introduce difference frames as an essential carrier of temporal-local motion messages. To evaluate the proposed method, we build and publish the first dynamic passive NLOS tracking dataset, NLOS-Track.
  arXiv  Detail & Related papers  (2023-03-21T12:18:57Z)
• LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking [42.87953709286856]
  Multi-Camera Multi-Object Tracking is currently drawing attention in the computer vision field due to its superior performance in real-world applications. We propose a mathematically elegant multi-camera multiple object tracking approach based on a spatial-temporal lifted multicut formulation.
  arXiv  Detail & Related papers  (2021-11-23T14:09:47Z)
• Learning Spatio-Temporal Transformer for Visual Tracking [108.11680070733598]
  We present a new tracking architecture with an encoder-decoder transformer as the key component. The whole method is end-to-end, does not need any postprocessing steps such as cosine window and bounding box smoothing. The proposed tracker achieves state-of-the-art performance on five challenging short-term and long-term benchmarks, while running real-time speed, being 6x faster than Siam R-CNN.
  arXiv  Detail & Related papers  (2021-03-31T15:19:19Z)
• DroTrack: High-speed Drone-based Object Tracking Under Uncertainty [0.23204178451683263]
  DroTrack is a high-speed visual single-object tracking framework for drone-captured video sequences. We implement an effective object segmentation based on Fuzzy C Means. We also leverage the geometrical angular motion to estimate a reliable object scale.
  arXiv  Detail & Related papers  (2020-05-02T13:16:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.