# Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering

arXiv: https://arxiv.org/abs/1805.10916 · HTML: https://mlsanity.com/paper/1805.10916/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2018.

## Built on by (most cited first, 6 of 6)

- [Tracking Pedestrian Heads in Dense Crowd](https://mlsanity.com/paper/2103.13516/) (2021)
- [Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches](https://mlsanity.com/paper/2111.06740/) (2021)
- [Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking](https://mlsanity.com/paper/2101.12159/) (2021)
- [Local Metrics for Multi-Object Tracking](https://mlsanity.com/paper/2104.02631/) (2021)
- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)
- [Real-time Online Multi-Object Tracking in Compressed Domain](https://mlsanity.com/paper/2204.02081/) (2022)

## Abstract (arXiv)

In this paper, we propose the methods to handle temporal errors during multi-object tracking. Temporal error occurs when objects are occluded or noisy detections appear near the object. In those situations, tracking may fail and various errors like drift or ID-switching occur. It is hard to overcome temporal errors only by using motion and shape information. So, we propose the historical appearance matching method and joint-input siamese network which was trained by 2-step process. It can prevent tracking failures although objects are temporally occluded or last matching information is unreliable. We also provide useful technique to remove noisy detections effectively according to scene condition. Tracking performance, especially identity consistency, is highly improved by attaching our methods.