# Occlusion-Robust Online Multi-Object Visual Tracking using a GM-PHD Filter with CNN-Based Re-Identification

arXiv: https://arxiv.org/abs/1912.05949 · HTML: https://mlsanity.com/paper/1912.05949/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2019.

## Built on by (most cited first, 12 of 12)

- [Simple Cues Lead to a Strong Multi-Object Tracker](https://mlsanity.com/paper/2206.04656/) (2022)
- [Multi-Object Tracking and Segmentation via Neural Message Passing](https://mlsanity.com/paper/2207.07454/) (2022)
- [Local Metrics for Multi-Object Tracking](https://mlsanity.com/paper/2104.02631/) (2021)
- [Online and Real-Time Tracking in a Surveillance Scenario](https://mlsanity.com/paper/2106.01153/) (2021)
- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)
- [Hand-Based Person Identification using Global and Part-Aware Deep Feature Representation Learning](https://mlsanity.com/paper/2101.05260/) (2021)
- [Local-Aware Global Attention Network for Person Re-Identification Based on Body and Hand Images](https://mlsanity.com/paper/2209.04821/) (2022)
- [BASE: Probably a Better Approach to Multi-Object Tracking](https://mlsanity.com/paper/2309.12035/) (2023)
- [Ego-Motion Aware Target Prediction Module for Robust Multi-Object Tracking](https://mlsanity.com/paper/2404.03110/) (2024)
- [FusionSORT: Fusion Methods for Online Multi-object Visual Tracking](https://mlsanity.com/paper/2501.00843/) (2025)
- [STURE: Spatial-Temporal Mutual Representation Learning for Robust Data Association in Online Multi-Object Tracking](https://mlsanity.com/paper/2201.06824/) (2022)
- [Model-based Multi-object Visual Tracking: Identification and Standard Model Limitations](https://mlsanity.com/paper/2508.13647/) (2025)

## Abstract (arXiv)

We propose a novel online multi-object visual tracker using a Gaussian mixture Probability Hypothesis Density (GM-PHD) filter and deep appearance learning. The GM-PHD filter has a linear complexity with the number of objects and observations while estimating the states and cardinality of time-varying number of objects, however, it is susceptible to miss-detections and does not include the identity of objects. We use visual-spatio-temporal information obtained from object bounding boxes and deeply learned appearance representations to perform estimates-to-tracks data association for target labeling as well as formulate an augmented likelihood and then integrate into the update step of the GM-PHD filter. We also employ additional unassigned tracks prediction after the data association step to overcome the susceptibility of the GM-PHD filter towards miss-detections caused by occlusion. Extensive evaluations on MOT16, MOT17 and HiEve benchmark datasets show that our tracker significantly outperforms several state-of-the-art trackers in terms of tracking accuracy and identification.