# Dynamic Object Tracking and Masking for Visual SLAM

arXiv: https://arxiv.org/abs/2008.00072 · HTML: https://mlsanity.com/paper/2008.00072/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2020.

## Built on by (most cited first, 8 of 8)

- [Semi-supervised 3D Object Detection via Adaptive Pseudo-Labeling](https://mlsanity.com/paper/2108.06649/) (2021)
- [D3FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance](https://mlsanity.com/paper/2207.08794/) (2022)
- [Semantic Visual Simultaneous Localization and Mapping: A Survey](https://mlsanity.com/paper/2209.06428/) (2022)
- [Image Patch-Matching with Graph-Based Learning in Street Scenes](https://mlsanity.com/paper/2311.04617/) (2023)
- [ViewBirdiformer: Learning to recover ground-plane crowd trajectories and ego-motion from a single ego-centric view](https://mlsanity.com/paper/2210.06332/) (2022)
- [DL-SLOT: Dynamic Lidar SLAM and Object Tracking Based On Graph Optimization](https://mlsanity.com/paper/2202.11431/) (2022)
- [HabitatDyn Dataset: Dynamic Object Detection to Kinematics Estimation](https://mlsanity.com/paper/2304.10854/) (2023)
- [Trajectory Prediction in Dynamic Object Tracking: A Critical Study](https://mlsanity.com/paper/2506.19341/) (2025)

## Abstract (arXiv)

In dynamic environments, performance of visual SLAM techniques can be impaired by visual features taken from moving objects. One solution is to identify those objects so that their visual features can be removed for localization and mapping. This paper presents a simple and fast pipeline that uses deep neural networks, extended Kalman filters and visual SLAM to improve both localization and mapping in dynamic environments (around 14 fps on a GTX 1080). Results on the dynamic sequences from the TUM dataset using RTAB-Map as visual SLAM suggest that the approach achieves similar localization performance compared to other state-of-the-art methods, while also providing the position of the tracked dynamic objects, a 3D map free of those dynamic objects, better loop closure detection with the whole pipeline able to run on a robot moving at moderate speed.