# A Universal Railway Obstacle Detection System based on Semi-supervised Segmentation And Optical Flow

arXiv: https://arxiv.org/abs/2406.18908 · HTML: https://mlsanity.com/paper/2406.18908/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 12 references that are in the map.
- First posted on arXiv 27 Jun 2024.

## Builds on (most cited first, 9 of 9)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications](https://mlsanity.com/paper/2204.11786/) (2022)
- [Optical Flow with Semantic Segmentation and Localized Layers](https://mlsanity.com/paper/1603.03911/) (2016)
- [Detecting floodwater on roadways from image data with handcrafted features and deep transfer learning](https://mlsanity.com/paper/1909.00125/) (2019)
- [DeVOS: Flow-Guided Deformable Transformer for Video Object Segmentation](https://mlsanity.com/paper/2405.08715/) (2024)
- [Local and Global Information in Obstacle Detection on Railway Tracks](https://mlsanity.com/paper/2307.15478/) (2023)
- [Enhancing Mobile Privacy and Security: A Face Skin Patch-Based Anti-Spoofing Approach](https://mlsanity.com/paper/2308.04798/) (2023)

## Built on by (most cited first, 1 of 1)

- [Enrich the content of the image Using Context-Aware Copy Paste](https://mlsanity.com/paper/2407.08151/) (2024)

## Abstract (arXiv)

Detecting obstacles in railway scenarios is both crucial and challenging due to the wide range of obstacle categories and varying ambient conditions such as weather and light. Given the impossibility of encompassing all obstacle categories during the training stage, we address this out-of-distribution (OOD) issue with a semi-supervised segmentation approach guided by optical flow clues. We reformulate the task as a binary segmentation problem instead of the traditional object detection approach. To mitigate data shortages, we generate highly realistic synthetic images using Segment Anything (SAM) and YOLO, eliminating the need for manual annotation to produce abundant pixel-level annotations. Additionally, we leverage optical flow as prior knowledge to train the model effectively. Several experiments are conducted, demonstrating the feasibility and effectiveness of our approach.