# Coherent Motion Segmentation in Moving Camera Videos using Optical Flow Orientations

arXiv: https://arxiv.org/abs/1511.01619 · HTML: https://mlsanity.com/paper/1511.01619/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2015.

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

- [The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos](https://mlsanity.com/paper/2111.06394/) (2021)
- [EM-driven unsupervised learning for efficient motion segmentation](https://mlsanity.com/paper/2201.02074/) (2022)
- [Fusion-FlowNet: Energy-Efficient Optical Flow Estimation using Sensor Fusion and Deep Fused Spiking-Analog Network Architectures](https://mlsanity.com/paper/2103.10592/) (2021)
- [The Right Spin: Learning Object Motion from Rotation-Compensated Flow Fields](https://mlsanity.com/paper/2203.00115/) (2022)
- [Un-EVIMO: Unsupervised Event-Based Independent Motion Segmentation](https://mlsanity.com/paper/2312.00114/) (2023)
- [Unsupervised Flow Refinement near Motion Boundaries](https://mlsanity.com/paper/2208.02305/) (2022)
- [A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects](https://mlsanity.com/paper/2506.13552/) (2025)
- [Optical Flow from Photons](https://mlsanity.com/paper/2608.00499/) (2026)

## Abstract (arXiv)

In moving camera videos, motion segmentation is commonly performed using the image plane motion of pixels, or optical flow. However, objects that are at different depths from the camera can exhibit different optical flows even if they share the same real-world motion. This can cause a depth-dependent segmentation of the scene. Our goal is to develop a segmentation algorithm that clusters pixels that have similar real-world motion irrespective of their depth in the scene. Our solution uses optical flow orientations instead of the complete vectors and exploits the well-known property that under camera translation, optical flow orientations are independent of object depth. We introduce a probabilistic model that automatically estimates the number of observed independent motions and results in a labeling that is consistent with real-world motion in the scene. The result of our system is that static objects are correctly identified as one segment, even if they are at different depths. Color features and information from previous frames in the video sequence are used to correct occasional errors due to the orientation-based segmentation. We present results on more than thirty videos from different benchmarks. The system is particularly robust on complex background scenes containing objects at significantly different depths