Motion Segmentation by Exploiting Complementary Geometric Models

Many real-world sequences cannot be conveniently categorized as general or degenerate; in such cases, imposing a false dichotomy in using the fundamental matrix or homography model for motion segmentation would lead to difficulty. Even when we are confronted with a general scene-motion, the fundamental matrix approach as a model for motion segmentation still suffers from several defects, which we discuss in this paper. The full potential of the fundamental matrix approach could only be realized if we judiciously harness information from the simpler homography model. From these considerations, we propose a multi-view spectral clustering framework that synergistically combines multiple models together. We show that the performance can be substantially improved in this way. We perform extensive testing on existing motion segmentation datasets, achieving state-of-the-art performance on all of them; we also put forth a more realistic and challenging dataset adapted from the KITTI benchmark, containing real-world effects such as strong perspectives and strong forward translations not seen in the traditional datasets.

Authors

Zhuwen Li

Postdoc, Intelligent Systems Lab

View authors bio

Loong-Fah Cheong

Xun Xu

Related Content

Efficient, Sparse Representation of Manifold Distance Matrices for...

Geodesic distance matrices can reveal shape properties that are largely invariant to non-rigid deformations, and thus are often used to...

View publication

HeNet: A Deep Learning Approach on IntelR Processor...

This paper presents HeNet, a hierarchical ensemble neural network, applied to classify hardware-generated control flow traces for malware detection. Deep...

View publication

WRPN: Wide Reduced-Precision Networks

For computer vision applications, prior works have shown the efficacy of reducing numeric precision of model parameters (network weights) in...

View publication

Learning Visual Knowledge Memory Networks for Visual Question...

Visual question answering (VQA) requires joint comprehension of images and natural language questions, where many questions can't be directly or...

View publication

Stay Connected


Keep tabs on all the latest news with our monthly newsletter.