Event-based Motion Segmentation with Spatio-Temporal Graph Cuts

by   Yi Zhou, et al.

Identifying independently moving objects is an essential task for dynamic scene understanding. However, traditional cameras used in dynamic scenes may suffer from motion blur or exposure artifacts due to their sampling principle. By contrast, event-based cameras are novel bio-inspired sensors that offer advantages to overcome such limitations. They report pixel-wise intensity changes asynchronously, which enables them to acquire visual information at exactly the same rate as the scene dynamics. We have developed a method to identify independently moving objects acquired with an event-based camera, i.e., to solve the event-based motion segmentation problem. This paper describes how to formulate the problem as a weakly-constrained multi-model fitting one via energy minimization, and how to jointly solve its two subproblems – event-cluster assignment (labeling) and motion model fitting – in an iterative manner, by exploiting the spatio-temporal structure of input events in the form of a space-time graph. Experiments on available datasets demonstrate the versatility of the method in scenes with different motion patterns and number of moving objects. The evaluation shows that the method performs on par or better than the state of the art without having to predetermine the number of expected moving objects.


Event-based Motion Segmentation by Cascaded Two-Level Multi-Model Fitting

Among prerequisites for a synthetic agent to interact with dynamic scene...

Event-Based Motion Segmentation by Motion Compensation

In contrast to traditional cameras, whose pixels have a common exposure ...

MOMS with Events: Multi-Object Motion Segmentation With Monocular Event Cameras

Segmentation of moving objects in dynamic scenes is a key process in sce...

The Spatio-Temporal Poisson Point Process: A Simple Model for the Alignment of Event Camera Data

Event cameras, inspired by biological vision systems, provide a natural ...

EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras

We present the first event-based learning approach for motion segmentati...

SiamEvent: Event-based Object Tracking via Edge-aware Similarity Learning with Siamese Networks

Event cameras are novel sensors that perceive the per-pixel intensity ch...

Exploring Event-driven Dynamic Context for Accident Scene Segmentation

The robustness of semantic segmentation on edge cases of traffic scene i...

Please sign up or login with your details

Forgot password? Click here to reset