Free Form based active contours for image segmentation and free space perception

TL;DR

This paper introduces a novel free form active contour method combining B{\'e}zier models and local Free Form Deformation, enabling efficient, real-time segmentation and free space perception for robotic navigation in complex environments.

Contribution

The paper presents a new active contour approach that handles topology changes and adapts to various shapes with low complexity, improving real-time segmentation for robotic applications.

Findings

Effective segmentation of free space in omnidirectional images

Comparable or superior performance to state-of-the-art methods

Real-time processing suitable for robotic navigation

Abstract

In this paper we present a novel approach for representing and evolving deformable active contours. The method combines piecewise regular B{\'e}zier models and curve evolution defined by local Free Form Deformation. The contour deformation is locally constrained which allows contour convergence with almost linear complexity while adapting to various shape settings and handling topology changes of the active contour. We demonstrate the effectiveness of the new active contour scheme for visual free space perception and segmentation using omnidirectional images acquired by a robot exploring unknown indoor and outdoor environments. Several experiments validate the approach with comparison to state-of-the art parametric and geometric active contours and provide fast and real-time robot free space segmentation and navigation.