Non-flat Ground Detection Based on A Local Descriptor

TL;DR

This paper introduces a novel local descriptor and a neural network framework for detecting non-flat ground planes using stereo vision, effectively handling slopes and multi-ground scenarios.

Contribution

It proposes a new disparity texture descriptor and a CNN-based framework specifically designed for non-flat ground detection in stereo images.

Findings

Effective detection of non-flat ground planes demonstrated.

Descriptor improves distinction of ground regions in disparity images.

Framework addresses challenges of varying slopes and multi-ground planes.

Abstract

The detection of road and free space remains challenging for non-flat plane, especially with the varying latitudinal and longitudinal slope or in the case of multi-ground plane. In this paper, we propose a framework of the ground plane detection with stereo vision. The main contribution of this paper is a newly proposed descriptor which is implemented in the disparity image to obtain a disparity texture image. The ground plane regions can be distinguished from their surroundings effectively in the disparity texture image. Because the descriptor is implemented in the local area of the image, it can address well the problem of non-flat plane. And we also present a complete framework to detect the ground plane regions base on the disparity texture image with convolutional neural network architecture.