Road segmentation via iterative deep analysis

Abstract

Nowadays, people are increasingly concerned about the safety of traffic systems. Road segmentation and recognition is a fundamental problem in perceiving traffic environments and serve as the basis for self-driving cars. In this paper, inspired by an iterative deep analysis thinking, we propose a novel method which is able to learning powerful features step by step, and solve the optimal precision by balancing local and global information to conduct pixel-level classification for road segmentation. Firstly, we introduce an iterative deep analysis thinking which shows that how to design a strong and robustness deep model from failure experience. Secondly, we choose a powerful global features learning network as basis to create a novel framework for our task. Meanwhile, we employ the patch and multi-scale pyramid as input to enhance local features learning. We conduct experiments on three datasets from KITTI Vision Benchmark, namely UU, UM, UMM. The experimental results demonstrate that our proposed method obtains comparable performance with state-of-the-art methods on these datasets.