Multi-line Fitting Using Two-Stage Iterative Adaptive Approach

Abstract

A new multi-line fitting algorithm using two-stage iterative adaptive approach (IAA) is proposed in this paper. The key points and main contributions are: i) The proposed algorithm decouples the multi-line fitting problem into two-stage spectral estimation problems; ii) In the first stage, it formulates the binary image into virtual far-field array signals with a single snapshot, and estimates the incoming angles using the iterative adaptive approach; iii) In the second stage, it formulates the binary image into multiple near-field signals, and estimates the offsets of these lines using IAA. Simulation and experimental (lane detection) results show that the proposed algorithm is an alternative multi-line fitting approach.