AI Article Synopsis

  • The article discusses two new rock detection methods designed for Mars rovers, which are crucial for safe navigation and obstacle avoidance.
  • The methods address challenges posed by the diversity of Martian rock shapes and limited pixel details that affect current detection techniques.
  • The proposed algorithms, KPRD and KLRD, enhance the accuracy and speed of rock detection, with KLRD offering improved results through a more sophisticated approach, validated by experimental results on a specially created dataset called MarsData.

Article Abstract

This article presents two kernel-based rock detection methods for a Mars rover. Rock detection on planetary surfaces is particularly pivotal for planetary vehicles regarding navigation and obstacle avoidance. However, the diverse morphologies of Martian rocks, the sparsity of pixel-wise features, and engineering constraints are great challenges to current pixel-wise object detection methods, resulting in inaccurate and delayed object location and recognition. We therefore propose a region-wise rock detection framework and design two detection algorithms, kernel principle component analysis (KPCA)-based rock detection (KPRD) and kernel low-rank representation (KLRR)-based rock detection (KLRD), using hypotheses of feature and sub-spatial separability. KPRD is based on KPCA and is expert in real-time detection yet with less accurate performance. KLRD is based on KPRD with KLRR which can generate more precise rock detection results with less delay. To validate the efficiency of the proposed methods, we build a small-scale Martian rock dataset, MarsData, containing various rocks. Preliminary experimental results show that our methods are efficient in dealing with complex images containing rocks, shadows, and gravel. The code and data are available at: https://github.com/CVIR-Lab/MarsData.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TNNLS.2021.3131206DOI Listing

Publication Analysis

Top Keywords

rock detection
24
detection
10
rock
8
detection framework
8
mars rover
8
detection methods
8
kernel-based multi-featured
4
multi-featured rock
4
rock modeling
4
modeling detection
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!