Design and Identification of Keypoint Patches in Unstructured Environments

TL;DR

This paper presents a novel approach for designing and identifying keypoint patches in cluttered environments, enhancing robustness for autonomous robot perception through customized neural networks and tested in real-world scenarios.

Contribution

It introduces four keypoint patch designs considering scale, rotation, and projection, along with a customized Superpoint network for improved detection under image degradation.

Findings

Effective keypoint detection in cluttered environments

Robust performance under image blur and shadows

Successful real-world video validation

Abstract

Reliable perception of targets is crucial for the stable operation of autonomous robots. A widely preferred method is keypoint identification in an image, as it allows direct mapping from raw images to 2D coordinates, facilitating integration with other algorithms like localization and path planning. In this study, we closely examine the design and identification of keypoint patches in cluttered environments, where factors such as blur and shadows can hinder detection. We propose four simple yet distinct designs that consider various scale, rotation and camera projection using a limited number of pixels. Additionally, we customize the Superpoint network to ensure robust detection under various types of image degradation. The effectiveness of our approach is demonstrated through real-world video tests, highlighting potential for vision-based autonomous systems.