Learning Local Feature Descriptor with Motion Attribute For Vision-based Localization

Abstract

In recent years, camera-based localization has been widely used for robotic applications, and most proposed algorithms rely on local features extracted from recorded images. For better performance, the features used for openloop localization are required to be short-term globally static, and the ones used for re-localization or loop closure detection need to be long-term static. Therefore, the motion attribute of a local feature point could be exploited to improve localization performance, e.g., the feature points extracted from moving persons or vehicles can be excluded from these systems due to their unsteadiness. In this paper, we design a fully convolutional network (FCN), named MD-Net, to perform motion attribute estimation and feature description simultaneously. MD-Net has a shared backbone network to extract features from the input image and two network branches to complete each sub-task. With MD-Net, we can obtain the motion attribute while avoiding increasing much more computation. Experimental results demonstrate that the proposed method can learn distinct local feature descriptor along with motion attribute only using an FCN, by outperforming competing methods by a wide margin. We also show that the proposed algorithm can be integrated into a vision-based localization algorithm to improve estimation accuracy significantly.

A Systematic Literature Review on Long-Term Localization and Mapping for Mobile Robots

“…from the semantic segmentation of EdgeNet. Instead of identifying object classes, Song et al 2019 proposes the MD-Net CNN to segment a grayscale image into unstable, static, and moving pixel points, only using static points for localization. The localization error was reduced compared to not estimated the pixel dynamic attribute.…”

SEKD: Self-Evolving Keypoint Detection and Description

“…DNN-based individual detector/descriptor methods. There are also a number of methods that only focus on DNN-based detector or descriptor, e.g., [36,30,8,13] proposed DNN-based keypoints detectors, and [31,22,34,21,20,33] worked on descriptor computation. However, we usually employ one local feature algorithm as a whole since either detector or descriptor would influence the performance of each other.…”

Application of Zernike moments in computer vision problems for infrared images

“…In this regard, a large number of algorithms have been proposed using local feature descriptors that are used to recreate or recognize patterns. Despite the rapid development of autonomous recognition systems, in which artificial neural networks (ANN) are often used, approaches based on the use of local descriptors remain relevant today [1][2][3]. Their main positive qualities are ease of use, speed and resistance to various types of noise.…”