文献类型：期刊文献

英文题名：Quantized Self-Supervised Local Feature for Real-Time Robot Indirect VSLAM

作者：Li, Shenghao[1];Liu, Shuang[2];Zhao, Qunfei[1];Xia, Qiaoyang[2]

机构：[1]Shanghai Jiao Tong Univ, Sch Elect Informat & Elect Engn, Dept Automat, Shanghai 200240, Peoples R China;[2]East China Univ Sci & Technol, Sch Mech & Power Engn, Shanghai 200237, Peoples R China

年份：2022

卷号：27

期号：3

起止页码：1414

外文期刊名：IEEE-ASME TRANSACTIONS ON MECHATRONICS

收录：;EI(收录号：20212310473799);WOS:【SCI-EXPANDED(收录号:WOS:000811604100022)】；

基金：This work was sponsored by the National Natural Science Foundation of China under Grant 51975214.

语种：英文

外文关键词：Feature extraction; Feature detection; Robustness; Visualization; Real-time systems; Tensors; Task analysis; Descriptor quantization; indirect VSLAM; local feature; robustness; self-supervised learning

摘要：The indirect visual simultaneous localization and mapping (VSLAM) is widely used in robot localization and navigation, thanks to its potential to achieve high localization accuracy with the local feature observations. However, the existing local features are subject to drift and mismatches under various visual conditions, which causes a degrading in localization accuracy and tracking loss. This article proposes a quantized self-supervised local feature for the indirect VSLAM to handle the environmental interference in robot localization tasks. A joint feature detection and description network is built in a lightweight manner to extract local features in real time. The network is iteratively trained by a self-supervised learning strategy, and the extracted local features are quantized by an orthogonal transformation for efficiency. We utilize frame-wise matching in Hamming space and bundle adjustment to establish a parallel indirect VSLAM. The proposed VSLAM demonstrates outstanding localization accuracy and tracking stability in the evaluation on multiple datasets and robustness in real-world experiments with the Realsense D435 RGB-D sensor. The efficiency experiment on Jetson TX2 indicates that the quantized self-supervised local feature is suitable for feature-based tasks on edge computing platforms.