移动机器人视觉SLAM回环检测原理、现状及趋势

近年来,视觉 SLAM 以结构简单、成本低、可结合语义信息等优势得到广泛关注。 回环检测在其中发挥着重要的作用。根据获得的回环信息,视觉 SLAM 后端优化算法便可以根据回环约束对位姿进行优化,消除移动机器人在长时间的工作下产生的累积误差,实现精确的长期定位,从而构建全局一致的运动轨迹和地图。 首先介绍视觉 SLAM 中回环检测原理及作用,从特征提取、相似度判断、实验评估几个方面对传统词袋模型进行深入分析,并概述目前基于词袋模型和概率的改进算法,对比总结基于深度学习的回环检测方法,简单概述结合语义信息的回环检测方法,最后对回环检测技术目前存在的问题以及未来的发展趋势进行总结与展望。

Principle, current situation and trend of visual SLAMloop

In recent years, visual SLAM has attracted wide attention due to its advantages of simple structure, low cost and ability tointegrate semantic information. Loop closure detection plays an important role on it. According to the loop information obtained, thevisual SLAM back-end optimization algorithm can optimize the pose according to the loop constraint, eliminate the cumulative errorgenerated after long-term work, and achieve accurate long-term positioning, in order to build a globally consistent motion track and map.First introduce the principle and function of loop closure detection in visual SLAM, then conduct an in-depth analysis of the traditionalbag-of-words model from feature extraction, similarity judgment, and experimental evaluation, and outlines several improved algorithmsbased on the bag-of-words model and probability, and summarizes several loop closure detection methods based on deep learning, brieflysummarize the loop closure detection methods combined with semantic information, and finally summarize and prospect the currentproblems and future development of loop closure detection.