Matching-range-constrained real-time loop closure detection with CNNs features

Abstract

The loop closure detection (LCD) is an essential part of visual simultaneous localization and mapping systems (SLAM). LCD is capable of identifying and compensating the accumulation drift of localization algorithms to produce an consistent map if the loops are checked correctly. Deep convolutional neural networks (CNNs) have outperformed state-of-the-art solutions that use traditional hand-crafted features in many computer vision and pattern recognition applications. After the great success of CNNs, there has been much interest in applying CNNs features to robotic fields such as visual LCD. Some researchers focus on using a pre-trained CNNs model as a method of generating an image representation appropriate for visual loop closure detection in SLAM. However, there are many fundamental differences and challenges involved in character between simple computer vision applications and robotic applications. Firstly, the adjacent images in the dataset of loop closure detection might have more resemblance than the images that form the loop closure. Secondly, real-time performance is one of the most critical demands for robots. In this paper, we focus on making use of the feature generated by CNNs layers to implement LCD in real environment. In order to address the above challenges, we explicitly provide a value to limit the matching range of images to solve the first problem; meanwhile we get better results than state-of-the-art methods and improve the real-time performance using an efficient feature compression method.

FADM-SLAM: a fast and accurate dynamic intelligent motion SLAM for autonomous robot exploration involving movable objects

“…Manual sparse image features, on the other hand, are currently limited due to challenges in mapping complex dynamics or large-scale scenarios with too many or too few feature points. Within the visual SLAM-based system, a deep learning-enhanced categorized image feature extraction approach has emerged in recent years, which is used for loop closure detection (Gao and Zhang, 2015) and visual odometry (Dosovitskiy et al, 2015;Handa et al, 2016;Costante et al, 2015;Bai, 2016). Bescos et al (2018) describe DynaSLAM, a visual SLAM system, that extends ORB-SLAM2 (Mur-Artal and Tard os, 2017) with dynamic object identification and backdrop inpainting.…”

Loop Closure Detection for SLAM Based on Siamese Convolutional Neural Network

“…Deep learning has made outstanding achievements in image processing and has shown excellent performance in image classification [10][11][12] and image detection [13][14][15]. Deep learning has become increasingly popular in the field of SLAM in recent years [16]. The features of the image can be extracted well by the large-scale pre-trained neural network.…”

Adaptive Real-Time Loop Closure Detection Based on Image Feature Concatenation

“…Compared with FAB-MAP, it was superior with higher recall rate. [17] used Places-CNNs and provided matching range of candidate images to prevent the matching between adjacent images. [18] utilized outputs at intermediate layer as descriptors.…”