CAE-VLAD-Net: A Loop Closure Detection System for Mobile Robots Using Convolutional Auto-Encoders Network with VLAD

Abstract

A critical part of visual SLAM is visual loop closure detection. It can solve the problem of trajectory drift caused by long time movement of mobile robots. The traditional loop closure detection system can not accurately detect the real closed loop. Factors such as different viewpoints, different lighting conditions and dynamic feature occlusion can seriously affect the positioning accuracy of mobile robots. Deep learning is made significant strides in computer visual in recent years, offering a fresh approach to the closing loop detection challenge. In this paper, We build a loop closure algorithm based on CAE-VLAD-Net (Convolutional Auto-Encoder-Vector of Locally Aggregated Descriptors-Network) model, which can solve these problems. This algorithm combines the characteristics of convolutional neural networks and stacked auto-encoders in deep learning, extracts features of continuous dense data collected by sensors, and applies them in loop closure based on key frames. We conduct comprehensive tests on various datasets, demonstrating that our method performs better than the state-of-the-art approach.