Scene Classification Method Based on Multi-Scale Convolutional Neural Network with Long Short-Term Memory and Whale Optimization Algorithm

Abstract

Indoor mobile robots can be localized by using scene classification methods. Recently, two-dimensional (2D) LiDAR has achieved good results in semantic classification with target categories such as room and corridor. However, it is difficult to achieve the classification of different rooms owing to the lack of feature extraction methods in complex environments. To address this issue, a scene classification method based on a multi-scale convolutional neural network (CNN) with long short-term memory (LSTM) and a whale optimization algorithm (WOA) is proposed. Firstly, the distance data obtained from the original LiDAR are converted into a data sequence. Secondly, a scene classification method integrating multi-scale CNN and LSTM is constructed. Finally, WOA is used to tune critical training parameters and optimize network performance. The actual scene data containing eight rooms are collected to conduct ablation experiments, highlighting the performance with the proposed algorithm with 98.87% classification accuracy. Furthermore, experiments with the FR079 public dataset are conducted to demonstrate that compared with advanced algorithms, the classification accuracy of the proposed algorithm achieves the highest of 94.35%. The proposed method can provide technical support for the precise positioning of robots.