Visual Place Recognition Model using Deep Learning with Arithmetic Optimization Algorithm

International Journal of Electronics and Communication Engineering

© 2023 by SSRG - IJECE Journal

Volume 10 Issue 7

Year of Publication : 2023

Authors : S. Senthamizhselvi, A. Saravanan

10.14445/23488549/IJECE-V10I7P108

How to Cite?

S. Senthamizhselvi, A. Saravanan, "Visual Place Recognition Model using Deep Learning with Arithmetic Optimization Algorithm," SSRG International Journal of Electronics and Communication Engineering, vol. 10,  no. 7, pp. 74-86, 2023. Crossref, https://doi.org/10.14445/23488549/IJECE-V10I7P108

Abstract:

Visual Place Recognition (VPR) has engrossed the interest of many researchers in several domains like robotics and Computer Vision (CV). It is the process of identifying a location visited previously, depending on visual input like videos or images. DL techniques have witnessed a potential to solve this task. One method for VPR utilizing deep learning is Convolutional Neural Networks (CNNs) to extract features in visual input. The CNN is trained on a large dataset of videos or images, with each video or image corresponding to a diverse location. The CNN extract discriminative features for each location, allowing it to detect previously visited locations depending on their visual appearance. Therefore, this study presents an Arithmetic Optimization Algorithm with Deep Learning-Driven Robust Visual Place Recognition (AOADL-VPR) technique. The AOADL-VPR technique's purpose is to recognise the visual places using the DL model properly. In the AOADL-VPR technique, Gaussian Filtering (GF) based pre-processing is performed to remove the noise. Meanwhile, the MobileNet-v2 model is utilized for generating a feature vector set. Furthermore, the AOA is exploited to adjust the hyperparameter values of the MobileNet-v2 model. At last, Minkowski Distance is exploited for effectual similarity measurement between two images, thereby recognising the places. A series of experimental analyses can be performed to ensure the improved performance of the AOADL-VPR approach. The simulation outcomes portrayed the enhancements of the AOADL-VPR system on the place recognition process.

Keywords:

Visual place recognition, Deep learning, Arithmetic optimization algorithm, MobileNetv2, Similarity measurement.

References:

[1] Bruno Arcanjo et al., “An Efficient and Scalable Collection of Fly-Inspired Voting Units for Visual Place Recognition in Changing Environments,” IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 2527-2534, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Ahmad Khaliq et al., “A Holistic Visual Place Recognition Approach using Lightweight CNNs for Significant Viewpoint and Appearance Changes,” IEEE Transactions on Robotics, vol. 36, no. 2, pp. 561-569, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Jurica Maltar, Ivan Marković, and Ivan Petrović, “Visual Place Recognition using Directed Acyclic Graph Association Measures and Mutual Information-Based Feature Selection,” Robotics and Autonomous Systems, vol. 132, p. 103598, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Baifan Chen et al., “Hierarchical Visual Place Recognition Based on Semantic-Aggregation,” Applied Sciences, vol. 11, no. 20, pp. 1-14, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Dong Xu et al., “A Heterogeneous 3D Map-Based Place Recognition Solution using Virtual LiDAR and a Polar Grid Height Coding Image Descriptor,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 183, pp. 1-18, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Weiqi Zhang et al., “Learning Second-Order Statistics for Place Recognition Based on Robust Covariance Estimation of CNN Features,” Neurocomputing, vol. 398, pp.197-208, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Bruno Ferrarini et al., “Binary Neural Networks for Memory-Efficient and Effective Visual Place Recognition in Changing Environments,” IEEE Transactions on Robotics, vol. 38, no. 4, pp. 2617-2631, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Luis G Camara, and Libor Přeučil, “Visual Place Recognition by Spatial Matching of High-Level CNN Features,” Robotics and Autonomous Systems, vol. 133, p. 103625, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Mihnea-Alexandru Tomită et al., “Convsequential-Slam: A Sequence-Based, Training-Less Visual Place Recognition Technique for Changing Environments,” IEEE Access, vol. 9, pp. 118673-118683, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Tariqul Islam, Sheikh Rabiul Islam, and Mahbubur Rahman, “Learning Condition-Invariant Scene Representations for Place Recognition across the Seasons using Auto-Encoder and ICA,” Journal of Electrical and Computer Engineering, vol. 2022, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] T. Rajendran et al., “A Deep Learning Based Methodological Analysis for Breast Cancer Classification,” SSRG International Journal of Electronics and Communication Engineering, vol. 10, no. 6, pp. 52-68, 2023.
[CrossRef] [Publisher Link]
[12] Kuniaki Noda et al., “Audio-Visual Speech Recognition using Deep Learning,” Applied Intelligence, vol. 42, pp. 722-737, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[13] G. N. Srikanth, and M. K. Venkatesha, “SEOA DRN: Social Exponential Optimization Algorithm Based Deep Residual Network for Visual Speech Recognition,” SSRG International Journal of Electrical and Electronics Engineering, vol. 10, no. 1, pp. 90-105, 2023.
[CrossRef] [Publisher Link]
[14] Anandh Nagarajan, and Gopinath M P, “Hybrid Optimization-Enabled Deep Learning for Indoor Object Detection and Distance Estimation to Assist Visually Impaired Persons,” Advances in Engineering Software, vol. 176, p. 103362, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] M. Muruga Lakshmi, and S. Thayammal, “Ship Detection in Medium-Resolution SAR Images using Deep learning,” SSRG International Journal of Electronics and Communication Engineering, vol. 8, no. 5, pp. 1-5, 2021.
[CrossRef] [Publisher Link]
[16] Sara Khosravi, and Abdolah Chalechale, “Chimp Optimization Algorithm to Optimize a Convolutional Neural Network for Recognizing Persian/Arabic Handwritten Words,” Mathematical Problems in Engineering, vol. 2022, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] S. Suma Christal Mary et al., “Selfish Herd Optimization with Improved Deep Learning Based Intrusion Detection for Secure Wireless Sensor Network,” SSRG International Journal of Electronics and Communication Engineering, vol. 10, no. 4, pp. 1-8, 2023.
[CrossRef] [Publisher Link]
[18] M. Usharani et al., “An Optimized Deep Learning Model Based PV Fault Classification for Reliable Power Generation,” SSRG International Journal of Electrical and Electronics Engineering, vol. 9, no. 9, pp. 23-31, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Mubariz Zaffar et al., “CoHog: A Light-Weight, Compute-Efficient, and Training-Free Visual Place Recognition Technique for Changing Environments,” IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 1835-1842, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Manuel Lopez Antequera, “Computer Vision Techniques for Calibration, Localization and Recognition,” University of Groningen, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Stefan Schubert, Peer Neubert, and Peter Protzel, “Fast and Memory Efficient Graph Optimization via ICM for Visual Place Recognition,” Robotics: Science and Systems, 2021.
[Google Scholar] [Publisher Link]
[22] Bo Yang et al., “Landmark Generation in Visual Place Recognition using Multi-Scale Sliding Window for Robotics,” Applied Sciences, vol. 9, no. 15, pp. 1-17, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Shaorong Xie et al., “Large-Scale Place Recognition Based on Camera-LiDAR Fused Descriptor,” Sensors, vol. 20, no. 10, pp. 1-21, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Md. Tariqul Islam et al., “Convolutional Auto-Encoder and Independent Component Analysis Based Automatic Place Recognition for Moving Robot in Invariant Season Condition,” Human-Centric Intelligent Systems, vol. 3, pp. 13-24, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[25] V. Nyemeesha, and B. Mohammed Ismail, “Implementation of Noise and Hair Removals from Dermoscopy Images using Hybrid Gaussian Filter,” Network Modeling Analysis in Health Informatics and Bioinformatics, vol. 10, pp. 1-10, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Parvathaneni Naga Srinivasu et al., “Classification of Skin Disease using Deep Learning Neural Networks with MobileNet V2 and LSTM,” Sensors, vol. 21, no. 8, pp. 1-27, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Sagnik M, and Ramaprasad P, “Comparative Study of Convolutional Neural Networks,” SSRG International Journal of Electronics and Communication Engineering, vol. 6, no. 8, pp. 18-21, 2019.
[CrossRef] [Publisher Link]
[28] Mohamed Abd Elaziz et al., “Medical Image Classifications for 6G IoT-Enabled Smart Health Systems,” Diagnostics, vol. 13, no. 5, pp. 1-26, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Mubariz Zaffar et al., “VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change,” International Journal of Computer Vision, vol. 129, no. 7, pp. 2136-2174, 2021.
[CrossRef] [Google Scholar] [Publisher Link]