2692-4048ISSN (Online)
2770-0070ISSN (Print)
Volume 14 , Issue 2 , PP: 119-131, 2024 | Cite this article as | XML | Html | PDF | Full Length Article
Y. Sreeraman 1 , D. Jagadeesan 2 * , J. Jegan 3 , T. Vivekanandan 4 , A. Srinivasan 5 , G. Asha 6
Doi: https://doi.org/10.54216/FPA.140210
Anomaly detection in pedestrian walkways is a vital research area, widely employed to enhance the safety of the pedestrians. Because of the widespread usage of the video surveillance systems and the increasing number of captured videos, the conventional manual examination of labeling abnormal events is a laborious process. Therefore, an automatic surveillance system to accurately detect anomalies becomes essential among computer vision researchers. Presently, the development of deep learning (DL) models has gained significant interest in different computer vision processes namely object classification and object detection, and these applications were depending on supervised learning that required labels. This article develops an Improved Meta-heuristic with Parallel Features Fusion Model for Anomaly Detection in Pedestrian Walkways (IMPFF-ADPW) method. The main aim of the IMPFF-ADPW approach is to recognize the existence of anomalies in pedestrian walkways. To obtain this, the IMPFF-ADPW method applies a joint bilateral filter (JBF) for the process of noise removal. Besides, a parallel fusion process comprising NasNet Mobile and Darknet-53 models can be utilized for feature extraction. For the anomaly detection method, the deep autoencoder (DAE) model is applied and its hyperparameters are finetuned by using an improved sparrow search algorithm (ISSA). A wide of experimental outcomes can be applied to the UCSD database to illustrate the betterment of the IMPFF-ADPW methodology. The simulation values indicated the enhanced performance of the IMPFF-ADPW method over other existing techniques.
Computer vision , Pedestrian walkways , Anomaly detection , Metaheuristics , Deep learning
[1] Pustokhina, I.V., Pustokhin, D.A., Vaiyapuri, T., Gupta, D., Kumar, S. and Shankar, K., 2021. An automated deep learning based anomaly detection in pedestrian walkways for vulnerable road users safety. Safety science, 142, p.105356.
[2] Dey, A., Mohammad, F., Ahmed, S., Sharif, R. and Saif, A.S., 2019. Anomaly detection in crowded scene by pedestrians behaviour extraction using long short term method: a comprehensive study. International Journal of Education and Management Engineering, 9(1), p.51.
[3] Yadav, D., Jain, A., Asati, S. and Yadav, A.K., 2023. Video Anomaly Detection for Pedestrian Surveillance. In Computer Vision and Machine Intelligence: Proceedings of CVMI 2022 (pp. 489-500). Singapore: Springer Nature Singapore.
[4] Zhang, Y., Bolten, N., Mehta, S. and Caspi, A., 2023. APE: An Open and Shared Annotated Dataset for Learning Urban Pedestrian Path Networks. arXiv preprint arXiv:2303.02323.
[5] Schaefer, M., Salari, H.E., Köckler, H. and Thinh, N.X., 2021. Assessing local heat stress and air quality with the use of remote sensing and pedestrian perception in urban microclimate simulations. Science of the total environment, 794, p.148709.
[6] Ertz, O., Fischer, A., Ghorbel, H., Hüsser, O., Sandoz, R. and Scius-Bertrand, A., 2021. Citizen Participation & Digital Tools to Improve Pedestrian Mobility in Cities. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 46, pp.29-34.
[7] Pan, H., Luo, Y., Zeng, L., Shi, Y., Hang, J., Zhang, X., Hua, J., Zhao, B., Gu, Z. and Buccolieri, R., 2023. Outdoor Thermal Environment Regulation of Urban Green and Blue Infrastructure on Various Types of Pedestrian Walkways. Atmosphere, 14(6), p.1037.
[8] Dewi, D.I.K., Rakhmatulloh, A.R. and Syahri, E.K., 2022. Adaptation of the pedestrian walkways design along the Trans Semarang Bus Corridor to COVID-19. International journal of built environment and sustainability, 9(2-3), pp.25-37.
[9] Lui, A.K.F., Chan, Y.H. and Leung, M.F., 2022, April. Modelling of pedestrian movements near an amenity in walkways of public buildings. In 2022 8th International Conference on Control, Automation and Robotics (ICCAR) (pp. 394-400). IEEE.
[10] Perera, I.M.H., Athapaththu, C.J. and Mampearachchi, W.K., 2020. Design of a porous concrete mixture for drainage coverslab in pedestrian walkways. Transportation Research Procedia, 48, pp.3678-3695.
[11] Alohali, M.A., Aljebreen, M., Nemri, N., Allafi, R., Duhayyim, M.A., Ibrahim Alsaid, M., Alneil, A.A. and Osman, A.E., 2023. Anomaly Detection in Pedestrian Walkways for Intelligent Transportation System Using Federated Learning and Harris Hawks Optimizer on Remote Sensing Images. Remote Sensing, 15(12), p.3092.
[12] Murugan, B.S., Elhoseny, M., Shankar, K. and Uthayakumar, J., 2019. Region-based scalable smart system for anomaly detection in pedestrian walkways. Computers & Electrical Engineering, 75, pp.146-160.
[13] Xu, Y., Piao, Z. and Gao, S., 2018. Encoding crowd interaction with deep neural network for pedestrian trajectory prediction. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5275-5284).
[14] Boyuan, W. and Muqing, W., 2020, December. Study on pedestrian detection based on an improved YOLOv4 algorithm. In 2020 IEEE 6th International Conference on Computer and Communications (ICCC) (pp. 1198-1202). IEEE.
[15] French, G., Finlayson, G. and Mackiewicz, M., 2018. Multi-spectral pedestrian detection via image fusion and deep neural networks. Journal of Imaging Science and Technology, pp.176-181.
[16] Hara, Y., Uchiyama, A., Umedu, T. and Higashino, T., 2018, October. Sidewalk-level people flow estimation using dashboard cameras based on deep learning. In 2018 eleventh international conference on mobile computing and ubiquitous network (ICMU) (pp. 1-6). IEEE.
[17] Zhong, J., Sun, H., Cao, W. and He, Z., 2020. Pedestrian motion trajectory prediction with stereo-based 3D deep pose estimation and trajectory learning. IEEE access, 8, pp.23480-23486.
[18] Jeong, S., Min, J. and Park, Y., 2021. Indoor positioning using deep-learning-based pedestrian dead reckoning and optical camera communication. IEEE access, 9, pp.133725-133734.
[19] Alamgir, F.M. and Alam, M.S., 2023. An artificial intelligence driven facial emotion recognition system using hybrid deep belief rain optimization. Multimedia Tools and Applications, 82(2), pp.2437-2464.
[20] Rehman, S., Khan, M.A., Alhaisoni, M., Armghan, A., Tariq, U., Alenezi, F., Kim, Y.J. and Chang, B., 2023. A Framework of Deep Optimal Features Selection for Apple Leaf Diseases Recognition. " CMC-COMPUTERS MATERIALS & CONTINUA, 75(2023), pp.697-714.
[21] Al-Khazraji, H., Nasser, A.R., Hasan, A.M., Al Mhdawi, A.K., Al-Raweshidy, H. and Humaidi, A.J., 2022. Aircraft engines remain useful for life prediction based on a hybrid model of autoencoder and deep belief network. IEEE Access, 10, pp.82156-82163.
[22] Du, Y., Yuan, H., Jia, K. and Li, F., 2023. Research on Threshold Segmentation Method of Two-dimensional Otsu Image Based on Improved Sparrow Search Algorithm. IEEE Access.
