{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:30:10Z","timestamp":1791394210823,"version":"4.3.3"},"reference-count":45,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T00:00:00Z","timestamp":1769126400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The unpredictable nature of outdoor settings introduces numerous safety concerns, making hazard detection crucial for safe navigation. To address this issue, this paper proposes a sidewalk hazard detection system that combines a Variational Autoencoder (VAE) with a One-Class Support Vector Machine (OCSVM), using a wearable RGB camera as the primary sensing modality to enable low-cost, portable deployment and provide visual detail for detecting surface irregularities and unexpected objects. The VAE is trained exclusively on clean, obstruction-free sidewalk data to learn normal appearance patterns. At inference time, the reconstruction error produced by the VAE is used to identify spatial anomalies within each frame. These flagged anomalies are passed to an OCSVM, which determines whether they constitute a non-hazardous anomaly or a true hazardous anomaly that may impede navigation. To support this approach, we introduce a custom dataset consisting of over 20,000 training images of normal sidewalk scenes and 8000 testing frames containing both hazardous and non-hazardous anomalies. Experimental results demonstrate that the proposed VAE + OCSVM model achieves an AUC of 0.92 and an F1 score of 0.85, outperforming baseline anomaly detection models for outdoor sidewalk navigation. These findings indicate that the hybrid method offers a robust solution for sidewalk hazard detection in real-world outdoor environments.<\/jats:p>","DOI":"10.3390\/s26030769","type":"journal-article","created":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T16:13:48Z","timestamp":1769444028000},"page":"769","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Sidewalk Hazard Detection Using a Variational Autoencoder and One-Class SVM"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6063-9099","authenticated-orcid":false,"given":"Edgar R.","family":"Guzman","sequence":"first","affiliation":[{"name":"Harvard John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1392-227X","authenticated-orcid":false,"given":"Robert D.","family":"Howe","sequence":"additional","affiliation":[{"name":"Harvard John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"86","DOI":"10.9790\/0661-1903028690","article-title":"A Smart Stick for Assisting Blind People","volume":"19","author":"Anwar","year":"2017","journal-title":"IOSR J. Comput. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"eabg6594","DOI":"10.1126\/scirobotics.abg6594","article-title":"Multimodal sensing and intuitive steering assistance improve navigation and mobility for people with impaired vision","volume":"6","author":"Slade","year":"2021","journal-title":"Sci. Robot."},{"key":"ref_3","unstructured":"Zou, Z., Chen, K., Shi, Z., Guo, Y., and Ye, J. (2019). Object Detection in 20 Years: A Survey. arXiv."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/s41745-019-0099-3","article-title":"Beyond Supervised Learning: A Computer Vision Perspective","volume":"99","author":"Chum","year":"2019","journal-title":"J. Indian Inst. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"911","DOI":"10.12785\/ijcds\/130172","article-title":"An Unsupervised Machine Learning Algorithms: Comprehensive Review","volume":"13","author":"Naeem","year":"2023","journal-title":"Int. J. Comput. Digit. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"106106","DOI":"10.1016\/j.neunet.2024.106106","article-title":"Self-supervised anomaly detection in computer vision and beyond: A survey and outlook","volume":"172","author":"Hojjati","year":"2024","journal-title":"Neural Netw."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Gaus, Y.F.A., Bhowmik, N., Isaac-Medina, B.K.S., Shum, H.P.H., Atapour-Abarghouei, A., and Breckon, T.P. (2023, January 17\u201324). Region-Based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPRW59228.2023.00301"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Andrade, E.L., Blunsden, S., and Fisher, R.B. (2006, January 20\u201324). Modelling Crowd Scenes for Event Detection. Proceedings of the 18th International Conference on Pattern Recognition (ICPR\u201906), Hong Kong, China.","DOI":"10.1109\/ICPR.2006.806"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"49","DOI":"10.57197\/JDR-2023-0021","article-title":"Assisting Visually Impaired People Using Deep Learning-Based Anomaly Detection in Pedestrian Walkways for Intelligent Transportation Systems on Remote Sensing Images","volume":"2","author":"Alsolai","year":"2023","journal-title":"J. Disabil. Res."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Gasparini, R., D\u2019Eusanio, A., Borghi, G., Pini, S., Scaglione, G., Calderara, S., Fedeli, E., and Cucchiara, R. (2021, January 10\u201315). Anomaly Detection, Localization and Classification for Railway Inspection. Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy.","DOI":"10.1109\/ICPR48806.2021.9412972"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1326","DOI":"10.1109\/LRA.2020.2967706","article-title":"Safe Robot Navigation via Multi-Modal Anomaly Detection","volume":"5","author":"Wellhausen","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1007\/s10514-006-9721-0","article-title":"Safe and effective navigation of autonomous robots in hazardous environments","volume":"22","author":"Seward","year":"2007","journal-title":"Auton. Robot."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Reynolds, D. (2015). Gaussian Mixture Models. Encyclopedia of Biometrics, Springer.","DOI":"10.1007\/978-1-4899-7488-4_196"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1002\/wics.101","article-title":"Principal Component Analysis","volume":"2","author":"Abdi","year":"2010","journal-title":"Wiley Interdiscip. Rev. Comput. Stat."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1109\/JSTARS.2012.2190266","article-title":"Classification in High-Dimensional Feature Spaces\u2014Assessment Using SVM, IVM and RVM with Focus on Simulated EnMAP Data","volume":"5","author":"Braun","year":"2012","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_16","unstructured":"Hsu, C.W., Chang, C.C., and Lin, C.J. (2003). A Practical Guide to Support Vector Classification, Department of Computer Science, National Taiwan University. Technical Report."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2531","DOI":"10.1016\/j.patcog.2013.02.007","article-title":"An Iterative SVM Approach to Feature Selection and Classification in High-Dimensional Datasets","volume":"46","author":"Liu","year":"2013","journal-title":"Pattern Recognit."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liu, F.T., Ting, K.M., and Zhou, Z.H. (2008, January 15\u201319). Isolation Forest. Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, Pisa, Italy.","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref_19","unstructured":"Ruff, L., Vandermeulen, R., Goernitz, N., Deecke, L., Siddiqui, S.A., Binder, A., M\u00fcller, E., and Kloft, M. (2018, January 10\u201315). Deep One-Class Classification. Proceedings of the 35th International Conference on Machine Learning, PMLR, Stockholm, Sweden."},{"key":"ref_20","unstructured":"Dinh, L., Sohl-Dickstein, J., and Bengio, S. (2016). Density Estimation Using Real NVP. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1561\/2200000056","article-title":"An Introduction to Variational Autoencoders","volume":"12","author":"Kingma","year":"2019","journal-title":"Found. Trends Mach. Learn."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"26321","DOI":"10.1007\/s00521-025-11659-8","article-title":"Video anomaly detection in 10 years: A survey and outlook","volume":"37","author":"Abdalla","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, M., Wang, J., Qi, Q., Sun, H., Zhuang, Z., Ren, P., Ma, R., and Liao, J. (2024, January 16\u201322). Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01646"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1007\/s11760-025-04156-x","article-title":"Inter-Patch Spatio-Temporal Relation Prediction for Video Anomaly Detection","volume":"19","author":"Shen","year":"2025","journal-title":"Signal Image Video Process."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"123977","DOI":"10.1109\/ACCESS.2021.3109102","article-title":"TransAnomaly: Video Anomaly Detection Using Video Vision Transformer","volume":"9","author":"Yuan","year":"2021","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"7094","DOI":"10.1007\/s10489-021-02205-9","article-title":"Unsupervised Deep Learning Approach for Network Intrusion Detection Combining Convolutional Autoencoder and One-Class SVM","volume":"51","author":"Binbusayyis","year":"2021","journal-title":"Appl. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"67098","DOI":"10.1109\/ACCESS.2023.3291674","article-title":"Semi-supervised Detection of Structural Damage Using Variational Autoencoder and a One-Class Support Vector Machine","volume":"11","author":"Pollastro","year":"2023","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Tellaeche Iglesias, A., Campos Anaya, M.A., Pajares Martinsanz, G., and Pastor-L\u00f3pez, I. (2021). On Combining Convolutional Autoencoders and Support Vector Machines for Fault Detection in Industrial Textures. Sensors, 21.","DOI":"10.3390\/s21103339"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2550","DOI":"10.1109\/LRA.2023.3256135","article-title":"Environment-Based Assistance Modulation for a Hip Exosuit via Computer Vision","volume":"8","author":"Tricomi","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2576","DOI":"10.1109\/TBME.2015.2448457","article-title":"Depth Sensing for Improved Control of Lower Limb Prostheses","volume":"62","author":"Krausz","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1010","DOI":"10.1109\/TMRB.2022.3206602","article-title":"Depth Vision-Based Terrain Detection Algorithm During Human Locomotion","volume":"4","author":"Ronsse","year":"2022","journal-title":"IEEE Trans. Med. Robot. Bionics"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Yang, K., Wang, K., Cheng, R., Hu, W., Huang, X., and Bai, J. (2017). Detecting Traversable Area and Water Hazards for the Visually Impaired with a pRGB-D Sensor. Sensors, 17.","DOI":"10.3390\/s17081890"},{"key":"ref_33","first-page":"109","article-title":"Enhancing Outdoor Mobility and Environment Perception for Visually Impaired Individuals Through a Customized CNN-Based System","volume":"14","author":"Athulya","year":"2023","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Weld, G., Jang, E., Li, A., Zeng, A., Heimerl, K., and Froehlich, J.E. (2019, January 28\u201330). Deep Learning for Automatically Detecting Sidewalk Accessibility Problems Using Streetscape Imagery. Proceedings of the 21st International ACM SIGACCESS Conference on Computers and Accessibility, Pittsburgh, PA, USA.","DOI":"10.1145\/3308561.3353798"},{"key":"ref_35","unstructured":"Wang, H., Qin, J., Bastola, A., Chen, X., Suchanek, J., Gong, Z., and Razi, A. (2024). VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation. arXiv."},{"key":"ref_36","unstructured":"Haghighi, Y., Demonsant, C., Chalimourdas, P., Naeini, M.T., Munoz, J.K., Bacca, B., Suter, S., Gani, M., and Alahi, A. (2024). HEADS-UP: Head-Mounted Egocentric Dataset for Trajectory Prediction in Blind Assistance Systems. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1252","DOI":"10.1177\/1541931213601794","article-title":"Watch Out! Or do we? A Review of Literature on Human Locomotion, Visual Gaze, and Expectation of Trip Hazards","volume":"Volume 61","author":"Dixon","year":"2017","journal-title":"Proceedings of the Human Factors and Ergonomics Society Annual Meeting; Human Factors and Ergonomics Society"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1007\/s00221-018-5203-9","article-title":"Route previewing results in altered gaze behaviour, increased self-confidence and improved stepping safety in both young and older adults during adaptive locomotion","volume":"236","author":"Hollands","year":"2018","journal-title":"Exp. Brain Res."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., and Girshick, R. (2022, January 18\u201324). Masked Autoencoders Are Scalable Vision Learners. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the Dimensionality of Data with Neural Networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"key":"ref_41","unstructured":"Sch\u00f6lkopf, B., Williamson, R.C., Smola, A., Shawe-Taylor, J., and Platt, J. (December, January 29). Support Vector Method for Novelty Detection. Proceedings of the Advances in Neural Information Processing Systems, Denver, CO, USA."},{"key":"ref_42","first-page":"1","article-title":"Variational Autoencoder Based Anomaly Detection Using Reconstruction Probability","volume":"2","author":"An","year":"2015","journal-title":"Spec. Lect. IE"},{"key":"ref_43","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yin, H., Wu, X., Wu, Z., Mi, Y., and Wang, S. (2021, January 20\u201325). From Shadow Generation to Shadow Removal. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00489"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1444","DOI":"10.1016\/j.procs.2020.03.355","article-title":"Machine Learning in Computer Vision","volume":"167","author":"Khan","year":"2020","journal-title":"Procedia Comput. Sci."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/769\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T16:20:30Z","timestamp":1769444430000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/769"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,23]]},"references-count":45,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["s26030769"],"URL":"https:\/\/doi.org\/10.3390\/s26030769","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,23]]}}}