A computer vision system for detecting motorcycle violations in pedestrian zones
This paper presents a system that relies on computer vision to identify instances of motorcycle violations in crosswalks utilizing CNNs. The system was trained and evaluated on a novel public dataset published by the authors, which contains traffic images classified into four categories: motorcycles...
- Autores:
-
Hernández-Díaz, Nicolás
Peñaloza, Yersica C.
Rios, Y. Yuliana
Martínez-Santos, Juan Carlos
Puertas, Edwin
- Tipo de recurso:
- Fecha de publicación:
- 2024
- Institución:
- Universidad Tecnológica de Bolívar
- Repositorio:
- Repositorio Institucional UTB
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.utb.edu.co:20.500.12585/12684
- Acceso en línea:
- https://hdl.handle.net/20.500.12585/12684
https://doi.org/10.1007/s11042-024-19356-9
- Palabra clave:
- IA model
Computer vision
Machine learning
Pedestrian areas
Autonomous traffic control system
LEMB
- Rights
- openAccess
- License
- http://creativecommons.org/licenses/by-nc-nd/4.0/
| id |
UTB2_2b0221a1ce83e5f54f86c2e8cb1122c4 |
|---|---|
| oai_identifier_str |
oai:repositorio.utb.edu.co:20.500.12585/12684 |
| network_acronym_str |
UTB2 |
| network_name_str |
Repositorio Institucional UTB |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
A computer vision system for detecting motorcycle violations in pedestrian zones |
| title |
A computer vision system for detecting motorcycle violations in pedestrian zones |
| spellingShingle |
A computer vision system for detecting motorcycle violations in pedestrian zones IA model Computer vision Machine learning Pedestrian areas Autonomous traffic control system LEMB |
| title_short |
A computer vision system for detecting motorcycle violations in pedestrian zones |
| title_full |
A computer vision system for detecting motorcycle violations in pedestrian zones |
| title_fullStr |
A computer vision system for detecting motorcycle violations in pedestrian zones |
| title_full_unstemmed |
A computer vision system for detecting motorcycle violations in pedestrian zones |
| title_sort |
A computer vision system for detecting motorcycle violations in pedestrian zones |
| dc.creator.fl_str_mv |
Hernández-Díaz, Nicolás Peñaloza, Yersica C. Rios, Y. Yuliana Martínez-Santos, Juan Carlos Puertas, Edwin |
| dc.contributor.author.none.fl_str_mv |
Hernández-Díaz, Nicolás Peñaloza, Yersica C. Rios, Y. Yuliana Martínez-Santos, Juan Carlos Puertas, Edwin |
| dc.subject.keywords.spa.fl_str_mv |
IA model Computer vision Machine learning Pedestrian areas Autonomous traffic control system |
| topic |
IA model Computer vision Machine learning Pedestrian areas Autonomous traffic control system LEMB |
| dc.subject.armarc.none.fl_str_mv |
LEMB |
| description |
This paper presents a system that relies on computer vision to identify instances of motorcycle violations in crosswalks utilizing CNNs. The system was trained and evaluated on a novel public dataset published by the authors, which contains traffic images classified into four categories: motorcycles in crosswalks, motorcycles outside crosswalks, pedestrians in cross walks, and only motorbike outside. We demonstrate the viability of leveraging deep learning models such as YOLOv8 for this purpose and provide details on the training and performance of the model. This system has the potential to enable intelligent traffic enforcement to mit igate accidents in pedestrian zones; to develop the system, a dataset comprising over 6,000 images was amassed from publicly available traffic cameras and subsequently annotated. Several models, including YOLOv8, SSD, and MobileNet, were trained on this dataset. The YOLOv8 model attained the highest performance with a mean average precision of 84.6% across classes. The study presents the system architecture and training process. Results illus trate the potential of utilizing deep learning to detect traffic violations in pedestrian zones, which can promote intelligent traffic enforcement and improved safety. |
| publishDate |
2024 |
| dc.date.accessioned.none.fl_str_mv |
2024-06-25T13:37:33Z |
| dc.date.available.none.fl_str_mv |
2024-06-25T13:37:33Z |
| dc.date.issued.none.fl_str_mv |
2024-05-02 |
| dc.date.submitted.none.fl_str_mv |
2024-06-25 |
| dc.type.coarversion.fl_str_mv |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/article |
| dc.type.hasversion.spa.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
| dc.type.spa.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_2df8fbb1 |
| status_str |
publishedVersion |
| dc.identifier.citation.spa.fl_str_mv |
Hernández-Díaz, N., Peñaloza, Y. C., Rios, Y. Y., Martinez-Santos, J. C., & Puertas, E. (2024). A computer vision system for detecting motorcycle violations in pedestrian zones. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-024-19356-9 |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/20.500.12585/12684 |
| dc.identifier.doi.none.fl_str_mv |
https://doi.org/10.1007/s11042-024-19356-9 |
| dc.identifier.instname.spa.fl_str_mv |
Universidad Tecnológica de Bolívar |
| dc.identifier.reponame.spa.fl_str_mv |
Repositorio Universidad Tecnológica de Bolívar |
| identifier_str_mv |
Hernández-Díaz, N., Peñaloza, Y. C., Rios, Y. Y., Martinez-Santos, J. C., & Puertas, E. (2024). A computer vision system for detecting motorcycle violations in pedestrian zones. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-024-19356-9 Universidad Tecnológica de Bolívar Repositorio Universidad Tecnológica de Bolívar |
| url |
https://hdl.handle.net/20.500.12585/12684 https://doi.org/10.1007/s11042-024-19356-9 |
| dc.language.iso.spa.fl_str_mv |
eng |
| language |
eng |
| dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| dc.rights.uri.*.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.cc.*.fl_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 Internacional |
| rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.none.fl_str_mv |
24 páginas |
| dc.format.mimetype.spa.fl_str_mv |
application/pdf |
| dc.publisher.place.spa.fl_str_mv |
Cartagena de Indias |
| dc.source.spa.fl_str_mv |
Multimedia Tools and Applications |
| institution |
Universidad Tecnológica de Bolívar |
| bitstream.url.fl_str_mv |
https://repositorio.utb.edu.co/bitstream/20.500.12585/12684/1/s11042-024-19356-9%201.pdf https://repositorio.utb.edu.co/bitstream/20.500.12585/12684/2/license_rdf https://repositorio.utb.edu.co/bitstream/20.500.12585/12684/3/license.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12684/4/s11042-024-19356-9%201.pdf.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12684/5/s11042-024-19356-9%201.pdf.jpg |
| bitstream.checksum.fl_str_mv |
76444156f0889c7974aa68af1cf57d7f 4460e5956bc1d1639be9ae6146a50347 e20ad307a1c5f3f25af9304a7a7c86b6 b0ab28740f3bd27efe71dc0f9d7dbcb6 b79e6650050f690924ce95c3a701fcd8 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional UTB |
| repository.mail.fl_str_mv |
repositorioutb@utb.edu.co |
| _version_ |
1814021644501385216 |
| spelling |
Hernández-Díaz, Nicolás63e39a63-8a3f-4573-bde7-cd014effbf78Peñaloza, Yersica C.f1fa3225-5d02-4d24-a1ae-29295105c3e6Rios, Y. Yuliana2e5d244a-ee96-4d51-8441-17659df20a44Martínez-Santos, Juan Carlos480cc438-b02b-45d2-bfc9-7bfa96f0271bPuertas, Edwin9e3c6f17-9041-40e3-a5fb-929a21d229012024-06-25T13:37:33Z2024-06-25T13:37:33Z2024-05-022024-06-25Hernández-Díaz, N., Peñaloza, Y. C., Rios, Y. Y., Martinez-Santos, J. C., & Puertas, E. (2024). A computer vision system for detecting motorcycle violations in pedestrian zones. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-024-19356-9https://hdl.handle.net/20.500.12585/12684https://doi.org/10.1007/s11042-024-19356-9Universidad Tecnológica de BolívarRepositorio Universidad Tecnológica de BolívarThis paper presents a system that relies on computer vision to identify instances of motorcycle violations in crosswalks utilizing CNNs. The system was trained and evaluated on a novel public dataset published by the authors, which contains traffic images classified into four categories: motorcycles in crosswalks, motorcycles outside crosswalks, pedestrians in cross walks, and only motorbike outside. We demonstrate the viability of leveraging deep learning models such as YOLOv8 for this purpose and provide details on the training and performance of the model. This system has the potential to enable intelligent traffic enforcement to mit igate accidents in pedestrian zones; to develop the system, a dataset comprising over 6,000 images was amassed from publicly available traffic cameras and subsequently annotated. Several models, including YOLOv8, SSD, and MobileNet, were trained on this dataset. The YOLOv8 model attained the highest performance with a mean average precision of 84.6% across classes. The study presents the system architecture and training process. Results illus trate the potential of utilizing deep learning to detect traffic violations in pedestrian zones, which can promote intelligent traffic enforcement and improved safety.24 páginasapplication/pdfenghttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessAttribution-NonCommercial-NoDerivatives 4.0 Internacionalhttp://purl.org/coar/access_right/c_abf2Multimedia Tools and ApplicationsA computer vision system for detecting motorcycle violations in pedestrian zonesinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_2df8fbb1http://purl.org/coar/version/c_970fb48d4fbd8a85IA modelComputer visionMachine learningPedestrian areasAutonomous traffic control systemLEMBCartagena de Indiasde Cartagena A (2023) Plan de Desarrollo Cartagena 2020-2023. sedcartagena.gov.co. http://www. sedcartagena.gov.co/plan-de-desarrollo-cartagena-2020-2023/Cartagena T (2021) Plan de acción Departamento Administrativo de Transito y Transporte - DATT 2021. DATT. https://www.transitocartagena.gov.co/normatividad/decretos-y-resoluciones.htmlToh CK, Sanguesa JA, Cano JC, Martinez FJ (2020) Advances in smart roads for future smart cities. Proc R Soc A Math Phys Eng Sci 476(2233):20190439. https://doi.org/10.1098/rspa.2019.0439Hernández Díaz N, Peñaloza YC, Ríos YY, Magre Colorado LA (2022) Software to assist visually impaired people during the craps game using machine learning on python platform. In: Narváez FR, Proaño J, Morillo P, Vallejo D, González Montoya D, Díaz GM (eds) Smart Technologies, Systems and Applications, pp 175–189. Springer, Cham. https://doi.org/10.1007/978-3-030-99170-8_13Suarez OJ, Hernández Díaz N, Pardo Garcia A (2020) A real-time pattern recognition module via Matlab Arduino interface, Virtual. https://doi.org/10.18687/LACCEI2020.1.1.646Suarez OJ, Macias-Garcia E, Vega CJ, Peñaloza YC, Díaz NH, Garrido VM (2023) Design of a segmen tation and classification system for seed detection based on pixel intensity thresholds and convolutional neural networks. In: Orjuela-Cañón AD, Lopez J, Arias-Londoño JD, Figueroa-García JC (eds) Applica tions of computational intelligence, pp 1–17. Springer, Cham. https://doi.org/10.1007/978-3-031-29783- 0_1Hernández-Díaz N, Pañaloza YC, Rios YY, Martinez-Santos JC, Puertas E (2023) Intelligent system to detect violations in pedestrian areas committed by vehicles in the city of cartagena de indias, 6. https:// doi.org/10.18687/LACCEI2023.1.1.1447lcaldía de Medellín (2023) Cámaras de CCTV. https://www.medellin.gov.co/simm/camaras-de circuito-cerrado Accessed 11-Dec-2020Díaz NH, Peñaloza YC, Rios YY,Martinez-Santos JC, Puertas E (2023) Dataset for detecting motorcyclists in pedestrian areas. Data in Brief 50:109610. https://doi.org/10.1016/j.dib.2023.109610Deruytter M, Peter J, Versavel J (2009) A detector for detecting traffic participants. https://worldwide. espacenet.com/publicationDetails/biblio?FT=D&date=20090527&DB=&locale=en_EP&CC=EP& NR=2063404A1&KC=A1&ND=112. Fascioli A, Fedriga RI, Ghidoni S (2007) Vision-based monitoring of pedestrian crossings. In: 14th International Conference on Image Analysis and Processing (ICIAP 2007), pp 566–574. https://doi.org/ 10.1109/ICIAP.2007.4362838Hariyono J, Jo K-H (2015) Detection of pedestrian crossing road. In: 2015 IEEE international conference on image processing (ICIP), pp 4585–4588. https://doi.org/10.1109/ICIP.2015.7351675Perdana MI, Anggraeni W, Sidharta HA, Yuniarno EM, Purnomo MH (2021) Early warning pedestrian crossing intention from its head gesture using head pose estimation. In: 2021 International seminar on intelligent technology and its applications (ISITIA), pp 402–407. https://doi.org/10.1109/ISITIA52817. 2021.9502231Hudson M, Martin B, Hagan T, Demuth HB (2023) Neural Network ToolboxTM 7 User’s Guide. https:// dcc.ufrj.br/sadoc/machinelearning/nnet_ug.pdfZhao C, Chen X (2018) The study of pedestrian re-identification with the illumination change. In: 2018 IEEE 3rd advanced information technology, electronic and automation control conference (IAEAC), pp 133–137. https://doi.org/10.1109/IAEAC.2018.8577489Pop DO, Rogozan A, Chatelain C, Nashashibi F, Bensrhair A (2019) Multi-task deep learning for pedes trian detection, action recognition and time to cross prediction. IEEE Access 7:149318–149327. https:// doi.org/10.1109/ACCESS.2019.2944792 123 Multimedia Tools and ApplicationsPorouhan P, Premchaiswadi W (2020) Proposal of a smart pedestrian monitoring system based on char acteristics of internet of things (iot). In: 2020 18th International conference on ICT and knowledge engineering (ICT KE), pp 1–4. https://doi.org/10.1109/ICTKE50349.2020.9289891Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: Single shot multibox detector. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer Vision - ECCV 2016. Springer, Cham, pp 21–37Wang Z, Feng J, Zhang Y (2022) Pedestrian detection in infrared image based on depth transfer learning. Multimed Tools Appl 81. https://doi.org/10.1007/s11042-022-13058-wFerguson M, ak R, Lee Y-T, Law K (2017) Automatic localization of casting defects with convolutional neural networks. In: 2017 IEEE international conference on big data (Big Data), pp 1726–1735. https:// doi.org/10.1109/BigData.2017.8258115Kadam K, Ahirrao S, Kotecha K (2022) Efficient approach towards detection and identification of copy move and image splicing forgeries using mask r-cnn with mobilenet v1. Comput Intell Neurosci 2022:1– 21. https://doi.org/10.1155/2022/6845326Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2019) MobileNetV2: Inverted Residuals and Linear Bottlenecks. https://doi.org/10.48550/arXiv.1801.04381Sandler M, Howard A (2018) MobileNetV2: The next generation of on-device computer vision networks. Google Research. https://ai.googleblog.com/2018/04/mobilenetv2-next-generation-of-on.htmlhao Q (2024) Qfgaohao/pytorch-SSD: Mobilenetv1, mobilenetv2, VGG based SSD/SSD-lite implemen tation in pytorch 1.0 / pytorch 0.4. out-of-box support for retraining on open images dataset. ONNX and caffe2 support. experiment ideas like coordconv. GitHub. https://github.com/qfgaohao/pytorch-ssdDusty-Nv N (2024) Dusty-NV/Jetson-inference: Hello AI World Guide to deploying deep-learning infer ence networks and deep vision primitives with TENSORRT and Nvidia Jetson. NVIDIA. https://github. com/dusty-nv/jetson-inferenceUltralytics Y (2024) Ultralytics/ultralytics: New - yolov8 in PyTorch; ONNX; CoreML; TFLite. Ultra lytics. https://github.com/ultralytics/ultralyticsHernández-Díaz N, Puertas E, Martinez-Santos JC, Archbold G, Rios Y, Peñaloza Y (2023) Dataset for Detecting Motorcyclists in Pedestrian Areas. Zenodo. https://doi.org/10.5281/zenodo.7935299Flow R (2024) Yolov5 Pytorch TXT annotation format. RoboFlow. https://roboflow.com/formats/yolov5- pytorch-txt 30. Flow R (2024) Pascal VOC XML annotation format. RoboFlow. https://roboflow.com/formats/pascal voc-xmlFoong NW (2022) Convert Pascal VOC XML to Yolo for Object Detection. Towards Data Science. https:// towardsdatascience.com/convert-pascal-voc-xml-to-yolo-for-object-detection-f969811ccba5Wang Y, Jia Y, Chen W, Wang T, Zhang A (2024) Examining safe spaces for pedestrians and e-bicyclists at urban crosswalks: An analysis based on drone-captured video. Accident Anal Prev 194:107365. https:// doi.org/10.1016/j.aap.2023.107365Han B, Wang Y, Yang Z, Gao X (2020) Small-scale pedestrian detection based on deep neural network. IEEE Trans Intell Trans Syst 21(7):3046–3055. https://doi.org/10.1109/TITS.2019.2923752Han R, Xu M, Pei S (2024) Crowded pedestrian detection with optimal bounding box relocation. Multimed Tools Appl. https://doi.org/10.1007/s11042-023-18019-5http://purl.org/coar/resource_type/c_2df8fbb1ORIGINALs11042-024-19356-9 1.pdfs11042-024-19356-9 1.pdfapplication/pdf3301053https://repositorio.utb.edu.co/bitstream/20.500.12585/12684/1/s11042-024-19356-9%201.pdf76444156f0889c7974aa68af1cf57d7fMD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805https://repositorio.utb.edu.co/bitstream/20.500.12585/12684/2/license_rdf4460e5956bc1d1639be9ae6146a50347MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-83182https://repositorio.utb.edu.co/bitstream/20.500.12585/12684/3/license.txte20ad307a1c5f3f25af9304a7a7c86b6MD53TEXTs11042-024-19356-9 1.pdf.txts11042-024-19356-9 1.pdf.txtExtracted texttext/plain53425https://repositorio.utb.edu.co/bitstream/20.500.12585/12684/4/s11042-024-19356-9%201.pdf.txtb0ab28740f3bd27efe71dc0f9d7dbcb6MD54THUMBNAILs11042-024-19356-9 1.pdf.jpgs11042-024-19356-9 1.pdf.jpgGenerated Thumbnailimage/jpeg6493https://repositorio.utb.edu.co/bitstream/20.500.12585/12684/5/s11042-024-19356-9%201.pdf.jpgb79e6650050f690924ce95c3a701fcd8MD5520.500.12585/12684oai:repositorio.utb.edu.co:20.500.12585/126842024-06-26 00:14:42.951Repositorio Institucional UTBrepositorioutb@utb.edu.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 |