ResearchSpace

Enhancing distracted driver detection with human body activity recognition using deep learning

Show simple item record

dc.contributor.author Zandamela, Frank
dc.contributor.author Nicolls, F
dc.contributor.author Kunene, Dumisani C
dc.contributor.author Stoltz, George G
dc.date.accessioned 2024-07-10T07:50:25Z
dc.date.available 2024-07-10T07:50:25Z
dc.date.issued 2023-12
dc.identifier.citation Zandamela, F., Nicolls, F., Kunene, D.C. & Stoltz, G.G. 2023. Enhancing distracted driver detection with human body activity recognition using deep learning. <i>South African Journal of Industrial Engineering, 34(4).</i> http://hdl.handle.net/10204/13705 en_ZA
dc.identifier.issn 2224-7890
dc.identifier.issn 1012-277X
dc.identifier.uri https://doi.org/10.7166/34-4-2983
dc.identifier.uri http://hdl.handle.net/10204/13705
dc.description.abstract Deep learning has gained traction due to its supremacy in terms of accuracy and ability to automatically learn features from input data. The literature proposes various approaches to detect distracted drivers. The performance of these algorithms is usually limited to image datasets with similar distribution as the training dataset, preventing the successful translation of the algorithm to real-world application. This paper proposes a robust distracted driver detection approach based on recognising distinctive activities of human body parts involved when a driver is operating a vehicle. Experimental results suggest that the proposed method outperforms current deep learning algorithms for distracted driver detection and significantly improves cross-dataset performance. A classification accuracy improvement of 15% was observed. Most importantly, a significant overall balanced (F1score) performance improvement of 23% was observed. en_US
dc.format Fulltext en_US
dc.language.iso en en_US
dc.relation.uri https://sajie.journals.ac.za/pub/article/view/2983 en_US
dc.source South African Journal of Industrial Engineering, 34(4) en_US
dc.subject Deep learning en_US
dc.subject Detecting Driver Distraction en_US
dc.subject Driver detection approach en_US
dc.subject Human body activity en_US
dc.title Enhancing distracted driver detection with human body activity recognition using deep learning en_US
dc.type Article en_US
dc.description.pages 17 en_US
dc.description.cluster Defence and Security en_US
dc.description.cluster Smart Places en_US
dc.description.impactarea Energy Supply and Demand en_US
dc.description.impactarea Optronic Sensor Systems en_US
dc.identifier.apacitation Zandamela, F., Nicolls, F., Kunene, D. C., & Stoltz, G. G. (2023). Enhancing distracted driver detection with human body activity recognition using deep learning. <i>South African Journal of Industrial Engineering, 34(4)</i>, http://hdl.handle.net/10204/13705 en_ZA
dc.identifier.chicagocitation Zandamela, Frank, F Nicolls, Dumisani C Kunene, and George G Stoltz "Enhancing distracted driver detection with human body activity recognition using deep learning." <i>South African Journal of Industrial Engineering, 34(4)</i> (2023) http://hdl.handle.net/10204/13705 en_ZA
dc.identifier.vancouvercitation Zandamela F, Nicolls F, Kunene DC, Stoltz GG. Enhancing distracted driver detection with human body activity recognition using deep learning. South African Journal of Industrial Engineering, 34(4). 2023; http://hdl.handle.net/10204/13705. en_ZA
dc.identifier.ris TY - Article AU - Zandamela, Frank AU - Nicolls, F AU - Kunene, Dumisani C AU - Stoltz, George G AB - Deep learning has gained traction due to its supremacy in terms of accuracy and ability to automatically learn features from input data. The literature proposes various approaches to detect distracted drivers. The performance of these algorithms is usually limited to image datasets with similar distribution as the training dataset, preventing the successful translation of the algorithm to real-world application. This paper proposes a robust distracted driver detection approach based on recognising distinctive activities of human body parts involved when a driver is operating a vehicle. Experimental results suggest that the proposed method outperforms current deep learning algorithms for distracted driver detection and significantly improves cross-dataset performance. A classification accuracy improvement of 15% was observed. Most importantly, a significant overall balanced (F1score) performance improvement of 23% was observed. DA - 2023-12 DB - ResearchSpace DP - CSIR J1 - South African Journal of Industrial Engineering, 34(4) KW - Deep learning KW - Detecting Driver Distraction KW - Driver detection approach KW - Human body activity LK - https://researchspace.csir.co.za PY - 2023 SM - 2224-7890 SM - 1012-277X T1 - Enhancing distracted driver detection with human body activity recognition using deep learning TI - Enhancing distracted driver detection with human body activity recognition using deep learning UR - http://hdl.handle.net/10204/13705 ER - en_ZA
dc.identifier.worklist 27172 en_US
dc.identifier.worklist 27572 en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record