Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/90507
Título: | Optimized in-vehicle multi person human body pose detection |
Autor(es): | Dixe, Sandra Sousa, Joao Fonseca, Jaime C. Moreira, António Herculano Jesus Borges, Joao |
Palavras-chave: | Body Posture Detection Computer Vision Deep Learning Shared Autonomous Vehicles |
Data: | 2022 |
Editora: | Elsevier 1 |
Revista: | Procedia Computer Science |
Citação: | Dixe, S., Sousa, J., Fonseca, J. C., Moreira, A. H. J., & Borges, J. (2022). Optimized in-vehicle multi person human body pose detection. Procedia Computer Science. Elsevier BV. http://doi.org/10.1016/j.procs.2022.08.059 |
Resumo(s): | The number of Shared Autonomous Vehicles (SAV) will increase in the coming years. The absence of human driver will create a new paradigm for in-car safety. This paper addresses this problem by presenting an approach to estimate the human body pose inside a vehicle. We propose to use a customized version of the OpenPose framework, to perform the task of human body pose detection for the front passengers inside a vehicle. The OpenPose method was been evaluated with three different backbones: VGG19, MobileNetV1 and MobileNetV2, using different hyperparameters and ablation scenarios. Moreover, synthetic images were used, which simulate a depth sensor perspective from the center of the front seats. The dataset is comprised by images with 1 and 2 passengers, from 18 different subjects inside of 7 different vehicles, thus making a total of 45360 different images. The OpenPose method with the MobileNetV2 backbone showed the most efficient results between precision and performance, achieving a mean Average Precision (mAP) of 90%, Area Under ROC Curve (AUC) of 73%, and 0.0189 seconds per image (s/img). |
Tipo: | Artigo em ata de conferência |
URI: | https://hdl.handle.net/1822/90507 |
DOI: | 10.1016/j.procs.2022.08.059 |
ISSN: | 1877-0509 |
Versão da editora: | https://www.sciencedirect.com/science/article/pii/S1877050922007979 |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: | CAlg - Artigos em revistas internacionais / Papers in international journals |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
optimized in-vehicle.pdf | 962,75 kB | Adobe PDF | Ver/Abrir |
Este trabalho está licenciado sob uma Licença Creative Commons