Proposal of Hybrid Deep Learning Algorithm for In Cabin Monitoring System
DOI:
https://doi.org/10.52783/jns.v14.1720Keywords:
LSTM, CNN, Deep Learning, Passenger Monitoring, Self-DrivingAbstract
An autonomous vehicle is defined as a vehicle that is capable of navigating and operating independently, without the necessity for input from a driver or passengers. The Society of Automotive Engineers (SAE) has established internationally recognised standards for the classification of autonomous driving technology, delineating the various levels of autonomy. The development of Level 4 autonomous vehicles is currently being led by leading technology companies, including Google, Nvidia, and Tesla. For vehicles classified as Level 3 or above, the autonomous system is required to fulfil the role of the driver. This necessitates the development of advanced decision-making algorithms to support high-level autonomy. To create an effective deep learning-based autonomous driving system, it is essential to have a diverse array of scenarios and a large dataset. This study introduces a novel image captioning algorithm that utilises a hybrid CNN-LSTM model to assess passenger conditions within the vehicle and generate corresponding scenarios. Furthermore, the study evaluates the suitability of the produced data for training a monitoring system through simulated environments
Downloads
Metrics
References
Ulbrich. S, Menzel, T, Reschka. A, Schuldt. F, and Maurer. M “Defining and substantiating the terms scene, situation, and scenario for automated driving,” in 2015 IEEE 18th international conference on intelligent transportation systems, Gran Canaria, pp. 982-988, 2015.
O. Vinyals, A. Toshev, S. Bengio, and D. Erhan, “Show and tell: A neural image caption generator,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston: MA, pp. 3156–3164, June 2015. DOI: 10.1109/CVPR.2015.7298935.
Y. LeCun et al., “Backpropagation Applied to Handwritten Zip Code Recognition,” Neural Computation, vol. 1, no. 4, pp. 541–551, 1989.
KATTENBORN, Teja, et al. Review on Convolutional Neural Networks (CNN) in vegetation remote sensing. ISPRS journal of photogrammetry and remote sensing, 2021, 173: 24-49.
STAUDEMEYER, Ralf C.; MORRIS, Eric Rothstein. Understanding LSTM--a tutorial into long short-term memory recurrent neural networks. arXiv preprint arXiv:1909.09586, 2019.
YU, Yong, et al. A review of recurrent neural networks: LSTM cells and network architectures. Neural computation, 2019, 31.7: 1235-1270.
WANG, Jin, et al. Dimensional sentiment analysis using a regional CNN-LSTM model. In: Proceedings of the 54th annual meeting of the association for computational linguistics (volume 2: Short papers). 2016. p. 225-230.
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780
PANDA, Manoj Kumar, et al. Modified ResNet-152 network with hybrid pyramidal pooling for local change detection. IEEE Transactions on Artificial Intelligence, 2023.
Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. “ImageNet Classification with Deep Convolutional Neural Networks.”Communications of the ACM. Vol. 60, No.6, pp. 84-90, 2017.
Kaming. He, Xiangyu Zhang, Shaoqing. Ren and Jian. Sun, “Deep Residaul Learning for Image Recognition,” in 2016 IEEE 18th conference on Computer Vision and Pattern Recognition(CVPR), Las Vegas, pp. 770-778, 2016.
[Diederik P. Kingma, Jimmy Ba. Adam: A Method for Stochastic Optimization [Internet]. Available: https://arxiv.org/abs/1412.6980
Moses, M. B., Nithya, S. E. & Parameswari, M. (2022). Internet of Things and Geographical Information System based Monitoring and Mapping of Real Time Water Quality System. International Journal of Environmental Sciences, 8(1), 27-36. https://www.theaspd.com/resources/3.%20Water%20Quality%20Monitoring%20Paper.pdf
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
