In the automotive industry, researchers, AI experts, and developers are actively pushing deep learning based approaches for In-vehicle safety. In this research paper, we propose a hybrid deep learning based visual system for providing feedback to the driver in a non-intrusive manner. We describe a hybrid SSD-RBM (Single Shot MultiBox Detector - Restricted Boltzmann Machine) model for face feature identification. In this system, object detection, object tracking, and observations are processed through a full pipeline of image processing and detect the driver's movements and generate a safe and efficient action plan in real time. This in-vehicle interactive system assists drivers in regulating driving performance and avoiding hazards.
. Global Status Report on Road Safety 2018.
. Steven Landry, Myounghoon, Pavlo, Jan Hammerschmidt, "Report on the in-vehicle auditory interactions workshop_ taxonomy, challenges, and approaches", AutomotiveUI, 2015.
. V. Mnih et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, pp. 529–533, 2015.
. Y. Bengio, “Learning deep architectures for AI,” Found. Trends Mach. Learn., vol. 2, no. 1, pp. 1–127, 2009.
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning.Cambridge, MA, USA: MIT Press, 2016.
. Sarkar, Dipanjan, “Practical Machine Learning with Python - A Problem-Solver's Guide to Building Real-World Intelligent Systems”, 2016, Apress publications.
. HaiguangWen Kuan Han, Junxing Shi, Yizhen Zhang, Eugenio Culurciello, Zhongming Liu, "Deep Predictive Coding Network for Object Recognition", International Conference on Machine Learning (ICML), 2018.
. Reinhard Klette, "Computer Vision in Vehicles - A Brief Introduction", Technical Report, February 2014, ResearchGate.
. Rajkumar Joghee Bhojan, Ramyachitra, Vivekanandan, Subramaniam Ganesan, “A Machine Learning Based Approach for Detecting Non-Deterministic Tests and its Analysis in Mobile Application Testing”, International Journal of Advanced Research in Computer Science, ISSN No. 0976-5697, pp. 220-223.
. Geoffrey Hinton, "A Practical Guide to Training Restricted Boltzmann Machines", 2010.
. D. H. Hubel and T. N. Wiesel, “Receptive fields, binocular interaction, and functional architecture in the cat’s visual cortex,” The Journal of Physiology, vol. 160, pp. 106–154, 1962.
. Athanasios Voulodimos, Nikolaos Doulamis, Anastasios Doulamis and Effychios Protopapadakis, “Deep Learning for Computer Vision: A Brief Review”, Computational Intelligence and Neuroscience, Vol 2018, Hindawi.
. Ali Mollahosseini et al. AffectNet: A Database for facial expression, Valence, and Arousal Computing in the Wild Department of Electrical and Computer Engineering, University of Denver, Denver, CO, 80210, 2015.
. Mirafe R Prospero, Edson B Lagmayo, Anndee Christian L Tumulak, "Skybiometry and AffectNet on Facial Emotion Recognition Using Supervised Machine Learning Algorithms", ICCCV 2018, Singapore.
. David Acuna, Huan Ling, Amlan Kar, Sanja Fidler, "Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++", CVPR, 2018.
. Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Chen-Yang Fu, Alexander C. Berg, "SSD: Single Shot MultiBox Detector", arXiv, 2016.
. Ronghang Hu, Piotr Dollar, Kaiming He, Trevor Darrel, Ross Girshick, "Learning to Segment Every Thing", Computer Vision and Pattern Recognition, 2018.
. Shaoshan Liu, Jie Tang, Zhe Zhang, Jean-Luc, "Computer Architectures for Autonomous Driving", Computer, Volume: 50, Issue: 8, 2017, IEEE Computer Society, DOI:10.1109/MC.2017.3001256.
. Chieh-Chi Kao, Teng-Yok Lee, Pradeep Sen, Ming-Yu Liu, "Localization-Aware Active Learning for Object Detection", arXiv:1801.0512v1, Jan 2018.
This work is licensed under a Creative Commons Attribution 4.0 International License.
The names and email addresses entered in this journal site will be used exclusively for the stated purposes of this journal and will not be made available for any other purpose or to any other party.
Submission of the manuscript represents that the manuscript has not been published previously and is not considered for publication elsewhere.