Improvement of Ground Truth Data for Eye Location on Infrared Driver Recordings
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 32799
Improvement of Ground Truth Data for Eye Location on Infrared Driver Recordings

Authors: Sorin Valcan, Mihail Găianu

Abstract:

Labeling is a very costly and time consuming process which aims to generate datasets for training neural networks in several functionalities and projects. For driver monitoring system projects, the need of labeled images has a significant impact on the budget and distribution of effort. This paper presents the modifications done to a ground truth data generation algorithm for 2D eyes location on infrared images with drivers in order to improve the quality of the data and performance of the trained neural networks. The algorithm restrictions become tougher which makes it more accurate but also less constant. The resulting dataset becomes smaller and shall not be altered by any kind of manual labels adjustment before being used in the neural networks training process. These changes resulted in a much better performance of the trained neural networks.

Keywords: Labeling automation, infrared camera, driver monitoring, eye detection, Convolutional Neural Networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 336

References:


[1] https://blog.datumize.com/evolution-dark-data
[2] https://www.ibm.com/blogs/cloud-archive/2017/08/ibm-data-catalog-datascientists- productivity/
[3] Barney G Glaser and Anselm L Strauss. 2017. Discovery of grounded theory:Strategies for qualitative research. Routledge.
[4] Valcan, S.; Gaianu, M. Ground Truth Data Generator for Eye Location on Infrared Driver Recordings. J. Imaging 2021, 7, 162. https://doi.org/10.3390/jimaging7090162.
[5] S. Valcan, ”Convolutional Neural Network Training System For Eye Location On Infrared Driver Recordings Using Automatically Generated Ground Truth Data,” 2021 23rd International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC), 2021, pp. 222-226, doi: 10.1109/SYNASC54541.2021.00045.
[6] Ian Hampson and Anne Junor. 2005. Invisible work, invisible skills: interactivecustomer service as articulation work. New Technology, Work and Employment20, 2 (2005), 166–181.
[7] Kjeld Schmidt. 2002. Remarks on the complexity of cooperative work. Revued’intelligence articielle 16, 4-5 (2002), 443–483.
[8] Susan Leigh Star. 1999. The ethnography of infrastructure. American behavioral scientist 43, 3 (1999), 377–391.
[9] Susan Leigh Star and Karen Ruhleder. 1996. Steps toward an ecology of infrastructure: Design and access for large information spaces. Information systems research 7, 1 (1996), 111–134.