Akcije

Telfor Journal
kako citirati ovaj članak
podeli ovaj članak

Metrika

  • citati u SCIndeksu: 0
  • citati u CrossRef-u:[2]
  • citati u Google Scholaru:[]
  • posete u poslednjih 30 dana:12
  • preuzimanja u poslednjih 30 dana:9

Sadržaj

članak: 5 od 23  
Back povratak na rezultate
2020, vol. 12, br. 2, str. 98-103
Implementation challenge and analysis of thermal image degradation on R-CNN face detection
(naslov ne postoji na srpskom)
aVlatacom Institute of High Technologies, Belgrade
bUniverzitet u Beogradu, Elektrotehnički fakultet
cUniverzitet Singidunum, Beograd

e-adresanikola.latinovic@vlatacom.com, tijanavukovic1996@gmail.com, ranko.petrovic@vlatacom.com, milos.pavlovic@vlatacom.com, marko.kadijevic@vlatacom.com, ilija.popadic@vlatacom.com, mveinovic@singidunum.ac.
Ključne reči: face detection; image degradation; R-CNN; thermal images; Video Signal Processing; GPU
Sažetak
(ne postoji na srpskom)
Face detection systems with color cameras were rapidly evolving and have been well researched. In environments with good visibility they can reach excellent accuracy. But changes in illumination conditions can result in performance degradation, which is the one of the major limitations in visible light face detection systems. The solution to this problem could be in using thermal infrared cameras, since their operation doesn't depend on illumination. Recent studies have shown that deep learning methods can achieve an impressive performance on object detection tasks, and face detection in particular. The goal of this paper is to find an effective way to take advantages from thermal infrared spectra and provide an analysis of various image degradation influence on thermal face detection performance in a system based on R-CNN with special accent on implementation on a hardware platform for video signal processing that institute Vlatacom has developed, called vVSP.
Reference
*** (2007) ITU-R Recommendation BT.656,Interfaces for digital component video signals in 525-line and 625-line television systems operating at the 4:2:2 level of Recommendation ITU-R BT.601 (Part A). International Telecommunication Union
*** (2008) SMPTE 259M-SDTV digital signal/data serial digital interface. ANSI/SMPTE
*** (2012) Specifications of the camera link interface standard for digital cameras and frame grabbers, version 2.0. Ann Arbor: Automated Imaging Association
*** (2009) High-definition multimedia interface, specification version 1.4. HDMI Licensing, LLC
Aghajan, H., Cavallaro, A. (2009) Multi-camera networks: Principles and application. Academic Press, 1 edition (April 25)
Bengio, Y. (2012) Practical recommendations for gradient-based training of deep architectures. u: Montavon G., Orr G.B., Müller K.R. [ur.] Neural Networks: Tricks of the Trade, Lecture Notes in Computer Science, Berlin-Heidelberg: Springer, 7700, 437-478
Budzier, H., Gerlach, G. (2011) Thermal infrared sensors: Theory, optimisation and practice. Wiley, 1 edition (February 14)
Cheong, Y.K., Yap, V.V., Nisar, H. (2014) A novel face detection algorithm using thermal imaging. u: IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), IEEE, 208-213
Dhanani, S., Parker, M. (2012) Digital video processing for engineers: A foundation for embedded systems design. Newnes, 1st edition (October 24)
Dodge, S., Karam, L. (2016) Understanding how image quality affects deep neural networks. u: 2016 Eighth international conference on quality of multimedia experience (QoMEX), IEEE, 1-6
Eger, S., Youssef, P., Gurevych, I. (2018) Is it time to swish?: Comparing deep learning activation functions across NLP tasks. EMNLP, 4415-4424
Farber, R. (2011) CUDA application design and development. 1st edition, November 14
Girshick, R., Donahue, J., Darrell, T., Malik, J. (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. u: IEEE conference on computer vision and pattern recognition, Proceedings, IEEE, 580-587
Herrmann, C., Ruf, M., Beyerer, J. (2018) CNN-based thermal infrared person detection by domain adaptation. u: Autonomous Systems: Sensors, Vehicles, Security and the Internet of Everything, SPIE, vol. 10643, pp.1064308
Junli, C., Licheng, J. (2000) Classification mechanism of support vector machines. u: WCC 2000 - ICSP 2000. 2000 5th International Conference on Signal Processing Proceedings, 16th World Computer Congress 2000, vol. 3, pp. 1556-1559
Kwasniewska, A., Ruminski, J., Rad, P. (2017) Deep features class activation map for thermal face detection and tracking. u: 2017 10th International Conference on Human System Interactions (HSI), IEEE, 41-47
Ma, C., Trung, N.T., Uchiyama, H., Nagahara, H., Shimada, A., Taniguchi, R. (2017) Adapting local features for face detection in thermal image. Sensors, 17(12), 2741
MIPI Alliance (2019) Evolving CSI-2 specification: Technology brief. https://www.mipi.org/sites/default/files/MIPI_CSI-2_Specification_Brief.pdf, [Mar. 20, 2019]
NVIDIA (2014 -2018) NVIDIA Jetson TX2 series system-on-module Pascal GPU + ARMv8 + LPDDR4 + eMMC. NVIDIA Corporation, Jetson TX2 Series Datasheet 1.2, subject to change
Peric, D., Livada, B. (2017) Analysis of SWIR imagers application in electro-optical systems. u: IcETRAN 2017, conference, Kladovo
Perić, D., Livada, B., Perić, M., Vujić, S. (2019) Thermal imager range: Predictions, expectations and reality. Sensors, 19(15), 3313
Redmon, J., Farhadi, A. (2018) Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767
Ribeiro, R.F., Fernandes, J.M., Neves, A.J.R. (2017) Face detection on infrared thermal image. u: SIGNAL 2017: The Second International Conference on Advances in Signal, Image and Video Processing, Spain, 38-42
Uijlings, J.R.R., van de Sande, K.E.A., Gevers, T., Smeulders, A.W.M. (2013) Selective search for object recognition. International Journal of Computer Vision, 104(2), 154-171
Vlatacom Institute Vlatacom Institute border protection-land. https://www.vlatacominstitute.com/border-protection-land
Vlatacom Institute vMSIS3-CHD-1200-T Vlatacom multi sensor imaging system 3-cooled high definition. https://docs.wixstatic.com/ugd/510d2b_ccea8cf0cd674d898c05e23a b58562a5.pdf [Mar. 20, 2019]
Vuković, T., Petrović, R., Pavlović, M., Stanković, S. (2019) Thermal image degradation influence on R-CNN face detection performance. u: 2019 27th Telecommunications Forum (TELFOR), Belgrade, Serbia, IEEE, 1-4
Xilinx (2019) Ultrascale architecture and product data sheet: Overview. Ultrascale Datasheet, DS890 (v3.7) February 20, 2019. https://www.xilinx.com/support/documentation/data_sheets/ds890ultrascale-overview.pdf, [Mar. 20, 2019]
Zheng, Y. (2012) Face detection and eyeglasses detection for thermal face recognition. u: Image Processing: Machine Vision Applications V. International Society for Optics and Photonics, vol. 8300., pp. 83000C
 

O članku

jezik rada: engleski
vrsta rada: neklasifikovan
DOI: 10.5937/telfor2002098L
primljen: 22.05.2020.
revidiran: 18.07.2020.
prihvaćen: 31.07.2020.
objavljen: 25.12.2020.
objavljen u SCIndeksu: 19.01.2021.

Povezani članci

Nema povezanih članaka