Call for Paper - January 2022 Edition
IJCA solicits original research papers for the January 2022 Edition. Last date of manuscript submission is December 20, 2021. Read More

Real Time Rain Removal from Live Video using FPGA and Raspberry Pi

Print
PDF
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2017
Authors:
Eman Yassien, Raja Masadeh, Omar Almomani, Esra Masadeh
10.5120/ijca2017914675

Eman Yassien, Raja Masadeh, Omar Almomani and Esra Masadeh. Real Time Rain Removal from Live Video using FPGA and Raspberry Pi. International Journal of Computer Applications 169(4):27-31, July 2017. BibTeX

@article{10.5120/ijca2017914675,
	author = {Eman Yassien and Raja Masadeh and Omar Almomani and Esra Masadeh},
	title = {Real Time Rain Removal from Live Video using FPGA and Raspberry Pi},
	journal = {International Journal of Computer Applications},
	issue_date = {July 2017},
	volume = {169},
	number = {4},
	month = {Jul},
	year = {2017},
	issn = {0975-8887},
	pages = {27-31},
	numpages = {5},
	url = {http://www.ijcaonline.org/archives/volume169/number4/27974-2017914675},
	doi = {10.5120/ijca2017914675},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

The usage of HD videos has become widely spread into almost every aspect of modern life. There’s a need to develop filters and image processing techniques to take a human observer’s attention off of any abnormality in a video stream, such as surveillance video footage. Software techniques solely might not have the ability to process a great number of frames efficiently unless operating on a high-tech device such as a state-of-the-art supercomputer however that’s not an affordable to most users. Hence there's a demand for a reliable yet, affordable method to filter HD videos, which is the aim of this research.

Removing Raindrops from a real-time video stream requires heavy image processing and computations which may cause an observer to miss a piece of information like a car's plate number. The proposed technique takes raw image input from a video frame and converts it into a binary image using pure hardware implemented with an FPGA circuit. Then the binary image is processed using FastICA technique under Raspberry Pi machine to make raindrops simpler to remove and then renders the video frame to a High Definition Multimedia Interface (HDMI) cable to be displayed on the screen.

References

  1. Quinn, Heather, Miriam Leeser, and Laurie Smith King. "Implementing image processing pipelines in a hardware/software environment." High Performance Embedded Computing Workshop. 2002.
  2. S. U. Bhandari, S. Subbaraman, S. Pujari and R. Mahajan, "Real Time Video Processing on FPGA Using on the Fly Partial Reconfiguration," 2009 International Conference on Signal Processing Systems, Singapore, 2009, pp. 244-247.
  3. A. Safaei and Q. M. J. Wu, "A system-level design for foreground and background identification in 3D scenes," 2016 IEEE International Symposium on Circuits and Systems (ISCAS), Montreal, QC, 2016, pp. 2571-2574.
  4. Comon, Pierre. "Independent component analysis, a new concept?." Signal processing 36.3 (1994), pp. 287-314.
  5. Lee, Te-Won, Anthony J. Bell, and Russell H. Lambert. "Blind separation of delayed and convolved sources." Advances in neural information processing systems (1997): 758-764.
  6. I. Dagher and R. Nachar, "Face recognition using IPCA-ICA algorithm," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 6, pp. 996-1000, June 2006.
  7. J. Dong and H. Liu, "Video Stabilization for Strict Real-Time Applications," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 27, no. 4, pp. 716-724, April 2017.
  8. M. Lewandowska, J. Rumiński, T. Kocejko and J. Nowak, "Measuring pulse rate with a webcam — A non-contact method for evaluating cardiac activity," 2011 Federated Conference on Computer Science and Information Systems (FedCSIS), Szczecin, 2011, pp. 405-410.
  9. Brewer, Nathan, and Nianjun Liu. "Using the shape characteristics of rain to identify and remove rain from video." Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR). Springer Berlin Heidelberg, 2008.

Keywords

HD video, FPGA, FastICA, Raspberry Pi, HDMI