MODEL OF ALGORITHM FOR STREAMING LABELING OF WIDE FORMAT IMAGES
Abstract
This article proposes a wide-format image processing algorithm for use in systems operating in real time with a high-speed video data stream. The issue of image preprocessing, its clustering, segmentation and labeling is of particular importance for systems for processing high-resolution video streams in real time. In addition, when implementing such algorithms, there is an urgent issue of minimizing the cost of computational resources of programmable logic integrated circuits (FPGAs), on which the direct deployment of streaming image processing algorithms takes place. Minimal resource consumption is ensured by single-pass marking algorithms, which eliminate the need for image buffering, which is especially important when processing high-resolution wide-format images. However, when implementing a single pass of an image through the processing system, many additional markers may be created that are subject to further combining, especially when analyzing images with high resolution. The additional markers created require an increase in the requirements for the number of usable memory cells on the FPGA. The algorithm for streaming high-resolution wide-format images described in the article makes it possible to label high-resolution streaming video images, reducing the likelihood of creating additional tags that need to be further combined. The essence of improving the algorithm relative to the standard one-pass one is to add additional elements to the scanning mask, which avoid the appearance of different labels corresponding to the same object, which allows, with a minimal increase in the amount of memory used on the FPGA, to avoid duplication of labels and overuse of device memory. The algorithm was simulated for implementation on an FPGA using the Xilinx System Generator for DSP tool in conjunction with the Matlab Simulink environment for model-based design (MBD). The results of the algorithm are presented on images obtained from a high-speed linear camera TELEDYNE DALSA LA-CC-04K05B-00-R using the Integre Technologies LLC FMC-200-A mezzanine, as well as the Xilinx ZYNQ Ultrascale+ MPSoC ZCU106 development board.
References
(JACM), 1966, 13.4, pp. 471-494.
2. Haralick R. Some neighborhood operations, Real Time/Parallel Computing Image Analysis, 1981,
pp. 11-35.
3. Chang F. and Chen C.-J. A Component-Labelling Algorithm Using Contour Tracing Technique, Proceedings
of the 7th International Conference on Document Analysis and Recognition (ICIDAR 2003),
2003. 0-7695-1960-1/03.
4. Chang F., Chen C.-J., Lu C. A linear-time component-labeling algorithm using contour tracing technique,
Computer Vision and Image Understanding, 2004, Vol. 93, No. 2, pp. 206-220.
5. Bailey D., Johnston C. Single pass connected components analysis, Image and Vision Computing New
Zealand, 2008, pp. 282-287.
6. Johnston C., Bailey D. FPGA implementation of a single pass connected components algorithm, Electronic
Design, Test and Applications, 2008, pp. 228-231.
7. Trein J., Schwarzbacher A., Hoppe B., Noffz K.H., Trenschel T. Development of a FPGA Based Real-
Time Blob Analysis Circuit, Irish Systems and Signals Conference, 2007, pp. 121-126.
8. Walczyk R., Armitage A., Binnie T.D. Comparative study on connected component labeling algorithms
for embedded video processing systems, IPCV, 2010, Vol. 10. Available at: researchgate.net/ publication/
220808599_Comparative_Study_on_Connected_Com
ponent_Labeling_Algorithms_for_Embedded_Video_Processing_Systems.
9. Yaman S. et al. Image and Video Processing Applications Using Xilinx System Generator, 2019 7th
International Symposium on Digital Forensics and Security (ISDFS). IEEE, 2019, pp. 1-5.
10. Raut N.P., Gokhale A.V. FPGA implementation for image processing algorithms using xilinx system
generator, IOSR Journal of VLSI and Signal Processing (IOSR-JVSP), 2013, Vol. 2, No. 4, pp. 26-36.
11. Lyakhov P.A., Valueva M.V. Primenenie sglazhivayushchikh fil'trov dlya ochistki ot shuma
izobrazheniy v ottenkakh serogo [Application of anti-aliasing filters for removing noise from images
in various grayscales], Nauka. Innovatsii. Tekhnologii [Science. Innovation. Technologies], 2015,
No. 3, pp. 37-50.
12. Sghaier A. et al. FPGA implementation of filtered image using 2D Gaussian filter, International Journal
of Advanced Computer Science and Applications, 2016, Vol. 7, No. 7.
13. Bakumenko A. et al. Connected component labeling algorithm in streaming image processing with
FPGAs, SPIE Future Sensing Technologies 2021. SPIE, 2021, Vol. 11914, pp. 328-340.
14. System Generator for DSP User Guide, UG640, 14.1. April 2012.
15. Zynq UltraScale+ Devices Register Reference UG1087 (v1.8) July 30, 2021.
16. Bakumenko A. et al. Crop seed classification based on a real-time convolutional neural network, SPIE
Future Sensing Technologies. SPIE, 2020, Vol. 11525, pp. 654-667.
17. Kovalev A.V., Bakumenko A.N. Algoritm markirovki svyazannykh oblastey pri potokovoy obrabotke
izobrazheniya [Algorithm for marking connected areas during streaming image processing],
Inzhenernyy vestnik Dona [Engineering Bulletin of the Don], 2022, No. 4 (88), pp. 191-201.
18. Bakhchevnikov V.V., Derkachev V.A., Bakumenko A.N. Sposob ispol'zovaniya sredstv bystrogo
prototipirovaniya dlya realizatsii svertochnoy neyronnoy seti na PLIS [Method of using fast prototyping
tools for implementing a convolutional neural network on FPGA], Izvestiya YuFU. Tekhnicheskie
nauki [Izvestiya SFedU. Engineering Sciences], 2020, No.. 3 (213), pp. 146-156.
19. Derkachev V.A., Bakhchevnikov V.V., Bakumenko A.N. Klassifikator izobrazheniy semyan
sel'skokhozyaystvennykh kul'tur s ispol'zovaniem svertochnoy neyronnoy seti [Classifier of images of
agricultural seeds using a convolutional neural network], Izvestiya YuFU. Tekhnicheskie nauki
[Izvestiya SFedU. Engineering Sciences], 2020, No. 4 (214), pp. 32-39.
20. Bakhchevnikov V.V., Derkachev V.A., Bakumenko A.N. Metod razrabotki iskusstvennykh neyronnykh
setey dlya prototipirovaniya na PLIS s pomoshch'yu sredstv Xilinx System Generator i Matlab [Method
for developing artificial neural networks for prototyping on FPGAs using Xilinx System Generator
and Matlab], Komp'yuternye i informatsionnye tekhnologii v nauke, inzhenerii i upravlenii" KomTekh-
2020" [Computer and information technologies in science, engineering and management" KomTech -
2020"], 2020, pp. 462-468.
