ALGORITHM FOR PRE-PROCESSING VIDEO IMAGES TO INCREASE THE ACCURACY OF SMALL OBJECT DETECTION
Abstract
Recognition of certain patterns in video images captured by a camera is carried out using
training methods based on convolutional neural networks. The larger the number of images with
multiple features and the more diverse the training sample of video images, the better the convolutional
neural networks extract features from the sequence of video images that were not included in
the training sample. This is a consequence of increasing the accuracy of detecting visual images on
video images containing features of target images. However, there are limitations in improving the
detection performance when the size of the image to be detected is much smaller than the background
area, or when the image is described with little information. To solve problems of this kind, the authors
of the article have developed an algorithm for the spatio-temporal integration of information
about the movement of dynamic images. The algorithm processes a fixed number of video images at
certain points in time and extracts new independent signs of motion of dynamic images based on
space-time processing of video images. Further, it combines new local motion features with the original
video image features. This allows you to add a motion feature of dynamic images while preserving
the original image features that describe static images. Areas of the video image that characterize
the motion feature are displayed in a «color» cluster. The use of pre-processing is aimed at improving the accuracy of pattern detection, provided there are dynamic visual images on a static background.
If the camera is in scan mode, a static background can be provided with a video stabilizer.
Experimentally, estimates of integral criteria for the accuracy of detection neural network algorithms
have been obtained, showing an increase in the accuracy of detecting visual images using
the algorithm for spatial-temporal integration of motion information.
References
and Techniques to Build Intelligent Systems. O'Reilly Media, 2017, 572 p.
2. Vapnik V.N. CHervonenkis A.Ya. Teoriya raspoznavaniya obrazov (statisticheskie problemy
obucheniya) [Pattern recognition theory (statistical learning problems)]. Moscow: Nauka,
1979, 416 p.
3. Senin A.G. Raspoznavanie sluchaynykh signalov [Recognition of random signals]. Novosibirsk:
Nauka, 1974, 76 p.
4. Arkad'ev A.G., Braverman E.M. Obuchenie mashiny raspoznavaniyu obrazov [Learning a
machine for pattern recognition]. Moscow: Izd-vo «Nauka», 1964.
5. Vasil'ev V.I. Raspoznayushchie sistemy [Recognition systems]. Kiev: Naukova dumka, 1983,
422 p.
6. Verkhagen K., Deyn R., Grun F. i [dr]. Raspoznavanie obrazov. Sostoyanie i perspektivy [Pattern
Recognition. State and prospects]. Moscow: Radio i svyaz', 1985, 104 p.
7. Alpatov B.A., Babayan P.V., Balashov O.E., Stepashkin A.I. Metody avtomaticheskogo
obnaruzheniya i soprovozhdeniya ob"ektov. Obrabotka izobrazheniy i upravlenie [Methods for
automatic detection and tracking of objects. Image processing and control]. Moscow:
Radiotekhnika, 2008, 176 p.
8. Zagoruyko N.G. Klassifikatsiya zadach raspoznavaniya obrazov [Classification of pattern
recognition problems], Vychislitel'nye sistemy [Computing systems], Issue 22. Novosibirsk,
1966.
9. Gansales R., Vuds R. Tsifrovaya obrabotka izobrazheniy [Digital image processing]. Moscow:
Tekhnosfera, 2005, 1012 p.
10. Fisenko V., Fisenko T. Komp'yuternaya obrabotka i raspoznavanie izobrazheniy: ucheb.
posobie [Computer processing and image recognition: textbook]. Saint Petersburg
SPbGUITMO, 2008, 192 p.
11. Redmon J., Farhadi A. YOLOv3: An Incremental Improvement, arXiv, 2018. Available at:
https://arxiv.org/abs/1804.02767v1.
12. Brkic K. An overview of traffic sign detection methods, Zagreb: Department of Electronics,
Microelectronics, Computer and Intelligent Systems, Faculty of Electrical Engineering and
Computing, 2010, 9 p.
13. Dumoulin V., Visin F. A guide to convolution arithmetic for deep learning, arXiv, 2018. Available
at: https://arxiv.org/abs/1603.07285v2.
14. LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D.
Backpropagation applied to handwritten zip code recognition, Neural Computation, 1989, 1:4,
pp. 541-551.
15. Rashid M., Vinu T. A Background Foreground Competitive Model for Background Subtraction
in Dynamic Background, Procedia Technology, 2016, Vol. 25, pp. 536-543.
16. Zivkovic Z. Improved adaptive gaussian mixture model for background subtraction, Proc. of
the 17th Intern. Conf. on Pattern recognition. ICPR 2004. IEEE, 2004, Vol. 2, pp. 28-31.
17. Buryachenko V. Metody stabilizatsii videoposledovatel'nostey slozhnykh staticheskikh i
dinamicheskikh stsen v sistemakh videonablyudeniya: avtoref. dis. … kand. tekh. nauk [Methods
of stabilization of video sequences of complex static and dynamic scenes in video surveillance
systems: abstract cand. of eng, sc, diss.]. Krasnoyars, 2014, pp. 23-24.
18. Van Etten A. Satellite imagery multiscale rapid detection with windowed networks, In 2019
IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, pp. 735-743.
19. Ze L., Yutong L., Yue C. Swin Transformer: Hierarchical Vision Transformer using Shifted
Windows, arXiv, 2021. Available at: https://arxiv.org/abs/2103.14030.
20. Tsung-Yi L., Michael M., Serge B. Microsoft COCO: Common Objects in Context. arXiv,
2015, Available at: https://arxiv.org/abs/1405.0312.
21. Shorten C., Khoshgoftaar T. A survey on Image Data Augmentation for Deep Learning, J Big
Data, 2019, 6: 60.
22. The Effectiveness of Data Augmentation in Image Classification using Deep Learning.
23. Wang J., Perez L. The Effectiveness of Data Augmentation in Image Classification using Deep
Learning, arXiv, 2017. Available at: https://arxiv.org/abs/1712.04621v1.
