Email this article 
Informative content evaluation of wild animal images based on production rules
- Authors: Favorskaya M.N.1, Natalenko D.N.1
-
Affiliations:
- Reshetnev Siberian State University of Science and Technology named after Academician M. F. Reshetnev
- Issue: Vol 32, No 1 (2026)
- Pages: 37-45
- Section: Digital processing of signals and images
- Published: 15.01.2026
- URL: https://journals.eco-vector.com/1684-6400/article/view/702343
- DOI: https://doi.org/10.17587/it.32.37-45
- ID: 702343
Cite item
Open Access
Access granted
Abstract
The wild animal images captured by camera traps often have different quality due to such artifacts as low lighting conditions, complex background, meteorological conditions, the use of low-resolution video cameras, etc. А modern solution to the problem of recognizing wild animals is the use of deep learning models that need to be trained on "good" examples. Thus, assessing the informative content of such images is in the scope of interest. Image quality factors (brightness, contrast, blurriness and weather conditions), as well as the shape and position of the animal relative to the camera trap, are taken into account. Production rules have been developed for making decisions about dividing images into classes of varying informative degrees of information content. The experiments were carried out using a data set collected in the Ergaki Natural Park, Krasnoyarskiy Kray, in 2012-2021. The average error value of the proposed method for all classes is 6.4 % relative to the expert assessment.
Full Text
About the authors
M. N. Favorskaya
Reshetnev Siberian State University of Science and Technology named after Academician M. F. Reshetnev
Author for correspondence.
Email: favorskaya@sibsau.ru
Dr. Tech. Sc., Professor
Russian Federation, KrasnoyarskD. N. Natalenko
Reshetnev Siberian State University of Science and Technology named after Academician M. F. Reshetnev
Email: dmitriy.natalenko@mail.ru
PhD Student
Russian Federation, KrasnoyarskReferences
- Fang Y., Ma K., Wang Z., Lin W., Fang Z., Zhai G. No-reference quality assessment of contrast-distorted images based on natural scene statistics, IEEE Signal Processing Letters, 2015, vol. 22, no. 7, pp. 838—842, doi: 10.1109/LSP.2014.2372333
- Li L., Lin W., Wang X., Yang G., Bahrami K., Kot А. C. No-reference image blur assessment based on discrete orthogonal moments, IEEE Transactions on Cybernetics, 2016, vol. 46, no. 1, pp. 39—50, doi: 10.1109/TCYB.2015.2392129
- Zhang M., Muramatsu C., Zhou X., Hara T., Fujita Н. Blind image quality assessment using the joint statistics of generalized local binary pattern, IEEE Signal Processing Letters, 2015, vol. 22, no. 2, pp. 207—210, doi: 10.1109/LSP.2014.2326399
- Li Q., Lin W., Xu J., Fang Y. Blind image quality assessment using statistical structural and luminance features, IEEE Transactions on Multimedia, 2016, vol. 18, no. 12, pp. 2457—2469, doi: 10.1109/TMM.2016.2601028
- Zhang W., Ma K., Yan J., Deng D., Wang Z. Blind image quality assessment using a deep bilinear convolutional neural network, IEEE Transactions on Circuits and Systems for Video Technology, 2020, vol. 30, no. 1, pp. 36—47. doi: 10.1109/TCSVT.2018.2886771
- Tang Z., Chen Y., Chen Z., Liang X., Zhang X. Q. Lightweight transformer and multi-head prediction network for no-reference image quality assessment, Neural Computing and Applications, 2024, vol. 36, no. 4, pp. 1931—1946, doi: 10.1007/s00521-023-09188-3
- Ma J., Chen Y., Chen L., Tang Z. Dual-attention pyramid transformer network for no-reference image quality assessment, Expert Systems With Applications, 2024, vol. 257, pp. 125008.1—125008.13, doi: 10.1016/j.eswa.2024.125008
- Mittal A., Soundararajan R., Bovik А. C. Making a ‘Completely blind’ image quality analyzer. IEEE Signal Processing Letters, 2013, vol. 20, no. 3, pp. 209—212, doi: 10.1109/LSP.2012.2227726
- Shannon C. E. А mathematical theory of communication. ACM SIGMOBILE Mobile Computing and Communications Review, 2001, vol. 5, no. 1, pp. 3—55. doi: 10.1145/584091.584093
- Blau Y., Michaeli T. The perception-distortion tradeoff, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, IEEE, Salt Lake City, UT, USA, pp. 6228—6237, doi: 10.1109/CVPR.2018.00652
- Zhu M., Yu L., Wang Z., Ke Z., Zhi C. Review: А survey on objective evaluation of image sharpness, Applied Sciences, 2023, vol. 13, no. 4, pp. 2652.1—2652.20, doi: 10.3390/app13042652
- Yu S., Jayi Wang J., Gu J., Jin M., Ma Y., Yang L., Li J. А hybrid indicator for realistic blurred image quality assessment, Journal of Visual Communication and Image Representation, 2023, vol. 94, pp. 103848.1—103848.9, doi: 10.1016/j.jvcir.2023.103848
- Lin W., Wu Y., Xu L., Chen W., Zhao T., Wei Н. No-reference quality assessment for low-light image enhancement: Subjective and objective methods, Displays, 2023, vol. 78, pp. 102432.1—102432.9, doi: 10.1016/j.displa.2023.102432
- Kajo I., Chahi A., Kas M., Ruichek Y. No-reference quality evaluation of realistic hazy images via singular value decomposition, Neurocomputing, 2024, vol. 610, pp. 128574.1—128574.11, doi: 10.1016/j.neucom.2024.128574
- Rajevenceltha J., Gaidhane V. H. А no-reference image quality assessment model based on neighborhood component analysis and Gaussian process, Journal of Visual Communication and Image Representation, 2024, vol. 98, pp. 104041.1—104041.13, doi: 10.1016/j.jvcir.2023.104041
- Favorskaya M., Buryachenko V. Selecting informative samples for animal recognition in the wildlife, Intelligent Decision Technologies — 2019, 2019, Springer, Singapore, SIST, vol. 143, pp. 65—75, doi: 10.1007/978-981-13-8303-8_6
- Favorskaya M. N., Natalenko D. N. Informative evaluation of images captured by camera traps based on production rules: Invited paper, Advanced Intelligent Technologies and Sustainable Society — ICAIT 2023, 2024, Springer, Singapore, SIST, vol. 391, pp. 3—18, doi: 10.1007/978-981-97-3210-4_1
- Bahrami K., Kot A. C. А fast approach for no-reference image sharpness assessment based on maximum local variation, IEEE Signal Processing Letters, 2014, vol. 21, pp. 751—755, doi: 10.1109/LSP.2014.2314487
- Yan X., Luo Y., Zheng X. Weather recognition based on images captured by vision system in vehicle, Advances in Neural Networks — ISNN 2009, 2009, Springer, Berlin, Heidelberg, LNCS, vol. 5553, pp. 390—398, doi: 10.1007/978-3-642-01513-7_42
Supplementary files
Supplementary Files
Action
1.
JATS XML
2.
Fig. 1. Examples of images: a — informative in daytime; b — informative at night; c — non-informative (with various artifacts) in daytime; d — non-informative at night
Download (335KB)
3.
Fig. 2. Examples of original images and their brightness histograms: a — dark image; b — bright image; c — image with a dark fragment; d — image with a light fragment; e, f — images without artifacts
Download (381KB)
4.
Fig. 3. Examples of original images and their gradient graphs: a — blurred image; b — sharp image; c, d — images without artifacts
Download (292KB)
5.
Fig. 4. Examples of original images and their gradient graphs: a — fog; b — snowfall; c, d — images without artifacts
Download (333KB)
6.
Fig. 5. Examples of detection: a — one animal; b — several animals; c — detection of head and body; d — detection of body
Download (199KB)
7.
Fig. 6. Training results of the first YOLOv8 medium model: a — object loss; b — classification loss; c — precision; d — recall; e — mAP50; f — mAP50-95
Download (1MB)
8.
Fig. 7. Training results of the second YOLOv8 medium model: a — object loss; b — classification loss; c — precision; d — recall; e — mAP50; f — mAP50-95
Download (1MB)
