METHODOLOGICAL SUPPORT FOR ASSESSING THE AVAILABILITY OF GOODS IN DISTRIBUTED STORAGE BASED ON COMPUTER VISION METHODS
DOI:
https://doi.org/10.18522/2311-3103-2026-1-%25pKeywords:
Product monitoring, storage systems, computer vision, convolutional neural networks, machine learningAbstract
This paper presents a formalization of the problem of automated monitoring of product availability on retail shelves and compliance with the prescribed planogram, leveraging computer vision and machine learning techniques. The aim of this research is to develop algorithmic solutions for the automatic assessment of product availability in distributed retail environments using computer vision methods, thereby addressing the challenge of maintaining optimal and necessary product assortments through continuous shelf monitoring and supporting data-driven managerial decision-making. A technological pipeline for visual data processing is proposed, comprising the stages of image normalization, segmentation, object localization, and classification, implemented with convolutional neural networks—specifically YOLO and U-Net architectures. An integrated product availability metric is introduced, which jointly accounts for physical, visual, and informational dimensions of availability. An optimization problem aimed at improving overall availability is formulated, and an adaptive neural network fine-tuning mechanism is implemented to enhance the accuracy of image recognition and segmentation, as well as the quality of analytical recommendations. Furthermore, an availability-improvement algorithm is proposed for a decision support system, based on the construction of an optimized merchandiser routing plan that prioritizes products and minimizes time expenditures. This routing problem is reduced to a generalized Traveling Salesman Problem (TSP) with priority-based weights. Methods for evaluating and enhancing product availability are proposed and described in detail. Based on the developed approaches and algorithms, a software system for monitoring and improving product availability has been implemented. Experimental results confirm the effectiveness of the proposed solutions: the average recognition accuracy reached 95.8%, and the integrated availability score achieved A = 0.93. The practical significance of this work lies in establishing an algorithmic foundation for intelligent shelf-monitoring systems that enable more efficient management of retail operations and inventory processes
References
1. Tiwari Tanya & Tiwari Tanuj & Tiwari Sanjay. How Artificial Intelligence, Machine Learning and Deep Learning are Radically Different?, International Journal of Advanced Research in Computer Sci-ence and Software Engineering, 2018, 8(2):1, 10.23956/ijarcsse.v8i2.569.
2. Mehwish Saqlain, Saddaf Rubab, Malik M. Khan, Nouman Ali, Shahzeb Ali. Hybrid Approach for Shelf Monitoring and Planogram Compliance (Hyb-SMPC) in Retails Using Deep Learning and Computer Vision, Mathematical Problems in Engineering, 2022, No. 1. Available at: https://doi.org/10.1155/2022/4916818.
3. Jorge Muñoz, Alonso Sanchez, Guillermo Kemper. End-to-end solution for automatic beverage stock detection in supermarkets based on image processing and convolutional neural networks, International Journal of Cognitive Computing in Engineering, 2024, No. 5, pp. 453-474. Available at: https://doi.org/10.1016/j.ijcce.2024.09.001.
4. Wei Yuchen, Tran Son, Xu Shuxiang, Kang Byeong, Springer Matthew. Deep Learning for Retail Prod-uct Recognition: Challenges and Techniques, Computational Intelligence and Neuroscience, 2020, 8875910, pp. 1-23. Available at: https://doi.org/10.1155/2020/8875910.
5. Gothai E. et al. Design features of grocery product recognition using deep learning, Intelligent Automa-tion and Soft Computing, 2022, Vol. 34, No. 2, pp. 1231-1246.
6. Reynkhard Klette. Komp'yuternoe zrenie. Teoriya i algoritmy [Computer vision. Theory and algorithms]: transl. from Engl. by A.A. Slinkin. Moscow: DMK Press, 2019, 506 p.
7. Yolo Data Augmentation, 2025. Available at: https://docs.ultralytics.com/guides/yolo-data-augmentation (accessed 02 May 2025).
8. Surono Sugiyarto & Rivaldi Muhammad & Arrova Dewi Deshinta & Irsalinda Nursyiva. New Ap-proach to Image Segmentation: U-Net Convolutional Network for Multiresolution CT Image Lung Seg-mentation, Emerging Science Journal, 2023, 7, pp. 498-506. 10.28991/ESJ-2023-07-02-014.
9. YOLOv9 Architecture Explained. Available at: https://stunningvisionai.com/article/yolov9-architecture (accessed 02 May 2025).
10. Desai Miral & Mewada Hiren & Pires Ivan & Roy Sparsh. Evaluating the Performance of the YOLO Object Detection Framework on COCO Dataset and Real-World Scenarios, Procedia Computer Science, 2024, 251, pp. 157-163. 10.1016/j.procs.2024.11.096.
11. Wang Decheng & Chen Xiangning & Yi Hui & Zhao Feng. Improvement of Non-Maximum Suppres-sion in RGB-D Object Detection, IEEE Access, 2019, Vol. 7. 10.1109/ACCESS.2019.2945834.
12. Bondarenko V.A., Gessen P.A., Pavlova V.A., Sozinova M.V., Tupikov V.A. Algoritm obnaruzheniya ob"ektov dlya optiko-elektronnykh sistem s obucheniem v real'nom vremeni [Object detection algorithm for optoelectronic systems with online learning], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2021, No. 1 (218).
13. Brink Kh., Richards D., Feverolf M. Mashinnoe obuchenie [Machine learning]. St. Petersburg: Piter, 2017, 336 p.
14. Said K & Jambek Asral. Analysis of Image Processing Using Morphological Erosion and Dilation, Journal of Physics: Conference Series, 2021, 2071(1):012033. 10.1088/1742-6596/2071/1/012033
15. Santra Bikash & Ghosh Udita & Mukherjee Dipti. Graph-based Modelling of Superpixels for Automat-ic Identification of Empty Shelves in Supermarkets, Pattern Recognition, 2022, 127(2): 108627. 10.1016/j.patcog.2022.108627.
16. Liu Song & Li Wanqing & Davis Stephen & Ritz Christian & Tian Hongda. Planogram Compliance Checking Based on Detection of Recurring Patterns, IEEE MultiMedia, 2016, Vol. 23, pp. 54-63. 10.1109/MMUL.2016.19.
17. Barkalov S.A., Karpovich M.A., Moiseev S.I. Metod analiza ierarkhiy: podkhod, osnovannyy na teorii latentnykh peremennykh [Hierarchy analysis method: an approach based on latent variable theory], Vest-nik YuUrGU. Seriya: Komp'yuternye tekhnologii, upravlenie, radioelektronika [Bulletin of SUSU. Se-ries: Computer Technologies, Control, Radio Electronics], 2022, No. 2.
18. Matai Rajesh & Singh Surya & Mittal M.L. Traveling Salesman Problem: an Overview of Applications, Formulations, and Solution Approaches, 2010. 10.5772/12909.
19. Cal Murat & Ekici Ali. Solving a Modified TSP Problem by a Greedy Heuristic for Cost Minimization, International Journal of Modeling and Optimization, 2018, 8, pp. 138-144. 10.7763/IJMO.2018.V8.638.
20. Nedvigin A.R., Sinetskiy R.M. Primenenie algoritmov obrabotki izobrazheniy svertochnykh neyronnykh setey v kachestve osnovy dlya razrabotki sistemy podderzhki prinyatiya resheniya [Application of image processing algorithms of convolutional neural networks as a basis for developing a decision support sys-tem], Izvestiya vuzov. Severo-Kavkazskiy region. Seriya: Tekhnicheskie nauki [Bulletin of Higher Edu-cational Institutions. North Caucasus Region. Technical Sciences], 2025, No. 1.
21. Nedvigin A.R., Sinetskiy R.M. Svidetel'stvo o gosudarstvennoy registratsii programmy dlya EVM
№ 2025664496 Rossiyskaya Federatsiya. Kompleksnaya otsenka dostupnosti tovarov s ispol'zovaniem tekhnologiy komp'yuternogo zreniya Riteyl-Diagnost. Servernaya chast'. Versiya 1.0 [Certificate of State Registration of a Computer Program No. 2025664496, Russian Federation. Comprehensive Assessment of Product Availability Using Computer Vision Technologies – Retail-Diagnost. Server Side. Version 1.0]; Filed on: 15.05.2025; Registered on: 04.06.2025
