Authors : Vasireddy Surya; Rooma Tyagi; Vineel Sai Kumar Rampally; Vivek Rajah; Shirish Kumar Gonala

Volume/Issue : Volume 10 - 2025, Issue 4 - April

Google Scholar : https://tinyurl.com/jwk3ymd9

Scribd : https://tinyurl.com/yjdch52p

DOI : https://doi.org/10.38124/ijisrt/25apr1626

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : Store businesses face a persistent challenge in ensuring that shelves are adequately stocked and products are available for customers all the time on racks. manual checks are inefficient and often leads to delay in stock refilling, this leads to customer dissatisfaction and potential loss of sales. To address this, we propose an AI-based smart monitoring system, designed for real-time detection of products displayed on racks. This solution is a low-cost design and can be deployed as an on-premise system. The solution uses yolo model trained on customized data to detect the products and classify them into three simple categories: in stock, low stock, and out of stock. This classification triggers timely alert notifications to staff members which leads to accelerated restocking procedures and enhanced shelf maintenance. This solution is built to be scalable and easy to integrate with a dashboard of stock inventory management. This system ensures minimum operational cost while offering significant improvements in inventory management. By automating the kiosk display monitoring system, the solution helps to improve the stock refill at right time without any delay ultimately changing a traditional manual method with smart ai powered automated stock-check methods. The system includes real-time image acquisition and YOLO-based model inference as well as a strong data collection and preprocessing module to provide high-quality input for model training and deployment. The stored images undergo preprocessing steps including resizing and normalization and augmentation to boost model accuracy before being placed in a centralized database. Items are divided into in-stock, low-stock, and out-of-stock divisions by the decision engine using predetermined stock thresholds. Using visual displays on kiosk screens, voice signals for prompt staff action, and email notifications for shop manager inventory tracking, the system creates multi-modal warnings. The closed-loop system enables proactive shelf replenishment which decreases stockout occurrences while enhancing customer satisfaction.

Keywords : AI-Based Smart Monitoring, Stock Classification, Proactive Replenishment, Inventory Management, Real-Time Monitoring, Low-Cost Design, Stock Management, Kiosk Display.

References :

1. Redmon, J., & Farhadi, A. (2018). YOLOv3: An Incremental Improvement. ArXiv, abs/1804.02767.Ultralytics. (2023).
2. YOLOv8 Official Documentation. https://docs.ultralytics.com/
3. OpenCV. (2023). Image Processing Guide: OpenCV 4.x Documentation. https://docs.opencv.org/4.x/d2/d96/tutorial_py_table_of_contents_imgproc.html
4. Lin, T.-Y., Maire, M., Belongie, S., Hays, J., et al. (2014). Microsoft COCO: Common objects in context. arXiv preprint, arXiv:1405.0312.
5. Ultralytics. (2023). YOLOv8 GitHub Repository. https://github.com/ultralytics/ultralytics
6. TensorFlow. (2023). Object Detection API Tutorial. https://tensorflow-object-detection-api-tutorial.readthedocs.io/
7. HumanSignal. (2023). LabelImg: Image Annotation Tool. https://github.com/HumanSignal/labelImg
8. Roboflow. (2023). Image Augmentation for Computer Vision. https://docs.roboflow.com/datasets/image-augmentation
9. NVIDIA. (2023). AI in Retail and Stores – Case Studies. https://www.nvidia.com/en-us/case-studies/
10. McKinsey & Company. (2023). LLM to ROI: How to scale Gen AI in retail. https://www.mckinsey.com/industries/retail/our-insights/llm-to-roi-how-to-scale-gen-ai-in-retail
11. Deloitte. (2025). Retail Industry Outlook 2025. https://www2.deloitte.com/us/en/insights/industry/retail-distribution/retail-distribution-industry-outlook.html
12. IBM. (2023). AI in Retail Transformation. https://www.ibm.com/think/topics/ai-in-retail
13. Harvard Business Review. (2000). Control your inventory in a world of lean retailing. https://hbr.org/2000/11/control-your-inventory-in-a-world-of-lean-retailing
14. Jose, John Anthony & Bertumen, Christopher & Roque, Marianne & Umali, Allan Emmanuel & Villanueva, Jillian Clara & TanAi, Richard & Sybingco, Edwin & San Juan, Jayne Lois & Gonzales, Erwin Carlo. (2024). Smart Shelf System for Customer Behavior Tracking in Supermarkets. Sensors. 24. 367. 10.3390/s24020367.
15. Pietrini, Rocco & Paolanti, Marina & Mancini, Adriano & Frontoni, Emanuele. (2024). Shelf Management: A deep learning-based system for shelf visual monitoring. Expert Systems with Applications. 255. 124635. 10.1016/j.eswa.2024.124635.
16. NVIDIA. (2023). AI Solutions in the Retail Industry. https://www.nvidia.com/en-us/industries/retail/
17. McKinsey & Company. (2023). Harnessing the power of AI in distribution operations. https://www.mckinsey.com/industries/industrials-and-electronics/our-insights/harnessing-the-power-of-ai-in-distribution-operations
18. Deloitte. (2023). Global Retail Trends. https://www.deloitte.com/nl/en/Industries/retail/perspectives/retail-trends.html
19. P S, Harish. (2023). COMPUTER VISION (AI) BASED RETAILER SHELVES MONITORING SYSTEM TO NOTIFY EMPTY SHELVES | HARISH KUMAR. 10.13140/RG.2.2.30549.60649.
20. William Villegas-Ch, Alexandra Maldonado Navarro, Santiago Sanchez-Viteri, Optimization of inventory management through computer vision and machine learning technologies, Intelligent Systems with Applications, Volume 24, 2024, 200438, ISSN 2667-3053, https://doi.org/10.1016/j.iswa.2024.200438.