Authors : Kunal G. Borase; Sowmiya R; Bharani Kumar Depuru

Volume/Issue : Volume 10 - 2025, Issue 3 - March

Google Scholar : https://tinyurl.com/mu59pfwx

Scribd : https://tinyurl.com/39veyweu

DOI : https://doi.org/10.38124/ijisrt/25mar1269

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 : Nowadays, keeping track of inventory accurately is a big challenge in warehouses, especially when dealing with large-scale pallet production. Traditional methods like manual counting can lead to errors, such as incorrect counts, causing inefficiencies and delays in order fulfillment. These issues not only slow down operations but also increase costs and impact the entire supply chain. This paper implements an high level solution deploying AI-powered system using deep learning and computer vision to accurately count stacked pallets in real-time, improving inventory management and operational efficiency to develop a reliable detection system, extensive data collection was carried out in warehouse settings capturing pallet images under different conditions the dataset was carefully labeled using polygon-based annotations via an open source annotation tool roboflow with extensive facilities for augmentations. To ensure precise object detection various data augmentation techniques such as shear, exposure, noise, blur, grayscale, horizontal flip, saturation, rotation and brightness adjustments were applied to improve model robustness against real-world variations For real-time and high-accuracy pallet detection and counting , YOLO (You Only Look Once) object detection models like YOLOv8, YOLOv9, and YOLO11 were used for training and optimization. These models offered fast inference speeds, ensuring low latency while maintaining high detection precision. A comparative analysis of different YOLO versions provided insights into model performance, accuracy, and efficiency. The optimized model was implemented in a warehouse setting and connected to a real-time monitoring system, enabling automatic pallet counting and reducing manual effort and errors. This research highlights the Switching from traditional inventory management to an AI-powered system, presenting how deep learning can enhance precision, minimize human mistakes, and cut operational expenses. By implementing an AI-driven vision system, Businesses can optimize supply chain processes, enhance order accuracy, and implement scalable warehouse automation.

Keywords : Pallet Detection and Counting, Object Detection, Annotations, YOLOv8, YOLOv9, YOLO11, Deep Learning, Computer Vision, Warehouse Automation, Inventory Management.

References :

1. Ishwari Sidwadkar, Pranjali Bandgar, Akshada Khadke, Tahesin Pathan, Prof S. R. Bhujbal  People Counting, Capturing Image Using YOLO Deep Learning Algorithm    https://www.jetir.org/papers/JETIR2404784
2. Mupparaju Sohan1, Thotakura SaiRam, and Ch. Venkata RamiReddy. A Review on YOLOv8 and Its Advancements. DOI:10.1007/978-981-99-7962-2_39
3. Ning Kang, Fangyu Ma, Wenkang Wan, Daihan Wang, Hua Yao, Kai Sheng. Improved YOLOv9-Based Objects Detection in Adverse Weather Conditions for Autonomous driving. https://doi.org/10.1016/j.ifacol.2024.11.155
4. Rahima Khanam and MuhammadHussain ,YOLO11: An Overview of the Key Architectural Enhancements. https://arxiv.org/abs/2410.17725
5. Stefan Studer , Thanh Binh Bui , Christian Drescher , Alexander Hanuschkin , Ludwig Winkler  , Steven Peters  and Klaus-Robert Müller Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodology .  https://doi.org/10.3390/make3020020
6. Prof. P. D. Kale, Comparative Analysis of Image Annotation Tools: LabelImg, VGG Annotator, Label Studio, And Roboflow", International Journal of Emerging Technologies and Innovative Research. https://www.jetir.org/papers/JETIR2405D59
7. Praneeth Yennamaneni; Vickram R; Samyak Sabannawar; SreePriya Naroju; Bharani Kumar Depuru ,Improving Warehouse Efficiency Through Automated Counting of Pallets: YOLOv8-Powered Solutions. https://doi.org/10.5281/zenodo.10276587
8. Fatma Betül Kara ArdaÇ; Pakize Erdogmus. Car Object Detection: Comparative Analysis of YOLOv9 and YOLOv10 Models. DOI: 10.1109/ASYU62119.2024.10756955
9. Mingming Zhang,Shutong Ye,Shengyu Zhao,Wei Wang andChao Xie. Pear Object Detection in Complex Orchard Environment Based on Improved YOLO11. https://doi.org/10.3390/sym17020255.
10. Himangi Dani, Pooja Bhople, Hariom Waghmare, Kartik Munginwar, Prof. Ankush Patil Review on Frameworks Used for Deployment of Machine Learning Model https://doi.org/10.22214/ijraset.2022.40222