Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{191910,
        author = {P.Anupama},
        title = {“An Efficient Deep Learning Model for Real-Time Object Detection Applications”},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {8525-8531},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191910},
        abstract = {Real-time object detection has become a cornerstone of modern computer-vision applications, including intelligent surveillance, autonomous navigation, smart agriculture and public-safety systems. However, achieving high detection accuracy alongside low latency and reduced computational cost remains a significant challenge, particularly for deployment on resource-constrained edge devices. This paper presents an efficient deep learning–based object detection model designed specifically for real-time applications. The proposed approach integrates a lightweight feature-extraction backbone with an optimised multi-scale feature fusion mechanism and an anchor-free detection head to balance speed and accuracy effectively. To further enhance efficiency, the model employs transfer learning, knowledge distillation and quantisation-aware training, enabling faster inference with minimal performance degradation. Experimental evaluation on standard benchmark datasets, supplemented with regionally relevant data from Indian contexts, demonstrates that the proposed model achieves competitive mean Average Precision while maintaining high frame rates suitable for real-time deployment. The findings indicate that the model is well suited for practical applications on edge devices and offers a scalable solution for real-time object detection in diverse and dynamic environments.},
        keywords = {Real-time object detection; YOLO; EfficientDet; edge inference; lightweight backbone; Andhra Pradesh; India; quantisation; knowledge distillation.},
        month = {January},
        }