Authors : U. Anjineyalu; Subhasree D. C.; Dr. Girish Kumar D.

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/4cn4zkvf

Scribd : https://tinyurl.com/37y3yjer

DOI : https://doi.org/10.38124/ijisrt/26apr2519

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

Abstract : Real-time Object detection systems often lose accuracy when handling low-resolution or visually degraded video, a common issue in real-world monitoring environments. This paper introduces FocusFusionNet, a super-resolution assisted object detection framework developed for both real- time processing and offline video analysis. The proposed approach combines a deep learning–based object detector with an optional super- resolution preprocessing stage that enhances visual quality before detection. FocusFusionNet supports live camera feeds as well as prerecorded video, enabling reliable multi-class object detection with frame-level tracking and confidence scoring. A graphical user interface is provided to allow intuitive video playback, object filtering, and visualization of detection statistics. Experimental evaluations indicate that super-resolution preprocessing improves detection stability in low-quality video while keeping computational costs low. The framework maintains performance levels suitable for real-time use. Overall, FocusFusionNet offers a practical and adaptable solution for intelligent video monitoring applications.

Keywords : FocusFusionNet, Super-Resolution Enhancement, Real-Time Object Detection, YOLOv8, Video Analytics System, Deep Learning–Based Vision, Low-Resolution Video Processing, Computer Vision Applications, Intelligent Video Monitoring, GUIBased Detection Framework.

References :

1. K. Srinivasan and R. Balaji, “Design of an interactive video-based object detection system using deep learning models,” International Journal of Computer Vision and Applications, vol. 14, no. 2, pp. 55–66, 2021.
2. P. Malhotra and S. Kulkarni, “Real-time object detection in video streams using YOLO architectures,” Journal of Artificial Intelligence Research and Applications, vol. 9, no. 1, pp. 18–27, 2022.
3. A. Choudhary, V. Nair, and M. Joseph, “Deep learning- driven video analytics for multi-object detection and tracking,” International Journal of Advanced Computing Systems, vol. 13, no. 4, pp. 201–210, 2021.
4. S. Iqbal and T. Rahman, “Efficient implementation of convolutional neural networks for real-time visual recognition,” Journal of Machine Learning Techniques, vol. 8, no. 3, pp. 112–121, 2020.
5. R. Menon and P. Das, “Graphical user interface design for AI-powered computer vision applications,” International Journal of Human–Computer Interaction in Computing, vol. 6, no. 2, pp. 44–52, 2022.
6. L. Fernandez and J. Kim, “Enhancing object detection accuracy in low-resolution video using super-resolution techniques,” Journal of Image and Video Processing, vol. 2021, no. 17, pp. 1–11, 2021.
7. M. Zhao, H. Li, and Y. Wang, “Performance analysis of YOLO-based models for real-time video object detection,” International Journal of Intelligent Vision Systems, vol. 10, no. 1, pp. 29–38, 2023.
8. S. Patel and A. Roy, “Data logging and visualization strategies for video analytics systems,” Journal of Data Engineering and Intelligent Systems, vol. 7, no. 3, pp. 95– 104, 2022.
9. N. Verma and K. Shinde, “Design considerations for scalable computer vision applications using Python,” International Journal of Software and AI Systems, vol. 11, no. 2, pp. 61–70, 2021.
10. J. Park and D. Lee, “A comprehensive survey on deep learning-based object detection in video surveillance,” International Journal of Smart Computing and Vision, vol. 12, no. 4, pp. 215–226, 2023.