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{206598,
        author = {Mohan Jattayya Devadiga and Chinthan Rai Kukkuvalli and Shvesh C Kottary and Frewin Johan Fernande},
        title = {Object Detection in Real Time Using MobileNet for SSD Model},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {94-98},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206598},
        abstract = {The development of machine learning models capable of identifying and locating multiple objects in a single image has proven to be a challenging task in computer vision. Object detection is one of the most prominent domains in deep learning, given its ability to learn features automatically. This paper presents a real-time object detection system that combines the Single Shot Multibox Detector (SSD) framework with the MobileNet lightweight convolutional neural network architecture. The proposed system accepts input from static images, pre-recorded video files, and live webcam streams, processing each frame through a pre-trained SSD MobileNet V3 model trained on the COCO dataset with over 80 object categories. The system accurately detects and classifies multiple objects per frame, drawing bounding boxes and assigning class labels with confidence scores. Experimental results demonstrate that SSD-based models with MobileNet achieve faster inference compared to Faster R-CNN while maintaining reasonable accuracy, making the system suitable for deployment on standard hardware. The application features a Tkinter-based graphical user interface for ease of use. Quantitative analysis shows the model processes 300×300 images at approximately 59 frames per second, confirming real-time capability. The proposed system provides an efficient, lightweight, and practical solution for real-time object detection suitable for applications in surveillance, traffic monitoring, and smart device integration.},
        keywords = {Object Detection, MobileNet, Single Shot Detector (SSD), Deep Learning, Real-Time Detection, TensorFlow, Computer Vision, Bounding Box, COCO Dataset.},
        month = {July},
        }