Home / Current Issue / Paper 1713245
SmartView: AI-Based Object Detection System
Subject area: Science,Engineering and Technology · Area of research: Machine Learning, Deep Learning
DOI: https://doi.org/10.64388/IREV9I7-1713245
Abstract
Recent advancements in computer vision have enabled automated systems to identify and localize multiple objects efficiently across diverse visual inputs. This paper presents Smart-view, an AI-based multi-source object detection system designed for both real-time and offline visual analysis. The system integrates the YOLOv8 deep learning model with a Flask-based web framework to support object detection from images, prerecorded videos, live webcam streams, and online video sources such as YouTube. Supporting tools including Open CV and FFMPEG are employed for frame acquisition, prepossessing and video conversion. To enhance usability, computationally intensive tasks are executed asynchronously, ensuring a responsive user interface. Detected objects are visually annotated and systematically logged in structured CSV format for further analysis. The proposed system demonstrates that efficient and scalable object detection can be achieved using lightweight models on CPU-based environments.
Keywords
Object Detection, YOLOv8, Computer Vision, Flask, Real-Time Processing, AI Applications.
How to cite this paper
@article{1713245,
author = {C M Sumana, Subani D, Alur Muskan Mahek, N Lakshmi, V. Ashwini},
title = {SmartView: AI-Based Object Detection System},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {7},
pages = {63-67},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1713245.pdf},
abstract = {Recent advancements in computer vision have enabled automated systems to identify and localize multiple objects efficiently across diverse visual inputs. This paper presents Smart-view, an AI-based multi-source object detection system designed for both real-time and offline visual analysis. The system integrates the YOLOv8 deep learning model with a Flask-based web framework to support object detection from images, prerecorded videos, live webcam streams, and online video sources such as YouTube. Supporting tools including Open CV and FFMPEG are employed for frame acquisition, prepossessing and video conversion. To enhance usability, computationally intensive tasks are executed asynchronously, ensuring a responsive user interface. Detected objects are visually annotated and systematically logged in structured CSV format for further analysis. The proposed system demonstrates that efficient and scalable object detection can be achieved using lightweight models on CPU-based environments.},
keywords = {Object Detection, YOLOv8, Computer Vision, Flask, Real-Time Processing, AI Applications.},
month = {January},
doi = {https://doi.org/10.64388/IREV9I7-1713245}
}