VisionX: An End-To-End Object Detection Platform Using YOLO And React

Dulam Rohit Sai Anjan , Puli Bhanu Kiran , Kodi Karthikaya , Velaga Rudra Bharath

Object Detection, YOLOv8, Computer Vision, Deep Learning, Real-Time Detection, React, Flask, Web-Based System, Surveillance Systems, Machine Learning.

Object detection is an important issue in computer vision. It enables computers to find objects in images and video streams automatically. This capability is crucial for many applications, including surveillance systems, self-driving cars, medical imaging, and automation. Traditionally, object detection relies on complex processes that involve proposing objects, extracting features, and classifying them. These processes can be resource-intensive. Recently, the field has progressed with the introduction of single-stage object detectors like YOLO (You Only Look Once). These detectors have significantly increased the speed of object detection while keeping accuracy high. This paper introduces a new object detection framework called VisionX. VisionX is a web-based system that uses deep learning object detectors and modern web technologies. Its goal is to create a unified framework for various object detection applications. The framework uses YOLOv8 for object detection. It supports multiple input sources, including images, video streams, and webcam feeds. VisionX is built with React for the frontend and Flask for the backend. It includes key features such as object model selection, dataset management, real-time detection, filtering objects based on confidence levels, and identifying suspicious objects for security purposes. The system processes input data through a series of steps, including data preprocessing, object detection with YOLOv8, filtering results, and visualizing the objects. Experimental results indicate that this object detection framework is effective in terms of accuracy and speed. It effectively connects machine learning object detectors with user applications. VisionX can be applied in various scenarios, such as surveillance systems, smart object monitoring, and AI-driven automation.

Volume 14 Issue 4, April-2026

Pages : a222-a231