A Computer Vision Based Approach for Real Time Classification and Placement

View at publisher Summarise with VIRAT
Authors: Vishwa Priya R.V, Ladson Samuel Newton, H. Prasanth S., Kavishvar S, Niranjan Sankar R
Cited by: 0
References: 1

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper explains a ball sorting system that uses computer vision and a robot arm. A YOLOv8 model is trained to detect red, green, and blue balls. The model is tested with images and a live camera feed to make sure it works in real time. A conveyor belt moves the balls to a fixed pickup point. A camera above the conveyor captures the image of the ball. The YOLOv8 model identifies the color of the ball. The system then sends commands to a robot arm in RoboDK. The robot picks the ball from the pickup point and places it into the basket that matches its color. The system is made using Python, YOLOv8, OpenCV, and the RoboDK API. The results show that the robot can detect and sort balls correctly.

Fields of Study & Subjects

Robot Manipulation and Learning Advanced Neural Network Applications Industrial Vision Systems and Defect Detection

Publication details

Journal / source
International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS)
Pages
1–4
Publication date
8 January 2026
Language
EN