Smart Night Vision Object Detection Using Yolov11 and Machine Learning with Real-Time Streamlit Interface for Surveillance

View at publisher Summarise with VIRAT
Authors: P. Pavan Kumar Reddy, Julia Punitha Malar Dhas, Deva Priya Isravel
Cited by: 0
References: 14

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

Night-time surveillance systems face significant challenges in object detection due to poor illumination, noise, and reduced contrast, which degrade the accuracy of traditional computer vision models. This paper presents a Smart Night Vision Object Detection System that integrates the YOLOv11 deep learning model with real-time machine learning-based distance estimation and a Streamlit interface for live monitoring. The proposed system enhances low-light visibility using preprocessing techniques such as gamma correction, CLAHE, and denoising before performing detection and classification through YOLOv11. The model identifies objects such as people and vehicles, estimates their distance using bounding box dimensions, and categorizes them into Safe, Warning, or Danger zones. Real-time alerts are triggered through email or SMS when objects enter the danger threshold. Experimental evaluation demonstrates the model's effectiveness, achieving 90% mean average precision, 92% precision, and 91% recall on night-vision surveillance data. This system provides an efficient and practical solution for intelligent security surveillance in low-light environments.

Fields of Study & Subjects

Advanced Neural Network Applications Video Surveillance and Tracking Methods Fire Detection and Safety Systems

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
01–08
Publication date
21 January 2026
Language
EN