Earticle

초록

영어

This study developed a real-time object detection and tracking system for an autonomous grenade launcher using frame differencing and adaptive thresholding. The system was designed to efficiently track moving objects in dynamic environments, focusing on human movement recognition. To assess its effectiveness, experiments were conducted by varying threshold values and analyzing their impact on detection accuracy. The results confirmed that a threshold of 30 optimally detected human movements while minimizing noise. Object detection experiments included analyzing detection results, cumulative motion visualizations, and object separation after background removal. The system achieved Precision 66.7%, Recall 88.9%, and F1 Score 76.2%, demonstrating reliable performance under general conditions. A comparison with a standard performance classification table further validated its accuracy. These findings suggest that the proposed method can be optimized for real-world applications requiring precise and robust object tracking.

목차

Abstract
1. Introduction
2. Method
2.1 Object detection and tracking system
2.2 Threshold
3. Result
3.1 Ground Truth and Detected Results
3.2 Performance Evaluation Metrics
3.3 Performance Evaluation
4. Conclusion
5. Reference

키워드

저자

• Su-Chak Ryu [ M.S., Department of Nanomechatronics Engineering, Pusan National University, Korea ]
• Dong-Hun Lee [ M.S., Department of Nanomechatronics Engineering, Pusan National University, Korea ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  The International Journal of Advanced Smart Convergence

• 간기

  계간

• pISSN

  2288-2847

• eISSN

  2288-2855

• 수록기간

  2012~2025

• 십진분류

  KDC 326 DDC 380