상세 보기
동적 임계값 추정 기반 최적 정제 모델 선정을 통한 로봇 비전 객체 탐지 라벨 정제 기법
- Hwang, Sung Tae;
- Hyun, Myung Han
SCOPUS
0초록
This study proposes a label refinement method for robot vision object detection utilizing multi-model-based dynamic threshold estimation. The ultimate goal of this research is to improve the recognition accuracy and robustness of intelligent waste-sorting robotic arm vision systems. To overcome the limitations of conventional fixed-threshold approaches, the proposed method applies multiple dynamic adaptive confidence thresholds that adjust according to the data distribution. Furthermore, it enhances refinement accuracy through an adaptive geometric prior-based noise reduction technique. Specifically, the proposed method adopts a two-stage approach, starting with an initial estimation of the label data to be refined. This is followed by the selection of an optimal refinement model, which collectively enhances both the precision and processing speed of the refinement process. Experimental results demonstrate that the proposed method improves the inference speed while increasing mean Average Precision (mAP) @.5:.95 by 0.0282 compared to the conventional methods. These findings indicate that the proposed framework effectively corrects inherent labeling errors and suppresses catastrophic forgetting during the fine-tuning process. Ultimately, this advancement provides a highly reliable and generalizable vision model solution for practical deployments in real-world automated sorting environments.
키워드
- 제목
- 동적 임계값 추정 기반 최적 정제 모델 선정을 통한 로봇 비전 객체 탐지 라벨 정제 기법
- 제목 (타언어)
- Label Refinement for Robot Vision Object Detection via Dynamic Threshold Estimation and Optimal Refinement Model Selection
- 저자
- Hwang, Sung Tae; Hyun, Myung Han
- 발행일
- 2026-08
- 유형
- Article
- 저널명
- 제어.로봇.시스템학회 논문지
- 권
- 32
- 호
- 8
- 페이지
- 1169 ~ 1177
- 언어
- KOR
- 출판사
- Institute of Control, Robotics and Systems
- 발행국가
- 대한민국
- 분량
- 9 페이지
- ISSN
- E 2233-4335
P 1976-5622