ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Small Object Detection using Context and Attention
Cited 37 time in scopus Download 3 time Share share facebook twitter linkedin kakaostory
저자
임정선, 마셀라, 윤현진, 이승익
발행일
202104
출처
International Conference on Artificial Intelligence in Information and Communication (ICAIIC) 2021, pp.181-186
DOI
https://dx.doi.org/10.1109/ICAIIC51459.2021.9415217
협약과제
21HS1600, 불확실한 지도 기반 실내ㆍ외 환경에서 최종 목적지까지 이동로봇을 가이드할 수 있는 AI 기술 개발, 이재영
초록
There are many limitations applying object detection algorithm on various environments. Specifically, detecting small objects is still challenging because they have low-resolution and limited information. We propose an object detection method using context for improving accuracy of detecting small objects. The proposed method uses additional features from different layers as context by concatenating multi-scale features. We also propose object detection with attention mechanism which can focus on the object in image, and it can include contextual information from target layer. Experimental results shows that proposed method also has higher accuracy than conventional SSD on detecting small objects. Moreover, for $300 \times 300$ input, we achieved 78.1% Mean Average Precision (mAP) on the PASCAL VOC2007 test set.
키워드
attention, context, object detection
KSP 제안 키워드
Attention mechanism, Contextual information, Detection Method, Detection algorithm, Different layers, Improving accuracy, Limited information, Multi-scale, Test Set, low resolution, mean average precision