ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 An Ensemble Method of CNN Models for Object Detection
Cited 9 time in scopus Download 0 time Share share facebook twitter linkedin kakaostory
저자
이진수, 이상광, 양성일
발행일
201810
출처
International Conference on Information and Communication Technology Convergence (ICTC) 2018, pp.898-901
DOI
https://dx.doi.org/10.1109/ICTC.2018.8539396
협약과제
18HS3100, 디지털콘텐츠 In-House R&D, 박수명
초록
Object detection is a research field that deals with detecting objects of a certain class in digital images and videos. Traditional methods of object detection were based on pre-structured features and had limitation on accuracy and computational efficiency. As deep learning had been proved to be a breakthrough, researches about object detection method based on deep learning, especially CNN, started. CNN-based object detection methods can be divided into two types. One is two-stage detector that once region proposals are generated, then they are classified. The other is one-stage detector that detects and classifies the object without generating region proposals. In two-stage detector case, combining CNN models is one of the ways to improve the accuracy in detection, which is called ensemble. In ensemble method, the region proposals generated from each CNN models are combined, classified, and finally voted. When selecting CNN models to be used in ensemble method, various properties of them should be considered in order to enhance complementary strength. In this paper, we propose advanced ensemble method in object detection with novel methods of model selecting and box voting. It is proved with experiment that the accuracy in object detection increased with our proposed methods. Also, combining the original method and our proposed method is expected to further increase the accuracy in detection and make ensemble model more robust.
키워드
CNN, Ensemble method, Object detection
KSP 제안 키워드
Complementary strength, Computational Efficiency, Detection Method, Ensemble Model, Ensemble method, Object detection, One-stage, Region proposal, Traditional methods, Two-Stage, Various properties