http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
클러스터링 알고리즘을 이용한 효과적인 그림자 영역 검출 방법
우창균(Chang-Gyun Woo),김윤호(Yoon-Ho Kim),박기홍(Ki-Hong Park) 한국디지털콘텐츠학회 2020 한국디지털콘텐츠학회논문지 Vol.21 No.1
Shadow detection has been mentioned many times in the field of digital image processing. Shadows distort the information in digital images, causing performance degradation in algorithms such as object recognition, segmentation, and tracking. Therefore, shadow detection and removal must be performed as a pre-processing operation of the image processing procedure. In this paper, we proposed an effective shadow detection method based on clustering algorithms. First, the input image is composed of superpixels that are grouped with similar pixels using SLIC algorithm, and then clustered and labeled with k-means++ algorithm. And, clustering the superpixels once again increases the accuracy of grouping similar features rather than clustering the original image, and thus detects the shadow region with this result image. In order to test the performance of the proposed algorithm, we experimented with single natural images including shadows, and found that the proposed method effectively detects shadow regions.
김진홍(Jin-Hong Kim),우창균(Chang-Gyun Woo),김주민(Joo-Min Kim),박기홍(Ki-Hong Park) 한국정보기술학회 2021 Proceedings of KIIT Conference Vol.2021 No.11
탄소중립 시대가 도래함에 따라 다양한 분야에서 전동화를 이룬 자동차가 개발 · 출시되고 있다. 이에 자율주행 차량 시대도 현실화 되면서 컴퓨터 비전기술 기반의 객체 탐지기술과 그림자 제거의 기술은 중요시되고 있다. 본 논문에서는 객체탐지의 효율성을 개선하기 위한 기법을 분석하고, 향후 그림자 제거 기술까지 적용하여 효율적인 차선인식율 향상을 위한 방법을 제안한다. As the era of carbon neutrality approaches, automobiles that have been electrified in various fields were developed. Accordingly, as the era of self-driving vehicles has become a reality, object detection technology based on computer vision technology and shadow removal technology are becoming important. In this paper, a technique for improving the efficiency of object detection is analyzed, and a method for efficient lane recognition rate is proposed by applying shadow removal technology in the future.