http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A comparative survey on SAR image segmentation using deep learning
Ohtae Jang,Sangho Jo,Sungho Kim 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
Synthetic Aperture Radar (SAR) image is a radar system that observes topographic maps using microwaves as an active sensor. Due to the backscattering characteristics of SAR, speckle is distributed in the image, making it difficult to analyze. This paper investigates the classically used unsupervised method of SAR image segmentation that can easily recognize and analyze SAR images and the recently used deep learning algorithm, and compare the accuracy using performance metrics. Although the method using deep learning has the problem of insufficient dataset, it improves performance by 10-20% compared to unsupervised. Also, among deep learning algorithms, how the algorithms used in Electro Optical / Infrared (EO / IR) are used in SAR images and problems are investigated. In a recent study, the SAR image considered as a visible light image and applied it to a deep learning algorithm using eo to obtain results. In the future, more benchmark datasets for SAR images should be built, and research on deep learning algorithms using SAR data information will be conducted.
Comparative Analysis of IR-IR Image Matching Using Classical Techniques
Seungeon Lee,Ohtae Jang,Wangheon Lee,Sungho Kim 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
In this paper, after finding feature points and description using classical feature detection and description techniques, this paper compares and analyzes the performance of each classical technique by matching descriptors of the IR-IR images with the FLANN technique and matching with the Homography technique. Usually, these classical techniques are often used in EO images, but recently, in technologies that require a high level of detection such as defense technology, not only EO images but also IR images are being used. Therefore, classical feature detection and description techniques specialized for reflected light are applied to IR-IR images, and their performance is compared, and the limitations of classical techniques are examined. Classical techniques to use include SIFT, SURF, and KAZE.