• 제목/요약/키워드: Local Region Growing

검색결과 107건 처리시간 0.029초

무인차량 자율주행을 위한 레이다 영상의 정지물체 너비추정 기법 (Width Estimation of Stationary Objects using Radar Image for Autonomous Driving of Unmanned Ground Vehicles)

  • 김성준;양동원;김수진;정영헌
    • 한국군사과학기술학회지
    • /
    • 제18권6호
    • /
    • pp.711-720
    • /
    • 2015
  • Recently many studies of Radar systems mounted on ground vehicles for autonomous driving, SLAM (Simultaneous localization and mapping) and collision avoidance have been reported. Since several pixels per an object may be generated in a close-range radar application, a width of an object can be estimated automatically by various signal processing techniques. In this paper, we tried to attempt to develop an algorithm to estimate obstacle width using Radar images. The proposed method consists of 5 steps - 1) background clutter reduction, 2) local peak pixel detection, 3) region growing, 4) contour extraction and 5)width calculation. For the performance validation of our method, we performed the test width estimation using a real data of two cars acquired by commercial radar system - I200 manufactured by Navtech. As a result, we verified that the proposed method can estimate the widths of targets.

A GEOSTATISTIC BASED SEGMENTATION APPROACH FOR REMOTELY SENSED IMAGES

  • Chen, Qiu-Xiao;Luo, Jian-Cheng
    • 대한원격탐사학회:학술대회논문집
    • /
    • 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
    • /
    • pp.1323-1325
    • /
    • 2003
  • As to many conventional segmentation approaches , spatial autocorrelation, perhaps being the first law of geography, is always overlooked. Thus, the corresponding segmentation results are always not so satisfying, which will further affect the subsequent image processing or analyses. In order to improve segmentation results, a geostatistic based segmentation approach with the consideration of spatial autocorrelation hidden in remote-sensing images is proposed in this article. First, by calculating the mean variance between each pair of pixels at given different lag distances, information like the size of typical targets in the scene can be obtained, and segmentation thresholds are calculated accordingly. Second, an initial region growing segmentation approach is implemented. Finally, based on the segmentation thresholds obtained at the first step and the initial segmentation results, the final segmentation results are obtained using the same region growing approach by taking the local mutual best fitting strategy. From the experiment results, we found the approach is rather promising. However, there still exists some problems to be settled, and further researches should be conducted in the future.

  • PDF

Sustaining the Technopolis: The Case of Austin, Texas

  • Gibson, David V.;Butler, John S.
    • World Technopolis Review
    • /
    • 제2권2호
    • /
    • pp.64-80
    • /
    • 2013
  • In "Creating the Technopolis: High Technology Development in Austin Texas," Smilor, Kozmetsky, and Gibson (1988) make the case that in the mid-1980s Austin was becoming a globally competitive high tech region. Indeed over the years and into 2013, Austin has established its reputation as a leading entrepreneurial and technology center and "talent magnet." Delegations from across the US and worldwide visit Austin to better understand how this central Texas city went from being a state government and university town to become a fast growing, globally competitive, technology hotspot leading the state and nation in job creation. Central to the concept of the Triple Helix and Technopolis Frameworks is the importance of university, business, and government cooperation. This paper gives examples of mechanisms, processes, and metrics on how The University of Texas at Austin; regional technology industry; federal, state, and local government policies; and support groups all contributed to growing and sustaining the Austin Technopolis.

수차례 재발한 다발성 부신경절종 1예 (A Case of Multiple Paraganglioma Presenting as Recurrent Tumor Nermerous Times)

  • 이석희;선민진;최미숙;이동욱
    • 대한두경부종양학회지
    • /
    • 제27권1호
    • /
    • pp.80-83
    • /
    • 2011
  • Paraganglioma is a relatively rare, generally benign and slow growing tumor arising from widely distributed paraganglionic tissue thought to originate from the neural crest. In the head and neck region, paraganglionic tissue is distributed in the superior and inferior paraganglia such as the carotid body, the vagal body, and the jugulotympanic region. Approximately 10% of patients with paraganglioma have a family history of such tumors. Multiple lesions can be found in 26% of patients with family history. It is important to distinguish between paraganglioma and atypical carcinoid tumor and medullary thyroid cancer. This can be done with histopathologic evaluation and immunohistochemical markers. Complete excision is recommended for the treatment of this tumor. Paraganglioma is particularly aggressive and rapid recurrence of paraganglioma is common after local resection. We present a case of malignant paraganglioma in the neck which recurred 2 months after local resection. We suppose that radiation therpay could be the last option for the treatment in this clinical setting.

An Improved Saliency Detection for Different Light Conditions

  • Ren, Yongfeng;Zhou, Jingbo;Wang, Zhijian;Yan, Yunyang
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제9권3호
    • /
    • pp.1155-1172
    • /
    • 2015
  • In this paper, we propose a novel saliency detection framework based on illumination invariant features to improve the accuracy of the saliency detection under the different light conditions. The proposed algorithm is divided into three steps. First, we extract the illuminant invariant features to reduce the effect of the illumination based on the local sensitive histograms. Second, a preliminary saliency map is obtained in the CIE Lab color space. Last, we use the region growing method to fuse the illuminant invariant features and the preliminary saliency map into a new framework. In addition, we integrate the information of spatial distinctness since the saliency objects are usually compact. The experiments on the benchmark dataset show that the proposed saliency detection framework outperforms the state-of-the-art algorithms in terms of different illuminants in the images.

지방자치단체의 IT 유지보수관리의 아웃소싱 서비스 요인에 관한 연구: AHP 분석을 기반으로 (A Study of IT Maintenance Outsourcing Service Factors of Local Governments: Based on AHP Analysis Method)

  • 전대호;장상현;이정재;최정일
    • 한국IT서비스학회지
    • /
    • 제21권3호
    • /
    • pp.43-61
    • /
    • 2022
  • With the development of information technology, IT-based services in public administration has become more indispensable. As a result, the importance of IT maintenance projects to improve the efficiency of IT services and secure service levels is growing. Due to the nature of IT maintenance projects on local government, which mainly involve small and medium-sized IT companies in the region, business participating companies often do not have an appropriate methodology for service quality management. To solve this situation, the government has prepared a service level agreements (SLAs) that can be applied to IT maintenance projects. However, most local governments do not use SLAs for IT maintenance projects. As a result, various problems such as failure of the IT maintenance project or deterioration of quality are occurring Thus, this paper suggested major indexes to evaluate which service factors affect the efficient operation of information systems and the improvement of service quality in IT maintenance projects of local governments and analyzed the importance of indexes based on AHP method. Using this research method, this study found the theoretical implications on the outsourcing service of IT maintenance.

ATMF를 이용한 영상의 과분할 방지에 관한 연구 (A Study of Resolving the Over Segmentation in Image using ATMF)

  • 박형근
    • 한국컴퓨터산업학회논문지
    • /
    • 제6권5호
    • /
    • pp.735-740
    • /
    • 2005
  • 경사 영상을 사용하는 워터쉐드에서는 영상 내의 잡음이 직접 국부적 최소 점들로 표현되어 영상의 과분할을 초래하게 된다. 특히 분할되어야 할 영역들의 경계에 대한 기울기 크기는 영역 분할의 정확성에 영향을 주어 전체 분할 성능을 좌우할 수 있다. 그러므로 본 논문에서는 기울기 크기를 결정하기 전에 영역들에 대한 경계의 선명도를 보존하면서 잡음을 제거함으로써 영상의 과분할을 줄일 수 있는 ATMF(Adaptive Trimmed Mean Filter)의 적용을 제안하였다.

  • PDF

현장 관측 자료를 이용한 금오산 계명대학교 동영학술림 부근의 생물기후환경 분석 (Analysis of Bioclimatic Variables in Mt. Geumo Region Adjacent to Keimyung Dongyeong Forest )

  • 김하영;박수진;김해동
    • 한국환경과학회지
    • /
    • 제32권5호
    • /
    • pp.365-374
    • /
    • 2023
  • Eight years (2014-2021) of climate data were collected from an automatic weather observation system installed at the foot of Mt. Geumo in Chilgok, Gyeongbuk. Using these data, we investigated local bio-climatological indices (warmth index, WI; coldness index, CI; and effective accumulated temperature, EAT) of the mountain region adjacent to the Keimyung Dongyeong forest. The study area's WI and CI were 109.3℃ and -11.3℃ per month, respectively, averaged across 8 years. These values are indicative of an evergreen broad-leaved forest in the warm temperate climate zone, suitable for cultivating sweet persimmons and figs. Additionally, EAT in Dongyeong was 2,113.7℃, averaged across 8 years, suitable for growing crops such as corn, soybean, and potato.

과수묘목재배지역의 영농조직에 대한 인식과 참여행태 -경상북도 경산시 경산과수종묘연합회를 사례로- (A Study on the Cognition of Farming Group Organization and Participational Behavior Types Shown in the Fruit Nursery Tree Growing Region : Centered on the Case of Gyeongsan Fruit Nursery Growers Association)

  • 우종현
    • 한국지역지리학회지
    • /
    • 제13권5호
    • /
    • pp.495-508
    • /
    • 2007
  • 본 연구는 FTA 시대를 맞이하여 위기가 심화된 우리나라 농업/농촌 문제의 해결을 위해 새롭게 인식되고 있는 지역단위 영농조직의 형성에 주목하였다. 구체적으로는 과수묘목재배지역의 영농조직에 대한 개별농가의 인식과 조직내 활동에 대한 참여행태를 분석하였다. 그 결과 지역농업의 경쟁력 제고를 위한 영농조직은 구성원의 사회적 관계 유지보다는 경제적 이익실현을 우선적 목표로 하여야 하며, 추상적인 명분보다는 구체적이고 실질적인 목표를 지향해야 한다. 또한 영농조직은 재배작물의 동질성을 기초로 조직되어야 하며, 조직의 규모는 구성원간의 신뢰여부를 고려할때 내부적 통제와 구성원 상호간에 원활한 상호작용이 가능하도록 적정수준에서 통제될 필요가 있다.

  • PDF

영역기반 방법의 영상 분할에서 과분할 방지를 위한 Adaptive Trimmed Mean 필터에 관한 연구 (A Study of ATM filter for Resolving the Over Segmentation in Image Segmentation of Region-based method)

  • 이완범
    • 대한전자공학회논문지SP
    • /
    • 제44권3호
    • /
    • pp.42-47
    • /
    • 2007
  • 영상 분할은 주어진 영상에서 관심 영역을 추출하거나 압축을 위한 비디오 처리 분야에서 중요한 부분이며 특히 영역 기반 비디오 코딩에서는 필수적인 부분이다. 영역 기반의 수리형태학적 영상분할에서는 영상을 단순화한 후 추출된 경사 영상을 가지고 영역 경계를 결정하는 워터쉐이드 기법을 이용하는 방법이 주로 제안되고 있다. 이 방법은 병합될 대상 영역의 수가 많아질수록 병합하는 과정에 필요한 계산량이 지수적으로 증가하고, 영상 내의 잡음이 직접 국부적 최소 점들로 표현되어 영역들의 경계에 대한 기울기에 영향을 주어 영상의 과분할을 초래하게 된다. 따라서 본 논문에서는 이러한 영상의 과분할 문제를 해결할 수 있는 ATM 필터를 제안하였다. 모의실험 결과 제안된 ATM 필터가 전체적인 잡음제거의 향상과 함께 잡음 비율이 20% 이상일 경우의 영상의 선명도 훼손의 정도가 줄어들었음을 확인하였다.