김영석 교수

Autonomous driving requires an accurate and fast 3D perception system that includes 3D object detection, tracking, and segmentation. Although recent low-cost camera-based approaches have shown promising results, they are susceptible to poor illumination or bad weather conditions and have a large localization error. Hence, fusing camera with low-cost radar, which provides precise long-range measurement and operates reliably in all environments, is promising but has not yet been thoroughly investi

Robust and accurate scene representation is essential for advanced driver assistance systems (ADAS) such as automated driving. The radar and camera are two widely used sensors for commercial vehicles due to their low-cost, high-reliability, and low-maintenance. Despite their strengths, radar and camera have very limited performance when used individually. In this paper, we propose a low-level sensor fusion 3D object detector that combines two Region of Interest (RoI) from radar and camera featur

In this paper, we present a method for estimating a position, size, and orientation using a single monocular image. The proposed method makes use of an inverse perspective mapping to effectively estimate the distance from the image. The proposed method consists of two stages: 1) cancel the pitch and roll motion of the camera using inertial measurement unit and project the corrected front view image onto the bird's eye view using inverse perspective mapping. 2) detect the position, size, and orie

We present Haptics Assisted Training (HAT) System, a force feedback workstation for transferring and improving handwriting skill. The HAT system is the first practical handwriting training system whose usability was tested both in typical and special education classrooms of a local school district. Simulating the role of occupational therapists (OT), the HAT system guides the user's hand along the sequence of strokes of the reference handwriting recorded by an expert or teacher. Since the handwr

In order to detect damage to underwater infrastructure for inspection, an expensive survey by a diver is generally conducted, but it carries the risk of accidents. Accordingly, the development of an effective unmanned underwater survey system is an important priority. The unmanned underwater survey system used in this study is equipped with sonar towed by an- Unmanned Surface Vehicle (USV) to conduct the survey, but the USV is more affected by the waves and swells than a common boat. As a result

The advent of social media has allowed channeling of the voice of sports fans that have essentially lead to gathering and storing fan-generated, large-scale opinions about sports match and team performance. Although research utilizing social media data for the purposes of supporting consumer market research has been increasing throughout the recent decade, there is a lack of studies using social media mining approach to improve team performance. In this paper, an opportunity mining approach is p

Grid computing promises the ability to share geographically and organizationally distributed resources to increase effective computational power and resource utilization. However, for the Grid computing to be successful, it is very important to provide middleware services that assist Grid users to easily interact with Grid environments. In this paper, we have designed and implemented a new general-purpose OGSI-compliant Grid resource broker service to hide the underlying complexity of the Grid r

Abstract – Symbols play an important role in identifying informative objects and are widely used in geo-spatial decision support systems and applications. In high level fusion applications, however, simply placing symbols often lead to information overload problem; symbols quickly grow fast in many applications, such as the post disaster monitoring system we are interested in. This leads to cluttered and overlapped icons. With today’s advanced technologies, new visual effects can lead to better

Although most diagnostic systems today largely depend on the automation of signal processing, we also observe experts still utilize their impressions for delicate or hard-to-recognizable symptoms. A good example is the diagnostics of arterial pressure pulses through the tactile perception, especially in oriental medicine. We have developed a real-time telehaptic rendering system where vital signs are captured, transmitted and replicated in a remote site. In this paper we report our developments

This paper presents a methodology of material property determination by a human subject’s active finger tapping. Object digitization by direct finger touch is a prerequisite for good quality intuitive haptic input interface. Previous attempts were limited to scanning the surface geometry, and were not capable of describing the material characteristics of the object being touched. In this research, a compound mechanical model was developed to characterize the non-linear, viscoelastic behavior of

Autonomous driving requires an accurate and fast 3D perception system that includes 3D object detection, tracking, and segmentation. Although recent low-cost camera-based approaches have shown promising results, they are susceptible to poor illumination or bad weather conditions and have a large localization error. Hence, fusing camera with low-cost radar, which provides precise long-range measurement and operates reliably in all environments, is promising but has not yet been thoroughly investi

Many young people in Korea are addicted to luxury brands. This phenomenon often ruins their lives. By examining the causes of social, historical, and economical luxury obsession, the research aims to get a better understanding of people’s behavior. Severance of nobility culture in Korean history led to wealthy people’s indiscreet imitation of western culture. Without traditional and cultural heritage, Korea’s wealthy people only seek material display. In addition, various Korean traits such as s

This study showed that there was no correlation between oral health parameters and characteristics of head and neck carcinoma.

본 연구는 국내에서 유통되고 있는 100 여종의 남성용 헬멧 제품을 대상으로 색채표현에 관한 고찰을 위해 구매 선호도가 높은 제품을 대상으로 색채의 이미지 스케일, PCCS 색체계를 적용한 색채분석, 그리고 제품 구매결정시 색채의 영향력을 고찰하였다. 연구대상이 되는 헬멧 제품은 자전거 탑승시에 사용되고 있는 남성용 헬멧으로 헬멧의 종류를 구분하지 않고 국내에서 유통되고 있는 전제품으로 설정하였다. 국내에서 유통 중인 남성용 헬멧에 대하여 일괄적으로 색채에 따라 이미지 스케일을 4영역(Soft, Hard, Dynamic, Static)으로 고찰하였으며, 또한 설문조사 결과 구매 빈도수가 상위 10위내의 제품이 갖는 색채의 이미지 스케일을 분석하였다. 그리고 이들 제품에 대하여 각각 PCCS 색체계에 의한 분석을 실시하였다. 마지막으로 실증분석으로 헬멧 제품 구입시 색채가 구매결정에 미치는 영향력을 분석하기 위해 설문조사를 실시하였다. 설문조사는 서울지역 S 대리점에 소속된 18개 자