• Annual Conference of KIPS
• /
• 2022.05a
• /
• pp.637-640
• /
• 2022

3차원 물체의 탐지와 자세 추정은 실내외 환경에서 장면 이해, 로봇의 물체 조작 작업, 자율 주행, 증강 현실 등과 같은 다양한 응용 분야들에서 공통적으로 요구되는 매우 중요한 시각 인식 기술이다. 깊이 지도를 요구하는 기존 연구들과는 달리, 본 논문에서는 RGB 컬러 영상만을 이용해 미지의 물체들, 즉 3차원 CAD 모델을 가지고 있지 않은 새로운 물체들을 탐지해내고, 이들의 자세를 추정해낼 수 있는 새로운 신경망 모델을 제안한다. 제안 모델에서는 최근 빠른 속도로 발전하고 있는 깊이 추정 기술을 이용함으로써, 깊이 측정 센서 없이도 물체 자세 추정에 필요한 깊이 지도를 컬러 영상에서 구해낼 수 있다. 본 논문에서는 벤치마크 데이터 집합을 이용한 실험을 통해, 제안 모델의 유용성을 평가한다.

• Annual Conference of KIPS
• /
• 2011.04a
• /
• pp.390-393
• /
• 2011

본 논문은 전자 제어 시스템의 응용분야로 많은 연구가 이루어 지고 있는 영상 데이터를 통한 물체 인식을 위한 방법으로서 영상처리와 기계학습을 활용하는 알고리즘을 제안하고 실제 구현과 실험을 통해 물체 인식 특성을 파악하는 것에 대한 것이다. 물체의 정확한 인식을 위해서는 영상 데이터로부터 물체의 특성을 파악할 수 있는 알고리즘과 함께 파악된 특성을 학습을 통해 데이터를 확보하는 두 가지 과정이 요구된다. 본 논문에서는 이러한 방법을 구체화하기 위해 사람의 얼굴을 인식하는 알고리즘을 예로 들어 영상데이터로부터 물체를 인식하는 알고리즘을 구현하고 실험을 통해 알고리즘의 동작 특성을 확인한다.

• Annual Conference of KIPS
• /
• 2011.11a
• /
• pp.249-252
• /
• 2011

본 논문은 실내 공간에서 RFID와 센서를 이용하여 이동로봇이 자기 위치를 파악하고 목표 물체를 인식할 수 있는 기법을 제안한다. RFID를 지면과 목표물체에 설치하고 로봇은 리더기와 다양한 센서를 갖춤으로써 이동시 자기 위치를 파악하고 물체로부터도 고유정보를 얻을 수 있게 구성하였다. 초음파 센서 신호의 귀환시간을 활용하여 전방 물체의 거리를 추출하며 바닥의 RFID로부터 이미 획득한 자기 위치를 활용하여 물체의 절대 위치를 구한다. 이는 로봇을 중심으로한 경로지도를 실시간으로 작성하는 것이 가능하며, 실내의 구조 및 목표 물체의 위치등을 포함한 전체적인 지도를 작성할 수 있다. 최종적으로는 최적의 경로 계획을 세워 로봇이 목표 위치로 이동하거나 자율적 탐색이 가능하도록 한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.539-540
• /
• 2023

최근 물체 인식 모델의 성능을 개선하기 위한 다양한 연구가 진행 중이다. 본 논문에서는 K-means 기반 앵커박스 선정 기법을 적용한 새로운 물체 인식 모델 성능 개선 방법을 제안한다. 제안된 방법은 항만 내 설치된 컨테이너 사고를 예방하기 위한 컨테이너 사고위험도 분류 모델에 적용하여 성능 평가를 하였다. 특히, 컨테이너 사고위험도 분류 모델은 작은 물체를 인식해야 하며 이런 환경에서는 기존 물체 인식 모델 성능이 낮게 나타난다. 본 논문에서는 제안한 K-means 기반 앵커박스 선정 기법을 적용하여 물체 인식 모델 성능이 개선됨을 확인하였디.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.210-214
• /
• 2008

It is actually impossible to model and store all objects which exist in real home environment into robot's database in advance. To resolve this problem, this paper proposes new object modeling method that can be available for robot self-modeling, which is capable of estimating whole model's shape from partial surface data using Generic Model. And this whole produce is conducted to cylindrical objects like cup, bottles and cans which can be easily found at indoor environment. The detailed process is firstly we obtain cylinder's initial principle axis using points coordinates and normal vectors from object's surface after we separate cylindrical object from 3D image. This 3D image is obtained from 3D sensor. And second, we compensate errors in the principle axis repeatedly. Then finally, we do modeling whole cylindrical object using cross sectional principal axis and its radius To show the feasibility of the algorithm, We implemented it and evaluated its accuracy.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.3_4
• /
• pp.168-185
• /
• 2003

This paper presents a progressive algorithm that not only can narrow down the search domain in the course of face identification but also can fast reconstruct various 3D objects from a sketch drawing. The sketch drawing, edge-vertex graph without hidden line removal, which serves as input for reconstruction process, is obtained from an inaccurate freehand sketch of a 3D wireframe object. The algorithm is executed in two stages. In the face identification stage, we generate and classify potential faces into implausible, basis, and minimal faces by using geometrical and topological constraints to reduce search space. The proposed algorithm searches the space of minimal faces only to identify actual faces of an object fast. In the object reconstruction stage, we progressively calculate a 3D structure by optimizing the coordinates of vertices of an object according to the sketch order of faces. The progressive method reconstructs the most plausible 3D object quickly by applying 3D constraints that are derived from the relationship between the object and the sketch drawing in the optimization process. Furthermore, it allows the designer to change viewpoint during sketching. The progressive reconstruction algorithm is discussed, and examples from a working implementation are given.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.38 no.10
• /
• pp.859-864
• /
• 2014

This experimental study investigates the effects of a downstream cylinder in the wake change on upstream object's diameter. A V-shaped object is placed in the upstream of the test section and a circular cylinder containing a load-cell is placed in the downstream. The velocity distribution of the wake generated from the upstream object with a change in its diameter is investigated. Further, the fluctuation in the lift coefficient and Karman-vortex emission frequency with a change in the position of the downstream cylinder is examined. The study results reveal the following. i) The flow velocity in the wake is smaller than that in the main stream. ii) The lock-in phenomenon occurs when the diameter of the upstream object is larger than that of the downstream cylinder. iii) To generate maximum fluctuating lift force of the downstream cylinder in the wake, the position of the downstream cylinder must be moved with changing diameter of the upstream object together.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.88-90
• /
• 2018

There are many studies on IR-UWB Radar. A number of studies have been conducted on the Personnel count and measurement distance to person, mainly using IR-UWB. In this paper, however, we use IR-UWB Radar to distinguish objects. In order to distinguish these objects, in this paper, the IR-UWB radar is operated by positioning the object at a certain distance and the object is classified by using the size and shape of the wave reflected by the object. To distinguish objects using only the size and shape of these waveforms, SVM (Support Vector Machine) was used to classify objects by learning shape and size of waveforms. In this paper, we show that the size and shape of the waveform received by the IR-UWB Radar can be identified by SVM pattern learning.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.1
• /
• pp.54-68
• /
• 2001

This paper proposes a new algorithm that detects and separates the occluding and occluded objects in a 2D image. An input image is represented by the attributed graph where a node corresponds to a surface and an arc connecting two nodes describes the adjacency of the nodes in the image. Each end of arc is weighted by relation value which tells the number of edges connected to the surface represented by the node in the opposite side of the arc. In attributed graph, homogeneous nodes pertained to a same object always construct one of three special patterns which can be simply classified by comparison of relation values of the arcs. The experimental results have shown that the proposed algorithm efficiently separates the objects overlapped arbitrarily, and that this approach of separating objects before matching operation reduces the matching time significantly by simplifying the matching problem of overlapped objects as the one of individual single object.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.4
• /
• pp.57-67
• /
• 2015

The concept of detection and classification of objects based on infrared camera is widely applied to military applications. While the object detection technology using infrared images has long been researched and the latest one can detect the object in sub-pixel, the object classification technology still needs more research. In this paper, we present object classification method based on measured radiant intensity of objects such as target, artillery, and missile using infrared camera. The suggested classification method was verified by radiant intensity measuring experiment using black body. Also, possible measuring errors were compensated by modelling-based correction for accurate radiant intensity measure. After measuring radiation of object, the model of radiant intensity is standardized based on theoretical background. Based on this research, the standardized model can be applied to the object classification by comparing with the actual measured radiant intensity of target, artillery, and missile.