• Journal of Korea Society of Industrial Information Systems
• /
• v.2 no.1
• /
• pp.73-87
• /
• 1997

Multilayer neural network using a modified beackpropagation learning algorithm was introduced to achieve automatic identification of different types of aircraft in a variety of 3-D orientations. A 3-D shape of an aircraft can be described by a library of 2-D images corresponding to the projected views of an aircraft. From each 2-D binary aircraft image we extracted 2-D invariant (L, Φ) feature vector to be used for training neural network aircraft classifier. Simulations concerning the neural network classification rate was compared using nearest-neighbor classfier (NNC) which has been widely served as a performance benchmark. And we also introduced reliability measure of the designed neural network classifier.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.10
• /
• pp.326-331
• /
• 2019

In the real world, there are both dynamic objects and static objects, but an autonomous vehicle or mobile robot cannot distinguish between them, even though a human can distinguish them easily. It is important to distinguish static objects from dynamic objects clearly to perform autonomous driving successfully and stably for an autonomous vehicle or mobile robot. To do this, various sensor systems can be used, like cameras and LiDAR. Stereo camera images are used often for autonomous driving. The stereo camera images can be used in object recognition areas like object segmentation, classification, and tracking, as well as navigation areas like 3D world reconstruction. This study suggests a method to distinguish static/dynamic objects using stereo vision for an online autonomous vehicle and mobile robot. The method was applied to a 3D world map reconstructed from stereo vision for navigation and had 99.81% accuracy.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.3
• /
• pp.83-91
• /
• 2011

Recently, many researchers in the world are concentrated to develop the robot platform which is to reduce the developing cost by reusing existing softwares. In this paper, we describe that the 3 dimension recognition object components for OPRoS (Open Platform for Robotic Services) which is developed in Korea. We present that the structure of the component, disparity map and depth map algorithm for recognizing 3 dimension space. We used stereo matching and block matching method to produce the disparity map. We test the component on the computer with OPRoS platform and show the results of accuracy and performance time.

• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.287-294
• /
• 2010

TOF technique is one of the skills that can obtain the object's 3D depth information. But depth image has low resolution and fingertip occupy very small region, so, it is difficult to find the precise fingertip's 3D information by only using depth image from TOF camera. In this paper, we estimate fingertip's 3D location using Arm Model and reliable hand's 3D location information that is modified by hexahedron as hand model. Using proposed method we can obtain more precise fingertip's 3D information than using only depth image.

• Journal of Korea Multimedia Society
• /
• v.5 no.5
• /
• pp.599-607
• /
• 2002

The octree model, a hierarchical volume description of 3D objects, nay be utilized to generate projected images from arbitrary viewing directions, thereby providing an efficient means of the data base for 3D object recognition and other applications. We present 2D projected image and made pseudo gray image of object using octree model and multi level boundary search algorithm. We present algorithm for finding feature points of 2D and 3D image and finding matched points using geometric transformation. The algorithm is made of data base, it will be widely applied to 3D object modeling and efficient feature points application for basic 3D object research.

• The Magazine of the IEIE
• /
• v.23 no.6
• /
• pp.74-79
• /
• 1996

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1841-1842
• /
• 2008

본 논문은 Scale Invariant Feature Transform(SIFT)알고리즘으로부터 얻어진 로컬 특징점으로부터 물체를 인식하는 방법에 대하여 논하였다. SIFT알고리즘은 물체의 스케일, 회전에 강인하고, 또한 3차원 시점의 변화에도 부분적으로 강인한 특징점을 추출한다. SIFT 알고리즘은 입력영상에 크기가 다른 가우시안 함수를 적용하고, 블러링된 영상들의 차 영상에서 극값을 추출하여 특징점으로 사용한다. 하지만 SIFT알고리즘에서 가우시안 함수를 적용하는 것은 상당히 많은 연산을 필요로 하기 때문에 본 논문에서는 하나의 옥타브를 사용하여 연산시간을 단축하였다. 하나의 옥타브를 사용함으로써 물체의 스케일이 크게 변하였을 때는 문제가 발생한다. 이를 해결하기 위하여 대상 물체의 작은 스케일, 큰 스케일에서 추출된 특징점을 혼합하여 DB를 생성하였다.

• Proceedings of the KIEE Conference
• /
• 1997.07d
• /
• pp.1370-1372
• /
• 1997

In this study, 3-D underwater object recognition using ultrasonic sensor fabricated with porous piezoelectric ceramics and SCL(Simple Competitive Learning) neural networks are presented. The recognition rates for the training data and the testing dara were 96 and 93%, respectively.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.1
• /
• pp.13-20
• /
• 2016

In this paper, we propose an object recognition system that can effectively find out its category, its instance name, and several attributes from the color and depth images of an object with hierarchical feature learning. In the preprocessing stage, our system transforms the depth images of the object into the surface normal vectors, which can represent the shape information of the object more precisely. In the feature learning stage, it extracts a set of patch features and image features from a pair of the color image and the surface normal vector through two-layered learning. And then the system trains a set of independent classification models with a set of labeled feature vectors and the SVM learning algorithm. Through experiments with UW RGB-D Object Dataset, we verify the performance of the proposed object recognition system.

• Journal of KIISE:Software and Applications
• /
• v.33 no.1
• /
• pp.130-137
• /
• 2006

The depth information in the face represents personal features in detail. In particular, the surface curvatures extracted from the face contain the most important personal facial information. This surface curvature and together with grouped projection vector which reduces the dimensions resulting less computations are collaborated into the proposed 3D face recognition algorithm. The maximum and minimum curvature are calculated from the surface curvature image, which are grouped into projected vectors for recognition. The minimum curvature showed the best recognition rate among the surface parameters.