• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.4
• /
• pp.2075-2092
• /
• 2017

Person re-identification is to match pedestrians observed from non-overlapping camera views. It has important applications in video surveillance such as person retrieval, person tracking, and activity analysis. However, it is a very challenging problem due to illumination, pose and viewpoint variations between non-overlapping camera views. In this work, we propose a viewpoint invariant method for matching pedestrian images using orientation of pedestrian. First, the proposed method divides a pedestrian image into patches and assigns angle to a patch using the orientation of the pedestrian under the assumption that a person body has the cylindrical shape. The difference between angles are then used to compute the similarity between patches. We applied the proposed method to real-time global multi-object tracking across multiple disjoint cameras with non-overlapping field of views. Re-identification algorithm makes global trajectories by connecting local trajectories obtained by different local trackers. The effectiveness of the viewpoint invariant method for person re-identification was validated on the VIPeR dataset. In addition, we demonstrated the effectiveness of the proposed approach for the inter-camera multiple object tracking on the MCT dataset with ground truth data for local tracking.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.1
• /
• pp.99-104
• /
• 2009

This article describes the analysis of stable grasping for multi-fingered robot. An analysis method of stable grasping, which is based on the three-dimensional acceleration convex polytope, is proposed. This method is derived from combining dynamic equations governing object motion and robot motion, force relationship and acceleration relationship between robot fingers and object's gravity center through contact condition, and constraint equations for satisfying no-slip conditions at every contact points. After mapping no-slip condition to torque space, we derived intersected region of given torque bounds and the mapped region in torque space so that the intersected region in torque space guarantees no excessive torque as well as no-slip at the contact points. The intersected region in torque space is mapped to an acceleration convex polytope corresponding to the maximum acceleration boundaries which can be exerted by the robot fingers under the given individual bounds of each joints torque and without causing slip at the contacts. As will be shown through the analysis and examples, the stable grasping depends on the joint driving torque limits, the posture and the mass of robot fingers, the configuration and the mass of an object, the grasp position, the friction coefficients between the object surface and finger end-effectors.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.429-432
• /
• 2000

The new MPEG-4 video coding standard enables content-based functionalities. In order to support the philosophy of the MPEG-4 visual standard, each frame of video sequences should be represented in terms of video object planes (VOP’s). In other words, video objects to be encoded in still pictures or video sequences should be prepared before the encoding process starts. Therefore, it requires a prior decomposition of sequences into VOP’s so that each VOP represents a moving object. A parallel processing system is required an automatic segmentation to be processed in real-time, because an automatic segmentation is time consuming. This paper addresses the parallel processing: system for an automatic segmentation for separating moving object from the background in image sequences. The proposed parallel processing system comprises of processing elements (PE’s) and a multi-access memory system (MAMS). Multi-access memory system is a memory controller to perform parallel memory access with the variety of types: horizontal, vertical, and block access way. In order to realize these ways, a multi-access memory system consists of a memory module selection module, data routing modules, and an address calculation and routing module. The proposed system is simulated and evaluated by the CADENCE Verilog-XL hardware simulation package.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.25.2-25
• /
• 2001

This paper describes a mobile robot intended for being employed in a multi-agent system. We have already proposed a multi-agent system which realizes patient-aid by helping a lying patient take a distant object on the table. In this paper, a mobile robot agent is developed and is included in the system. An effective man-machine communication strategy is proposed by use of a vision agent settled on the ceiling. If a human (assumed to be a patient) wishes to take an object distant on the floor, he points to the object. The vision agent detects the direction of his arm by image processing and guesses which object he intends to take. The vision agent asks him if it is what he wants and, if yes, the mobile robot runs to take and bring it to him. The system is overviewed with the explanation of a mobile robot. Some experimental results are shown with discussion.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10c
• /
• pp.215-217
• /
• 1999

CORBA 2.0 규격에 따라 구현돈 인터넷 Java ORB인 iORB는 Common Object Request Broker Architecture (CORBA) 객체 호출을 위한 Basic Object Adapter (BOA)를 클라이언트와 서버 객체 사이의 연결 설정과 요청 처리를 분리한 다중 쓰레드 방식으로 제공하고 있다. 본 논문은 다중 쓰레드 방식을 지원하는 iORB의 BOA 설계 및 구현에 관한 것이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3729-3749
• /
• 2021

At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.

• 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.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.25 no.5
• /
• pp.841-849
• /
• 2001

The pixel information of the object was obtained sequentially and pixels were clustered to a label by the line labeling method. Feature points were determined by finding the slope for edge pixels after selecting the fixed number of edge pixels. The slope was estimated by the least square method to reduce the detection error. Once a matching point was determined by comparing the feature information of the object and the pattern, the parameters for translation, scaling and rotation were obtained by selecting the longer line of the two which passed through the matching point from left and right sides. Finally, modified Hausdorff Distance has been used to identify the similarity between the object and the given pattern. The multi-label method was developed for recognizing the patterns with more than one label, which performs the modified Hausdorff Distance twice. Experiments have been performed to verify the performance of the proposed algorithm and method for simple target image, complex target image, simple pattern, and complex pattern as well as the partially hidden object. It was proved via experiments that the proposed image matching algorithm for recognizing the object had a good performance of matching.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.29 no.1 s.232
• /
• pp.1-13
• /
• 2005

Kinematics of grasping and manipulation by a multi-fingered robotic hand where multi-fingertip surfaces are in contact with an object is solved. The surface of the object was represented by B-spline surfaces in order to model the objects of various shapes. The fingers were modeled by cylindrical links and a half ellipsoid fingertip. Geometric equations of contact locations have been solved for all possible contact combinations between the fingertip surface and the object. The simulation system calculated joint displacements and contact locations for a given trajectory of the object. Since there are no closed form solutions for contact or intersection between these surfaces, kinematics of grasping was solved by recursive numerical calculation. The initial estimate of the contact point was obtained by approximating the B-spline surface to a polyhedron. As for the simulation of manipulation, exact contact locations were updated by solving the contact equations according to the given contact states such as pure rolling, twist-rolling or slide-twist-rolling. Several simulation examples of grasping and manipulation are presented.

• 시스템엔지니어링워크숍
• /
• s.4
• /
• pp.70-80
• /
• 2004

Most rail system related simulations currently used are designed to simulate only one discipline system. This obviously assunes the other discipline system are running regularly not being affected by the system being simulated. In this paper a multi discipline simulator is proposed and its design concept is presented.A multi discipline simulator is the simultor in which major subsystems with different technical discipline are simulated simultaneously. The advantage of the simulator is in that it makes it possible to analyze the systems behavior while other discipline system vary. With this we can identify the possible to analyze the systems ehavior find their solutions. A proto type simulator has bee developed using object oriented programming. Object concept was judged best suitable to model the various multi-discipline self-controlling railway subsystems. It was applied to the target system, which is under development by the Korea Railroad Research institute. The test results show it is very useful in design verification. It could also be a good tool in research and development work to make to improe the system.