• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.3
• /
• pp.62-78
• /
• 2002

In this paper, we describe a system that can interact with agents in the virtual space incorporated in the system. This system is constructed by an analysis system for analyzing human gesture and an interact system for interacting with agents in the virtual space using analyzed information. An implemented analysis system for analyzing gesture extracts a head and hands region after taking image sequence of an operator's continuous behavior using CCD cameras. In interact system, we construct the virtual space that exist an avatar which incarnating operator himself, an autonomous object (like a Puppy), and non-autonomous objects which are table, door, window and object. Recognized gesture is transmitted to the avatar in the virtual space, then transit to next state based on state transition diagram. State transition diagram is represented in a graph in which each state represented as node and connect with link. In the virtual space, the agent link an avatar can open and close a window and a door, grab or move an object like a ball, order a puppy to do and respond to the Puppy's behavior as does the puppy.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.7
• /
• pp.1047-1055
• /
• 2015

We proposes a method for improving the identification and tracking of the moving objects in intelligent video surveillance system. The proposed method consists of 3 parts: object detection, object recognition, and object tracking. First of all, we use a GMM(Gaussian Mixture Model) to eliminate the background, and extract the moving object. Next, we propose a labeling technique forrecognition of the moving object. and the method for identifying the recognized object by using the optical flow and EMD algorithm. Lastly, we proposes method to track the location of the identified moving object regions by using location information of moving objects and Kalman filter. Finally, we demonstrate the feasibility and applicability of the proposed algorithms through some experiments.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.391-401
• /
• 2022

As deep learning-based object detection and recognition research have been developed recently, the scope of application to industry and real life is expanding. But deep learning-based systems in the construction system are still much less studied. Calculating materials in the construction system is still manual, so it is a reality that transactions of wrong volumn calculation are generated due to a lot of time required and difficulty in accurate accumulation. A fast and accurate automatic drawing recognition system is required to solve this problem. Therefore, we propose an AI-based automatic drawing recognition accumulation system that detects and recognizes steel materials in construction drawings. To accurately detect steel materials in construction drawings, we propose data augmentation techniques and spatial attention modules for improving small object detection performance based on YOLOv4. The detected steel material area is recognized by text, and the number of steel materials is integrated based on the predicted characters. Experimental results show that the proposed method increases the accuracy and precision by 1.8% and 16%, respectively, compared with the conventional YOLOv4. As for the proposed method, Precision performance was 0.938. The recall was 1. Average Precision AP_0.5 was 99.4% and AP_0.5:0.95 was 67%. Accuracy for character recognition obtained 99.9.% by configuring and learning a suitable dataset that contains fonts used in construction drawings compared to the 75.6% using the existing dataset. The average time required per image was 0.013 seconds in the detection, 0.65 seconds in character recognition, and 0.16 seconds in the accumulation, resulting in 0.84 seconds.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.1
• /
• pp.13-18
• /
• 2010

Most of the research in the multi-touch area is based on the FTIR(Frustrated Total Internal Re리ection), which is just implemented by using the previous approach. Moreover, there are not the software solutions to improve a performance in the multi touch-blobs detection or the user gesture recognition. Therefore, we implement a multi-touch table-top display that is based on the DI(Diffused Illumination), the improved touch-points detection and user gesture recognition. The proposed method supports a simultaneous transformation multi-touch command for objects in the running application. Also, the system latency time is reduced by the proposed ore-testing method in the multi touch-blobs detection processing. Implemented device is simulated by programming the Flash AS3 application in the TUIO(Tangible User Interface Object) environment that is based on the OSC(Open Sound Control) protocol. As a result, Our system shows the 37% system latency reduction, and is successful in the multi-touch gestures recognition.

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.816-820
• /
• 1990

This paper is pre-stage for getting EGI which can be used for modeling of an object. It discusses the construction of the vision processing system and its algorithm for getting needle diagram from tie object image. We realize the algorithm with monocular camera system, using Reflectance Map theory and photometric stereo method. We can calculate the surface normal at any point in the image if we take multiple images at the different lighting conditions. From the 3 images taken from different lighting conditions through the experiment, we get the needle diagrams of the sphere and the object. We confirm the validness of the surface, normal acquisition algorithm comparing the experimental needle diagram with the ideal one obtained from the surface normal of the known object.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.128.6-128
• /
• 2001

In this paper, we present a methodology of sensing and control for a robot system designed to be capable of grasping an object and moving it to target point Stereo vision system is employed to determine to depth map which represents the distance from the camera. In stereo vision system we have used a center-referenced projection to represent the discrete match space for stereo correspondence. This center-referenced disparity space contains new occlusion points in addition to the match points which we exploit to create a concise representation of correspondence an occlusion. And from the depth map we find the target object´s pose and position in 3-D space. To find the target object´s pose and position, we use the method of the model-based recognition.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.1
• /
• pp.200-210
• /
• 1996

Re-engineering has the potential to improve software productivity and quality y across the entire life cycle. It involves improving the software maintenance process and improving existing systems by applying new technologies and tools to software maintenance. Re-engineering can help us understanding existing systems and discover software components(e.g., design structure, data structure that are common across systems. These common components then can be reused in the development (or redevelopment )of systems, thereby significantly shortening the time and lessening the risk of developing systems. The Object-Oriented paradigm has been known to improve software maintainability. There still exist many problems in recognizing object, attributes and operations that are conceptually integrated and constructing of object class. In this paper, we propose a method that defines a fundamental theories of re-engineering and a concept recognition for object- oriented paradigm. We also describe the re-engineering tool that translates the existing procedure-oriented program into object-oriented system. This tool has a strength to solve the conceptual integrity problem in object-oriented recognition.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.2 s.46
• /
• pp.71-76
• /
• 2007

Object detection process which makes decision on the existence of meaningful objects in a given image is a crucial part of image recognition in computer vision system. Hausdorff distance metric has been used in object detection and shows good results in applications such as face recognition. It defines the dissimilarity between two sets of points and is used to find the object that is most similar to the given model. This paper proposes a Hausdorff distance based detection method that uses directional information of points to improve detection accuracy when the sets of points are derived from edge extraction as is in usual cases. In this method, elastic energy needed to make two directional points coincident is used as a measure of similarity.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1439-1446
• /
• 2011

This paper describes the algorithm that lowers the dimension, maintains the object recognition and significantly reduces the eigenspace configuration time by combining the higher correlation feature information and Principle Component Analysis. Since the suggested method doesn't require a lot of computation than the method using existing geometric information or stereo image, the fact that it is very suitable for building the real-time system has been proved through the experiment. In addition, since the existing point to point method which is a simple distance calculation has many errors, in this paper to improve recognition rate the recognition error could be reduced by using several successive input images as a unit of recognition with K-Nearest Neighbor which is the improved Class to Class method.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.2
• /
• pp.100-104
• /
• 2020

Over the past several years, deep learning has been widely used for feature extraction in image and video for various applications such as object classification and facial recognition. This paper introduces an implantation of embedded Linux system for embossed digits recognition using CNN based deep learning methods. For this purpose, we implemented a coin recognition system based on deep learning with the Keras open source library on Raspberry PI. The performance evaluation has been made with the success rate of coin classification using the images captured with ultra-wide angle camera on Raspberry PI. The simulation result shows 98% of the success rate on average.