• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.1
• /
• pp.25-31
• /
• 2005

In this paper, we present a face detection system using the Support Vector Domain Description (SVDD) in color images. Conventional face detection algorithms require a training procedure using both face and non-face images. In SVDD however we employ only face images for training. We can detect faces in color images from the radius and center pairs of SVDD. We also use Entropic Threshold for extracting the facial feature and sliding window for improved performance while saving processing time. The experimental results indicate the effectiveness and efficiency of the proposed algorithm compared to conventional PCA (Principal Component Analysis)-based methods.

• The Journal of Korea Robotics Society
• /
• v.1 no.1
• /
• pp.66-72
• /
• 2006

In face recognition, learning speed of face is very important since the system should be trained again whenever the size of dataset increases. In existing methods, training time increases rapidly with the increase of data, which leads to the difficulty of training with a large dataset. To overcome this problem, we propose SVDD (Support Vector Domain Description)-based learning method that can learn a dataset of face rapidly and incrementally. In experimental results, we show that the training speed of the proposed method is much faster than those of other methods. Moreover, it is shown that our face recognition system can improve the accuracy gradually by learning faces incrementally at real environments with illumination changes.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.5
• /
• pp.518-528
• /
• 2014

In this paper, we propose a method to recognize the action direction of human by developing 4D space-time (4D-ST, [x,y,z,t]) features. For this, we propose 4D space-time interest points (4D-STIPs, [x,y,z,t]) which are extracted using 3D space (3D-S, [x,y,z]) volumes reconstructed from images of a finite number of different views. Since the proposed features are constructed using volumetric information, the features for arbitrary 2D space (2D-S, [x,y]) viewpoint can be generated by projecting the 3D-S volumes and 4D-STIPs on corresponding image planes in training step. We can recognize the directions of actors in the test video since our training sets, which are projections of 3D-S volumes and 4D-STIPs to various image planes, contain the direction information. The process for recognizing action direction is divided into two steps, firstly we recognize the class of actions and then recognize the action direction using direction information. For the action and direction of action recognition, with the projected 3D-S volumes and 4D-STIPs we construct motion history images (MHIs) and non-motion history images (NMHIs) which encode the moving and non-moving parts of an action respectively. For the action recognition, features are trained by support vector data description (SVDD) according to the action class and recognized by support vector domain density description (SVDDD). For the action direction recognition after recognizing actions, each actions are trained using SVDD according to the direction class and then recognized by SVDDD. In experiments, we train the models using 3D-S volumes from INRIA Xmas Motion Acquisition Sequences (IXMAS) dataset and recognize action direction by constructing a new SNU dataset made for evaluating the action direction recognition.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.3
• /
• pp.1264-1274
• /
• 2015

Human action recognition received many interest in the computer vision community. Most of the existing methods focus on either construct robust descriptor from the temporal domain, or computational method to exploit the discriminative power of the descriptor. In this paper we explore the idea of using local action attributes to form an action descriptor, where an action is no longer characterized with the motion changes in the temporal domain but the local semantic description of the action. We propose an novel framework where introduces local action attributes to represent an action for the final human action categorization. The local action attributes are defined for each body part which are independent from the global action. The resulting attribute descriptor is used to jointly model human action to achieve robust performance. In addition, we conduct some study on the impact of using body local and global low-level feature for the aforementioned attributes. Experiments on the KTH dataset and the MV-TJU dataset show that our local action attribute based descriptor improve action recognition performance.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.264-265
• /
• 2008

기존 영상감시 시스템의 물체 탐지 알고리즘은 주로 배경 모델링 기법을 기반으로 하고 있다. 이 기법은 차영상 기법보다는 성능이 뛰어나기는 하지만 여전히 정지 카메라에서만 활용이 가능하고, 주변 환경에 따라 알고리즘 상의 많은 임계값을 현재 상황에 맞춰 일일이 조절해 주어야 한다는 한계점이 있다. 따라서 이 논문에서는 배경모델링 기법을 사용하지 않고 입력되는 영상의 Color 정보를 이용하여 영상 내에 있는 여러 대상을 직접 판단하여 관심 있는 물체를 탐지하는 방법을 제안하고자 한다. 제안된 알고리즘은 먼저 현재의 영상을 하나의 물체로 추정되는 영역이 하나의 영역으로 구분되어지게 간단하게 분할해낸다 그리고 나누어진 영역마다 대표 Color 값을 계산하여 미리 학습된 데이터를 기준으로 Support Vector Domain Description (SVDD) 알고리즘을 사용하여 구별해내고 그 결과를 바탕으로 영역이 무엇인지를 판별해낸다. 이 방법은 정지되어 있는 카메라뿐만 아니라 움직이는 카메라 상에서도 사용되어질 수 있으며 알고리즘 상에서 사용되는 임계값의 종류가 적기 때문에 많은 상황에서 일반적으로 쓰일 수 있다.

• Computers and Concrete
• /
• v.23 no.6
• /
• pp.445-457
• /
• 2019

Cracks are an important distress of concrete bridges, and may reduce the life and safety of bridges. However, the traditional manual crack detection means highly depend on the experience of inspectors. Furthermore, it is time-consuming, expensive, and often unsafe when inaccessible position of bridge is to be assessed, such as viaduct pier. To solve this question, the real-time automatic crack detecting system with unmanned aerial vehicle (UAV) become a choice. This paper designs a new automatic detection system based on real-time comprehensive image processing for bridge crack. It has small size, light weight, low power consumption and can be carried on a small UAV for real-time data acquisition and processing. The real-time comprehensive image processing algorithm used in this detection system combines the advantage of connected domain area, shape extremum, morphology and support vector data description (SVDD). The performance and validity of the proposed algorithm and system are verified. Compared with other detection method, the proposed system can effectively detect cracks with high detection accuracy and high speed. The designed system in this paper is suitable for practical engineering applications.