http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Particle Filter with Adaptive Model for Object Tracking
Budi Sugandi,Hyoungseop Kim,Joo Kooi Tan,Seiji Ishikawa 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8
This paper proposed an object tracking method employing a particle filter algorithm with an adaptive target model. The particle filtering is used because it is very robust for non-linear and non-Gaussian dynamic state estimation problems and performs well when clutter and occlusions are present on the image. The target is modeled using histogram-based framework. Histograms are useful because they have property that they allow changes in the object appearance while the histograms remain the same. Bhattacharyya distance is used to measure the similarity between each sample"s histogram with a specified target model and it makes the measurement matching and sample’ weight updating more reasonable. We proposed the adaptive model of likelihood and the adaptive color model that allow more flexibility in the object tracking. The adaptive likelihood is used in weighting the samples and the adaptive target model is used to overcome the appearance changes due to illumination changes, occlusions or noise. The method is capable to track successfully the moving object in different outdoor environment. The experimental results show the feasibility and the effectiveness of our proposed method.
Real Time Object Tracking and Identification Using a Camera
Budi Sugandi,Hyoungseop Kim,Joo Kooi Tan,Seiji Ishikawa 대한전자공학회 2008 ITC-CSCC :International Technical Conference on Ci Vol.2008 No.7
In this paper, we proposed a method for detecting and tracking of moving objects based on low resolution image employing a block matching technique and also proposed an identification method using a color and spatial information. Many tracking algorithms have better performance under static background but sometimes mistracking results are obtained under background with complex motions. Since a low resolution image has a nice property that it can remove the small size pixels, it is adopted to solve this problem due to the fact that most of the fake motions in the background have small region. In tracking the moving object, many applications have problems when objects occlude each other. The peripheral increment sign correlation is used to solve this problem. The identification object is performed using a color and spatial information of the tracked object. The experimental results prove the feasibility and usefulness of the proposed method.
Face direction estimation based on eigenspace technique
Jun Okubo,Budi Sugandi,Hyoungseop Kim,Joo Kooi Tan,Seiji Ishikawa 제어로봇시스템학회 2008 제어로봇시스템학회 국제학술대회 논문집 Vol.2008 No.10
In this paper, we propose a method for identification of persons using feature points which are taken from different angle and estimating of face direction using eigenspace technique. The face images are extracted on image sequences which are captured by a camera using image processing techniques. The face directions are estimated based on the eigenspace technique. Furthermore, the locations of face feature points are determined using a separability filter. Finally, the human faces are identified using the statistical features. The feature points for face identification are six points which are obtained the length of eyes, nostrils and angle of mouth. The experiments are performed on real time video image. The satisfactory results are shown along with discussions.