• Journal of KIISE:Software and Applications
• /
• v.29 no.5
• /
• pp.319-325
• /
• 2002

Tracking moving objects is one of the most important techniques in motion analysis and understanding, and it has many difficult problems to solve. Especially, estimating and identifying moving objects, when the background and moving objects vary dynamically, are very difficult. It is possible under such a complex environment that targets may disappear totally or partially due to occlusion by other objects. The Kalman filter has been used to estimate motion information and use the information in predicting the appearance of targets in succeeding frames. In this paper, we propose another version of the Kalman filter, to be called structured Kalman filter, which can successfully work its role of estimating motion information under a deteriorating condition such as occlusion. Experimental results show that the suggested approach is very effective in estimating and tracking non-rigid moving objects reliably.

• Research in Vestibular Science
• /
• v.17 no.4
• /
• pp.134-141
• /
• 2018

Objectives: We aimed to study the role of vestibular input on spatial memory performance in mice that had undergone bilateral surgical labyrinthectomy, semicircular canal (SCC) occlusion and 4G hypergravity exposure. Methods: Twelve to 16 weeks old ICR mice (n=30) were used for the experiment. The experimental group divided into 3 groups. One group had undergone bilateral chemical labyrinthectomy, and the other group had performed SCC occlusion surgery, and the last group was exposed to 4G hypergravity for 2 weeks. The movement of mice was recorded using camera in Y maze which had 3 radial arms (35 cm long, 7 cm high, 10 cm wide). We counted the number of visiting arms and analyzed the information of arm selection using program we developed before and after procedure. Results: The bilateral labyrinthectomy group which semicircular canal and otolithic function was impaired showed low behavioral performance and spacial memory. The semicircular canal occlusion with $CO_2$ laser group which only semicircular canal function was impaired showed no difference in performance activity and spatial memory. However the hypergravity exposure group in which only otolithic function impaired showed spatial memory function was affected but the behavioral performance was spared. The impairment of spatial memory recovered after a few days after exposure in hypergravity group. Conclusions: This spatial memory function was affected by bilateral vestibular loss. Space-related information processing seems to be determined by otolithic organ information rather than semicircular canals. Due to otolithic function impairment, spatial learning was impaired after exposure to gravity changes in animals and this impaired performance was compensated after normal gravity exposure.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.912-928
• /
• 2019

Crowd behavior analysis research has revealed a central role in helping people to find safety hazards or crime optimistic forecast. Thus, it is significant in the future video surveillance systems. Recently, the growing demand for safety monitoring has changed the awareness of video surveillance studies from analysis of individuals behavior to group behavior. Group detection is the process before crowd behavior analysis, which separates scene of individuals in a crowd into respective groups by understanding their complex relations. Most existing studies on group detection are scene-specific. Crowds with various densities, structures, and occlusion of each other are the challenges for group detection in diverse crowded scenes. Therefore, we propose a group detection approach called Collective Interaction Filtering to discover people motion interaction from trajectories. This approach is able to deduce people interaction with the Expectation-Maximization algorithm. The Collective Interaction Filtering approach accurately identifies groups by clustering trajectories in crowds with various densities, structures and occlusion of each other. It also tackles grouping consistency between frames. Experiments on the CUHK Crowd Dataset demonstrate that approach used in this study achieves better than previous methods which leads to latest results.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.365-367
• /
• 2008

A digital city model represents a 3D environment of a city with various city object information such as 3D building model, road, and land cover. Usually, at least two satellite images with some image overlap are necessary and a complex satellite-related computation needs to be carried out to create a city model. This is an expensive technique, because it requires many resources and excessive computational cost. The authors propose a methodology to create a digital city model including 3D building model and land cover information from a single high resolution satellite image. The approach consists of image pan-sharpening, shadow recovery, building occlusion restoration, building model extraction, and land cover classification. We create a digital city model using a single KOMPSAT-2 image and review the result.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.4 no.1
• /
• pp.25-31
• /
• 2008

In this paper, we propose a new method that separates background and foreground from stereo images. This method can be improved automatic target tracking system by using disparity map of the stereo vision system and background-separating mask, which can be obtained camera configuration parameters. We use disparity map and camera configuration parameters to separate object from background. Disparity map is made with block matching algorithm from stereo images. A morphology filter is used to compensate disparity error that can be caused by occlusion area. We could obtain a separated object from background when the proposed method was applied to real stereo cameras system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5C
• /
• pp.530-535
• /
• 2007

Disparity space image (DSI) technique is a method of establishing correspondence between a pair of images. It has a merit of generating a dense disparity map for each pixel. DSI has a cost function to be minimized, and it needs empirical weighting factors for occlusion penalty and match reward. This paper provides theoretical basis for the weighting factors, which depend on image noise and contrast between an object and background.

• Journal of information and communication convergence engineering
• /
• v.16 no.2
• /
• pp.114-124
• /
• 2018

This paper illustrates a vision-based vehicle positioning method at an intersection to support the C-ITS. It removes the minor shadow that causes the merging problem by simply eliminating the fractional parts of a quotient image. In order to separate the occlusion, it firstly performs the distance transform to analyze the contents of the single foreground object to find seeds, each of which represents one vehicle. Then, it applies the watershed to find the natural border of two cars. In addition, a general vehicle model and the corresponding space estimation method are proposed. For performance evaluation, the corresponding ground truth data are read and compared with the vision-based detected data. In addition, two criteria, IOU and DEER, are defined to measure the accuracy of the extracted data. The evaluation result shows that the average value of IOU is 0.65 with the hit ratio of 97%. It also shows that the average value of DEER is 0.0467, which means the positioning error is 32.7 centimeters.

• Journal of Internet Computing and Services
• /
• v.19 no.6
• /
• pp.41-51
• /
• 2018

Recently, in the field of video surveillance, deep learning based learning method is applied to intelligent video surveillance system, and various events such as crime, fire, and abnormal phenomenon can be robustly detected. However, since occlusion occurs due to the loss of 3d information generated by projecting the 3d real-world in 2d image, it is need to consider the occlusion problem in order to accurately detect the object and to estimate the pose. Therefore, in this paper, we detect moving objects by solving the occlusion problem of object detection process by adding depth information to existing RGB information. Then, using the convolution neural network in the detected region, the positions of the 14 keypoints of the human joint region can be predicted. Finally, in order to solve the self-occlusion problem occurring in the pose estimation process, the method for 3d human pose estimation is described by extending the range of estimation to the 3d space using the predicted result of 2d keypoint and the deep neural network. In the future, the result of 2d and 3d pose estimation of this research can be used as easy data for future human behavior recognition and contribute to the development of industrial technology.

• Korean Journal of Radiology
• /
• v.20 no.6
• /
• pp.1001-1002
• /
• 2019

• Journal of Digital Contents Society
• /
• v.3 no.1
• /
• pp.1-9
• /
• 2002

This paper is proposed to algorithm for measuring traffic information automatically, for example, volume count, speed and occupancy rate, from CCTV camera images installed on highway, add to function of image detectors which can be collected the traffic information. Recently the method of traffic informations are counted in lane one by one, but this manner is occurred critical errors by occlusion frequently in case of passing larger vehicles(bus, truck etc.) and is impossible to measure in the 8 lanes of highway. In this paper, installed the detection area include with all lanes, traffic informations are collected using tracking algorithm with passing vehicles individually in this detection area, thus possible to detect all of 8 lanes. The experiment have been conducted two different real road scenes for 20 minutes. For the experiments, the images are provided with CCTV camera which was installed at Kiheung Interchange upstream of Kyongbu highway, and video recording images at Chungkye Tunnel. For image processing, images captured by frame-grabber board 30 frames per second, $640{\times}480$ pixels resolution and 256 gray-levels to reduce the total amount of data to be interpreted.