• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.9
• /
• pp.139-147
• /
• 2014

In this paper, we present a novel method for simultaneous detection and tracking of multiple objects using dual-layer particle filtering. The proposed dual-layer particle sampling (DLPS) algorithm consists of parent-particles (PP) in the first layer for detecting multiple objects and child-particles (CP) in the second layer for tracking objects. In the first layer, PPs detect persons using a classifier trained by the intersection kernel support vector machine (IKSVM) at each particle under a randomly selected scale. If a certain PP detects a person, it generates CPs, and makes an object model in the detected object region for tracking the detected object. While PPs that have detected objects generate CPs for tracking, the rest of PPs still move for detecting objects. Experimental results show that the proposed method can automatically detect and track multiple objects, and efficiently reduce the processing time using the sampled particles based on motion distribution in video sequences.

• Journal of IKEEE
• /
• v.17 no.4
• /
• pp.418-427
• /
• 2013

In this paper, we propose a parallel deblocking filter algorithm for H.264/AVC video standard. The deblocking filter has different filter processes according to boundary strength (BS) and each filter process requires various conditional calculations. The order of filtering makes it difficult to parallelize deblocking filter calculations. The proposed deblocking filter algorithm is performed on PRAGRAM which is a 1-D coarse grained reconfigurable architecture (CGRA). Each filter calculation is accelerated using uni-directional pipelined architecture of PRAGRAM. The filter selection and the conditional calculations are efficiently performed using dynamic reconfiguration and conditional reconfiguration. The parallel deblocking filter algorithm uses 225 cycles to process a macroblock and it can process a full HD image at 150 MHz.

• Smart Media Journal
• /
• v.1 no.3
• /
• pp.29-35
• /
• 2012

A depth image-based rendering (DIBR) technique is one of the rendering processes of virtual views with a color image and the corresponding depth map. The most important issue of DIBR is that the virtual view has no information at newly exposed areas, so called dis-occlusion. In this paper, we propose an intermediate view generation algorithm using the Kinect depth camera that utilizes the infrared structured light. After we capture a color image and its corresponding depth map, we pre-process the depth map. The pre-processed depth map is warped to the virtual viewpoint and filtered by median filtering to reduce the truncation error. Then, the color image is back-projected to the virtual viewpoint using the warped depth map. In order to fill out the remaining holes caused by dis-occlusion, we perform a background-based image in-painting operation. Finally, we obtain the synthesized image without any dis-occlusion. From experimental results, we have shown that the proposed algorithm generated very natural images in real-time.

• Smart Media Journal
• /
• v.2 no.4
• /
• pp.27-33
• /
• 2013

Multi-view video system provides both realistic 3D feelings and free-view navigation. But it is hard to transmit too huge data, so we send only two or three view images and generate intermediate view image using depth information. In this paper, we propose high quality multi-view image generation method from stereoscopic images. Since the stereo matching method does not provide accurate disparity values for all the pixels, especially at the occlusion area, we propose an occlusion handling method using the background pixels at first. We also apply a joint bilateral filtering to enhance the disparity map at the object boundary since it can affect the quality of synthesized images significantly. Finally, we can generate virtual view images at intermediate view positions using confidence map to reduce bad pixel and hole's error. Experimental results show the proposed method performs better than the conventional method.

• Korean Journal of Applied Biomechanics
• /
• v.17 no.4
• /
• pp.65-71
• /
• 2007

The purpose of this study was to investigate variability of kinematic factors affecting the record in women's javelin throwing. For this study, 8 female-javelin thrower participated in this experiment. The three digital video cameras (Sony, 120x) were used to record motions. Kwon3D 2.1 was used to process data and they were analyzed with Excell for factors. The sampling rate of a camera was 60Hz and shutter speed of a camera was 1/1000sec. The coordinate data were filtered using a fourth-order Butterworth low pass filtering with an estimated optimum cut-off frequency of 6Hz. The results were as follows: 1. From cross step to landing of delivery, the average velocities of CoM of non-dominant athletes were greater than dominant athletes and those of CoM of non-dominant athletes less than dominant athletes, but at release dominant athletes had a lower average velocity and a variability than non-dominant athletes. 2. From cross step to landing of delivery, the average throwing velocities and variabilities of a javelin of dominant athletes were greater than dominant athletes, but at release, dominant athletes had a higher velocity than dominant athletes and had a equal variability. 3. At every events, a forward or backward angles and variabilities of non-dominant athletes were greater than dominant athletes. 4. From cross step to landing of delivery, dominant athletes' elbow average angles were greater than non-dominant athletes and the variabilities of latter less than non-dominant athletes, but at release dominant athletes' variabilities were smaller than non-dominant athletes. 5. At landing of delivery, dominant athletes' knee average angles and variabilities of a supporting foot were a greater than non-dominant athletes, and at release, dominant athletes' knee average angles was a greater but variabilities less than non-dominant athletes. In conclusion, the dominant threw javelins fast while having stable postures and the range of elbow's angle large.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.22-27
• /
• 2014

Blocking and ringing artifacts continue to be the most serious defects that occur in images and video streams compressed to low bit rates using block-based discrete cosine transform(DCT) compression standards. These artifacts contain the high frequency components near the block and the edge boundaries. Usually the lowpass filter can remove them. However, simple lowpass filter results into blur by removing important information such as edges at the same time. To overcome these problems, we propose a novel postfiltering algorithm that calculate the weight value based on the intensity similarity in the neighboring pixels and multiply this weight to the Gaussian lowpass filter coefficient. Experimental results show that the proposed technique provides satisfactory performance in both objective and subjective image quality.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.1
• /
• pp.20-28
• /
• 2012

Gait analysis is an examination which extracts objective information from observing human gait and assesses the function. The equipments used recently for gait analysis are expensive due to multiple cameras and force plates, and require the large space to set up the system. In this paper, we proposed a method to measure human gait motions in 3D from a monocular video. Our approach was based on particle filtering to track human motion without training data and previous information about a gait. We used dynamics to make physics-based motions with the consideration of contacts between feet and base. In a walking sequence, our approach showed the mean angular error of $12.4^{\circ}$ over all joints, which was much smaller than the error of $34.6^{\circ}$ with the conventional particle filter. These results showed that a monocular camera is able to replace the existing complicated system for measuring human gait quantitatively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.4C
• /
• pp.277-282
• /
• 2012

In this paper, we present a real-time eye contact system for realistic telepresence using a Kinect depth camera. In order to generate the eye contact image, we capture a pair of color and depth video. Then, the foreground single user is separated from the background. Since the raw depth data includes several types of noises, we perform a joint bilateral filtering method. We apply the discontinuity-adaptive depth filter to the filtered depth map to reduce the disocclusion area. From the color image and the preprocessed depth map, we construct a user mesh model at the virtual viewpoint. The entire system is implemented through GPU-based parallel programming for real-time processing. Experimental results have shown that the proposed eye contact system is efficient in realizing eye contact, providing the realistic telepresence.

• Journal of Broadcast Engineering
• /
• v.10 no.3
• /
• pp.286-296
• /
• 2005

This paper presents a stereo-based image compression and transmission system for 3D realistic television. In the proposed system, a disparity map is extracted from an input stereo image pair and the extracted disparity map and one of two input images are transmitted or stored at a local or remote site. However, correspondences can not be determined in occlusion areas. Thus, it is not easy to recover 3D information in such regions. In this paper, a reconstruction image compensation algorithm based on error block concealment and in-loop filtering is proposed to minimize the reconstruction error in generating stereo image pair. The effectiveness of the proposed algorithm is shown in term of objective accuracy of reconstruction image with several real stereo image pairs.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.10 no.3
• /
• pp.139-147
• /
• 2007

In military transportation, the use of wide trailer for transporting the large and heavy weight equipments such as tank, armoured vehicle, and mobile gunnery is quite common. So, the vulnerability of causing traffic accidents for these wide military trailer to bump or collide with another car in adjacent lane is very high due to its broad width in excess of its own lane's width. Also, the possibility of these strayed accidents can be increased especially by the careless driver. In this paper, the recognition system of lane and vehicle headway direction is developed to detect the possible collision and warn the driver to prevent the fatal accident. In the system development, Kalman filtering is used first to extract the border of driving lane from the video images supplied by the CCD camera attached to the vehicle and the driving lane detection is completed with regression analysis. Next, the vehicle headway direction is recognized by using neural network scheme with the extracted parameters of the detected driving lane feature. The practical experiments for the developed system are also carried out in the real traffic road of Seoul city area and the results show us the more than 90% accuracy in recognizing the driving lane and vehicle headway direction.