• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.5
• /
• pp.2327-2347
• /
• 2018

Human actions can be recognized from depth sequences. In the proposed algorithm, we initially construct depth, motion maps (DMM) by projecting each depth frame onto three orthogonal Cartesian planes and add the motion energy for each view. The body part of the action (BPoA) is calculated by using bounding box with an optimal window size based on maximum spatial and temporal changes for each DMM. Furthermore, feature vector is constructed by using BPoA for each human action view. In this paper, we employed an ensemble based learning approach called Rotation Forest to recognize different actions Experimental results show that proposed method has significantly outperforms the state-of-the-art methods on Microsoft Research (MSR) Action 3D and MSR DailyActivity3D dataset.

• Journal of Broadcast Engineering
• /
• v.22 no.4
• /
• pp.429-437
• /
• 2017

2D-to-3D conversion technology has been studied over past decades and integrated to commercial 3D displays and 3DTVs. Generally, depth cues extracted from a static image is used for generating a depth map followed by DIBR (Depth Image Based Rendering) for producing a stereoscopic image. Further, motion is also an important cue for depth estimation and is estimated by block-based motion estimation, optical flow and so forth. This papers proposes a new method for motion depth generation using Motion History Image (MHI) and evaluates the feasiblity of the MHI utilization. In the experiments, the proposed method was performed on eight video clips with a variety of motion classes. From a qualitative test on motion depth maps as well as the comparison of the processing time, we validated the feasibility of the proposed method.

• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.3-10
• /
• 2018

Depth map has been utilized in a varity of fields. Recently research on generating depth map by artificial neural network (ANN) has gained much interest. This paper validates the feasibility of implementing the ready-made depth map generation by convolutional neural network (CNN). First, for a given image, a depth map is generated by the weighted average of a saliency map as well as a motion history image. Then CNN network is trained by test images and depth maps. The objective and subjective experiments are performed on the CNN and showed that the CNN can replace the ready-made depth generation method.

• Journal of Broadcast Engineering
• /
• v.16 no.1
• /
• pp.44-53
• /
• 2011

In this paper, we propose a 3D conversion algorithm of 2D video using depth layer partition method. In the proposed algorithm, we first set frame groups using cut detection algorithm. Each divided frame groups will reduce the possibility of error propagation in the process of motion estimation. Depth image generation is the core technique in 2D/3D conversion algorithm. Therefore, we use two depth map generation algorithms. In the first, segmentation and motion information are used, and in the other, edge directional histogram is used. After applying depth layer partition algorithm which separates objects(foreground) and the background from the original image, the extracted two depth maps are properly merged. Through experiments, we verify that the proposed algorithm generates reliable depth map and good conversion results.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1207-1210
• /
• 2022

2D 이미지로부터 카메라의 위치 정보를 추정할 수 있는 Structure-from-Motion (SfM) 기술과 dense depth map 을 추정하는 Multi-view Stereo (MVS) 기술을 이용하여 2D 이미지에서 point cloud 와 같은 3D data 를 얻을 수 있다. 3D data 는 VR, AR, 메타버스와 같은 컨텐츠에 사용되기 위한 핵심 요소이다. Point cloud 는 보통 VR, AR, 메타버스와 같은 많은 분야에 이용되기 위해 mesh 형태로 변환된 후 texture 를 입히는 Texturing 과정이 필요하다. 기존의 Texturing 방법에서는 mesh의 face에 사용될 image의 outlier를 제거하기 위해 color 정보만을 이용했다. Color 정보를 이용하는 방법은 mesh 의 face 에 대응되는 image 의 수가 충분히 많고 움직이는 물체에 대한 outlier 에는 효과적이지만 image 의 수가 부족한 경우와 부정확한 카메라 파라미터에 대한 outlier 에는 부족한 성능을 보인다. 본 논문에서는 Texturing 과정의 view selection 에서 depth 정보를 추가로 이용하여 기존 방법의 단점을 보완할 수 있는 방법을 제안한다.

• International Journal of Contents
• /
• v.10 no.3
• /
• pp.9-16
• /
• 2014

Depth-image-based rendering is generally used in real-time 2D-to-3D conversion for 3DTV. However, inaccurate depth maps cause flickering issues between image frames in a video sequence, resulting in eye fatigue while viewing 3DTV. To resolve this flickering issue, we propose a new 2D-to-3D conversion scheme based on fast and robust depth-map generation from a 2D video sequence. The proposed depth-map generation algorithm divides an input video sequence into several cuts using a color histogram. The initial depth of each cut is assigned based on a hypothesized depth-gradient model. The initial depth map of the current frame is refined using color and motion information. Thereafter, the depth map of the next frame is updated using the difference image to reduce depth flickering. The experimental results confirm that the proposed scheme performs real-time 2D-to-3D conversions effectively and reduces human eye fatigue.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.5
• /
• pp.1856-1869
• /
• 2015

This paper addresses the issues of 3D human activity detection, tracking and recognition from RGB-D video sequences using a feature structured framework. During human tracking and activity recognition, initially, dense depth images are captured using depth camera. In order to track human silhouettes, we considered spatial/temporal continuity, constraints of human motion information and compute centroids of each activity based on chain coding mechanism and centroids point extraction. In body skin joints features, we estimate human body skin color to identify human body parts (i.e., head, hands, and feet) likely to extract joint points information. These joints points are further processed as feature extraction process including distance position features and centroid distance features. Lastly, self-organized maps are used to recognize different activities. Experimental results demonstrate that the proposed method is reliable and efficient in recognizing human poses at different realistic scenes. The proposed system should be applicable to different consumer application systems such as healthcare system, video surveillance system and indoor monitoring systems which track and recognize different activities of multiple users.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.356-359
• /
• 2007

In this paper, the stability of a rotating cantilever pipe conveying fluid with a crack is investigated by the numerical method. That is, the influences of the rotating angular velocity, mass ratio and crack severity on the critical flow velocity for flutter instability of system are studied. The equations of motion of rotating pipe are derived using the Euler beam theory and the Lagrange's equation. The crack section of pipe is represented by a local flexibility matrix connecting two undamaged pipe segments. The crack is assumed to be in the first mode of fracture and to be always opened during the vibrations. Generally, the critical flow velocity for flutter is proportional to the angular velocity and the depth of crack. Also, the critical flow velocity and stability maps of the rotating pipe system as a function of mass ratio for the changing each parameter are obtained.

• Journal of Computing Science and Engineering
• /
• v.12 no.1
• /
• pp.1-11
• /
• 2018

Human activities recognition is a challenging task due to its complexity of human movements and the variety performed by different subjects for the same action. This paper presents a recognition algorithm by using skeleton information generated from depth maps. Concatenating motion features and temporal constraint feature produces feature vector. Reducing dictionary scale proposes an improved fast classifier based on sparse representation. The developed method is shown to be effective by recognizing different activities on the UTD-MHAD dataset. Comparison results indicate superior performance of our method over some existing methods.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.17 no.10
• /
• pp.1002-1009
• /
• 2007

In this paper, the dynamic stability of a cracked simply supported pipe conveying fluid with an attached mass is investigated. Also, the effect of attached mass on the dynamic stability of a simply supported pipe conveying fluid is presented for the different positions and depth of the crack. Based on the Euler-Bernouli beam theory, the equation of motion can be constructed by the energy expressions using extended Hamilton's principle. The crack section is represented by a local flexibility matrix connecting two undamaged pipe segments. The crack is assumed to be in the first mode of a fracture and to be always opened during the vibrations. Finally, the critical flow velocities and stability maps of the pipe conveying fluid are obtained by changing the attached mass and crack severity.