• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.111-113
• /
• 2012

KINECT is a gesture recognition camera produced by Microsoft Corp. KINECT SDK are widely available and many applications are actively being developed. Especially, KIET (Kinect Image Extraction Technique) has been used mainly for extracting moving objects from the input image. However, KIET has difficulty in extracting the human head due to the absorption of light. In order to overcome this problem, this paper proposes a new method for improving the KIET performance by using both color-image and depth image. Through experimental results, it is shown that the proposed method performs better than the conventional KIET algorithm.

• 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.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.5
• /
• pp.457-461
• /
• 2013

This paper proposes an image feature-based real-time RGB-D (Red-Green-Blue Depth) 3D SLAM (Simultaneous Localization and Mapping) system. RGB-D data from Kinect style sensors contain a 2D image and per-pixel depth information. 6-DOF (Degree-of-Freedom) visual odometry is obtained through the 3D-RANSAC (RANdom SAmple Consensus) algorithm with 2D image features and depth data. For speed up extraction of features, parallel computation is performed with GPU acceleration. After a feature manager detects a loop closure, a graph-based SLAM algorithm optimizes trajectory of the sensor and builds a 3D point cloud based map.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3924-3940
• /
• 2020

Dynamic hand gesture recognition(d-HGR) plays an important role in human-computer interaction(HCI) system. With the growth of hand-pose estimation as well as 3D depth sensors, depth, and the hand-skeleton dataset is proposed to bring much research in depth and 3D hand skeleton approaches. However, it is still a challenging problem due to the low resolution, higher complexity, and self-occlusion. In this paper, we propose a hand-shape feature extraction(HSFE) network to produce robust hand-shapes. We build a hand-shape model, and hand-skeleton based on LSTM to exploit the temporal information from hand-shape and motion changes. Fusion between two models brings the best accuracy in dynamic hand gesture (DHG) dataset.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.10
• /
• pp.1731-1737
• /
• 2016

In this paper, a method is proposed to recognize human actions as nonverbal expression; the proposed method is composed of two steps which are action representation and action recognition. First, MHI(Motion History Image) is used in the action representation step. This method includes segmentation based on depth information and generates spatio-temporal templates to describe actions. Second, CNN(Convolution Neural Network) which includes feature extraction and classification is employed in the action recognition step. It extracts convolution feature vectors and then uses a classifier to recognize actions. The recognition performance of the proposed method is demonstrated by comparing other action recognition methods in experimental results.

• Journal of Sensor Science and Technology
• /
• v.15 no.5
• /
• pp.328-333
• /
• 2006

Magnetic Flux Leakage (MFL) methods are widely employed for the nondestructive evaluation (NDE) of gas pipelines. In the application of MFL pipeline inspection technology, corrosion anomalies are detected and identified via their leakage filed due to changes in wall thickness. The gas industry is keenly interested in automating the interpretation process, because a large amount of data to be analyzed is generated for in-line inspection. This paper presents a novel approach to the tasks of data segmentation, feature extraction and depth estimation from gas pipelines. Also, we will show that the proposed method successfully identifying artificial defects.

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.270-273
• /
• 1999

Circular dynamic stereo has special advantages as it enables a 3-D measurement using a single TV camera and also enables a high accurate measurement without a cumbersome calibration. Annular particle streaks are recorded using this system and the size of annular streaks directly concerns to the depth from TV camera. That is, the size of annular streaks is inversely proportional to the depth from the TV camera and the depth can be measured automatically by image processing technique. Overlapped streaks can be processed also by our method. The flow measurement in a water tank is one of the applications of our system. Tracer particles are introduced into the water in a flow measurement. Since the tracer particles flow with water, three-dimensional velocity distributions in the water tank can be obtained by measuring the all movement of tracer particles. Experimental results demonstrate the feasibility of our method.

• Journal of the Optical Society of Korea
• /
• v.17 no.5
• /
• pp.410-414
• /
• 2013

In this paper, we propose a 3D display method combining a pickup process using axially recorded multiple images and an integral imaging display process. First, we extract the color and depth information of 3D objects for displaying 3D images from axially recorded multiple 2D images. Next, using the extracted depth map and color images, elemental images are computationally synthesized based on a ray mapping model between 3D space and an elemental image plane. Finally, we display 3D images optically by an integral imaging system with a lenslet array. To show the usefulness of the proposed system, we carry out optical experiments for 3D objects and present the experimental results.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.27 no.1
• /
• pp.62-70
• /
• 1985

The purpose of this study is to investigate the basic data such the total, the daily maximum, and the peak stage of consumptive use of water and also the soil moisture extraction pattern for irrigation plan of tobacco during the growing period. The plots at which this study was conducted are divided into three fertilization levels of 30g, 60g, and 90g. Each block for three levels is divided as vinyl mulching and irrigation plot, vinyl mulching and nonirrigation plot, and nonmulching and irrigation plot. The results obtained are summarized as follows: 1. The evapotranspiration amount of mulching-irrigation plots are similar to that of mulching-nonirrigation plots. While, the evapotranspiration amount of mulching plots are different obviousely from that of nonmulching plots. Therefore, a significance was recognized between the mulching plots and the nonmulching plots. 2. The amount of evapotranspiration in case of 60g and 90g fertilization level was larger than that of 30g. But the 60g plots and the 90g plots showed little differences. 3. In the total amount of evapotranspiration for each of the experimental plots during the growing period, nonmulching-irrigation plot showed the largest value of 332.9mm, second the mulching-irrigation plot, 284. 9mm, and the mulching-nonirrigation plot, the smallest as 255. 9mm. 4. In the monthly average amount of evapotranspiration for each of the treatment plots, the mulching-irrigation the mulching-nonirrigation, and the nonmulching-irrigation plot showed 3. 6mm, 3. 2mm and 4. 2mm respectively. The daily maximum amount of evapotranspiration showed 5. 1mm, 4. 5mm, and 6.4mm for the mulching-irrigation, the mulching-nonirrigationl, and the nonmulching-irrigation plot respectively. 5. It was confirmed that the higher correlationship exists between the weight of dried leaves and the amount of evapotranspiration, and between the weight of dried leaves and the coefficient of evapotranspiration with the function of logarithms. The coefficient of evapotranspiration have a tendency to increase in proportion to the leaf area index. 6. The maximum coefficient of evapotranspration and the largest leaf area index showed 1. 45 and 5.5 respectively. The stage appeared maximum values was assumed to be before and after flowering. 7. The soil moisture extraction pattern has changed by the depth of root zone for the tobacco's growing. The soil moisture extraction influenced on the 20cm depth of soil after 15 days passed, the 30cm depth after 25 days passed and the whole root zone after 45 days passed from planting. It was shown in the only mulching-irrigation plot after S5days passed from planting that the rate of soil moisture extraction of 20cm layer was larger than that of 10cm layer.

• Journal of the Mineralogical Society of Korea
• /
• v.26 no.2
• /
• pp.129-138
• /
• 2013

River bank filtration has been considered as a promising alternative water management scheme, in which groundwater is extracted from an aquifer near a river after infiltration of the river water into the aquifer, thereby improving and maintaining the quality of water recovered. Iron (Fe) associated with sediment in contact with groundwater and infiltrating surface water is an important factor in determining the quality of water recovered from the pumping wells in river bank filtration. This study reports the results of Fe speciation in the aquifer sediment samples collected from different depths at the river bank filtration site in Changwon, studied using four different chemical extraction methods, namely, ferrozine, oxalate, HCl, and DCB methods. Overall, the results show that Fe(II) as well as the total Fe content decreases with depth down to ~20 m and then increases further below. This trend is consistent with the redox characteristics suggested by visual observation. The silt/clay size fraction (${\phi}$ < 62.5 ${\mu}M$) has up to 2~10 times more Fe compared with the sand size fraction (62.5 ${\mu}M$ < ${\phi}$ < 2 mm), depending on the extraction method. Of the four extraction methods, DCB solution extracted the most Fe from the sediment samples. The amounts of Fe extracted by the different extraction methods can be a good indicator of the redox conditions along the depth of the aquifer.