• The Journal of the Korea Contents Association
• /
• v.18 no.2
• /
• pp.1-10
• /
• 2018

Aggression among pigs adversely affects economic returns and animal welfare in intensive pigsties. Recently, some studies have applied information technology to a livestock management system to minimize the damage resulting from such anomalies. Nonetheless, detecting each pig in a crowed pigsty is still challenging problem. In this paper, we propose a new Kinect camera and deep learning-based monitoring system for the detection of the individual pigs. The proposed system is characterized as follows. 1) The background subtraction method and depth-threshold are used to detect only standing-pigs in the Kinect-depth image. 2) The standing-pigs are detected by using YOLO (You Only Look Once) which is the fastest and most accurate model in deep learning algorithms. Our experimental results show that this method is effective for detecting individual pigs in real time in terms of both cost-effectiveness (using a low-cost Kinect depth sensor) and accuracy (average 99.40% detection accuracies).

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.268-269
• /
• 2021

본 논문에서는 RGB이미지와 Depth 이미지를 촬영할 수 있는 촬영 장비인 Azure Kinect를 사용해 다시점 촬영 시스템 구성을 위한 카메라 동기화 시스템을 제안한다. 제안한 시스템에는 8대의 Azure Kinect 카메라를 사용하고 있으며 각 카메라는 3.5-mm 오디오 케이블로 연결되어 외부동기화 신호를 전달한다. 그리고 이미지를 저장할 때 발생하는 메모리에서의 병목현상을 최소화하기 위해 촬영 시스템의 동작을 16개의 버퍼로 나누어 병렬 컴퓨팅으로 진행한다. 이후 동기화 여부에 따른 차리를 디바이스 타임스탬프를 기준으로 하여 비교한다.

• Journal of Broadcast Engineering
• /
• v.25 no.5
• /
• pp.808-811
• /
• 2020

This paper proposes a method to minimize the error of the Kinect camera sensor by using a random undirected Kalman filter. Kinect cameras, which provide RGB values and depth information, cause nonlinear errors in the sensor, causing problems in various applications such as skeleton detection. Conventional methods have tried to remove errors by using various filtering techniques. However, there is a limit to removing nonlinear noise effectively. Therefore, in this paper, a randomized unscented Kalman filter was applied to predict and update the nonlinear noise characteristics, we next tried to enhance a performance of skeleton detection. The experimental results confirmed that the proposed method is superior to the conventional method in quantitative results and reconstructed images on 3D space.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.12 no.1
• /
• pp.27-33
• /
• 2016

In this study we propose a method for 3D landform reconstruction and object modeling method by generating contour lines on the map using a depth sensor which abstracts characteristics of geological layers from the depth map. Unlike the common visual camera, the depth-sensor is not affected by the intensity of illumination, and therefore a more robust contour and object can be extracted. The algorithm suggested in this paper first abstracts the characteristics of each geological layer from the depth map image and rearranges it into the proper order, then creates contour lines using the Bezier curve. Using the created contour lines, 3D images are reconstructed through rendering by mapping RGB images of the visual camera. Experimental results show that the proposed method using depth sensor can reconstruct contour map and 3D modeling in real-time. The generation of the contours with depth data is more efficient and economical in terms of the quality and accuracy.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.9 no.1
• /
• pp.141-150
• /
• 2013

This study proposes technology using Active Shape Model to track the object separating it by depth-sensors. Unlike the common visual camera, the depth-sensor is not affected by the intensity of illumination, and therefore a more robust object can be extracted. The proposed algorithm removes the horizontal component from the information of the initial depth map and separates the object using the vertical component. In addition, it is also a more efficient morphology, and labeling to perform image correction and object extraction. By applying Active Shape Model to the information of an extracted object, it can track the object more robustly. Active Shape Model has a robust feature-to-object occlusion phenomenon. In comparison to visual camera-based object tracking algorithms, the proposed technology, using the existing depth of the sensor, is more efficient and robust at object tracking. Experimental results, show that the proposed ASM-based algorithm using depth sensor can robustly track objects in real-time.

• Journal of the Society of Naval Architects of Korea
• /
• v.58 no.6
• /
• pp.382-390
• /
• 2021

The present study suggests the application of a depth camera for wave height field measurement, focusing on the calibration procedure and test setup. Azure Kinect system is used to measure the water surface elevation, with a field of view of 800 mm × 800 mm and repetition rate of 30 Hz. In the optimal optical setup, the spatial resolution of the field of view is 288 × 320 pixels. To detect the water surface by the depth camera, tracer particles that float on the water and reflects infrared is added. The calibration consists of wave height scaling and correction of the barrel distortion. A polynomial regression model of image correction is established using machine learning. The measurement results by the depth camera are compared with capacitance type wave height gauge measurement, to show good agreement.

• The Journal of Korea Robotics Society
• /
• v.13 no.4
• /
• pp.230-236
• /
• 2018

3D depth perception has played an important role in robotics, and many sensory methods have also proposed for it. As a photodetector for 3D sensing, single photon avalanche diode (SPAD) is suggested due to sensitivity and accuracy. We have researched for applying a SPAD chip in our fusion system of time-of-fight (ToF) sensor and stereo camera. Our goal is to upsample of SPAD resolution using RGB stereo camera. Currently, we have 64 x 32 resolution SPAD ToF Sensor, even though there are higher resolution depth sensors such as Kinect V2 and Cube-Eye. This may be a weak point of our system, however we exploit this gap using a transition of idea. A convolution neural network (CNN) is designed to upsample our low resolution depth map using the data of the higher resolution depth as label data. Then, the upsampled depth data using CNN and stereo camera depth data are fused using semi-global matching (SGM) algorithm. We proposed simplified fusion method created for the embedded system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.8
• /
• pp.1931-1940
• /
• 2014

In this paper, we propose a new hand shape recognition algorithm based on the geometric features using the convex-hull from the depth image acquired by Kinect system. Kinect is a camera providing a depth image and user's skeleton information and used for detecting hand region. In the proposed algorithm, hand region is detected in a depth image acquired by Kinect and convex-hull of the region is found. Boundary points caused by noise and unnecessary points for recognition are eliminated in the convex-hull that changes depending on hand shape. Hand shape is recognized by the sum of internal angle of a polygon that is matched with convex-hull reconstructed with selected boundary points. Through experiments, we confirm that proposed algorithm shows high recognition rate not only for five models but also those cases rotated.

• Korean Journal of Computational Design and Engineering
• /
• v.21 no.1
• /
• pp.9-19
• /
• 2016

Applying human engineering simulation to analyzing work capability and movements of operators during manufacturing is highly demanded. However, difficulty in modeling digital human required for simulation makes engineers to be reluctant to utilize human simulation for their tasks. This paper addresses such problem on human engineering simulation by developing the technology to automatize human modeling with multiple Kinects at different depths. The Kinects enable us to acquire the movements of digital human which are essential data for implementing human engineering simulation. In this paper, we present a system for modeling automation of digital human. Especially, the system provides a way of generating the digital model of workers' movement and position using multiple Kinects which cannot be generated by single Kinect. Lastly, we verify the effects of the developed system in terms of modeling time and accuracy by applying the system to four different scenarios. In conclusion, the proposed system makes it possible to generate the digital human model easily and reduce costs and time for human engineering simulation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2585-2598
• /
• 2015

Hand posture recognition has played a very important role in Human Computer Interaction (HCI) and Computer Vision (CV) for many years. The challenge arises mainly due to self-occlusions caused by the limited view of the camera. In this paper, a robust hand posture recognition approach based on 3D point cloud from two RGB-D sensors (Kinect) is proposed to make maximum use of 3D information from depth map. Through noise reduction and registering two point sets obtained satisfactory from two views as we designed, a multi-viewed hand posture point cloud with most 3D information can be acquired. Moreover, we utilize the accurate reconstruction and classify each point cloud by directly matching the normalized point set with the templates of different classes from dataset, which can reduce the training time and calculation. Experimental results based on posture dataset captured by Kinect sensors (from digit 1 to 10) demonstrate the effectiveness of the proposed method.