• Journal of Broadcast Engineering
• /
• v.17 no.3
• /
• pp.437-446
• /
• 2012

A face detection algorithms using two-dimensional (2-D) intensity or color images have been studied for decades. Recently, with the development of low-cost range sensor, three-dimensional (3-D) information (i.e., depth image that represents the distance between a camera and objects) can be easily used to reliably extract facial features. Most people have a similar pattern of 3-D facial structure. This paper proposes a face detection method using intensity and depth images. At first, adaboost algorithm using intensity image classifies face and nonface candidate regions. Each candidate region is divided into $5{\times}5$ blocks and depth values are averaged in each block. Then, $5{\times}5$ block rank pattern is constructed by sorting block averages of depth values. Finally, candidate regions are classified as face and nonface regions by matching the constructed depth map based block rank patterns and a template pattern that is generated from training data set. For template matching, the $5{\times}5$ template block rank pattern is prior constructed by averaging block ranks using training data set. The proposed algorithm is tested on real images obtained by Kinect range sensor. Experimental results show that the proposed algorithm effectively eliminates most false positives with true positives well preserved.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.12C
• /
• pp.1029-1038
• /
• 2008

In this paper, we propose a method for an arbitrary-view image generation in multi-view video and methods for pre- and post-processing to compensate unattended regions in the generated image. To generate an arbitrary-view image, camera geometry is used. Three dimensional coordinates of image pixels can be obtained by using depth information of multi-view video and parameter information of multi-view cameras, and by replacing three dimensional coordinates on a two dimensional image plane of other view, arbitrary-view image can be reconstructed. However, the generated arbitrary-view image contains many unattended regions. In this paper, we also proposed a method for compensating these regions considering temporal redundancy and spatial direction of an image and an error of acquired multi-view image and depth information. Test results show that we could obtain a reliably synthesized view-image with objective measurement of PSNR more than 30dB and subjective estimation of DSCQS(double stimulus continuous quality scale method) more than 3.5 point.

• Journal of Broadcast Engineering
• /
• v.23 no.5
• /
• pp.598-605
• /
• 2018

Behavior awareness is a technology that recognizes human behavior through data and can be used in applications such as risk behavior through video surveillance systems. Conventional behavior recognition algorithms have been performed using the 2D camera image device or multi-mode sensor or multi-view or 3D equipment. When two-dimensional data was used, the recognition rate was low in the behavior recognition of the three-dimensional space, and other methods were difficult due to the complicated equipment configuration and the expensive additional equipment. In this paper, we propose a method of recognizing human behavior using only CCTV images without additional equipment using only RGB and depth information. First, the skeleton extraction algorithm is applied to extract points of joints and body parts. We apply the equations to transform the vector including the displacement vector and the relational vector, and study the continuous vector data through the RNN model. As a result of applying the learned model to various data sets and confirming the accuracy of the behavior recognition, the performance similar to that of the existing algorithm using the 3D information can be verified only by the 2D information.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.1
• /
• pp.78-84
• /
• 2015

Depth estimation is often required for robot vision, 3D modeling, and motion control. Previous method is based on the focus measures which are calculated for a series of image by a single camera at different distance between and object. This method, however, has disadvantage of taking a long time for calculating the focus measure since the mask operation is performed for every pixel in the image. In this paper, we estimates the depth by using the focus measure of the boundary pixels located between the objects in order to minimize the depth estimate time. To detect the boundary of an object consisting of a straight line and a circle, we use the Hough transform and estimate the depth by using the focus measure. We performed various experiments for PCB images and obtained more effective depth estimation results than previous ones.

• Journal of Broadcast Engineering
• /
• v.14 no.3
• /
• pp.366-377
• /
• 2009

In this paper, we implement the real-time system which extracts 3-dimensional coordinates from right and left images captured by a stereo camera and provides users with reality through a virtual space operated by the 3-dimensional coordinates. In general, all pixels in correspondence region are compared for the disparity estimation. However, for a real time process, the central coordinates of the correspondence region are only used in the proposed algorithm. In the implemented system, 3D coordinates are obtained by using the depth information derived from the estimated disparity and we set user's hand as a region of interest(ROI). After user's hand is detected as the ROI, the system keeps tracking a hand's movement and generates a virtual space that is controled by the hand. Experimental results show that the implemented system could estimate the disparity in real -time and gave the mean-error less than 0.68cm within a range of distance, 1.5m. Also It had more than 90% accuracy in the hand recognition.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.12
• /
• pp.197-207
• /
• 2014

In this paper, I propose an automatic extraction method of golf swing features using a practical TOF camera Kinect. I extracted 7 key swing frames and features using joints and depth information from a Kinect. I tested the proposed method on 50 swings from 10 players and showed the performace. It is meaningful that 3D swing features are extracted automatically using an inexpensive and simple system and specific numerical feature values can be used for the building of automatic swing analysis system.

• Journal of Information Processing Systems
• /
• v.13 no.2
• /
• pp.256-267
• /
• 2017

An active research area in computer vision, stereo matching is aimed at obtaining three-dimensional (3D) information from a stereo image pair captured by a stereo camera. To extract accurate 3D information, a number of studies have examined stereo matching algorithms that employ adaptive support weight. Among them, the adaptive census transform (ACT) algorithm has yielded a relatively strong matching capability. The drawbacks of the ACT, however, are that it produces low matching accuracy at the border of an object and is vulnerable to noise. To mitigate these drawbacks, this paper proposes and analyzes the features of an improved stereo matching algorithm that not only enhances matching accuracy but also is also robust to noise. The proposed algorithm, based on the ACT, adopts the truncated absolute difference and the multiple sparse windows method. The experimental results show that compared to the ACT, the proposed algorithm reduces the average error rate of depth maps on Middlebury dataset images by as much as 2% and that is has a strong robustness to noise.

• The Journal of Korea Robotics Society
• /
• v.3 no.1
• /
• pp.33-41
• /
• 2008

Based on object recognition technology, we present a new global localization method for robot navigation. For doing this, we model any indoor environment using the following visual cues with a stereo camera; view-based image features for object recognition and those 3D positions for object pose estimation. Also, we use the depth information at the horizontal centerline in image where optical axis passes through, which is similar to the data of the 2D laser range finder. Therefore, we can build a hybrid local node for a topological map that is composed of an indoor environment metric map and an object location map. Based on such modeling, we suggest a coarse-to-fine strategy for estimating the global localization of a mobile robot. The coarse pose is obtained by means of object recognition and SVD based least-squares fitting, and then its refined pose is estimated with a particle filtering algorithm. With real experiments, we show that the proposed method can be an effective vision- based global localization algorithm.

• Journal of Broadcast Engineering
• /
• v.16 no.1
• /
• pp.33-43
• /
• 2011

Recently, 3D displays are supplied in the 3D markets so that the demand for 3D stereoscopic contents increases. In general, a simple method is to use a stereoscopic camera. As well, the production of 3D from 2D materials is regarded as an important technology. Such conversion works have gained much interest in the field of 3D converting. However, the stereoscopic image generation from a single 2D image is limited to simple 2D to 3D conversion so that the better realistic perception is difficult to deliver to the users. This paper presents a new stereoscopic content production method where foreground objects undergo alive action events. Further stereoscopic animation is viewed on 3D displays. Given a 2D image, the production is composed of background image generation, foreground object extraction, object/background depth maps and stereoscopic image generation The alive objects are made using the geometric transformation (e.g., translation, rotation, scaling, etc). The proposed method is performed on a Korean traditional painting, Danopungjung as well as Pixar's Up. The animated video showed that through the utilization of simple object transformations, more realistic perception can be delivered to the viewers.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.95-101
• /
• 2023

Colmap is one of the innovative artificial intelligence technologies, highly effective as a tool in 3D reconstruction tasks. Moreover, it excels at constructing intricate 3D models by utilizing images and corresponding metadata. Colmap generates 3D models by merging 2D images, camera position data, depth information, and so on. Through this, it achieves detailed and precise 3D reconstructions, inclusive of objects from the real world. Additionally, Colmap provides rapid processing by leveraging GPUs, allowing for efficient operation even within large data sets. In this paper, we have presented a method of collecting 2D images of traditional Korean towers and reconstructing them into 3D models using Colmap. This study applied this technology in the restoration process of traditional stone towers in South Korea. As a result, we confirmed the potential applicability of Colmap in the field of cultural heritage restoration.