• Annual Conference of KIPS
• /
• 2010.11a
• /
• pp.1784-1787
• /
• 2010

General Purpose Graphic Processing Unit (GPGPU) computing is a technique that utilizes the high-performance many-core processors of high-end graphic cards for general-purpose computations such as 3D graphics, video/image processing, computer vision, scientific computing, HPC and many more. GPGPUs offer a vast amount of raw computing power, but programming is extremely challenging because of hardware idiosyncrasies. The open computing language (OpenCL) has been proposed as a vendor-independent GPGPU programming interface. OpenCL is very close to the hardware and thus does little to increase GPGPU programmability. In this paper we present how a set of digital camera image signal processing (ISP) filters can be realized efficiently on GPGPUs using OpenCL. Although we found ISP filters to be memory-bound computations, our GPGPU implementations achieve speedups of up to a factor of 64.8 over their sequential counterparts. On GPGPUs, our proposed optimizations achieved speedups between 145% and 275% over their baseline GPGPU implementations. Our experiments have been conducted on a Geforce GTX 275; because of OpenCL we expect our optimizations to be applicable to other architectures as well.

• Journal of Ocean Engineering and Technology
• /
• v.38 no.4
• /
• pp.174-186
• /
• 2024

In coastal video monitoring, the direct linear transform (DLT) method with ground control points (GCPs) is commonly used for geo-rectification. However, current practices often overlook the impact of GCP quantity, arrangement, and the geographical characteristics of beaches. To address this, we designed scenarios at Chuam Beach to evaluate how factors such as the distance from the camera to GCPs, the number of GCPs, and the height of each point affect the DLT method. Accuracy was assessed by calculating the root mean square error of the distance errors between the actual GCP coordinates and the image coordinates for each setting. This analysis aims to propose an optimal GCP placement method. Our results show that placing GCPs within 200 m of the camera ensures high accuracy with few points, whereas positioning them at strategic heights enhances shoreline extraction. However, since only fixed cameras were used in this study, factors like varying heights, orientations, and resolutions could not be considered. Based on data from a single location, we propose an optimal method for GCP placement that takes into account distance, number, and height using the DLT method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.4
• /
• pp.429-441
• /
• 2002

This paper concerns extracting 3D motion information from a 3D input device in real time focused to enabling effective human-computer interaction. In particular, we develop a novel algorithm for extracting 6 degrees-of-freedom motion information from a 3D input device by employing an epipolar geometry of stereo camera, color, motion, and structure information, free from requiring the aid of camera calibration object. To extract 3D motion, we first determine the epipolar geometry of stereo camera by computing the perspective projection matrix and perspective distortion matrix. We then incorporate the proposed Motion Adaptive Weighted Unmatched Pixel Count algorithm performing color transformation, unmatched pixel counting, discrete Kalman filtering, and principal component analysis. The extracted 3D motion information can be applied to controlling virtual objects or aiding the navigation device that controls the viewpoint of a user in virtual reality setting. Since the stereo vision-based 3D input device is wireless, it provides users with a means for more natural and efficient interface, thus effectively realizing a feeling of immersion.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.43 no.10
• /
• pp.902-909
• /
• 2015

In this paper, monovision based relative navigation for a satellite proximity operation is studied. The chaser satellite only uses one camera sensor to observe the target satellite and conducts image tracking to obtain the target pose information. However, by using only mono-vision, it is hard to get the depth information which is related to the relative distance to the target. In order to resolve the well-known difficulty in computing the depth information with the use of a single camera, the active contour method is adopted for the image tracking process. The active contour method provides the size of target image, which can be utilized to indirectly calculate the relative distance between the chaser and the target. 3D virtual reality is used in order to model the space environment where two satellites make relative motion and produce the virtual camera images. The unscented Kalman filter is used for the chaser satellite to estimate the relative position of the target in the process of glideslope approaching. Closed-loop simulations are conducted to analyze the performance of the relative navigation with the active contour method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.2
• /
• pp.79-88
• /
• 2004

Gaze detection is to locate the position on a monitor screen where a user is looking by computer vision. Gaze detection systems have numerous fields of application. They are applicable to the man-machine interface for helping the handicapped to use computers and the view control in three dimensional simulation programs. In our work, we implement it with a computer vision system setting a IR-LED based single camera. To detect the gaze position, we locate facial features, which is effectively performed with IR-LED based camera and SVM(Support Vector Machine). When a user gazes at a position of monitor, we can compute the 3D positions of those features based on 3D rotation and translation estimation and affine transform. Finally, the gaze position by the facial movements is computed from the normal vector of the plane determined by those computed 3D positions of features. In addition, we use a trained neural network to detect the gaze position by eye's movement. As experimental results, we can obtain the facial and eye gaze position on a monitor and the gaze position accuracy between the computed positions and the real ones is about 4.8 cm of RMS error.

• Korean Institute of Interior Design Journal
• /
• v.23 no.2
• /
• pp.71-79
• /
• 2014

The purpose of this study is to elucidate that photo, which has been used as original photo's purpose of information transfer in modern age, is now used as romantic reproduction which is the communication methods of architect's idea and thought through photographic vision which is beyond photograph own capabilities. The photos of Mies van der Rohe and Le Corbusier's architectural works are taken as an example for studying and analysing the way of deliverying the concept of creative work in the functional spaces in the modern era. It looked at the way of modern archirecture configuration, which architects wanted to show by pictures, such as concurrency, movement, sense of exhibition and concept of time-space and planarity on photographic vision such as multiview, movement, daily life exclusion, scenography and perspective loss. Reflecting that, I presents Le Corbusier and Mies van der Rohe's intention through photo by analyzing their picture of architecture by way of photograph techniques-camera position moving, over exposure, photomontage, silhouette technic and overlap technic. Mies van der Rohe and Le corbusier demonstrated the change and manipulation of the their architectural photos in different point of view. They express their architectural theories by photos of their works and overcome the limitation of expression of constructed building designed by them. The photos of architects's works in the case study with photos and descriptions introduce to their design concept. The design concept of the architects have become ideal concept for many contemporary architects and keep reproducing through the photos of their architectural works.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.3 s.309
• /
• pp.39-49
• /
• 2006

This paper proposes a hand-posture recognition method using reinforcement learning for the performance improvement of vision-based hand-posture recognition. The difficulties in vision-based hand-posture recognition lie in viewing direction dependency and self-occlusion problem due to the high degree-of-freedom of human hand. General approaches to deal with these problems include multiple camera approach and methods of limiting the relative angle between cameras and the user's hand. In the case of using multiple cameras, however, fusion techniques to induce the final decision should be considered. Limiting the angle of user's hand restricts the user's freedom. The proposed method combines angular features and appearance features to describe hand-postures by a two-layered data structure and reinforcement learning. The validity of the proposed method is evaluated by appling it to the hand-posture recognition system using three cameras.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.11
• /
• pp.75-87
• /
• 1998

KARES (KAIST Rehabilitation Engineering System) is the rehabilitation robot system in the type of the 6 degrees of freedom robot arm mounted on the wheelchair, in order to assist the independent livelihood of the disabled and the elderly. The interface device for programming and controlling of the robot arm is essential in the rehabilitation robotic system. Specially, in the case of the manual operation of the robot arm, the user has the burden of cognition and the difficulty for the operation of the robot arm. As a remedy, color vision system for the autonomous performance of jobs is proposed, and four basic desired jobs are specified. By mounting the camera in eye-in-hand type, color vision system for KARES is set up. The desired jobs for picking up the target and moving it to the user's face for drinking are successfully performed in real-time at the indoor environment.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.12
• /
• pp.1259-1266
• /
• 2014

Road signs provide important safety information about road and traffic conditions to drivers. Road signs include not only common traffic signs but also warning information regarding unexpected obstacles and road constructions. Therefore, accurate detection and identification of road signs is one of the most important research topics related to safe driving. In this paper, we propose a 3-D vision technique to automatically detect and track road signs in a video sequence which is acquired from a stereo vision camera mounted on a vehicle. First, color information is used to initially detect the sign candidates. Second, the SVM (Support Vector Machine) is employed to determine true signs from the candidates. Once a road sign is detected in a video frame, it is continuously tracked from the next frame until it is disappeared. The 2-D position of a detected sign in the next frame is predicted by the 3-D motion of the vehicle. Here, the 3-D vehicle motion is acquired by using the 3-D pose information of the detected sign. Finally, the predicted 2-D position is corrected by template-matching of the scaled template of the detected sign within a window area around the predicted position. Experimental results show that the proposed method can detect and track many types of road signs successfully. Tracking comparisons with two different methods are shown.

• Journal of Oral Medicine and Pain
• /
• v.21 no.1
• /
• pp.37-54
• /
• 1996

In this thesis, a new superimposition scheme using a computer vision system was proposed with 7 pairs of skull and ante-mortem photographs, which were already identified through other tests and DNA fingerprints at the Korea National Institute of Scientific Investigation. At this computer vision system, an unidentified skull was caught by video-camcoder with the MPEG and a ante-mortem photograph was scanned by scanner. These two images were processed and superimposed using pixel processing. Recognition of the individual identification by anatomical references was performed on the two superimposed images. These results were as followings. 1. For the enhancement of skull and ante-mortem photographs, various image processing schemes, such as SMOOTH, SHARPEN, EMBOSS, MOSAIC, ENGRAVE, INVERT, NEON and COLOR TO MONO, were applied using 3*5 window processing. As an image processing result of these methods, the optimal techniques were NEON, INVERT and ENGRAVE for the edge detection of skull and ante-mortem photograph. 2. Using various superimposition image processing techniques (SRCOR, SRCAND, SRCINVERT, SRCERASE, DSTINVERT, MERGEPAINT) were compared for the enhancement of image recognition. 3. By means of the video camera, the skull image was inputed directly to a computer system : superimposing it on the ante-mortem photograph made the identification more precise and time-saving. As mentioned above, this image processing techniques for the superimposition of skull and ante-mortem photographs simply used the previous approach, In other wrods, taking skull photographs and developing it to the same size as the ante-mortem photographs. This system using various image processing techniques on computer screen, a more precise and time-saving superimposition technique could be able to be applied in the area of individual identification in forensic practice.