• The KIPS Transactions:PartA
• /
• 제14A권5호
• /
• pp.301-308
• /
• 2007

This paper proposes high performance coprocessor architecture for real time dense disparity computation based on a phase-based binocular stereo matching technique called local weighted phase-correlation(LWPC). The algorithm combines the robustness of wavelet based phase difference methods and the basic control strategy of phase correlation methods, which consists of 4 stages. For parallel and efficient hardware implementation, the proposed architecture employs SIMD(Single Instruction Multiple Data Stream) architecture for each functional stage and all stages work on pipelined mode. Such that the newly devised pipelined linear array processor is optimized for the case of row-column image processing eliminating the need for transposed memory while preserving generality and high throughput. The proposed architecture is implemented with Xilinx HDL tool and the required hardware resources are calculated in terms of look up tables, flip flops, slices, and the amount of memory. The result shows the possibility that the proposed architecture can be integrated into one chip while maintaining the processing speed at video rate.

• The Journal of the Korea Contents Association
• /
• 제10권2호
• /
• pp.130-137
• /
• 2010

Light Drawing is a photographic technique which exposures are made at night or in a darkened room usually by moving a hand-held light source[1]. Due to the limitations of equipment and environment, users having difficulty in drawing a picture in 3D space. If user take a light drawing, they need a camera that have function and darkened environment. Alternative solution is that we can make a light drawing picture by using the computer drawing tool as in Photoshop. Nevertheless, this solution will let the User lose their interest in drawing because this solution cannot synchronize between the real action of human hand motion and the electronic input devices such as mouse and keyboard. This paper proposed a digital content that can make light drawing easier. We used a digital content that will facility Light Drawing easier. We can measure the light spot position by using the stereo camera. Based on the measured position of the light spot, we reproduce light drawing in virtual space by using drawing effect method.

• The Transactions of the Korea Information Processing Society
• /
• 제6권8호
• /
• pp.2262-2270
• /
• 1999

In this paper, we describe gesture recognition algorithm using computer vision sensor and HMM. The automatic hand region extraction has been proposed for initializing the tracking of the tele-operation gestures. For this, distance informations(disparity map) as results of stereo matching of initial left and right images are employed to isolate the hand region from a scene. PDOE(positive difference of edges) feature images adapted here have been found to be robust against noise and background brightness. The KNU/KAERI(K/K) gesture instruction set is defined for tele-operation in atomic electric power stations. The composite recognition model constructed by concatenating three gesture instruction models including pre-orders, basic orders, and post-orders has been proposed and identified by discrete HMM. Our experimental results showed that consecutive orders composed of more than two ones are correctly recognized at the rate of above 97%.

• Korean Journal of Agricultural Science
• /
• 제47권2호
• /
• pp.315-326
• /
• 2020

In this study, a real-time crop recognition system was developed for an unmanned farm machine for upland farming. The crop recognition system was developed based on a stereo camera, and an image processing framework was proposed that consists of disparity matching, localization of crop area, and estimation of crop height with coordinate transformations. The performance was evaluated by attaching the crop recognition system to a tractor for five representative crops (cabbage, potato, sesame, radish, and soybean). The test condition was set at 3 levels of distances to the crop (100, 150, and 200 cm) and 5 levels of camera height (42, 44, 46, 48, and 50 cm). The mean relative error (MRE) was used to compare the height between the measured and estimated results. As a result, the MRE of Chinese cabbage was the lowest at 1.70%, and the MRE of soybean was the highest at 4.97%. It is considered that the MRE of the crop which has more similar distribution lower. the results showed that all crop height was estimated with less than 5% MRE. The developed crop recognition system can be applied to various agricultural machinery which enhances the accuracy of crop detection and its performance in various illumination conditions.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• 제38권3호
• /
• pp.269-279
• /
• 2020

Traffic estimation mainly involves surveying equipment such as automatic vehicle classification, vehicle detection system, toll collection system, and personnel surveys through CCTV (Closed Circuit TeleVision), but this requires a lot of manpower and cost. In this study, we proposed a method of estimating traffic volume using deep learning and stereo CCTV to overcome the limitation of not detecting the entire vehicle in case of single CCTV. COCO (Common Objects in Context) dataset was used to train deep learning models to detect vehicles, and each vehicle was detected in left and right CCTV images in real time. Then, the vehicle that could not be detected from each image was additionally detected by using affine transformation to improve the accuracy of traffic volume. Experiments were conducted separately for the normal road environment and the case of weather conditions with fog. In the normal road environment, vehicle detection improved by 6.75% and 5.92% in left and right images, respectively, than in a single CCTV image. In addition, in the foggy road environment, vehicle detection was improved by 10.79% and 12.88% in the left and right images, respectively.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제17권1호
• /
• pp.331-339
• /
• 2016

This paper developed a home wellness robot platform to perform the roles in basic health care and life care in an aging society. A robotic platform and a sensory platform were implemented for an indoor wellness service. In the robotic platform, the precise mobility and the dexterous manipulation are not only developed in a symbiotic service-robot, but they also ensure the robot architecture of human friendliness. The mobile robot was made in the agile system, which consists of Omni-wheels. The manipulator was made in the anthropomorphic system to carry out dexterous handwork. In the sensing platform, RF tags and stereo camera were used for self and target localization. They were processed independently and cooperatively for accurate position and posture. The wellness robot platform was integrated in a real-time system. Finally, its good performance was confirmed through live indoor tests for health and life care.

• Journal of the Korea Society of Computer and Information
• /
• 제11권3호
• /
• pp.31-39
• /
• 2006

This paper presents a novel approach to real-time recognition of 3D environment and objects for various applications such as intelligent robots, intelligent vehicles, intelligent buildings,..etc. First, we establish the three fundamental principles that humans use for recognizing and interacting with the environment. These principles have led to the development of an integrated approach to real-time 3D recognition and modeling, as follows: 1) It starts with a rapid but approximate characterization of the geometric configuration of workspace by identifying global plane features. 2) It quickly recognizes known objects in environment and replaces them by their models in database based on 3D registration. 3) It models the geometric details the geometric details on the fly adaptively to the need of the given task based on a multi-resolution octree representation. SIFT features with their 3D position data, referred to here as stereo-sis SIFT, are used extensively, together with point clouds, for fast extraction of global plane features, for fast recognition of objects, for fast registration of scenes, as well as for overcoming incomplete and noisy nature of point clouds.

• International conference on construction engineering and project management
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.313-322
• /
• 2020

The recognition of the risk hazards is a vital step to effectively prevent accidents on a construction site. The advanced development in computer vision systems and the availability of the large visual database related to construction site made it possible to take quick action in the event of human error and disaster situations that may occur during management supervision. Therefore, it is necessary to analyze the risk factors that need to be managed at the construction site and review appropriate and effective technical methods for each risk factor. This research focuses on analyzing Occupational Safety and Health Agency (OSHA) related to risk zone identification rules that can be adopted by the image recognition technology and classify their risk factors depending on the effective technical method. Therefore, this research developed a pattern-oriented classification of OSHA rules that can employ a large scale of safety hazard recognition. This research uses joint reasoning of risk zone Identification and numeric input by utilizing a stereo camera integrated with an image detection algorithm such as (YOLOv3) and Pyramid Stereo Matching Network (PSMNet). The research result identifies risk zones and raises alarm if a target object enters this zone. It also determines numerical information of a target, which recognizes the length, spacing, and angle of the target. Applying image detection joint logic algorithms might leverage the speed and accuracy of hazard detection due to merging more than one factor to prevent accidents in the job site.

• Journal of Korean Ophthalmic Optics Society
• /
• 제18권4호
• /
• pp.465-471
• /
• 2013

Purpose: This study was conducted to research effects of influence factors on stereopsis of induced aniseikonia in emmetropia. Methods: 20 college students (a mean age of $22.50{\pm}2.72$ years, 14 males, 6 females) were selected as subjects and all of them had no ocular disease or systemic disease, the refractive correction of spherical equivalent within ${\pm}0.50$ D, the corrected visual acuity of 1.0 or better and the aniseikonia values less than 1% by AWAYA. Subject's dominant eye was checked by Hole in card method and contact lenses of -7.00 ~ +7.00D were fitted to cause anisometropia in dominant eye or non-dominant eye, respectively. And then aniseikonia was induced with spectacles to correct refractive error by contact lenses. Stereopsis was measured by Random Dot Stereo Acuity Test with LEA symbols$^{(R)}$ (Vision Assessment Corporation$^{TM}$, USA). Results: Stereopsis was remarkably reduced by inducing aniseikonia, with induced aniseikonia in dominant eye, with higher diopter of wearing contact lenses to induce anisometropia, with spectacles lenses correction of minus power after fitting contact lenses with plus power and in case of men. Conclusions: It should be considered to correct anisometropia that aniseikonia could cause reduction of stereopsis.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• 제46권6호
• /
• pp.28-37
• /
• 2009

In this paper, we propose an obstacle localization method using a road feature based on a V-disparity map binarized by a maximum frequency value. In a conventional method, the detection performance is severely affected by the size, number and type of obstacles. It's especially difficult to extract a large obstacle or a continuous obstacle like a median strip. So we use a road feature as a new decision standard to localize obstacles irrespective of external environments. A road feature is proper to be a new decision standard because it keeps its rough feature very well in V-disparity under environments where many obstacles exist. And first of all, we create a binary V-disparity map using a maximum frequency value to extract a road feature easily. And then we compare the binary V-disparity map with a median value to remove noises. Finally, we use a linear interpolation for rows which have no value. Comparing this road feature with each column value in disparity map, we can localize obstacles robustly. We also propose a post-processing technique to remove noises made in obstacle localization stage. The results in real road tests show that the proposed algorithm has a better performance than a conventional method.