• Journal of the Economic Geographical Society of Korea
• /
• v.24 no.3
• /
• pp.350-364
• /
• 2021

The purpose of this study is to examine changes in local government objectives due to the change of local government heads in Hwasun-gun of Jeonnam province, and to analyze performances of regional development policies, regional development vision, and local government objectives setting by the 6th local election. The local government objective and slogan of hwasun-gun continued to change due to frequent replacement of local government heads from 1st to 6th local election. The slogan of the 6th local election was set as 'Luxury Hwasun, Happy Citizens' and addition, six local government objectives were set: trusted administration, shared welfare, attractive culture, vibrant rural areas, dream-planting education, and vibrant economies. The performance of local government objectives of the 6th local election showed a 90% achievement rate compared to the planned goal.

• The Journal of Korea Robotics Society
• /
• v.9 no.4
• /
• pp.197-205
• /
• 2014

As computer vision algorithms are developed on a continuous basis, the visual information from vision sensors has been widely used in the context of simultaneous localization and mapping (SLAM), called visual SLAM, which utilizes relative motion information between images. This research addresses a visual SLAM framework for online localization and mapping in an unstructured seabed environment that can be applied to a low-cost unmanned underwater vehicle equipped with a single monocular camera as a major measurement sensor. Typically, an image motion model with a predefined dimensionality can be corrupted by errors due to the violation of the model assumptions, which may lead to performance degradation of the visual SLAM estimation. To deal with the erroneous image motion model, this study employs a local bundle optimization (LBO) scheme when a closed loop is detected. The results of comparison between visual SLAM estimation with LBO and the other case are presented to validate the effectiveness of the proposed methodology.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.17-25
• /
• 2023

In this paper, we propose a model that can perform human pose estimation through a MobileViT-based model with fewer parameters and faster estimation. The based model demonstrates lightweight performance through a structure that combines features of convolutional neural networks with features of Vision Transformer. Transformer, which is a major mechanism in this study, has become more influential as its based models perform better than convolutional neural network-based models in the field of computer vision. Similarly, in the field of human pose estimation, Vision Transformer-based ViTPose maintains the best performance in all human pose estimation benchmarks such as COCO, OCHuman, and MPII. However, because Vision Transformer has a heavy model structure with a large number of parameters and requires a relatively large amount of computation, it costs users a lot to train the model. Accordingly, the based model overcame the insufficient Inductive Bias calculation problem, which requires a large amount of computation by Vision Transformer, with Local Representation through a convolutional neural network structure. Finally, the proposed model obtained a mean average precision of 0.694 on the MS COCO benchmark with 3.28 GFLOPs and 9.72 million parameters, which are 1/5 and 1/9 the number compared to ViTPose, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4429-4447
• /
• 2018

Local binary descriptors are well-suited for many real-time and/or large-scale computer vision applications, while their low computational complexity is usually accompanied by the limitation of performance. In this paper, we propose a new optimization framework, RLDB (Robust-LDB), to improve a typical region-based binary descriptor LDB (local difference binary) and maintain its computational simplicity. RLDB extends the multi-feature strategy of LDB and applies a more complete region-comparing configuration. A cascade bit selection method is utilized to select the more representative patterns from massive comparison pairs and an online learning strategy further optimizes descriptor for each specific patch separately. They both incorporate LDP (linear discriminant projections) principle to jointly guarantee the robustness and distinctiveness of the features from various scales. Experimental results demonstrate that this integrated learning framework significantly enhances LDB. The improved descriptor achieves a performance comparable to floating-point descriptors on many benchmarks and retains a high computing speed similar to most binary descriptors, which better satisfies the demands of applications.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.163-166
• /
• 2000

Real-time traffic detection scheme based on Computer Vision is capable of efficient traffic control using automatically computed traffic information and obstacle detection in moving automobiles. Traffic information is extracted by segmenting vehicle region from road images, in traffic detection system. In this paper, we propose the advanced segmentation of vehicle from road images using multiple local region information. Because multiple local region overlapped in the same lane is processed sequentially from small, the traffic detection error can be corrected.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.589-592
• /
• 1999

Matching is a key problem in computer vision, image analysis and pattern recognition. In this paper a multiscale image matching algorithm by wavelet local extrema is proposed. This algorithm is based on the multiscale wavelet transform of the curvature which can utilize both the information of local extrema positions and magnitudes of transform results. This method has advantages in computational cost to a single scale image matching. It is also rotation-, translation-, and scale-independent image matching method. This matching can be used for the recognition of occluded objects.

• International Journal of Aeronautical and Space Sciences
• /
• v.12 no.1
• /
• pp.24-36
• /
• 2011

A new approach for spacecraft absolute attitude estimation based on the unscented Kalman filter (UKF) is extended to relative attitude estimation and navigation. This approach for nonlinear systems has faster convergence than the approach based on the standard extended Kalman filter (EKF) even with inaccurate initial conditions in attitude estimation and navigation problems. The filter formulation employs measurements obtained from a vision sensor to provide multiple line(-) of(-) sight vectors from the spacecraft to another spacecraft. The line-of-sight measurements are coupled with gyro measurements and dynamic models in an UKF to determine relative attitude, position and gyro biases. A vector of generalized Rodrigues parameters is used to represent the local error-quaternion between two spacecraft. A multiplicative quaternion-error approach is derived from the local error-quaternion, which guarantees the maintenance of quaternion unit constraint in the filter. The scenario for bounded relative motion is selected to verify this extended application of the UKF. Simulation results show that the UKF is more robust than the EKF under realistic initial attitude and navigation error conditions.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.15 no.4
• /
• pp.268-273
• /
• 2003

In the present study, the characteristics of upward bubble flow were experimentally investigated in a liquid bath. An electro-conductivity probe was used to measure local volume fraction and bubble frequency. Since the gas is concentrated at the near nozzle, the flow parameters are high near the nozzle. In general their axial and radial values tended to decrease with increasing distance. For visualization of flow characteristics, a Particle Image Velocimetry (P.I..V) and a thermo-vision camera were used in the present study. The experimental results show that heat transfer from bubble surface to water is largely completed within z=10mm from the nozzle, and then the temperature of bubble surface reaches that of water rapidly. Due to the centrifugal force, the flow was more developed near the wall than at bubble-water plume. Vortex flow in the bottom region was relatively weaker than that in the upper region.

• International Journal of Air-Conditioning and Refrigeration
• /
• v.13 no.1
• /
• pp.44-50
• /
• 2005

In the present study, the characteristics of upward bubble flow were experimentally investigated in a liquid bath. An electro-conductivity probe was used to measure local volume fraction and bubble frequency. Since the gas was concentrated at the near the nozzle, the flow parameters were high near the nozzle. In general their axial and radial values tended to decrease with increasing distance. For visualization of flow characteristics, a Particle Image Velocimetry (PIV) and a thermo-vision camera were used in the present study. The experimental results showed that heat transfer from bubble surface to water was largely completed within z = 10 mm from the nozzle, and then the temperature of bubble surface reached that of water rapidly. Due to the centrifugal force, the flow was more developed near the wall than at bubble-water plume. Vortex flow in the bottom region was relatively weaker than that in the upper region.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.663-668
• /
• 1991

In order to navigate, mobile robot needs to avoid obstacles on his way. We describe a stereo vision method for detecting obstacles on the floor ground. With the knowledge of floor geometry, stereo images are transformed so that the relative views of obstacle to the floor are seen. After comparing the transformed images, obstacles information such as location and size are extracted and determined from the local disparities. Some experimental results are shown.