• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.1
• /
• pp.9-18
• /
• 2018

Recently, the use of image stitching technology has been increasing as the number of contents based on virtual reality increases. Image Stitching is a method for matching multiple images to produce a high resolution image and a wide field of view image. The image stitching is used in various fields beyond the limitation of images generated from one camera. Image Stitching detects feature points and corresponding points to match multiple images, and calculates the homography among images using the RANSAC algorithm. Generally, corresponding points are needed for calculating conversion relation. However, the corresponding points include various types of noise that can be caused by false assumptions or errors about the conversion relationship. This noise is an obstacle to accurately predict the conversion relation. Therefore, RANSAC algorithm is used to construct an accurate conversion relationship from the outliers that interfere with the prediction of the model parameters because matching methods can usually occur incorrect correspondence points. In this paper, we propose an algorithm that extracts more accurate inliers and computes accurate transformation relations by using correspondence point relation information used in RANSAC algorithm. The correspondence point relation information uses distance ratio between corresponding points used in image matching. This paper aims to reduce the processing time while maintaining the same performance as RANSAC.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.471-476
• /
• 2016

In this paper, recognition system for continuous human action is explained by using motion history image and histogram of oriented gradient with spotter model based on depth information, and the spotter model which performs action spotting is proposed to improve recognition performance in the recognition system. The steps of this system are composed of pre-processing, human action and spotter modeling and continuous human action recognition. In pre-processing process, Depth-MHI-HOG is used to extract space-time template-based features after image segmentation, and human action and spotter modeling generates sequence by using the extracted feature. Human action models which are appropriate for each of defined action and a proposed spotter model are created by using these generated sequences and the hidden markov model. Continuous human action recognition performs action spotting to segment meaningful action and meaningless action by the spotter model in continuous action sequence, and continuously recognizes human action comparing probability values of model for meaningful action sequence. Experimental results demonstrate that the proposed model efficiently improves recognition performance in continuous action recognition system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.9
• /
• pp.7-13
• /
• 2019

Unlike a typical video wall system, video wall systems used for integrated monitoring in smart city environments should be able to display various videos, images, and texts simultaneously. In this paper, we propose an Internet Protocol (IP)-based video wall system that has no limit on the number of videos that can be monitored simultaneously, and that can arrange the monitor screen layout without restrictions. The proposed system is composed of multiple display servers, a wall controller, and video source providers, and they communicate with each other through an IP network. Since the display server receives and decodes the video stream directly from the video source devices, and displays it on the attached monitor screens, more videos can be simultaneously displayed on the entire video wall. When one video is displayed over several screens attached to multiple display servers, only one display server receives the video stream and transmits it to the other display servers by using IP multicast communications, thereby reducing the network load and synchronizing the video frames. Experiments show that as the number of videos increases, a system consisting of more display servers shows better decoding and rendering performance, and there is no performance degradation, even if the display server continues to be expanded.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.766-773
• /
• 2021

Chemicals, such as ammunition, are disposable items that cannot be reused because of their operational characteristics. The reliability of the test process and test results are important factors in evaluating the performance of guns and ammunition. The pressure after firing is a crucial value in an acceptance test of guns and ammunition performance; hence, accurate measurements are required. The pressure in the artillery is measured using the copper crusher gauge. The compression amount of copper is converted into a pressure by either a length-pressure conversion table or conversion formula. Therefore, the exact measurement of the squeeze of the copper crusher is related directly to the correct estimate of the pressure. Currently, the pressure is measured manually by the operator, which always includes some human error. In this study, the cause of the measurement error was analyzed, and the automatic measuring system for copper crusher deformation was developed to minimize the error elements. A copper crusher could be measured using the probe sensor and CCD camera, and the Jig for stable positioning was also designed. A designated SW was also developed for the system operating and measurement-analysis. This measuring system through this study may be used for an ammunition stockpile reliability test and gun/ammunition acceptance test.

• Korean Journal of Optics and Photonics
• /
• v.31 no.6
• /
• pp.281-289
• /
• 2020

This paper reports a slim mobile lens design using a hybrid refractive/diffractive optical element. Conventionally a wide field of view (FOV) camera-lens design adopts a retrofocus type having a negative (-) lens at the forefront, so that it improves in imaging performance over the wide FOV, but with the sacrifice of longer total track length (TTL). However, we chose a telephoto type as a baseline design layout having a positive (+) lens at the forefront, to achieving slimness, based on the specification analysis of 23 reported optical designs. Following preliminary optimization of a baseline design and aberration analysis based on Zernike-polynomial decomposition, we applied a hybrid refractive/diffractive element to effectively reduce the residual chromatic spherical aberration. The optimized optical design consists of 6 optical elements, including one hybrid element. It results in a very slim telephoto ratio of 1.7, having an f-number of 2.0, FOV of 90°, effective focal length of 2.23 mm, and TTL of 3.7 mm. Compared to a comparable conventional lens design with no hybrid elements, the hybrid design improved the value of the modulation transfer function (MTF) at a spatial frequency of 180 cycles/mm from 63% to 71-73% at zero field (0 F), and about 2-3% at 0.5, 0.7, and 0.9 fields. It was also found that a design with a hybrid lens with only two diffraction zones at the stop achieved the same performance improvement.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.228-239
• /
• 2022

In this paper, we propose an unmanned vehicle scratch detection deep learning model for car sharing services. Conventional scratch detection models consist of two steps: 1) a deep learning module for scratch detection of images before and after rental, 2) a manual matching process for finding newly generated scratches. In order to build a fully automatic scratch detection model, we propose a one-step unmanned scratch detection deep learning model. The proposed model is implemented by applying transfer learning and fine-tuning to the deep learning model that detects changes in satellite images. In the proposed car sharing service, specular reflection greatly affects the scratch detection performance since the brightness of the gloss-treated automobile surface is anisotropic and a non-expert user takes a picture with a general camera. In order to reduce detection errors caused by specular reflected light, we propose a preprocessing process for removing specular reflection components. For data taken by mobile phone cameras, the proposed system can provide high matching performance subjectively and objectively. The scores for change detection metrics such as precision, recall, F1, and kappa are 67.90%, 74.56%, 71.08%, and 70.18%, respectively.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.190-196
• /
• 2023

Recently, following the development of LIDAR technology which can detect distance from the object, the interest for LIDAR based 3D object detection network is getting higher. Previous networks generate inaccurate localization results due to spatial information loss during voxelization and downsampling. In this study, we propose an attention-based convergence method and a camera-LIDAR convergence system to acquire high-level features and high positional accuracy. First, by introducing the attention method into the Voxel-RCNN structure, which is a grid-based 3D object detection network, the multi-scale sparse 3D convolution feature is effectively fused to improve the performance of 3D object detection. Additionally, we propose the late-fusion mechanism for fusing outcomes in 3D object detection network and 2D object detection network to delete false positive. Comparative experiments with existing algorithms are performed using the KITTI data set, which is widely used in the field of autonomous driving. The proposed method showed performance improvement in both 2D object detection on BEV and 3D object detection. In particular, the precision was improved by about 0.54% for the car moderate class compared to Voxel-RCNN.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.44-55
• /
• 2022

In order to automatically provide information on fruits in agricultural related broadcasting contents, instance image segmentation of target fruits is required. In addition, the information on the 3D pose of the corresponding fruit may be meaningfully used. This paper represents research that provides information about tomatoes in video content. A large amount of data is required to learn the instance segmentation, but it is difficult to obtain sufficient training data. Therefore, the training data is generated through a data augmentation technique based on a small amount of real images. Compared to the result using only the real images, it is shown that the detection performance is improved as a result of learning through the synthesized image created by separating the foreground and background. As a result of learning augmented images using images created using conventional image pre-processing techniques, it was shown that higher performance was obtained than synthetic images in which foreground and background were separated. To estimate the pose from the result of object detection, a point cloud was obtained using an RGB-D camera. Then, cylinder fitting based on least square minimization is performed, and the tomato pose is estimated through the axial direction of the cylinder. We show that the results of detection, instance image segmentation, and cylinder fitting of a target object effectively through various experiments.

• Smart Media Journal
• /
• v.13 no.3
• /
• pp.18-26
• /
• 2024

Road surface monitoring is essential for maintaining road environment safety through managing risk factors like rutting and crack detection. Using autonomous driving-based UGVs with high-performance 2D laser sensors enables more precise measurements. However, the increased energy consumption of these sensors is limited by constrained battery capacity. In this paper, we propose a fusion sensor system for efficient surface monitoring with UGVs. The proposed system combines color information from cameras and depth information from line laser sensors to accurately detect surface displacement. Furthermore, a dynamic sampling algorithm is applied to control the scanning frequency of line laser sensors based on the detection status of monitoring targets using camera sensors, reducing unnecessary energy consumption. A power consumption model of the fusion sensor system analyzes its energy efficiency considering various crack distributions and sensor characteristics in different mission environments. Performance analysis demonstrates that setting the power consumption of the line laser sensor to twice that of the saving state when in the active state increases power consumption efficiency by 13.3% compared to fixed sampling under the condition of λ=10, µ=10.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.12
• /
• pp.51-57
• /
• 2019

In this paper, we analyzed the performance of IoT based smart wearable mine detection device. There are various mine detection methods currently used by the military. Still, in the general field, mine detection is performed by visual detection, probe detection, detector detection, and other detection methods. The detection method by the detector is using a GPR sensor on the detector, which is possible to detect metals, but it is difficult to identify non-metals. It is hard to distinguish whether the area where the detection was performed or not. Also, there is a problem that a lot of human resources and time are wasted, and if the user does not move the sensor at a constant speed or moves too fast, it is difficult to detect landmines accurately. Therefore, we studied the smart wearable mine detection device composed of human body antenna, main microprocessor, smart glasses, body-mounted LCD monitor, wireless data transmission, belt type power supply, black box camera, which is to improve the problem of the error of mine detection using unidirectional ultrasonic sensing signal. Based on the results of this study, we will conduct an experiment to confirm the possibility of detecting underground mines based on the Internet of Things (IoT). This paper consists of an introduction, experimental environment composition, simulation analysis, and conclusion. Introduction introduces the research contents such as mines, mine detectors, and research progress. It consists of large anti-personnel mine, M16A1 fragmented anti-mine, M15 and M19 antitank mines, plastic bottles similar to mines and aluminum cans. Simulation analysis is conducted by using MATLAB to analyze the mine detection device implementation performance, generating and transmitting IoT signals, and analyzing each received signal to verify the detection performance of landmines. Then we will measure the performance through the simulation of IoT-based mine detection algorithm so that we will prove the possibility of IoT-based detection landmine.