• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.2
• /
• pp.160-167
• /
• 2023

This study focuses on the development of a Last-Mile delivery service using unmanned vehicles to deliver goods directly to the end consumer utilizing drones to perform autonomous delivery missions and an image-based precision landing algorithm for handoff to a robot in an intermediate facility. As the logistics market continues to grow rapidly, parcel volumes increase exponentially each year. However, due to low delivery fees, the workload of delivery personnel is increasing, resulting in a decrease in the quality of delivery services. To address this issue, the research team conducted a study on a Last-Mile delivery service using unmanned vehicles and conducted research on the necessary technologies for drone-based goods transportation in this paper. The flight scenario begins with the drone carrying the goods from a pickup location to the rooftop of a building where the final delivery destination is located. There is a handoff facility on the rooftop of the building, and a marker on the roof must be accurately landed upon. The mission is complete once the goods are delivered and the drone returns to its original location. The research team developed a mission planning algorithm to perform the above scenario automatically and constructed an algorithm to recognize the marker through a camera sensor and achieve a precision landing. The performance of the developed system has been verified through multiple trial operations within ETRI.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.205-208
• /
• 2022

Multi-exposure high dynamic range (HDR) image reconstruction, the task of reconstructing an HDR image from multiple low dynamic range (LDR) images in a dynamic scene, often produces ghosting artifacts caused by camera motion and moving objects and also cannot deal with washed-out regions due to over or under-exposures. While there has been many deep-learning-based methods with motion estimation to alleviate these problems, they still have limitations for severely moving scenes. They also require large parameter counts, especially in the case of state-of-the-art methods that employ attention modules. To address these issues, we propose a frequency domain approach based on the idea that the transform domain coefficients inherently involve the global information from whole image pixels to cope with large motions. Specifically we adopt Residual Fast Fourier Transform (RFFT) blocks, which allows for global interactions of pixels. Moreover, we also employ Depthwise Overparametrized convolution (DO-conv) blocks, a convolution in which each input channel is convolved with its own 2D kernel, for faster convergence and performance gains. We call this LFFNet (Lightweight Frequency Fusion Network), and experiments on the benchmarks show reduced ghosting artifacts and improved performance up to 0.6dB tonemapped PSNR compared to recent state-of-the-art methods. Our architecture also requires fewer parameters and converges faster in training.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.1-8
• /
• 2023

In recent years, robots have been utilized in various industries to reduce workload and enhance work efficiency. The following mobility offers users convenience by autonomously tracking specific locations and targets without the need for additional equipment such as forklifts or carts. In this paper, deep learning techniques were employed to recognize individuals and assign each of them a unique identifier to enable the recognition of a specific person even among multiple individuals. To achieve this, the distance and angle between the robot and the targeted individual are transmitted to respective controllers. Furthermore, this study explored the control methodology for mobility that tracks a specific person, utilizing Simultaneous Localization and Mapping (SLAM) and Proportional-Integral-Derivative (PID) control techniques. In the PID control method, a genetic algorithm is employed to extract the optimal gain value, subsequently evaluating PID performance through simulation. The SLAM method involves generating a map by synchronizing data from a 2D LiDAR and a depth camera using Real-Time Appearance-Based Mapping (RTAB-MAP). Experiments are conducted to compare and analyze the performance of the two control methods, visualizing the paths of both the human and the following mobility.

• Journal of the Society of Disaster Information
• /
• v.20 no.2
• /
• pp.315-328
• /
• 2024

Purpose: The purpose of this paper is to present a service construction plan using multiple complex sensor information to detect abnormal situations in urban life safety that are difficult to identify on CCTV. Method: This study selected service scenarios based on actual testbed data and analyzed service importance for local government control center operators, which are main users. Result: Service scenarios were selected as detection of day and night dynamic object, Detection of sudden temperature changes, and Detection of time-series temperature changes. As a result of AHP analysis, walking and mobility collision risk situation services and fire foreshadowing detection services leading to immediate major disasters were highly evaluated. Conclusion: This study is significant in proposing a plan to build an anomaly detection service that can be used in local governments based on real data. This study is significant in proposing a plan to build an anomaly detection service that can be used by local governments based on testbed data.

• Journal of Broadcast Engineering
• /
• v.18 no.3
• /
• pp.481-490
• /
• 2013

In this paper, an investigation of weapon tracking performance is shown in regard to improving individual weapon performance of aiming objects. On the battlefield, a battle can last only a few hours, sometimes it can last several days until finished. In these long-lasting combats, a wide variety of factors will gradually lower the visual ability of soldiers. The experiments were focusing on enhancing the degraded aiming performance by applying visual tracking technology to roof mounted sights so as to track the movement of troops automatically. In order to select the optimal algorithm among the latest visual tracking techniques, performance of each algorithm was evaluated using the real combat images with characteristics of overlapping problems, camera's mobility, size changes, low contrast images, and illumination changes. The results show that VTD (Visual Tracking Decomposition)[2], IVT (Incremental learning for robust Visual Tracking)[7], and MIL (Multiple Instance Learning)[1] perform the best at accuracy, response speed, and total performance, respectively. The evaluation suggests that the roof mounted sights equipped with visual tracking technology are likely to improve the reduced aiming ability of forces.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.11B
• /
• pp.1303-1310
• /
• 2009

Glassless 3D display requires multiple images taken from different viewpoints to show a scene. The simplest way to get multi-view image is using multiple camera that as number of views are requires. To do that, synchronize between cameras or compute and transmit lots of data comes critical problem. Thus, generating such a large number of viewpoint images effectively is emerging as a key technique in 3D video technology. Image-based view synthesis is an algorithm for generating various virtual viewpoint images using a limited number of views and depth maps. In this paper, because the virtual view image can be express as a transformed image from real view with some depth condition, we propose an algorithm to compute multi-view synthesis from two reference view images and their own depth-map by stepwise duplex forward mapping. And also, because the geometrical relationship between real view and virtual view is repetitively, we apply our algorithm into OpenGL Shading Language which is a programmable Graphic Process Unit that allow parallel processing to improve computation time. We demonstrate the effectiveness of our algorithm for fast view synthesis through a variety of experiments with real data.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.3C
• /
• pp.307-314
• /
• 2003

In the general multiple video object coder, more interested objects such as speaker or moving object is consistently coded with higher priority. Since the priority of each object may not be fixed in the whole sequence and be variable on frame basis, it must be adjusted in a frame. In this paper, we analyze the independent rate control algorithm and global algorithm that the QP value is controled by the static parameters, object importance or priority, target PSNR, weighted distortion. The priority among static parameters is analyzed and adjusted into dynamic parameters according to the visual interests or importance obtained by camera interface. Target PSNR and weighted distortion are proportionally derived by using magnitude, motion, and distortion. We apply those parameters for the weighted distortion control and the priority-based control resulting in the efficient bit-rate distribution. As results of this paper, we achieved that fewer bits are allocated for video objects which has less importance and more bits for those which has higher visual importance. The duration of stability in the visual quality is reduced to less than 15 frames of the coded sequence. In the aspect of PSNR, the proposed scheme shows higher quality of more than 2d13 against the conventional schemes. Thus the coding scheme interfaced to human- eye proves an efficient video coder dealing with the multiple number of video objects.

• Korean Journal of Optics and Photonics
• /
• v.26 no.1
• /
• pp.23-29
• /
• 2015

In this paper, we propose a microscope system for detecting both a tumor and blood vessels in brain tumor surgery as fluorescence images by using multiple light sources and a beam-splitter module. The proposed method displays fluorescent images of the tumor and blood vessels on the same display device and also provides accurate information about them to the operator. To acquire a fluorescence image, we utilized 5-ALA (5-aminolevulinic acid) for the tumor and ICG (Indocyanine green) for blood vessels, and we used a beam-splitter module combined with a microscope for simultaneous detection of both. The beam-splitter module showed the best performance at 600 nm for 5-ALA and above 800 nm for ICG. The beam-splitter is flexible to enable diverse objective setups and designed to mount a filter easily, so beam-splitter and filter can be changed as needed, and other fluorescent dyes besides 5-ALA and ICG are available. The fluorescent images of the tumor and the blood vessels can be displayed on the same monitor through the beam-splitter module with a CCD camera. For ICG, a CCD that can detect the near-infrared region is needed. This system provides the acquired fluorescent image to an operator in real time, matching it to the original image through a similarity transform.

• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.7
• /
• pp.279-286
• /
• 2021

Recently, We are carrying out a policy of physical distancing of at least 1m from each other to prevent the spreading of COVID-19 disease in public places. In this paper, we propose a method for measuring distances between people in real time and an automation system that recognizes objects that are within 1 meter of each other from stereo images acquired by drones or CCTVs according to the estimated distance. A problem with existing methods used to estimate distances between multiple objects is that they do not obtain three-dimensional information of objects using only one CCTV. his is because three-dimensional information is necessary to measure distances between people when they are right next to each other or overlap in two dimensional image. Furthermore, they use only the Bounding Box information to obtain the exact coordinates of human existence. Therefore, in this paper, to obtain the exact two-dimensional coordinate value in which a person exists, we extract a person's key point to detect the location, convert it to a three-dimensional coordinate value using Stereo Vision and Camera Calibration, and estimate the Euclidean distance between people. As a result of performing an experiment for estimating the accuracy of 3D coordinates and the distance between objects (persons), the average error within 0.098m was shown in the estimation of the distance between multiple people within 1m.