• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.281-288
• /
• 2022

According to statistics conducted by the Korea Coast Guard, the number of accidents on small boats under 5 tons is increasing every year. This is because only a small number of people are on board. The previously developed maritime distress and safety systems are not well distributed because passengers must be equipped with additional remote equipment. The purpose of this study is to develop a distress awareness system that recognizes man over-board situations in real time. This study aims to present the part of the passenger tracking system among the small ship's distress awareness situational system that can generate passenger's location information in real time using deep learning based object detection and tracking technologies. The system consisted of the following steps. 1) the passenger location information is generated in the form of Bounding box using its detection model (YOLOv3). 2) Based on the Bounding box data, Deep SORT predicts the Bounding box's position in the next frame of the image with Kalman filter. 3) When the actual Bounding Box is created within the range predicted by Kalman-filter, Deep SORT repeats the process of recognizing it as the same object. 4) If the Bounding box deviates the ship's area or an error occurs in the number of tracking occupant, the system is decided the distress situation and issues an alert. This study is expected to complement the problems of existing technologies and ensure the safety of individuals aboard small boats.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2008.11a
• /
• pp.57-58
• /
• 2008

• Journal of Korea Spatial Information System Society
• /
• v.6 no.2 s.12
• /
• pp.3-13
• /
• 2004

The TPR-tree exploits bounding rectangles based on the function of time in order to index moving objects. As time passes on, each edge of a BR expands with the fastest velocity vector. Since the expansion of the BR results in a serious overlaps between neighboring nodes, the performance of range query is getting worse. In this paper, we propose schemes to reorganize bounding rectangles of nodes. When inserting a moving object, we exploit a forced merging scheme to merge two overlapped nodes and re-split it. When deleting a moving object, we used forced reinsertion schemes to reinsert other objects of a node into a tree. The forced reinsertion schemes are classified into a deleted node reinsertion scheme and an overlapped nodes reinsertion scheme. The overlapped nodes reinsertion scheme outperforms the forced merging scheme and the deleted node reinsertion scheme in all experiments.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Korean Journal of Computational Design and Engineering
• /
• v.4 no.1
• /
• pp.60-68
• /
• 1999

In reverse engineering (RE) sustems, the quality of the data aquisition process is crucial to the accuracy of the reverse engineered three dimensional computer-aided design (CAD) model. However, these tasks are predominantly done manually, and little work has been done to improve the efficiency of scanning by determining the minimum number of scans and the optimal scanning directions. In this paper, new scanning and registration methods using tooling balls are developed to assist in determining the optimal parameter for these processes. When the object to scanned has no concavity, attaching path of the object and its bounding rectangle are used for optimal scanning and registration. Then minimum number of tooling balls and their positions are calculated automatically. In the case of concave parts, the scanning plan should include a complete scan of the concave area. With the surface normal vector and the scanning direction, the minimum degree of rotating the part can be calculated. But the maximum rotation should be restricted in order to prevent occlusion of the part. Finally tow sample part ar scanned based on the proposed methods and the results are discussed.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.4
• /
• pp.381-389
• /
• 2022

Detecting partially occluded objects is difficult due to the appearances and shapes of occluders are highly variable. These variabilities lead to challenges of localizing accurate bounding box or classifying objects with visible object parts. To address these problems, we propose a two-stage part-based attention approach for robust object detection under partial occlusion. First, our part attention network(PAN) captures the important object parts and then it is used to generate weighted object features. Based on the weighted features, the re-weighted object features are produced by our reinforced PAN(RPAN). Experiments are performed on our collected military vehicle dataset and synthetic occlusion dataset. Our method outperforms the baselines and demonstrates the robustness of detecting objects under partial occlusion.

• Journal of Korean Public Health Nursing
• /
• v.14 no.2
• /
• pp.216-228
• /
• 2000

The purpose of this study was to clarify the level of knowledge and the attitude about AIDS. according to high school students demographics. and the AIDS education effects in a week or 6 months. The data were surveyed from 74 bounding for university high school students and 98 vocational high school students from two counties in Chonnam. The data were collected from November 5. 1999 to May 24. 2000. using a 50-item Questionnaire. and analyzed by SPSS PC+ program for t-test. ANOVA, Repeated measure ANOVA, Duncan test. $x^2-test$ and pearson correlation coefficients. The result of study summarized as follows : 1. The knowledge score for AIDS was significantly higher in the group bounding for university. in the second grade group and the group who have drunken experience. The positive attitude score for AIDS was significantly higher in the group who have smoked experience. 2. After 1 week of AIDS education. the knowledge score for AIDS(15.02 points) was significantly higher than the one before the education(10.85 points) but after 6 months of AIDS education. the knowledge score for AIDS(12.30 points) was significantly lower than in a week(F=55.49. p=.000). 3. After 1 week of AIDS education. the positive attitude score for AIDS(3.54 points) was significantly higher than the one before the education(3.35 points) and after 6 months of AIDS education. the positive attitude score for AIDS was same the one in a week(F=7.85. p=.000). 4. We could find the significant correlation between the knowledge and the attitude for AIDS just only in a week(r=.249. p=.001). In conclusion. the knowledge score for AIDS had increased in a week of education on AIDS but it had decreased as time goes by since education. The increased positive attitude for AIDS in a week has maintained the same as time goes by since education. Therefore. It should be needed re-education on AIDS to students at proper time in order to get the aim of AIDS education. We have to develop variety education methods for educational effects. It should be included comprehensive social aspect such as a question of personal rights to increase the positive attitude for AIDS.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.77-84
• /
• 2022

In this paper, we propose a Label Reassignment Strategy to improve the performance of an object detection algorithm. Our approach involves two stages: an inference stage and an assignment stage. In the inference stage, we perform multi-scale inference with predefined scale sizes on a trained model and re-infer masked images to obtain robust classification results. In the assignment stage, we calculate the IoU between bounding boxes to remove duplicates. We also check box and class occurrence between the detection result and annotation label to re-assign the dominant class type. We trained the YOLOX-L model with the re-annotated dataset to validate our strategy. The model achieved a 3.9% improvement in mAP and 3x better performance on AP_S compared to the model trained with the original dataset. Our results demonstrate that the proposed Label Reassignment Strategy can effectively improve the performance of an object detection model.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.1
• /
• pp.41-48
• /
• 2013

The aim of the present study is to design a memory-efficient octree for querying large 3D point cloud. The aim has been fulfilled by omitting variables for minimum bounding hexahedral (MBH) of each octree node expressed in C++ language and by passing the re-estimated MBH from parent nodes to child nodes. More efficiency has been reported by two-fold processes of generating pseudo and regular trees to declare an array for all anticipated nodes, instead of using new operator to declare each child node. Experiments were conducted by constructing tree structures and querying neighbor points out of real point cloud composed of more than 18 million points. Compared with conventional methods using MBH information defined in each node, the suggested methods have proved themselves, in spite of existing trade-off between speed and memory efficiency, to be more memory-efficient than the comparative ones and to be practical alternatives applicable to large 3D point cloud.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.5
• /
• pp.39-54
• /
• 2012

Picture Archiving and Communication System (PACS) has been planted as one of the key infrastructures with an overall improvement in standards of medical informationization and the stream of digital hospitalization in recent days. The kind and data of digital medical imagery are also increasing rapidly in volume. This trend emphasizes the medical image compression for storing large-scale medical image data. Digital Imaging and Communications in Medicine (DICOM), de facto standard in digital medical imagery, specifies Run Length Encode (RLE), which is the typical lossless data compressing technique, for the medical image compression. However, the RLE is not appropriate approach for medical image data with bilateral symmetry of the human organism. we suggest two preprocessing algorithms that detect interested area, the minimum bounding rectangle, in a medical image to enhance data compression efficiency and that re-code image pixel values to reduce data size according to the symmetry characteristics in the interested area, and also presents an improved image compression technique for brain CT imagery with high bilateral symmetry. As the result of experiment, the suggested approach shows higher data compression ratio than the RLE compression in the DICOM standard without detecting interested area in images.