• Journal of the Society of Disaster Information
• /
• v.18 no.2
• /
• pp.269-279
• /
• 2022

Purpose: The purpose of this study is to develop a deep learning-based personal protective equipment detection model for disaster prevention at construction sites, and to apply it to actual construction sites and to analyze the results. Method: In the method of conducting this study, the dataset on the real environment was constructed and the developed personal protective equipment(PPE) detection model was applied. The PPE detection model mainly consists of worker detection and PPE classification model.The worker detection model uses a deep learning-based algorithm to build a dataset obtained from the actual field to learn and detect workers, and the PPE classification model applies the PPE detection algorithm learned from the worker detection area extracted from the work detection model. For verification of the proposed model, experimental results were derived from data obtained from three construction sites. Results: The application of the PPE recognition model to construction site brings up the problems related to mis-recognition and non-recognition. Conclusions: The analysis outcomes were produced to apply the object recognition technology to a construction site, and the need for follow-up research was suggested through representative cases of worker recognition and non-recognition, and mis-recognition of personal protective equipment.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.73-82
• /
• 2023

With 78% of current fisheries workers being elderly, there's a pressing need to address labor shortages. Consequently, active research on smart aquaculture technologies, centered on object detection and tracking algorithms, is underway. These technologies allow for fish size analysis and behavior pattern forecasting, facilitating the development of real-time monitoring and automated systems. Our study utilized video data from cameras outside aquaculture facilities and implemented fish detection and tracking algorithms. We aimed to tackle high maintenance costs due to underwater conditions and camera corrosion from ammonia and pH levels. We evaluated the performance of a real-time system using YOLOv7 for fish detection and the SORT algorithm for movement tracking. YOLOv7 results demonstrated a trade-off between Recall and Precision, minimizing false detections from lighting, water currents, and shadows. Effective tracking was ascertained through re-identification. This research holds promise for enhancing smart aquaculture's operational efficiency and improving fishery facility management.

• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.449-455
• /
• 2014

Detection of moving objects is a fundamental task in most of the computer vision applications, such as video surveillance, activity recognition and human motion analysis. This is a difficult task due to many challenges in realistic scenarios which include irregular motion in background, illumination changes, objects cast shadows, changes in scene geometry and noise, etc. In this paper, we propose an foreground extraction algorithm based on codebook, a database of information about background pixel obtained from input image sequence. Initially, we suppose a first frame as a background image and calculate difference between next input image and it to detect moving objects. The resulting difference image may contain noises as well as pure moving objects. Second, we investigate a codebook with color and brightness of a foreground pixel in the difference image. If it is matched, it is decided as a fault detected pixel and deleted from foreground. Finally, a background image is updated to process next input frame iteratively. Some pixels are estimated by input image if they are detected as background pixels. The others are duplicated from the previous background image. We apply out algorithm to PETS2009 data and compare the results with those of GMM and standard codebook algorithms.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.4
• /
• pp.104-114
• /
• 2016

Potholes have caused diverse problems such as wheel damage and car accident. A pothole detection technology is the most important to provide efficient pothole maintenance. The previous pothole detections have been performed by manual reporting methods. Thus, the problems caused by potholes have not been solved previously. Recently, many pothole detection systems based on video cameras have been studied, which can be implemented at low costs. In this paper, we propose a new pothole detection algorithm based on saliency map information in order to improve our previously developed algorithm. Our previous algorithm shows wrong detection with complicated situations such as the potholes overlapping with shades and similar surface textures with normal road surfaces. To address the problems, the proposed algorithm extracts more accurate pothole regions using the saliency map information, which consists of candidate extraction and decision. The experimental results show that the proposed algorithm shows better performance than our previous algorithm.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.6
• /
• pp.84-92
• /
• 2007

The gait recognition is presented for human identification from a sequence of noisy silhouettes segmented from video by capturing at a distance. The proposed gait recognition algorithm gives better performance than the baseline algorithm because of segmentation of the object by using multiple modules; i) motion detection, ii) object region detection, iii) head detection, and iv) active shape models, which solve the baseline algorithm#s problems to make background, to remove shadow, and to be better recognition rates. For the experiment, we used the HumanID Gait Challenge data set, which is the largest gait benchmarking data set with 122 objects, For realistic simulation we use various values for the following parameters; i) viewpoint, ii) shoe, iii) surface, iv) carrying condition, and v) time.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.27-34
• /
• 2013

Background subtraction is one of the key techniques for automatic video content analysis, especially in the tasks of visual detection and tracking of moving object. In this paper, we present a new sample-based technique for background extraction that provides background image as well as background model. To handle both high-frequency and low-frequency events at the same time, multiple interval background models are adopted. The main innovation concerns the use of a confidence factor to select the best model from the multiple interval background models. To our knowledge, it is the first time that a confidence factor is used for merging several background models in the field of background extraction. Experimental results revealed that our approach based on multiple interval sampling works well in complicated situations containing various speed moving objects with environmental changes.

• Journal of Digital Convergence
• /
• v.17 no.4
• /
• pp.255-260
• /
• 2019

This study is about an efficient synthesis of $360^{\circ}$ video and 3D graphics. First, the video image filmed by a binocular integral type $360^{\circ}$ camera was stitched, and location values of the camera and objects were extracted. And the data of extracted location values were moved to the 3D program to create 3D objects, and the methods for natural compositing was researched. As a result, as the method for natural compositing of $360^{\circ}$ video image and 3D graphics, rendering factors and rendering method were derived. First, as for rendering factors, there were 3D objects' location and quality of material, lighting and shadow. Second, as for rendering method, actual video based rendering method's necessity was found. Providing the method for natural compositing of $360^{\circ}$ video image and 3D graphics through this study process and results is expected to be helpful for research and production of $360^{\circ}$ video image and VR video contents.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1567-1577
• /
• 2020

Urban land cover classification is role in urban planning and management. So, it's important to improve classification accuracy on urban location. In this paper, machine learning model, Support Vector Machine (SVM) and Artificial Neural Network (ANN) are proposed for urban land cover classification based on high resolution satellite imagery (KOMPSAT-3A). Satellite image was trained based on 25 m rectangle grid to create training data, and training models used for classifying test area. During the validation process, we presented confusion matrix for each result with 250 Ground Truth Points (GTP). Of the four SVM kernels and the two activation functions ANN, the SVM Polynomial kernel model had the highest accuracy of 86%. In the process of comparing the SVM and ANN using GTP, the SVM model was more effective than the ANN model for KOMPSAT-3A classification. Among the four classes (building, road, vegetation, and bare-soil), building class showed the lowest classification accuracy due to the shadow caused by the high rise building.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_1
• /
• pp.1421-1434
• /
• 2020

The frequency and intensity of heatwaves have been increasing due to climate change. Since urban areas are more severely damaged by heatwaves as they act in combination with the urban heat island phenomenon, every possible preparation for such heat threats is required. Many overseas local governments build heat maps using a variety of spatial information to prepare for and counteract heatwaves, and prepare heatwave measures suitable for each region with different spatial characteristics within a relevant city. Building a heat map is a first and important step to prepare for heatwaves. The cases of heat map construction and thermal environment analysis involve various area distributions from urban units with a large area to local units with a small area. The method of constructing a heat map varies from a method utilizing remote sensing to a method using simulation, but there is no standard for using differentiated spatial information according to spatial scale, so each researcher constructs a heat map and analyzes the thermal environment based on different methods. For the above reason, spatial information standards required for building a heat map according to the analysis scale should be established. To this end, this study examined spatial information, analysis methodology, and final findings related to Korean and oversea analysis studies of heatwaves and urban thermal environments to suggest ways to improve the utilization efficiency of spatial information used to build urban heat maps. As a result of the analysis, it was found that spatial, temporal, and spectral resolutions, as basic resolutions, are necessary to construct a heat map using remote sensing in the use of spatial information. In the use of simulations, it was found that the type of weather data and spatial resolution, which are input condition information for simulation implementation, differ according to the size of analysis target areas. Therefore, when constructing a heat map using remote sensing, spatial, spectral, and temporal resolution should be considered; and in the case of using simulations, the spatial resolution, which is an input condition for simulation implementation, and the conditions of weather information to be inputted, should be considered in advance. As a result of understanding the types of monitoring elements for heatwave analysis, 19 types of elements were identified such as land cover, urban spatial characteristics, buildings, topography, vegetation, and shadows, and it was found that there are differences in the types of the elements by spatial scale. This study is expected to help give direction to relevant studies in terms of the use of spatial information suitable for the size of target areas, and setting monitoring elements, when analyzing heatwaves.

• Journal of Advanced Navigation Technology
• /
• v.20 no.5
• /
• pp.425-432
• /
• 2016

When user estimates user's position, GPS positions can be obtained from the navigation message transmitted from the GPS. However, the broadcast ephemeris cannot be used in the applications required high-level accuracies because it can cause errors of several meters. To correct satellite positions and clocks, user can use RTS corrections provided by IGS. In this paper, the accuracy of broadcast and RTS corrections are analyzed by comparing with the IGS final for 3-months. The RTS errors are analyzed for each user's locations and satellite blocks. The correlations between errors and shadow condition, and solar and geomagnetic activities are analyzed. The latency is applied to the RTS corrections, and these are extrapolated by polynomial. Then, the extrapolated RTS are compared with true RTS. The single-day performances of the PPP by broadcast ephemeris and RTS corrected ephemeris are analyzed. As a result, RTS 3D orbit and clock errors are 1/20 and 1/3 less than broadcast ephemeris errors. 3D positioning error of the RTS is 1/5 less than that of broadcast ephemeris.