• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1641-1652
• /
• 2021

To analyze the crime scene, the role of digital evidence such as CCTV and black box is very important. Such digital evidence is often damaged due to device defects or intentional deletion. In this case, the deleted video can be restored by well-known techniques like the frame-based recovery method. Especially, the data such as the video can be generally fragmented and saved in the case of the memory used almost fully. If the fragmented video were recovered in units of images, the sequence of the recovered images may not be continuous. In this paper, we proposed a new video restoration method to match the sequence of recovered images. First, the images are recovered through a frame-based recovery technique. Then, after analyzing the time information marked on the images, the time information was extracted and recognized via optical character recognition (OCR). Finally, the recovered images are rearranged based on the time information obtained by OCR. For performance evaluation, we evaluate the recovery rate of our proposed video restoration method. As a result, it was shown that the recovery rate for the fragmented video was recovered from a minimum of about 47% to a maximum of 98%.

• Journal of Drive and Control
• /
• v.19 no.3
• /
• pp.23-31
• /
• 2022

Traffic safety issues have recently been seriously magnified, due to child deaths in apartment complexes and parking lots. Accordingly, traffic safety technologies are being developed to recognize dangerous situations on living roads and to provide warning services. In this study, a collision detection algorithm was developed to prevent collision accidents between moving objects, by using object type and location information provided from CCTV monitoring devices. To determine the exact collision between moving objects, an object movement model was developed to predict the range of movement by considering the moving characteristics of the object, and a collision detection algorithm was developed to efficiently analyze the presence and location of the collision. The developed object movement model as well as the collision detection algorithm were simulated, in a virtual space of an actual living road to verify performance and derive supplementary matters.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.183-193
• /
• 2022

Smart cities are expected to provide residents with convenience via various agents such as CCTV, delivery robots, security robots, and unmanned shuttles. Environmental data collected by various agents can be used for various purposes, including advertising and security monitoring. This study suggests a surveillance map data framework for efficient and integrated multimodal data representation from multi-agents. The suggested surveillance map is a multilayered global information grid, which is integrated from the multimodal data of each agent. To confirm this, we collected surveillance map data for 4 months, and the behavior patterns of humans and vehicles, distribution changes of elevation, and temperature were analyzed. Moreover, we represent an anomaly detection algorithm based on a surveillance map for security service. A two-stage anomaly detection algorithm for unusual situations was developed. With this, abnormal situations such as unusual crowds and pedestrians, vehicle movement, unusual objects, and temperature change were detected. Because the surveillance map enables efficient and integrated processing of large multimodal data from a multi-agent, the suggested data framework can be used for various applications in the smart city.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.133-139
• /
• 2023

This paper proposes a two-stage Water Shield Automation System (WSAS) to predict the possibility of river overflow and vehicle flooding due to sudden rainfall. The WSAS uses a two-stage Deep Neural Network (DNN) model. First, a river overflow prediction module is designed with LSTM to decide whether the river is flooded by predicting the river's water level rise. Second, a vehicle flooding prediction module predicts flooding of underground parking lots by detecting flooded tires with YOLOv5 from CCTV images. Finally, the WSAS automatically installs the water barrier whenever the river overflow and vehicle flooding events happen in the underground parking lots. The only constraint to implementing is that collecting training data for flooded vehicle tires is challenging. This paper exploits the Image C&S data augmentation technique to synthesize flooded tire images. Experimental results validate the superiority of WSAS by showing that the river overflow prediction module can reduce RMSE by three times compared with the previous method, and the vehicle flooding detection module can increase mAP by 20% compared with the naive detection method, respectively.

• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.385-393
• /
• 2023

Since the proportion of elderly citizens is increasing every year, the social interest is increasing for the health and the safety of the elderly. The nursing home is continually being created to care for more elderly people. However, the quality of service is not enough due to the lack of elderly caregivers. Elderly care and management services are being studied to replace the shortage of caregivers. Existing research for the implementation of an automatic care system has a high initial system cost. Furthermore, it lacks the ability to store and manage large amounts of data. In this paper, we propose a system that manages a large amount of data continuously generated through CCTV and provides a streaming service with a high level of quality-of-service (QoS) to users with collected video. Through the proposed system, it is possible to record and manage the behavioral information of the elderly occurring in the nursing home together with the video. In addition, according to the user's request, it has built a service that streams the video and behavioral information according to the date and time in real-time.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.791-794
• /
• 2021

범죄차량 판독 시스템, 지능화된 CCTV 등 차량과 관련된 시각지능에 관한 연구가 큰 관심을 받고 있다. 이 중 차량 분류 기술은, 특정 차량을 인식하는 핵심기술이다. 이와 관련한 기존 연구들은 큰 차종으로만 분류하거나, 분류 가능한 차종의 수, 정확도 등이 낮아 실용성 및 신뢰성이 떨어진다는 단점이 있다. 따라서, 본 논문에서는 차종을 정확하게 분류할 수 있는 2단계 차종 분류 알고리즘을 제안한다. 제안 시스템은 CNN으로 학습된 모델을 기반으로 1차로 차량의 유형을 분류하고, 2차로 정확한 차종을 분류한다. 실험 결과, 52개의 차종을 분류함에 있어 단일 분류 모델에 비해 5.3%p 더 높은 90.2%의 분류 정확도를 보였다. 이를 통해, 더욱 정확한 차종 분류가 가능하다.

• Journal of People, Plants, and Environment
• /
• v.22 no.5
• /
• pp.467-480
• /
• 2019

Standard estimates are the numerical data of a unit quantity required for construction work such as the amount of materials, manpower, and the use of equipment required and are also a basis to calculate construction costs. Unfortunately, standard estimates for construction have also been used for garden construction these days as no standard estimates for garden construction have been developed or documented until now. As a result, many problems have arisen at garden construction sites since landscape construction and garden construction differ in terms of scope, size, design and construction methods. The purpose of this study was to develop standard estimates for garden construction for proper calculation of the cost of garden construction and to ensure gardens are created following appropriate construction processes. In order to develop standard estimates for garden construction, a preliminary survey was conducted on experts to understand current issues at first. After that, a questionnaire survey was done to examine problems of construction processes and ways of improvement, and on-site inspections were conducted utilizing CCTVs at construction sites to identify the actual amount of manpower required on site. Based on the results of the surveys and on-site inspections, a draft version of standard estimates for 5 types of planting work for garden construction was developed. Developing standard estimates for garden construction will serve as a stepping stone for the transparent and proper compensation for garden construction work, which will not only contribute to addressing issues between consumers and construction companies, but also to the stabilization of market economy and job creation.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.951-952
• /
• 2023

소위 '인생네컷'이라 불리는 셀프사진관은 MZ 세대의 새로운 놀이 문화로 떠오르며 사용자 수가 나날이 증가하고 있다. 그러나 짧은 시간 내에 다양한 포즈를 취해야 하는 셀프사진관 특성상 촬영이 낯선 사람에게는 여전히 진입장벽이 존재한다. 더불어 매번 비슷한 포즈와 사진 결과물에 기존 사용자는 점차 흥미를 잃어가는 문제점도 발생하고 있다. 이에 본 연구에서는 셀프사진관 사용자의 관계를 분류하는 모델을 개발하여 관계에 따른 적합하고 다양한 포즈를 추천하는 프레임워크를 제안한다. 사용자의 관계를 'couple', 'family', 'female_friend', 'female_solo', 'male_friend', 'male_solo' 총 6 개로 구분하였고 실제 현장과 유사하도록 단색 배경의 이미지를 우선으로 학습 데이터를 수집하여 모델의 성능을 높였다. 모델 학습 단계에서는 모델의 성능을 높이기 위해 여러 CNN 기반의 모델을 전이학습하여 각각의 정확도를 비교하였다. 결과적으로 195 장의 test_set 에서 accuracy 0.91 의 성능 평가를 얻었다. 본 연구는 객체 인식보다 객체 간의 관계를 학습시켜 관계성을 추론하고자 하는 것을 목적으로, 연구 결과가 희박한 관계 분류에 대한 주제를 직접 연구하여 추후의 방향성이나 방법론과 같은 초석을 제안할 수 있다. 또한 관계 분류 모델을 CCTV 에 활용하여 미아 방지 혹은 추적과 구조 등에 활용하여 국가 치안을 한층 높이는 데 기대할 수 있다.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.147-153
• /
• 2023

In recent times, an absence of effective crowd management has led to numerous stampede incidents in crowded places. A crucial component for enhancing on-site crowd management effectiveness is the utilization of crowd counting technology. Current approaches to analyzing congested scenes have evolved beyond simple crowd counting, which outputs the number of people in the targeted image to a density map. This development aligns with the demands of real-life applications, as the same number of people can exhibit vastly different crowd distributions. Therefore, solely counting the number of crowds is no longer sufficient. CSRNet stands out as one representative method within this advanced category of approaches. In this paper, we propose a crowd counting network which is adaptive to the change in the density of people in the scene, addressing the performance degradation issue observed in the existing CSRNet(Congested Scene Recognition Network) when there are changes in density. To overcome the weakness of the CSRNet, we introduce a system that takes input from the image's information and adjusts the output of CSRNet based on the features extracted from the image. This aims to improve the algorithm's adaptability to changes in density, supplementing the shortcomings identified in the original CSRNet.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.57 no.4
• /
• pp.479-488
• /
• 2024

In recent years, changes in the fishing ground environment have led to reduced catches by fishermen at traditional fishing spots and increased operational costs related to vessel exploration, fuel, and labor. In this study, we developed a deep learning model to classify the fishing activities of drift gillnet fishing boats using AIS (automatic identification system) trajectory data. The proposed model integrates long short-term memory and 1-dimensional convolutional neural network layers to effectively distinguish between fishing (throwing and hauling) and non-fishing operations. Training on a dataset derived from AIS and validation against a subset of CCTV footage, the model achieved high accuracy, with a classification accuracy of 90% for fishing events. These results show that the model can be used effectively to monitor and manage fishing activities in coastal waters in real time.