• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.186-198
• /
• 2021

Security control using surveillance cameras is established when people observe all surveillance videos directly. However, this task is labor-intensive and it is difficult to detect all abnormal situations. In this paper, we propose a deep neural network model, called AT-Net, that automatically detects abnormal situations in the surveillance video, and introduces an automatic video surveillance system developed based on this network model. In particular, AT-Net alleviates the ambiguity of existing abnormal situation detection methods by mapping features representing relationships between people and objects in surveillance video to the new tensor structure based on sparse coding. Through experiments on actual surveillance videos, AT-Net achieved an F1-score of about 89%, and improved abnormal situation detection performance by more than 25% compared to existing methods.

• Journal of Korea Multimedia Society
• /
• v.8 no.8
• /
• pp.1057-1068
• /
• 2005

This paper proposes a real-time face detection system which detects multiple faces from low resolution video such as web-camera video. First, It finds face region candidates by using AdaBoost based object detection method which selects a small number of critical features from a larger set. Next, it generates reduced feature vector for each face region candidate by using principle component analysis. Finally, it classifies if the candidate is a face or non-face by using SVM(Support Vector Machine) based binary classification. According to experiment results, the proposed method achieves real-time face detection from low resolution video. Also, it reduces the false detection rate than existing methods by using PCA and SVM based face classification step.

• Journal of Korea Multimedia Society
• /
• v.18 no.12
• /
• pp.1432-1438
• /
• 2015

We present a methodology to detect moving shadows in video sequences, which is considered as a challenging and critical problem in the most visual surveillance systems since 1980s. While most previous moving shadow detection methods used hand-crafted features such as chromaticity, physical properties, geometry, or combination thereof, our method can automatically learn features to classify whether image segments are shadow or foreground by using a deep learning architecture. Furthermore, applying Markov Random Field enables our system to refine our shadow detection results to improve its performance. Our algorithm is applied to five different challenging datasets of moving shadow detection, and its performance is comparable to that of state-of-the-art approaches.

• Journal of Convergence Society for SMB
• /
• v.3 no.1
• /
• pp.31-41
• /
• 2013

There have been various recent methods proposed in detecting driver drowsiness (DD) to avert fatal accidents. This work proposes a hardware/software (HW/SW) co-design approach in implementation of a DD detection system adapted from an AdaBoost-based object detection algorithm with Haar-like features [1] to monitor driver's eye closure rate. In this work, critical functions of the DD detection algorithm is accelerated through custom hardware components in order to speed up processing, while the software component implements the overall control and logical operations to achieve the complete functionality required of the DD detection algorithm. The HW/SW architecture was implemented on an Altera DE2 board with a video daughter board. Performance of the proposed implementation was evaluated and benchmarked against some recent works.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.10 no.2 s.21
• /
• pp.49-53
• /
• 2004

In this paper, we study a FDS(fishery detection system) for protection of an aquaculture farm. The FDS will identify a robbing vessel with real time and detect variance of the position of aquaculture farm. We also propose a F-AIS(Fishery- Automatic Identification System), which can detect the object approaching to aquaculture farm and distinguish fishing boats from thief vessel The F-AIS with low price and wideband responsibility will be adopted to the FDS.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.5 no.2
• /
• pp.57-62
• /
• 1996

Basically, the idea underlying most edge-detection technique is the computation of a local derivative operator used for edge detection in gray level image. This concept can be easily illustrated with the aid of object which shows an image of a simple lilght on a dark background, Using the gray level profile along a horizontal scan line of the image. the first and second derivatives of it were acquired. This study is to develop an automatic measuring system based on the digital image processing which can be applied to the real time measurement of the characteristics of the ultra-thin thickness. The experimental results indicate that the developed automatic inspection can be applied in real situation.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.5 no.1
• /
• pp.13-19
• /
• 2012

In this paper, we propose the pulmonary nodule detection method based on hierarchical 3D block analysis. The proposed system consists of two main part. In the first part, we select the block which is need to analysis. In the second part, we analysis the selected blocks. We extract the shape based features of the object in the selected blocks. Support Vector Machine is applied to the extracted features to classify into nodules and non-nodules.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.4
• /
• pp.1-11
• /
• 2022

Recently, research on license plate recognition, which is a core technology of an intelligent transportation system(ITS), is being actively conducted. In this paper, we propose a method to extract numbers and characters from low-quality license plate images by applying the YOLOv4 algorithm. YOLOv4 is a one-stage object detection method using convolution neural network including BACKBONE, NECK, and HEAD parts. It is a method of detecting objects in real time rather than the previous two-stage object detection method such as the faster R-CNN. In this paper, we studied a method to directly extract number and character regions from low-quality license plate images without additional edge detection and image segmentation processes. In order to evaluate the performance of the proposed method we experimented with 500 license plate images. In this experiment, 350 images were used for training and the remaining 150 images were used for the testing process. Computer simulations show that the mean average precision of detecting number and character regions on vehicle license plates was about 93.8%.

• International Journal of Advanced Culture Technology
• /
• v.11 no.1
• /
• pp.320-324
• /
• 2023

As urbanization accelerates and facilities that use energy increase, human life and property damage due to fire is increasing. Therefore, a fire monitoring system capable of quickly detecting a fire is required to reduce economic loss and human damage caused by a fire. In this study, we aim to develop an improved artificial intelligence model that can increase the accuracy of low fire alarms by mixing DeepSORT, which has strengths in object tracking, with the YOLOv5s model. In order to develop a fire detection model that is faster and more accurate than the existing artificial intelligence model, DeepSORT, a technology that complements and extends SORT as one of the most widely used frameworks for object tracking and YOLOv5s model, was selected and a mixed model was used and compared with the YOLOv5s model. As the final research result of this paper, the accuracy of YOLOv5s model was 96.3% and the number of frames per second was 30, and the YOLOv5s_DeepSORT mixed model was 0.9% higher in accuracy than YOLOv5s with an accuracy of 97.2% and number of frames per second: 30.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.277-278
• /
• 2022

최근 전동킥보드 보급이 이루어지면서 이와 관련된 교통사고가 증가하고 있다. 이에 따라 전동킥보드 주행 시 헬멧 착용을 의무화하는 도로교통법 개정안이 시행되고 있지만, 물리적으로 대부분 현장에서 단속이 어렵다. 본 논문에서는 딥러닝 영상인식 기술을 활용한 객체검출(object detection) 모델인 YOLOv4를 기반으로 전동킥보드 사용자의 헬멧 미착용 검출시스템을 제안하였다. 이를 통해 전동킥보드 주행 시 헬멧 착용 여부를 효율적으로 단속하는데 활용 할 수 있을 것으로 기대한다.