• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.2
• /
• pp.161-168
• /
• 2019

Recently, video equipments such as CCTV, which is spreading rapidly, is being used as a means to monitor and cope with abnormal situations in almost governments, companies, and households. However, in most cases, since recognizing the abnormal situation is carried out by the monitoring person, the immediate response is difficult and is used only for post-analysis. In this paper, we present the results of the development of video surveillance system that automatically recognizing the abnormal situations and sending such events to the smartphone immediately using the latest deep learning technology. The proposed system extracts skeletons from the human objects in real time using Openpose library and then recognizes the human behaviors automatically using deep learning technology. To this end, we reconstruct Openpose library, which developed in the Caffe framework, on Darknet framework to improve real-time processing. We also verified the performance improvement through experiments. The system to be introduced in this paper has accurate and fast behavioral recognition performance and scalability, so it is expected that it can be used for video surveillance systems for various applications.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.3
• /
• pp.70-77
• /
• 2017

Recently, Internet of Things (IoT) and deep learning techniques have affected video surveillance systems in various ways. The surveillance features that perform detection, tracking, and classification of specific objects in Closed Circuit Television (CCTV) video are becoming more intelligent. This paper presents real-time algorithm that can run in a PC environment using only a low power CPU. Traditional tracking algorithms combine background modeling using the Gaussian Mixture Model (GMM), Hungarian algorithm, and a Kalman filter; they have relatively low complexity but high detection errors. To supplement this, deep learning technology was used, which can be trained from a large amounts of data. In particular, an SRGB(Sequential RGB)-3 Layer CNN was used on tracked objects to emphasize the features of moving people. Performance evaluation comparing the proposed algorithm with existing ones using HOG and SVM showed move-in and move-out error rate reductions by 7.6 % and 9.0 %, respectively.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.165-171
• /
• 2018

Shadow is a physical phenomenon observed in natural scenes and has a negative effect on various image processing systems such as intelligent video surveillance, traffic surveillance and aerial imagery analysis. Therefore, shadow detection should be considered as a preprocessing process in all areas of computer vision. In this paper, we define and analyze various feature elements for shadow detection in a single natural image that does not require a reference image. The shadow elements describe the intensity, chromaticity, illuminant-invariant, color invariance, and entropy image, which indicate the uncertainty of the information. The results show that the chromaticity and illuminant-invariant images are effective for shadow detection. In the future, we will define a fusion map of various shadow feature elements, and continue to study shadow detection that can adapt to various lighting levels, and shadow removal using chromaticity and illuminance invariant images.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.78-89
• /
• 2020

Human activity recognition (HAR) has become effective as a computer vision tool for video surveillance systems. In this paper, a novel biometric system that can detect human activities in 3D space is proposed. In order to implement HAR, joint angles obtained using an RGB-depth sensor are used as features. Because HAR is operated in the time domain, angle information is stored using the sliding kernel method. Haar-wavelet transform (HWT) is applied to preserve the information of the features before reducing the data dimension. Dimension reduction using an averaging algorithm is also applied to decrease the computational cost, which provides faster performance while maintaining high accuracy. Before the classification, a proposed thresholding method with inverse HWT is conducted to extract the final feature set. Finally, the K-nearest neighbor (k-NN) algorithm is used to recognize the activity with respect to the given data. The method compares favorably with the results using other machine learning algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.10
• /
• pp.5006-5022
• /
• 2017

Effect and robust detection of targets in infrared images has crucial meaning for many applications, such as infrared guidance, early warning, and video surveillance. However, it is not an easy task due to the special characteristics of the infrared images, in which the background clutters are severe and the targets are weak. The recent literature demonstrates that sparse representation can help handle the detection problem, however, the detection performance should be improved. To this end, in this text, a hybrid method based on local sparse representation and contrast is proposed, which can effectively and robustly detect the infrared targets. First, a residual image is calculated based on local sparse representation for the original image, in which the target can be effectively highlighted. Then, a local contrast based method is adopted to compute the target prediction image, in which the background clutters can be highly suppressed. Subsequently, the residual image and the target prediction image are combined together adaptively so as to accurately and robustly locate the targets. Based on a set of comprehensive experiments, our algorithm has demonstrated better performance than other existing alternatives.

• Journal of Korea Multimedia Society
• /
• v.23 no.3
• /
• pp.395-401
• /
• 2020

In this paper, a motion-based ROI extraction algorithm from a high resolution fisheye image is proposed for multi-view monitoring systems. Lately fisheye cameras are widely used because of the wide angle-of-view and they basically provide a lens correction functionality as well as various viewing modes. However, since the distortion-free angle of conventional algorithms is quite narrow due to the severe distortion ratio, there are lots of unintentional dead areas and they require much computation time in finding undistorted coordinates. Thus, the proposed algorithm adopts an image decimation and a motion detection methods, that can extract the undistorted ROI image with a standard angle-of-view for the fast and intelligent surveillance system. In addition, a mesh-type ROI is presented to reduce the lens correction time, so that this independent ROI scheme can parallelize and maximize the processor's utilization.

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.759-768
• /
• 2005

This paper describes an algorithm that can recognize gestures constructing subspace gesture symbols with hybrid feature information. The previous popular methods based on geometric feature and appearance have resulted in ambiguous output in case of recognizing between similar gesture because they use just the Position information of the hands, feet or bodily shape features. However, our proposed method can classify not only recognition of motion but also similar gestures by the partial feature information presenting which parts of body move and the global feature information including 2-dimensional bodily motion. And this method which is a simple and robust recognition algorithm can be applied in various application such surveillance system and intelligent interface systems.

• Journal of Advanced Navigation Technology
• /
• v.18 no.4
• /
• pp.387-392
• /
• 2014

Recently, various research for intelligent video surveillance system have been proposed, but the existing monitoring systems are inefficient because all of situational awareness is judged by the human. In this paper, shadow removal based moving object tracking method is proposed using the chromaticity and entropy image. The background subtraction model, effective in the context awareness environment, has been applied for moving object detection. After detecting the region of moving object, the shadow candidate region has been estimated and removed by RGB based chromaticity and minimum cross entropy images. For the validity of the proposed method, the highway video is used to experiment. Some experiments are conducted so as to verify the proposed method, and as a result, shadow removal and moving object tracking are well performed.

• Convergence Security Journal
• /
• v.23 no.1
• /
• pp.139-145
• /
• 2023

The ROK Army is promoting cutting-edge, future-oriented military development such as a mobile, intelligent, and hyper-connected Army TIGER system. The future infantry brigade plans to increase mobility with squad-level tactical vehicles to enable combat in multi-domain operations and to deploy various weapon systems such as surveillance and reconnaissance drones. In addition, it will be developed into an intelligent unit that transmits and receives data collected through the weapon system through a hyper-connected network. Accordingly, the future infantry brigade will transmit and receive more data. However, the Army's tactical information communication system has limitations in operating as a tactical communication system for future units, such as low transmission speed and bandwidth and restrictions on communication support. Therefore, in this paper, the information distribution capability of the future infantry brigade is presented through the offensive operation scenario and M&S.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.3
• /
• pp.239-245
• /
• 2016

In the midst of continuing international recession, the rate of maritime traffic and marine leisure markets are consistently growing. The Republic of Korea controls the marine traffic volume through vessel traffic centers and various other management facilities. Nevertheless, the continuous growth and complexity of marine traffic is resulting in repeated occurrences of marine accidents. Recovery is very difficult in cases of human injuries or deaths caused by marine accidents due to its nature, and the scale of marine accidents is also becoming greater with advanced ship building technologies. Passenger ships, oil tankers, and other such vessels used for specific purposes requires a more detailed navigational status surveillance and analysis, and numerous research has been conducted with an objective for monitoring such special purpose vessels. However, the data elements transmitted from the ocean to the shore station are limited to AIS and ARPA. We are implementing IoT ship sensor collection and a syncing system capable of transmitting various ship sensing data to the shore station, and also proposing a Safe Navigation Status Analysis System utilizing the collected data.