• 한국정밀공학회지
• /
• 제21권3호
• /
• pp.74-82
• /
• 2004

This paper proposes a fast zooming and focusing technique for implementing a real-time surveillance camera system which can capture a face image in less than 1 second. It determines the positions of zooming and focusing lenses using two-step algorithm. In the first step, it moves the zooming and focusing lenses simultaneously to the positions calculated using the lens equations for achieving the predetermined magnification. In the second step the focusing lens is adjusted so that it is positioned at the place where the focus measure is the maximum. The camera system implemented for the experiments has shown that the proposed algorithm spends about 0.56 second on average fur obtaining a focused image.

• 전기학회논문지
• /
• 제63권11호
• /
• pp.1559-1563
• /
• 2014

Recently, the prevention of crime using CCTV draws special in accordance with the higher crime incidence rate. Therefore security systems like a CCTV with audio capability are developing for giving an instant alarm. This paper proposes a scream detecting engine from various ambient noises in real environment for surveillance systems. The proposed engine detects scream signals among the various ambient noises using the features extracted in time/frequency domain. The experimental result shows the performance of our engine is very promising in comparison with the traditional engines using the model based features like LPC, LPCC and MFCC. The proposed method has a low computational complexity by using FFT and cross correlation coefficients instead of extracting complex features like LPC, LPCC and MFCC. Therefore the proposed engine can be efficient for audio-based surveillance systems with low SNRs in real field.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권5호
• /
• pp.1711-1725
• /
• 2014

Multi-target tracking is the main purpose of many video surveillance applications. Recently, multi-target tracking based on the particle filter method has achieved robust results by using the data association process. However, this method requires many calculations and it is inadequate for real time applications, because the number of associations exponentially increases with the number of measurements and targets. In this paper, to reduce the computational cost of the data association process, we propose a novel multi-target tracking method that excludes particle samples in the overlapped predictive region between the target to track and marginal targets. Moreover, to resolve the occlusion problem, we define an occlusion mode with the normal dynamic mode. When the targets are occluded, the mode is switched to the occlusion mode and the samples are propagated by Gaussian noise without the sampling process of the particle filter. Experimental results demonstrate the robustness of the proposed multi-target tracking method even in occlusion.

• ETRI Journal
• /
• 제41권4호
• /
• pp.494-505
• /
• 2019

In this paper, we propose a new framework for detecting the unauthorized dumping of garbage in real-world surveillance camera. Although several action/behavior recognition methods have been investigated, these studies are hardly applicable to real-world scenarios because they are mainly focused on well-refined datasets. Because the dumping actions in the real-world take a variety of forms, building a new method to disclose the actions instead of exploiting previous approaches is a better strategy. We detected the dumping action by the change in relation between a person and the object being held by them. To find the person-held object of indefinite form, we used a background subtraction algorithm and human joint estimation. The person-held object was then tracked and the relation model between the joints and objects was built. Finally, the dumping action was detected through the voting-based decision module. In the experiments, we show the effectiveness of the proposed method by testing on real-world videos containing various dumping actions. In addition, the proposed framework is implemented in a real-time monitoring system through a fast online algorithm.

• 한국군사과학기술학회지
• /
• 제12권6호
• /
• pp.768-775
• /
• 2009

In this paper, the sound source localization system in real time which uses the time delay of arrival signal is proposed. This system uses minimum microphones and surveillance camera for estimation of the sound source localization and sound direction. To apply this system to the military field, four models(model1~model4) are derived. Model 1 can be used to evaluate the sound source localization at the long distance. Model2 and model3 can be applied to estimate the sound direction. Model4 is useful for the special purpose and potable device. It is possible for this system to be used for the military guard and surveillance. As a result of experiments, It is shown that this system can estimate the sound source localization and the sound direction using minimum microphones.

• 한국멀티미디어학회논문지
• /
• 제25권6호
• /
• pp.807-818
• /
• 2022

In order to further improve the accuracy and time efficiency of behavior recognition in intelligent monitoring scenarios, a human behavior recognition algorithm based on YOLO combined with LSTM and CNN is proposed. Using the real-time nature of YOLO target detection, firstly, the specific behavior in the surveillance video is detected in real time, and the depth feature extraction is performed after obtaining the target size, location and other information; Then, remove noise data from irrelevant areas in the image; Finally, combined with LSTM modeling and processing time series, the final behavior discrimination is made for the behavior action sequence in the surveillance video. Experiments in the MSR and KTH datasets show that the average recognition rate of each behavior reaches 98.42% and 96.6%, and the average recognition speed reaches 210ms and 220ms. The method in this paper has a good effect on the intelligence behavior recognition.

• 한국멀티미디어학회논문지
• /
• 제19권2호
• /
• pp.215-223
• /
• 2016

To reduce huge losses in pig farms, weaning pigs with weak immune systems are required to be carefully supervised. Even if various researches have been performed for livestock monitoring environment, segmenting each pig from touching pigs is still entrenched as a difficult problem. In this paper, we propose a real-time segmentation method for moving pigs by using motion information in a 24-h video surveillance system. The experimental results with the videos obtained from a domestic pig farm illustrated the possibility for segmenting by using our proposed method in real-time.

• 한국멀티미디어학회논문지
• /
• 제19권1호
• /
• pp.10-21
• /
• 2016

Images taken from outdoor are degraded quality by fog or haze, etc. In this paper, we propose a method that provides the visibility improved images through fog or haze removal. We proposed haze removal method that uses brightness transform based on atmospheric scatter coefficient rate with local histogram equalization. To calculate the transmission rate that indicate fog rate in original image, we use atmospheric scatter coefficient rate based on quadratic equations about haze model. And primary brightness transformed image can be obtained by using the obtained transmission rate. Also we use local histogram equalization with proposed brightness transform for effectively image visibility enhancement. Unlike existing methods, our method can process real-time with stable and effect image visibility enhancement. Proposed method use only the luminance images processed by good performance surveillance systems because it represents the real-time processing is required, black-box, digital camera and multimedia equipment is applicable. Also because it shows good performance only with the luminance images processed, Surveillance systems, black boxes, digital cameras, and multimedia devices etc, that require real-time processing can be applied.

• 융합보안논문지
• /
• 제15권1호
• /
• pp.83-89
• /
• 2015

다수의 CCTV(Closed Circuit Television)로 광범위한 지역을 관리하는 보안 감시 시스템에서 시간과 장소에 구애받지 않고 CCTV를 원격으로 실시간 모니터링 할 수 있도록 어플리케이션을 설계 및 구현했다. Xcode를 사용하여 개발된 어플리케이션은 폐쇄적인 중앙 관제 시스템으로부터 안전한 관리자 인터페이스를 제공하는 역할을 한다. 효율적이며 직관적인 인터페이스를 통해 어플리케이션은 중앙관제 시스템에서 제공하는 실시간 상황 알림보고 및 상황 인지 추론 결과를 원격의 관리자에게 전달한다. 사용자의 편의를 위해, 어플리케이션은 이벤트 발생시의 push 알림, SNS(Social Network Service) 연동을 포함한 다양한 기능을 제공한다. 실시간 모니터링을 위해 카메라의 화면을 스트림 해줄 서비스는 Wirecast와 Wowza media server를 이용한다. Wowza stream engine은 실시간 스트리밍을 돕는 개발규격에 맞춘 URL을 제공한다. 이를 통해 모바일에서 실시간 스트리밍 결과를 받아 볼 수 있으며, 그 과정에서 발생되는 자원 소모에 관련된 성능분석을 보였다.

• 전자공학회논문지C
• /
• 제36C권8호
• /
• pp.62-69
• /
• 1999

본 논문에서는 영상에 기반한 실시간 교통 감시 시스템을 구현한다. 영상 기반의 교통 감시 시스템은 루프 감지기 등의 센서를 이용한 방법에 비해 비용과 설치, 유지, 보수 면에서의 장점으로 인하여 많이 연구되고 있다. 제안한 시스템은 인터넷상에서 FPA (Field Processing Agent)와 TSM (Traffic Surveillance Manager)으로 구성되며, FPA는 TSM에게 도로 영상과 차량의 속도, 도로 점유율과 같은 교통 정보를 제공한다. 차량의 평균 속도와 도로 점유율은, 도로색 영상과 연속된 입력 영상간의 샘플링 지점의 색상 차이 변화를 이용하여 추출한다. 제안한 방법은 근사적인 교통정보를 추출해 주며, 입력 영상 전체에 대한 처리 과정 없이 제한된 영역만을 처리하기 때문에, 실시간 감시 시스템을 구축하는데 용이하다.