• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.661-664
• /
• 2009

최근 지능형 감시카메라에 대한 연구가 활발히 진행되고 있다. 그러나 현재의 연구들은 대부분 통합시스템 구현보다는 단일 모듈에 대한 성능향상에 중점을 두고 있다. 따라서 본 논문에서는 이동이 가능한 몸체, 얼굴검출, 모션 센서 통합 모듈로 구성하는 이동형 무선감시 시스템을 구현하였다. 이동형 무선 감시 시스템의 구현에는 sharp사의 카메라 모듈과 ecom사의 무선영상전송 모듈, A4WD1 Combo kit for RC를 이용한 이동로봇 바디, roboblock의 ZigBee RF 무선컨트롤 송수신 모듈을 사용 하였고, 모션 센서 모듈에는 PANASONIC의 AMN14111를 사용하였다. OpenCV 라이브러리를 이용한 얼굴검출과 MFC로 소프트웨어를 구현하였다. 본 논문에서 구현한 시스템은 모션 센서를 이용하는 이동형 영상 감시 시스템이나 얼굴검출이 필요한 시스템, 원격조정이 필요한 작업환경에 유용하게 사용될 수 있다.

• 한국컴퓨터정보학회논문지
• /
• 제14권4호
• /
• pp.47-57
• /
• 2009

최근 컴퓨터비젼 분야에서 이벤트 검출 및 인식이 활발히 연구되고 있으며, 도전적인 주제들 중 하나이다. 본 논문에서는 사무실 환경에서 발생할 수 있는 이벤트의 검출 및 인식을 위한 방법을 제안한다. 제안된 방법은 MHI(Motion History Image) 시퀀스(sequence)를 이응한 인간의 모션을 분석하며, 사람의 처형과 착용한 옷의 종류와 색상, 그리고 카메라로부터의 위치관계에 불변한 특성을 가진다. 제안된 방법은 기존의 방법들 중, 칼라 정보를 이용한 방법에 비해 조명의 변화에 민감하지 않은 장점이 있으며, 관심의 대상이 되는 객체의 외형과 같은 사전지식에 의존하는 방법에 비해 스케일에 민감하지 않은 장점이 있다. 에지검출 기술을 HMI 순서 영상 정보와 결합하여 사람 모션의 기하학적 특징을 추출한 후, 이벤트 인식의 기본정보로 활용한다. 제안된 방법은 단순한 이벤트 검출 프레임웍을 사용하기 때문에 검출하고자 하는 이벤트의 설명만을 첨가하는 것으로 확장이 가능하다. 또한, 제안된 방법은 컴퓨터비젼 기술에 기반한 많은 감시시스템 뿐 아니라 상황인식 기반의 이벤트 검출 시스템에 핵심기술이다.

• ETRI Journal
• /
• 제32권6호
• /
• pp.881-890
• /
• 2010

Conventional fire detection systems use physical sensors to detect fire. Chemical properties of particles in the air are acquired by sensors and are used by conventional fire detection systems to raise an alarm. However, this can also cause false alarms; for example, a person smoking in a room may trigger a typical fire alarm system. In order to manage false alarms of conventional fire detection systems, a computer vision-based fire detection algorithm is proposed in this paper. The proposed fire detection algorithm consists of two main parts: fire color modeling and motion detection. The algorithm can be used in parallel with conventional fire detection systems to reduce false alarms. It can also be deployed as a stand-alone system to detect fire by using video frames acquired through a video acquisition device. A novel fire color model is developed in CIE $L^*a^*b^*$ color space to identify fire pixels. The proposed fire color model is tested with ten diverse video sequences including different types of fire. The experimental results are quite encouraging in terms of correctly classifying fire pixels according to color information only. The overall fire detection system's performance is tested over a benchmark fire video database, and its performance is compared with the state-of-the-art fire detection method.

• ETRI Journal
• /
• 제42권3호
• /
• pp.411-419
• /
• 2020

In real-world intelligent transportation systems, accuracy in vehicle license plate detection and recognition is considered quite critical. Many algorithms have been proposed for still images, but their accuracy on actual videos is not satisfactory. This stems from several problematic conditions in videos, such as vehicle motion blur, variety in viewpoints, outliers, and the lack of publicly available video datasets. In this study, we focus on these challenges and propose a license plate detection and recognition scheme for videos based on a temporal matching prior network. Specifically, to improve the robustness of detection and recognition accuracy in the presence of motion blur and outliers, forward and bidirectional matching priors between consecutive frames are properly combined with layer structures specifically designed for plate detection. We also built our own video dataset for the deep training of the proposed network. During network training, we perform data augmentation based on image rotation to increase robustness regarding the various viewpoints in videos.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.1960-1963
• /
• 2003

For applications such as video surveillance and human computer interface, we propose an efficiently integrated method to detect and track faces. Various visual cues are combined to the algorithm: motion, skin color, global appearance and facial pattern detection. The ICA (Independent Component Analysis)-SVM (Support Vector Machine based pattern detection is performed on the candidate region extracted by motion, color and global appearance information. Simultaneous execution of detection and short-term tracking also increases the rate and accuracy of detection. Experimental results show that our detection rate is 91％ with very few false alarms running at about 4 frames per second for 640 by 480 pixel images on a Pentium IV 1㎓.

• ETRI Journal
• /
• 제45권2호
• /
• pp.329-337
• /
• 2023

For safe last-mile autonomous robot delivery services in complex environments, rapid and accurate collision prediction and detection is vital. This study proposes a suitable neural network model that relies on multiple navigation sensors. A light detection and ranging technique is used to measure the relative distances to potential collision obstacles along the robot's path of motion, and an accelerometer is used to detect impacts. The proposed method tightly couples relative distance and acceleration time-series data in a complementary fashion to minimize errors. A long short-term memory, fully connected layer, and SoftMax function are integrated to train and classify the rapidly changing collision countermeasure state during robot motion. Simulation results show that the proposed method effectively performs collision prediction and detection for various obstacles.

• IEIE Transactions on Smart Processing and Computing
• /
• 제2권4호
• /
• pp.203-207
• /
• 2013

The appropriate handling of motion artifacts is essential for clinical diagnosis in magnetic resonance imaging (MRI). In many cases, motion is an inherent part of MR images because it is difficult to control during MR imaging. As the motion in the human body occur in a deformable manner, they are difficult to deal with. This paper proposes a novel detection method for periodically moving regions to produce MR images with less motion artifacts. When the data is acquired by the radial trajectory, the proposed method can extract the deformable region easily using the difference in the modulated sinograms, which have different periodic phase terms. The simulation results applied to the various cases confirmed the good performance of the proposed method.

• 통합자연과학논문집
• /
• 제9권2호
• /
• pp.155-160
• /
• 2016

Applying image processing techniques to education, the face of the learner is photographed, and expression and movement are detected from video, and the system which estimates degree of concentration of the learner is developed. For one learner, the measuring system is designed in terms of estimating a degree of concentration from direction of line of learner's sight and condition of the eye. In case of multiple learners, it must need to measure each concentration level of all learners in the classroom. But it is inefficient because one camera per each learner is required. In this paper, position in the face region is estimated from video which photographs the learner in the class by the difference between frames within the motion direction. And the system which detects the face direction by the face part detection by template matching is proposed. From the result of the difference between frames in the first image of the video, frontal face detection by Viola-Jones method is performed. Also the direction of the motion which arose in the face region is estimated with the migration length and the face region is tracked. Then the face parts are detected to tracking. Finally, the direction of the face is estimated from the result of face tracking and face parts detection.

• 대한임베디드공학회논문지
• /
• 제11권5호
• /
• pp.277-285
• /
• 2016

Moving object detection system has been an emerging research field in various advanced driver assistance systems (ADAS) and surveillance system. In this paper, we propose two optical flow based moving object detection methods at dynamic scenes. Both proposed methods consist of three successive steps; pre-processing, foreground segmentation, and post-processing steps. Two proposed methods have the same pre-processing and post-processing steps, but different foreground segmentation step. Pre-processing calculates mainly optical flow map of which each pixel has the amplitude of motion vector. Dense optical flows are estimated by using Farneback technique, and the amplitude of the motion normalized into the range from 0 to 255 is assigned to each pixel of optical flow map. In the foreground segmentation step, moving object and background are classified by using the optical flow map. Here, we proposed two algorithms. One is Gaussian mixture model (GMM) based background subtraction, which is applied on optical map. Another is adaptive thresholding based foreground segmentation, which classifies each pixel into object and background by updating threshold value column by column. Through the simulations, we show that both optical flow based methods can achieve good enough object detection performances in dynamic scenes.

• 한국항행학회논문지
• /
• 제14권2호
• /
• pp.284-288
• /
• 2010

비디오 감시 장치는 사회안전망 구축분야에서 다양하게 응용되고 있다. 본 논문은 고정 카메라에서 취득된 시각정보를 이용한 침입 탐지 알고리즘을 제안하였다. 제안한 알고리즘은 비디오 시퀀스에서 AMF를 이용하여 모델링된 배경으로부터 물체 프레임 후보를 찾아내고, 감지된 물체는 움직임 정보의 분석으로 계산된다. 움직임 검출은 RGB 공간에서 2D 물체의 상대적 크기로 결정하였으며 물체 감지를 위한 임계값은 실험적인 방법으로 결정하였다. 실험 결과, 시 공간적 후보 정보들이 급격히 변화할 때, 물체 감지의 성능이 우수함을 확인할 수 있었다.