• ETRI Journal
• /
• 제42권1호
• /
• 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)
• /
• 제11권10호
• /
• 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.

• 한국전자통신학회논문지
• /
• 제10권8호
• /
• pp.867-874
• /
• 2015

어촌계를 중심으로 부두나 해안가에는 인양기가 설치되어 있다. 인양기는 어구 및 해산물의 하역작업에 사용되거나, 태풍이나 악천후에 어선을 방파제 또는 육상으로 인양하기 위한 장치이다. 본 논문에서 제안하는 선착장 안전 모니터링을 위한 이동 객체 추적 시스템은 이러한 기본 역할에 선착장에서 발생하는 선박의 파손, 도난 및 침입 탐지 등의 안전을 수행할 수 있는 영상 감지 및 이동 객체 추적을 위한 시스템이다. 모션템플릿을 활용하여 광역감시에서 움직임을 실시간으로 감지하고 이동하는 객체(사람, 선박 등)에 대해 PTZ 카메라를 이용하여 집중 감시하는 객체 추적 시스템이다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제36권11호
• /
• pp.955-959
• /
• 2009

본 논문에서는 휴먼 객체들의 이동 궤적 정보를 기반으로 휴먼 상호 행동을 인식하기 위한 새로운 모델을 제안한다. 복잡한 휴먼 상호 행동들은 의미있는 작은 단위로 분할될 수 있는데 이를 '부-상호행동'이라 하며, 이들을 표현하는 모델들의 순차적 연결 또는 네트워크로 상호 행동을 모델링한다. 제안하는 모델은 서로 다른 상호 행동들에 공통적으로 나타나는 부-상호 행동들을 공유하도록 함으로써 모델의 복잡도를 낮추어 매우 효율적이다. 상호 행동 네트워크 모델의 동작 분석 및 기존 방법과의 비교 실험을 통해 제안한 방법의 우수성을 확인할 수 있었다.

• 사물인터넷융복합논문지
• /
• 제3권2호
• /
• pp.1-5
• /
• 2017

CCTV 기술이 발달하면서 여러 분야에서 사용하고 있다. 현제 CCTV 운영에 대해서 구체적으로 알아보고자 하며 또한 많은 분야에서 CCTV가 생기면서 운영에 대한 문제점이 생기고 있는데 문제점을 해결하기 위해 새로운 시스템을 설계하고자한다. 본 논문에서는 CCTV가 효율적으로 운영될 수 있도록 K-means을 이용하여 데이터 분석을 진행하고 영상기술도 증가시키고 효율적으로 운영이 가능하도록 기존 시스템에 새로운 기술을 및 기능을 추가하여 문제점을 해결하고 더 좋은 기술로 발전하고자 한다. 또한 관제센터에서 효율적으로 CCTV를 운영할 수 있도록 k-means를 이용하여 CCTV 기술에 새로운 시스템을 설계하여 문제점을 해결 효율적 관리를 위해 제안하고자 한다.

• 한국정보전자통신기술학회논문지
• /
• 제9권5호
• /
• pp.472-477
• /
• 2016

영상 감시 시스템에서 핵심적인 기술은 얼마나 정확하게 검출을 할 수 있는가 하는 것이다. 객체를 정확하게 추적하기 위해서는 영상에서 배경과 객체를 정확히 분리 할 수 있어야 한다. 하지만 사람의 시각이 아닌 시스템 스스로가 배경과 객체를 정확히 구분하고, 상황을 판단하는 것은 쉽지 않다. 영상처리 시스템의 신뢰도를 높이기 위해서는 배경과 객체를 정확히 검출해 내야 객체를 정확하게 추적할 수 있게 되며 이는 시스템 제작의 성공 여부에 큰 영향을 끼친다. 본 논문은 시시각각으로 변하는 배경 환경을 정확히 파악하기 위해 배경의 변화를 관찰하여 배경과 객체를 보다 정확하게 구분할 수 있는 방안을 제안하였다.

• 한국멀티미디어학회논문지
• /
• 제16권11호
• /
• pp.1261-1271
• /
• 2013

Zoom tracking involves the automatic adjustment of the focus motor in response to the zoom motor movements for the purpose of keeping an object of interest in focus, and is typically achieved by moving the zoom and focus motors in a zoom lens module so as to follow the so-called "trace curve", which shows the in-focus motor positions versus the zoom motor positions for a specific object distance. Thus, one can simply implement zoom tracking by following the most closest trace curve after all the trace curve data are stored in memory. However, this approach is often prohibitive in practical implementation because of its large memory requirement. Many other zoom tracking methods such as GZT, AZT and etc. have been proposed to avoid large memory requirement but with a deteriorated performance. In this paper, we propose a new zoom tracking method called 'Approximate Feedback Zoom Tracking method (AFZT)' on DM36x-based IP network camera, which does not need large memory by approximating nearby trace curves, but generates better zoom tracking accuracy than GZT or AZT by utilizing focus value as feedback information. Experiments through real implementation shows the proposed zoom tracking method improves the tracking performance and works in real-time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권4호
• /
• pp.2075-2092
• /
• 2017

Person re-identification is to match pedestrians observed from non-overlapping camera views. It has important applications in video surveillance such as person retrieval, person tracking, and activity analysis. However, it is a very challenging problem due to illumination, pose and viewpoint variations between non-overlapping camera views. In this work, we propose a viewpoint invariant method for matching pedestrian images using orientation of pedestrian. First, the proposed method divides a pedestrian image into patches and assigns angle to a patch using the orientation of the pedestrian under the assumption that a person body has the cylindrical shape. The difference between angles are then used to compute the similarity between patches. We applied the proposed method to real-time global multi-object tracking across multiple disjoint cameras with non-overlapping field of views. Re-identification algorithm makes global trajectories by connecting local trajectories obtained by different local trackers. The effectiveness of the viewpoint invariant method for person re-identification was validated on the VIPeR dataset. In addition, we demonstrated the effectiveness of the proposed approach for the inter-camera multiple object tracking on the MCT dataset with ground truth data for local tracking.

• Journal of Gastric Cancer
• /
• 제14권3호
• /
• pp.207-210
• /
• 2014

The peritoneum is the most frequent site of recurrence for gastric cancer after gastrectomy, followed by the liver and lymph nodes. In contrast, metastasis to the thymus is rare. Annual surveillance with computed tomography was performed on a 67-year-old man who previously underwent a distal gastrectomy and D2 lymph node dissection for gastric cancer at Tottori University. Five years after the initial operation, an anterior mediastinal tumor was detected by computed tomography. The patient underwent video-assisted thoracic surgery to remove the tumor. Histopathology revealed adenocarcinoma cells similar to those of the gastric cancer resected 5 years previously. Thymic metastasis was considered likely based on the location of the tumor. The recognition that gastric cancer can metastasize to unusual anatomic locations, such as the thymus, can facilitate an accurate, prompt diagnosis and appropriate treatment.

• 산업기술연구
• /
• 제38권1호
• /
• pp.41-52
• /
• 2018

Recently, object detection is a critical function for any system that uses computer vision and is widely used in various fields such as video surveillance and self-driving cars. However, the conventional methods can not detect the objects clearly because of the dynamic background change in the beach. In this paper, we propose a new technique to detect humans correctly in the dynamic videos like shores. A new background modeling method that combines spatial GMM (Gaussian Mixture Model) and temporal GMM is proposed to make more correct background image. Also, the proposed method improve the accuracy of people detection by using SVM (Support Vector Machine) to classify people from the objects and KCF (Kernelized Correlation Filter) Tracker to track people continuously in the complicated environment. The experimental result shows that our method can work well for detection and tracking of objects in videos containing dynamic factors and situations.