• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.750-754
• /
• 2007

본 논문은 실내의 로비나 복도에 설치된 방범 카메라로부터 얻어진 일련의 영상으로부터 '걷기', '뛰기', '앉기', '일어서기', '넘어짐'의 비교적 짧은 시간에 일어나는 인간 행동들을 실시간으로 인식하는 시스템의 구현에 관해 다룬다. 먼저 입력으로 받은 영상을 계층적 색인 구조를 갖는 다중 가우시안 기반의 배경 모델을 이용하여 윤곽을 추출하고 객체를 인식하여 시간차에 의한 가중치로 누적하여 시간 템플릿을 만든다. 만들어진 시간 템플릿으로부터 특징을 추출하여 신경망 모델에 적용하여 5가지 인간행동을 구분한다. 구현된 시스템으로 인간행동 인식 실험을 수행하였는데, 실험 참가자들의 행동 방식이 약간씩 달랐음에도 불구하고 높은 인식률을 보여주었다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.3
• /
• pp.387-391
• /
• 2008

For the detection of moving objects, background subtraction methods are widely used. In case the background has variation, we need to update the background in real-time for the reliable detection of foreground objects. Gaussian mixture model (GMM) combined with probabilistic learning is one of the most popular methods for the real-time update of the background. However, it does not work well in the complex and dynamic backgrounds with high traffic regions. In this paper, we propose a new method for modelling and updating more reliably the complex and dynamic backgrounds based on the probabilistic learning and the layered processing.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.5
• /
• 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.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.11C
• /
• pp.1161-1168
• /
• 2003

In this paper, we propose an improved statistical model-based voice activity detection algorithm and threshold update method. We first improve signal-to-noise ratio by using speech enhancement preprocessing algorithm combined power subtraction method and matched filter, then apply it to LLR test optimum decision rule for improving the performance even in low SNR conditions. And we propose an adaptive threshold update method that was not concerned in any papers. We also perform extensive computer simulations to demonstrate the performance improvement of the proposed VAD algorithm employing the proposed speech enhancement preprocessing algorithm and adaptive threshold update method under various background noise environments. Finally we verify our results by comparing ITU-T G.729 Annex B.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.6
• /
• pp.88-94
• /
• 2009

This paper proposes real time object detection and tracking algorithm that can be applied to security and supervisory system field. A proposed system is devide into object detection phase and object tracking phase. In object detection, we suggest Adaptive background subtraction method and Adaptive block based model which are advanced motion detecting methods to detect exact object motions. In object tracking, we design a multiple vehicle tracking system based on Kalman filtering. As a result of experiment, motion of moving object can be estimated. the result of tracking multipul object was not lost and object was tracked correctly. Also, we obtained improved result from long range detection and tracking.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.321-322
• /
• 2007

본 논문에서는 로봇과 인간의 인터액션을 위해 인간 몸의 실루엣 및 액티브 스켈레톤 추출 기법을 제안한다. 연속된 이미지 정보로 부터 얻어진 옷영역등의 정보에서 background subtraction를 이용한 adaptive fusion을 통해 추출된 인간 몸의 실루엣을 바탕으로 active contour와 가상 신체 모델인 skeleton model을 응용하여 작은 움직임에 보다 강한 active skeleton model을 이용하여 인간 몸의 특징 점 위치를 추출하는 방법을 한다.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.8 no.2
• /
• pp.133-138
• /
• 2014

In this paper, a simple but efficient gait recognition method using spatial-temporal silhouette analysis is proposed. For each image sequence, a background subtraction algorithm and a PBAS(pixel based adaptive segmenter) procedure are first used to segment the moving silhouettes of a walking figure. Then, to identify people, the step count and stride length of walking figure is obtained in silhouette images. Experimental results on a CASIA dataset including 124 subjects demonstrate the validity of the proposed method. Also, the proposed system are believed to have a sufficient feasibility for the application to gait recognition.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.22-29
• /
• 2010

A real-time detection and tracking of moving objects in video sequences is very important for smart surveillance systems. In this paper, we propose a novel algorithm for the detection of moving objects that is the entropy-based adaptive Gaussian mixture model (AGMM). First, the increment of entropy generally means the increment of complexity, and objects in unstable conditions cause higher entropy variations. Hence, if we apply these properties to the motion segmentation, pixels with large changes in entropy in moments have a higher chance in belonging to moving objects. Therefore, we apply the Clausius entropy theory to convert the pixel value in an image domain into the amount of energy change in an entropy domain. Second, we use an adaptive background subtraction method to detect moving objects. This models entropy variations from backgrounds as a mixture of Gaussians. Experiment results demonstrate that our method can detect motion object effectively and reliably.

• Journal of Korea Multimedia Society
• /
• v.18 no.11
• /
• pp.1289-1301
• /
• 2015

Pedestrian detection (PD) is an essential task in various applications and sliding window-based methods utilizing HOG (Histogram of Oriented Gradients) or HOG-like descriptors have been shown to be very effective for accurate PD. However, due to exhaustive search across images, PD methods based on sliding window usually require heavy computational time. In this paper, we propose a real-time PD method for embedded visual surveillance with fixed backgrounds. The proposed PD method employs HOG descriptors as many PD methods does, but utilizes selective search so that it can save processing time significantly. The proposed selective search is guided by restricting searching to candidate regions extracted from Adaptive Gaussian Mixture Model (AGMM)-based background subtraction technique. Moreover, approximate computation of HOG descriptor and implementation in fixed-point arithmetic mode contributes to reduction of processing time further. Possible accuracy degradation due to approximate computation is compensated by applying an appropriate one among three offline trained SVM classifiers according to sizes of candidate regions. The experimental results show that the proposed PD method significantly improves processing speed without noticeable accuracy degradation compared to the original HOG-based PD and HOG with cascade SVM so that it is a suitable real-time PD implementation for embedded surveillance systems.

• KIISE Transactions on Computing Practices
• /
• v.22 no.2
• /
• pp.61-68
• /
• 2016

Surveillance cameras have been installed in many places because security and safety has become an important issue in modern society. However, watching surveillance videos and judging accidental situations is very labor-intensive and time-consuming. So now, requests for research to automatically analyze the surveillance videos is growing. In this paper, we propose a surveillance system to track multiple persons in videos and to summarize the videos based on tracking information. The proposed surveillance summarization system applies an adaptive illumination correction, subtracts the background, detects multiple persons, tracks the persons, and saves their tracking information in a database. The tracking information includes tracking one's path, their movement status, length of staying time at the location, enterance/exit times, and so on. The movement status is classified into six statuses(Enter, Stay, Slow, Normal, Fast, and Exit). This proposed summarization system provides a person's status as a graph in time and space and helps to quickly determine the status of the tracked person.