• 한국멀티미디어학회논문지
• /
• 제23권10호
• /
• pp.1236-1249
• /
• 2020

In a most recent object tracking research work, applying Convolutional Neural Network and Recurrent Neural Network-based strategies become relevant for resolving the noticeable challenges in it, like, occlusion, motion, object, and camera viewpoint variations, changing several targets, lighting variations. In this paper, the LSTM Network-based Tracking association method has proposed where the technique capable of real-time multi-object tracking by creating one of the useful LSTM networks that associated with tracking, which supports the long term tracking along with solving challenges. The LSTM network is a different neural network defined in Keras as a sequence of layers, where the Sequential classes would be a container for these layers. This purposing network structure builds with the integration of tracking association on Keras neural-network library. The tracking process has been associated with the LSTM Network feature learning output and obtained outstanding real-time detection and tracking performance. In this work, the main focus was learning trackable objects locations, appearance, and motion details, then predicting the feature location of objects on boxes according to their initial position. The performance of the joint object tracking system has shown that the LSTM network is more powerful and capable of working on a real-time multi-object tracking process.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제30권7_8호
• /
• pp.713-718
• /
• 2003

조건부 밀도 전파(Condensation)는 강건한 추적 성능과 실시간 구현이 가능하다는 장점을 지닌다. 그러나 정확한 추적을 수행하기 위해서는 복잡한 형태 모델과 많은 수의 샘플을 요구하므로 현실적으로 실시간 다중 추적에 적합하지 않은 경우가 많다. 본 논문에서는 실시간 응용에 적합하도록 작은 탐색 공간을 갖는 이산 형태의 형태 모델과 다중 추적 시각 추적기간의 상호 경쟁 관계를 고려하여 적은 수의 샘플로도 좋은 추적 성능을 보이는 경쟁적 Condensation 알고리즘을 제안한다. 실험 결과, 제안한 경쟁적 추적 알고리즘은 복잡하게 이동하는 여러 군중을 실시간으로 강건하게 추적함을 보인다.

• 한국컴퓨터정보학회논문지
• /
• 제19권2호
• /
• pp.125-132
• /
• 2014

본 논문에서는 저가의 웹 카메라를 사용하여 마커 없이 손끝과 붓을 트래킹 하는 시스템을 제시한다. 트래킹 시스템은 CUDA를 사용하여 병렬처리를 적용했다. 이 트래킹 시스템은 노트북이나 데스크탑과 같은 환경에서 수행이 가능하고, 실시간 애플리케이션에 사용 가능한 성능을 가진다. 또한 본 논문에서는 사적인 수성 사인펜 드로잉 모델을 제시하고 구현된 결과를 보여준다. 제안하는 시스템은 손끝과 붓을 트래킹 하는 저가의 실시간 트래킹 시스템으로 사실적 드로잉 애플리케이션과 연동하여 미래 최첨단 교육 환경 구축의 테스트베드로의 활용을 기대한다.

• 산업공학
• /
• 제24권4호
• /
• pp.428-434
• /
• 2011

In these days, mobile technology such as smart phone and GPS have an effect on business processes of many companies especially a transportation company. The purpose of this paper is to present the development processes of real time vehicles tracking and intelligent TMS (Transportation Management System) using smart phone applications. The objective of this study is two-fold. The first is to redesign business process of the transportation company. Using BPR (business process re-engineering), we analyze current processes to find opportunities for improvement redefining processes after adopting mobile technology precisely. The second is to develop the real time vehicles tracking and intelligent TMS. Proposed system consists of four parts : (1) intelligent TMS(web system) (2) real time vehicle tracking application for TMS (3) real time tracking application for customer (4) salesman supporting application. Developed system was tested at the transportation company and was found to be an useful system.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.162-167
• /
• 2003

In this paper, a novel feasible real-time system was researched for a differential driven wheeled autonomous mobile robot so that the mobile robot can move in a smooth, safe and elegant way. Least Square Minimum Path Planning was well used for the system to generate a smooth executable path for the mobile robot, and the point-to-point tracking algorithm was presented as well as its application in arbitrary path tracking. In order to make sure the robot can run elegantly and safely, trapezoidal speed was integrated into the point-to-point path tracking algorithm. The application to guest following for the autonomous mobile robot shows its wide application of the algorithm. The novel design was successfully proved to be feasible by our experiments on our mobile robot Interactive Robot Usher (IRU) in National University of Singapore.

• 전자공학회논문지A
• /
• 제31A권3호
• /
• pp.1-9
• /
• 1994

In this paper as a new approach for real-time multitarget tracking, a hybrid OptoNeural multitarget tracking system based on optical BJTC and neural networks data association algorithm is suggested. In the proposed hybrid tracking system, an optical BJTC is introduced as a preprocessor to reduce the massive input target data into a few correlation peak signals and then the neural networks data association algorithm is used for the massively parallel data association between measurement signals and targets in real-time. Finally, new hybrid type OptoNeural target tracking system is constructed and then some experimental results on multitarget tracking is included. The real-time implementation method of the proposed hybrid system is also discussed.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.135-135
• /
• 2001

In recent years there have been increasing interests in real-time object tracking with image information. Since image information is affected by illumination, this paper presents the real-time object tracking method based on neural networks that have robust characteristics under various illuminations. This paper proposes three steps to track the object and the fast tracking method. In the first step the object color is extracted using neural networks. In the second step we detect the object feature information based on invariant moment. Finally the object is tracked through a shape recognition using neural networks. To achieve the fast tracking performance, we have a global search for entire image and then have tracking the object through local search when the object is recognized.

• 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.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2009년도 학술대회
• /
• pp.146-149
• /
• 2009

실시간 영상에서 사람의 얼굴 검출은 얼굴 인식분야에 있어서 주요한 관심 분야 중의 하나이다. 본 논문에서는 실시간 입력되는 영상에서 피부 색상과 Haar-like feature를 이용한 얼굴 검출 및 추적 알고리듬을 제안한다. 제안된 알고리듬은 컬러 색 공간에서 피부색상과 특징점을 가지고 얼굴 영역 및 추적하였다. 실험 결과 실시간 영상에 대해 조명 변화 및 가림 현상에서 강건한 추적 결과를 얻을 수 있었다.

• 정보학연구
• /
• 제10권4호
• /
• pp.27-39
• /
• 2007

Object tracking in a real time environment is one of challenging subjects in computer vision area during past couple of years. This paper proposes a method of object detection and tracking using adaptive background estimation in real time environment. To obtain a stable and adaptive background, we combine 3-frame differential method and running average single gaussian background model. Using this background model, we can successfully detect moving objects while minimizing false moving objects caused by noise. In the tracking phase, we propose a matching criteria where the weight of position and inner brightness distribution can be controlled by the size of objects. Also, we adopt a Kalman Filter to overcome the occlusion of tracked objects. By experiments, we can successfully detect and track objects in real time environment.