• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2016년도 춘계학술대회
• /
• pp.101-103
• /
• 2016

최근 들어, 영상 추적(Visual Tracking)에서의 목표물을 sparse coefficient vector로 나타낼 수 있게 되면서, L1 minimization 방법을 이용한 영상처리 속도 향상이 필요하게 되었다. 더 나아가서, L1 minimization 방법은 영상 추적 과정에서 주로 발생하는 occlusion 문제를 해결하는 방법으로 많이 사용되고 있다. 다라서 본 논문에서는 영상 추적 과정에서 발생하는 occlusion 문제의 해결을 위해서 L1 minimization의 parameter를 분석하였다. L1 minimization에는 최소화 결과에 영향을 미치는 weighted parameter가 존재하며, 이들은 고정 상수나 목표물의 중간값, 평균값, 표준편차로 나타내어 진다. 실험 결과를 바탕으로 분석하였을 때, weighted parameter 중에서 평균값이 OPE(One Pass Evaluation)을 기반으로 한 success rate와 precision performance에서 좋은 결과를 갖는 것을 확인할 수 있었다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2013년도 추계학술대회
• /
• pp.1015-1017
• /
• 2013

물체의 움직임에 관한 추적방법은 여러 가지 문제점을 갖고 있다. 물체의 움직임에 관한 추적방법은 물제의 장면, 비 강체 물체의 구조, 물체와 물체 및 물체의 장면 폐색 및 카메라의 움직임과 모두 움직이는 물체의 패턴변화에 의해 결정되기 때문이다. 추적방법은 일반적으로 매 프레임의 위치나 물체의 형상을 필요로 하는 높은 수준의 응용프로그램이나 시스템 내에서 처리된다. 본 논문에서는 확장 칼만 필터(EKF)에 따라 물체의 활성 시각 추적 물체 잠금 시스템을 실행하고, 실행된 데이터를 바탕으로 분석하여 도입된 단일 카메라 추적 시스템 알고리즘에 2대의 카메라와 각각의 비전에 따라 물체 추적 시스템을 설명하고, 물체의 상태를 파악하여 각 카메라에서 움직임에 관한 추적이 실행된 후 개별 트랙에 최종 시스템 물체의 움직임 트랙과 결합하여 사용되는 추적시스템에 대해 연구하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.408-410
• /
• 2009

We present an efficient and robust measurement model for visual tracking. This approach builds on and extends work on subspace representations of measurement model. Subspace-based tracking algorithms have been introduced to visual tracking literature for a decade and show considerable tracking performance due to its robustness in matching. However the measures used in their measurement models are often restricted to few approaches. We propose a novel measure of object matching using Angle In Feature Space, which aims to improve the discriminability of matching in subspace. Therefore, our tracking algorithm can distinguish target from similar background clutters which often cause erroneous drift by conventional Distance From Feature Space measure. Experiments demonstrate the effectiveness of the proposed tracking algorithm under severe cluttered background.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.100.1-100
• /
• 2001

With the prolific growth of cable, satellite digital broadcasting and internet related industry, new digital contents are being demanded. Today, more end-users seek participations in the media through interactivity. Visual tracking technology, based on image processing, is mainly used in fields of human face tracking, security inspection, and traffic monitoring applications. In this research, we describe the interactive modules such as information display, e1-commerce and other services along with on-screen visuals on the streaming media using object visual tracking technology. The ...

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권3호
• /
• pp.1121-1141
• /
• 2020

We propose a robust visual object tracking algorithm fusing a convolutional neural network tracker trained offline from a large number of video repositories and a color histogram based tracker to track objects for mixing immersive audio. Our algorithm addresses the problem of occlusion and large movements of the CNN based GOTURN generic object tracker. The key idea is the offline training of a binary classifier with the color histogram similarity values estimated via both trackers used in this method to opt appropriate tracker for target tracking and update both trackers with the predicted bounding box position of the target to continue tracking. Furthermore, a histogram similarity constraint is applied before updating the trackers to maximize the tracking accuracy. Finally, we compute the depth(z) of the target object by one of the prominent unsupervised monocular depth estimation algorithms to ensure the necessary 3D position of the tracked object to mix the immersive audio into that object. Our proposed algorithm demonstrates about 2% improved accuracy over the outperforming GOTURN algorithm in the existing VOT2014 tracking benchmark. Additionally, our tracker also works well to track multiple objects utilizing the concept of single object tracker but no demonstrations on any MOT benchmark.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.798-802
• /
• 2003

The robustness and reliability of vision algorithms is the key issue in robotic research and industrial applications. In this paper, the robust real time visual tracking in complex scene is considered. A common approach to increase robustness of a tracking system is to use different models (CAD model etc.) known a priori. Also fusion of multiple features facilitates robust detection and tracking of objects in scenes of realistic complexity. Because voting is a very simple or no model is needed for fusion, voting-based fusion of cues is applied. The approach for this algorithm is tested in a 3D Cartesian robot which tracks a toy vehicle moving along 3D rail, and the Kalman filter is used to estimate the motion parameters, namely the system state vector of moving object with unknown dynamics. Experimental results show that fusion of cues and motion estimation in a tracking system has a robust performance.

• 대한임베디드공학회논문지
• /
• 제11권4호
• /
• pp.219-225
• /
• 2016

Visual object tracking is one of the key tasks in computer vision. Robust trackers should address challenging issues such as fast motion, deformation, occlusion and so on. In this paper, we therefore propose a visual object tracking method that exploits inter-frame correlations of convolutional feature maps in Convolutional Neural Net (ConvNet). The proposed method predicts the location of a target by considering inter-frame spatial correlation between target location proposals in the present frame and its location in the previous frame. The experimental results show that the proposed algorithm outperforms the state-of-the-art work especially in hard-to-track sequences.

• 한국지능시스템학회논문지
• /
• 제14권5호
• /
• pp.539-544
• /
• 2004

본 논문에서는 CONDENSATION 알고리즘을 이용하여 입자 필터(particle filter)에 기반 한 물체 추적 알고리즘을 제안한다. 입자 필터는 조건 확률 전파 모델(Conditional Density Propagation)인 베이지안(Bayesian) 추론 규칙을 적용하는 추적구조를 갖고 있기 때문에 다른 어떤 종류의 추적 알고리즘보다 뛰어난 성능을 보인다. 논문에서는 실험 결과를 통해, 외곽(contour) 추적 입자 필터가 복잡한 환경 속에서 강인한 추적 성능을 나타냄을 증명한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 Proceedings of the Korea Automatic Control Conference, 11th (KACC); Pohang, Korea; 24-26 Oct. 1996
• /
• pp.145-148
• /
• 1996

In moving object tracking based on the visual sensory feedback, a prerequisite is to determine which feature or which object is to be tracked and then the feature or the object identification precedes the tracking. In this paper, we focus on the object identification not image feature identification. The target identification is realized by finding out corresponding line segments to the hypothesized model segments of the target. The key idea is the combination of the Mahalanobis distance with the geometrica relationship between model segments and extracted line segments. We demonstrate the robustness and feasibility of the proposed target identification algorithm by a moving vehicle identification and tracking in the video traffic surveillance system over images of a road scene.

• 제어로봇시스템학회논문지
• /
• 제15권7호
• /
• pp.694-699
• /
• 2009

This paper presents the implementation of the real-time object tracking control of the ROBOKER head. The visual servoing technique is used to track the moving object, but suffers from ill-estimated Jacobian of the virtual link design. To improve the tracking performance, the RBF(Radial Basis Function) network is used to compensate for uncertainties in the kinematics of the robot head in on-line fashion. The reference compensation technique is employed as a neural network control scheme. Performances of three schemes, the kinematic based scheme, the Jacobian based scheme, and the neural network compensation scheme are verified by experimental studies. The neural compensation scheme performs best.