• 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.

• 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.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.311-315
• /
• 2009

The ubiquitous smart home is the home of future that takes advantage of context information from user and home environment and provides automatic home services for the user. User's location and motion are the most important contexts in the ubiquitous smart home. This paper presents a method positioning user's location using four cameras and some home context parameter together with user preferences provided. Some geometry math problems would be raised to figure out approximately which area is monitored by cameras. The moving object is detected within the image frames and then simulated in a 2D window to present visually where user is located and show his moving. The moving ways are statistically recorded and used for predicting user's future moving.

• 제어로봇시스템학회논문지
• /
• 제21권8호
• /
• pp.766-772
• /
• 2015

This paper proposes an object detection method based on motion estimation using background subtraction in the fisheye images obtained through omni-directional camera mounted on the vehicle. Recently, most of the vehicles installed with rear camera as a standard option, as well as various camera systems for safety. However, differently from the conventional object detection using the image obtained from the camera, the embedded system installed in the vehicle is difficult to apply a complicated algorithm because of its inherent low processing performance. In general, the embedded system needs system-dependent algorithm because it has lower processing performance than the computer. In this paper, the location of object is estimated from the information of object's motion obtained by applying a background subtraction method which compares the previous frames with the current ones. The real-time detection performance of the proposed method for object detection is verified experimentally on embedded board by comparing the proposed algorithm with the object detection based on LKOF (Lucas-Kanade optical flow).

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.138-143
• /
• 2002

This paper describes a framework for extending GIS databases to support moving object data type and query language. The rapid progress of wireless communications, positioning systems, and mobile computing devices have led location-aware applications to be essential components for commercial and industrial systems. Location-aware applications require GIS databases system to represent moving objects and to support querying on the motion properties of objects. For example, fleet management applications may require storage of information about moving vehicles. Also, advanced CRM(Customer Relationship Management) applications may require to store and query the trajectories of mobile phone users. In this trend, maintaining consistent information about the location of continuously moving objects and processing motion-specific queries is challenging problem. We formally define a data model and query language for mobile objects that includes complex evolving spatial structure, and propose core algebra to process the moving object query language. Main profit of proposed moving objects query language and algebra is that proposed model can be constructed on the top of GIS databases.

• 한국항행학회논문지
• /
• 제2권2호
• /
• pp.107-115
• /
• 1998

본 논문에서는 물체가 서로 겹쳤다가 분리되는 상황하에서도 이동물체를 견고히 추적할 수 있는 모션에너지와 예측에 기반한 이동물체 추적 방법을 제안한다. 이동물체 추적은 이동물체의 추적 단계와 추적된 이동물체의 추적 단계로 나뉘는데 이동물체 추적을 위해서는 개선된 모션에너지 방법을 사용하였다. 이동물체 추적을 위해서는 이동물체 중심점의 이동위치를 거리와 방향정보를 이용, 예측함으로써 탐색공간을 줄여 실시간 추적이 가능하도록 하였다. 실험실에서 만든 모사 영상열과 실세계 영상열에 적용한 결과 겹침(occlusion)과 나타남(disocclusion)이 발생하는 경우에도 추적이 잘 이루어짐을 볼 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제15권3호
• /
• pp.336-344
• /
• 2012

객체 인식(recognition)과 추적(tracking)은 컴퓨터 비전의 중요 분야로써 작게는 동작 인식으로부터 크게는 우주 항공까지 그 활용 가능성이 무궁무진하다. 객체 인식의 정확도를 향상시키는 방법 중 하나는 회전, 스케일 그리고 가려짐에 강건한 컬러를 이용하는 것이다. 컬러를 이용함으로써 더 많은 특징점들을 추출하기 위한 계산 비용을 감소시킬 수 있다. 또한, 빠른 객체 인식을 위해 알고리즘의 정확도를 낮추는 것보다 객체의 위치를 예측하고 좀 더 작은 영역에서 인식을 수행하는 것이 더욱 효과적이다. 본 논문은, 인식 정확도를 향상시키기 위해 대표적인 객체 인식 알고리즘인 SURF와 컬러모델을 적용한 기술자(descriptor)를 사용하고, 움직임 예측 알고리즘인 Kalman filter를 결합하여 빠른 객체 추적 방법을 제안한다. 그 결과, 제안하는 방법은 다른 컬러를 갖는 같은 패턴의 객체들을 구분하고, 객체의 향후 움직임을 미리 예측한 관심영역(ROI)에서 인식을 수행함으로써 빠른 추적 결과를 보였다.

• 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.

• 전자공학회논문지B
• /
• 제32B권11호
• /
• pp.1405-1416
• /
• 1995

An effective algorithm for implementation of unmanned surveillance system which detects moving object from image sequences, predicts the direction of it, and drives the camera in real time is proposed. Outputs of proposed algorithm are coordinates of location of moving object, and they are converted to the values according to camera model. As a pre- processing, extraction of moving object and shape discrimination are performed. Existence of the moving object or scene change is detected by computing the temporal derivatives of consecutive two or more images in a sequence, and this result of derivatives is combined with the edge map from one original gray level image to obtain the position of moving object. Shape discri-mination(Target identification) is performed by analysis of distribution of projection profiles in x and y directions. To reduce the prediction error due to the fact that the motion cha- racteristic of walking man may have an abrupt change of moving direction, an order adaptive lattice structured linear predictor is proposed.

• Transactions on Control, Automation and Systems Engineering
• /
• 제4권1호
• /
• pp.92-99
• /
• 2002

To obtain visual information of a target object, a camera should be placed within the visibility region. As the visibility region is dependent on the relative position of the target object and the surrounding object, the position change of the surrounding object during a task requires recalculation of the visibility region. For a fast computation of the visibility region so as to modify the camera position to be located within the visibility region, we propose a spherical projection method. After being projected onto the sphere the visibility region is represented in $\theta$-$\psi$ spaces of the spherical coordinates. The reduction of calculation space enables a fast modification of the camera location according to the motion of the surrounding objects so that the continuous observation of the target object during the task is possible.