• 방송공학회논문지
• /
• 제25권2호
• /
• pp.192-199
• /
• 2020

최근 딥러닝 모델을 기반으로 한 객체 추적 알고리즘의 활용도가 증가하고 있다. 영상에서의 다중 객체의 추적을 위한 시스템은 대표적으로 객체 검출 알고리즘과 객체 추적 알고리즘의 연쇄된 형태로 구성되어있다. 하지만 여러 모듈로 구성된 연쇄 형태의 시스템은 고성능 컴퓨팅 환경을 요구하며 실제 어플리케이션으로의 적용에 제한사항으로 존재한다. 본 논문에서는 위와 같은 객체 검출-추적의 연쇄 형태의 시스템에서 객체 검출 모듈의 연산 관련 프로세스를 조정하여 저성능 컴퓨팅 환경에서도 실시간 동작을 가능하게 하는 방법을 제안한다.

• 반도체디스플레이기술학회지
• /
• 제16권3호
• /
• pp.78-81
• /
• 2017

Augmented Reality(AR) is the core technology of the future knowledge service industry. It is expected to be used in various fields such as medical, education, entertainment etc. Briefly, augmented reality technology is a technique in which a mapped virtual object is augmented when a real-world object is viewed through a device after mapping a real-world object and a virtual object. In this paper, we implemented object detection and tracking system, which is a key technology of augmented reality. To speed up the object tracking, the ORB algorithm, which is a lightweight algorithm compared to the detection algorithm, is applied. In addition, KNN classifier, which is a machine learning algorithm, was applied to detect a single object by learning multiple images.

• 대한임베디드공학회논문지
• /
• 제9권1호
• /
• pp.53-59
• /
• 2014

In multiple object tracking, accurate detection for each of objects that appear sequentially and effective tracking in complicated cases that they are overlapped with each other are very important. In this paper, we propose a multiple object tracking system that has a concrete detection and tracking characteristics by using multi-lateral histogram and SIFT feature extraction algorithm. Especially, by limiting the matching area to object's inside and by utilizing the location informations in the keypoint matching process of SIFT algorithm, we advanced the tracking performance for multiple objects. Based on the experimental results, we found that the proposed tracking system has a robust tracking operation in the complicated environments that multiple objects are frequently overlapped in various of directions.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.597-600
• /
• 1999

In this paper, we propose a fast object-tracking algorithm in a moving picture. The proposed object-tracking algorithm is based on a projection scheme. More specifically, to alleviate the computational complexities of the previous motion estimation methods, we propose to use the projected row and column 1-D image data to extract the motion information. Experimental results show that the proposed method can detect the motion of an object fairly well with reduced computational time.

• 디지털융복합연구
• /
• 제12권8호
• /
• pp.337-343
• /
• 2014

본 논문은 감지와 통신 데이터 전송량의 관점에서 서베일런스 네트워크에서 움직이는 객체를 추적하기 위하여 전송 데이터를 감소시키는 최소 윤곽선 추적 알고리즘을 제안한다. 이 알고리즘은 객체 추적에 대한 감지를 수행하고 서버와의 영상 데이터 전송 시 영상 데이터 전송량을 줄임으로써 서버와의 통신 부하를 최소화한다. 이 알고리즘은 객체의 운동학을 기초로 최소 추적 영역을 사용한다. 객체의 운동학의 모델링은 예정된 시간 안에서 이동할 수 있는 객체에 의해 운동 역학적으로 방문될 수 없는 추적 영역의 부분을 제거하는 것으로써 시작한다. 실시간으로 객체를 검출하는 응용 분야에서 대량의 영상 데이터를 전송시에 전송 부하를 줄일 수 있는 효과가 있다.

• 융합신호처리학회논문지
• /
• 제15권4호
• /
• pp.112-118
• /
• 2014

본 연구는 칼라기반에서 단일 이동객체 추적을 다루고 있다. 우선 매 영상에서 이동객체 영상의 밝기 변화에 따른 추적 약점을 개선하기 위해 기존의 Camshift 알고리즘을 보완하였다. 보완된 알고리즘도 추적중인 물체와 색상이 같은 주변 물체가 존재할 경우 불안정한 추적을 보여주었는데 본 연구에서는 이를 해결하기 위해 Optical Flow기반의 KLT 알고리즘과 병합하는 방법을 제시하였다. 픽셀기반의 특징점 추적을 수행하는 KLT 알고리즘은 칼라기반의 Camshift의 단점을 보완할 수 있다. 실험 결과 제안된 병합 방법은 기존의 추적단점을 보완하였으며 추적성능이 개선됨을 실험으로 확인하였다.

• 제어로봇시스템학회논문지
• /
• 제4권2호
• /
• pp.187-193
• /
• 1998

This paper proposes an advanced visual tracking algorithm for the stable grasping of a moving target(2D). This algorithm is programmed to find grasping points of an unknown polygonal object and execute visual tracking. The Kalman Filter(KF) algorithm based on the SVD(Singular Value Decomposition) is applied to the visual tracking system for the tracking of a moving object. The KF based on the SVD improves the accuracy of the tracking and the robustness in the estimation of state variables and noise statistics. In addition, it does not have the numerical unstability problem that can occur in the visual tracking system based on Kalman filter. In the grasping system, a parameterized family is constructcd, and through the family, the grasping system finds the stable grasping points of an unknown object through the geometric properties of the parameterized family. In the previous studies, many researchers have been studied on only 'How to track a moving target'. This paper concern not only on 'how to track' but also 'how to grasp' and apply the grasping theory to a visual tracking system.

• 한국멀티미디어학회논문지
• /
• 제25권1호
• /
• pp.72-81
• /
• 2022

Visual Object Tracking is known as the most fundamental problem in the field of computer vision. Object tracking localize the region of target object with bounding box in the video. In this paper, a custom CNN is created to extract object feature that has strong and various information. This network was constructed as a Siamese network for use as a feature extractor. The input images are passed convolution block composed of a bottleneck layers, and features are emphasized. The feature map of the target object and the search area, extracted from the Siamese network, was input as a local proposal network. Estimate the object area using the feature map. The performance of the tracking algorithm was evaluated using the OTB2013 dataset. Success Plot and Precision Plot were used as evaluation matrix. As a result of the experiment, 0.611 in Success Plot and 0.831 in Precision Plot were achieved.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 춘계학술대회논문집B
• /
• pp.307-312
• /
• 2001

In this paper, we proposed the object-tracking algorithm that recognizes and estimates the any shaped and size objects using vision system. For the extraction of the object from the background of the acquired images, spatio-temporal filter and signature parsing algorithm are used. Specially, for the solution of correspondence problem of the multiple objects tracking, we compute snake energy and position information of the target objects. Through the real-time tracking experiment, we verified the effectiveness of the suggested tracking algorithm.

• 전기학회논문지P
• /
• 제67권4호
• /
• pp.227-232
• /
• 2018

In this paper, we propose a faster object detection and tracking method using Deep Learning, UAV(unmanned aerial vehicle), Kalman filter and YOLO(You Only Look Once)v3 algorithms. The performance of the object tracking system is decided by the performance and the accuracy of object detecting and tracking algorithms. So we applied to the YOLOv3 algorithm which is the best detection algorithm now at our proposed detecting system and also used the Kalman Filter algorithm that uses a variable detection area as the tracking system. In the experiment result, we could find the proposed system is an excellent result more than a fixed area detection system.