추적레이다의 표적 탐지 및 추적 기술 동향

신한섭(Han-Seop Shin),최지환(Jee-Hwan Choi),김대오(Dae-Oh Kim),김태형(Tae-Hyung Kim) 한국항공우주연구원 2009 항공우주산업기술동향 Vol.7 No.1

추적레이다는 안테나로부터 폭이 매우 좁은 펄스를 표적에 위치시켜 표적에서 돌아오는 신호를 수신하여 표적의 위치 (거리, 각도, 속도 등)를 추적하는 장비이다. 추적레이다가 특정한 표적을 탐지하고 추적하기에 앞서 표적과 주변 환경의 특성을 예측하기 위해 잡음 신호와 표적 신호의 수학적 모델이 필요하다. 본 논문에서는 일반적으로 적용되는 잡음 신호와 표적 신호의 모텔에 대한 이론적인 내용을 소개하였고, 이와 더불어 표적의 탐지와 추적을 위한 거리 추적, 각도 추적 및 도플러 주파수 추적에 대한 일반적인 기법들을 기술하였다. In this paper, we described the model of noise, target for tracking radar and range tracking, angle tracking, and Doppler frequency tracking for target acquisition and tracking. Target signal as well as the noise signal is modeled as random process varying with elapsed time. This paper addresses three areas of radar target tracking: range tracking, angle tracking, and Doppler frequency tracking. In general, range tracking is prerequisite to and inherent in both angle and Doppler frequency tracking systems. First, we introduced the several range tracking and described techniques for achieving range tracking. Second, we described the radar angle tracking techniques including conical scan, sequential lobing, and monopulse. Finally, we presented concepts and techniques for Doppler frequency tracking for several radar types.

크기 변화에 적응적인 비정형 객체 추적을 위한 연구

변정현(Byun, Jung-Hyun),채승호(Chae, Seung-Ho),최희승(Choi, Hee-seung),한탁돈(Han, Tak-Don) 한국HCI학회 2016 한국HCI학회 학술대회 Vol.2016 No.1

컴퓨터 비전 연구에서 객체 추적은 활발히 연구되는 주제 중 하나이다. 기존의 객체 추적 연구는 이미지 매칭 기반으로 대상을 추적하는 방식이 많이 이용하기 때문에 주로 정형 객체 추적(rigid tracking) 에 집중한다. 이와 달리 tracking-by-detection 방법은 추적 문제를 분류기를 이용한 검출 문제처럼 다루기 때문에 비정형 객체 추적(non-rigid tracking)을 수행하는데 효과적이다. 본 논문에서는 이러한 tracking-by-detection 방법 중 하나로 structured output Support Vector Machine(SVM) 을 활용하는 Struck [1]의 분석하고 보완하는 연구를 진행하였다. Struck 은 일반적인 상황에서는 우수한 추적 성능을 보여주지만 크기 변화에 대응할 수 없고, 가림 현상이 일어나 추적 대상이 화면에 보이지 않을 때도 무조건 학습을 진행한다. 따라서 background clutter 와 잘못된 학습으로 인해 추적과 학습에 drift 가 일어날 수 있다. 본 연구에서는 이러한 Struck 의 단점을 보완하기 위해 추적 대상의 크기에 맞춰 추적 상자의 크기를 조절해 background clutter 를 방지하고 크기변화에 대응하는 scale-adaptive tracking 방법을 제안한다. 후속 연구로는 SVM 의 평가 함수 점수의 임계값을 이용하는 F score with threshold 방법을 이용하여 대상이 가려졌는지 여부를 확인해 잘못된 학습을 방지할 수 있다는 것을 보여준다. 또한 이러한 비정형 객체 추적을 활용할 수 있는 응용분야를 제시하고자 한다. Object tracking is one of many popular topics in computer vision literature. Previous object tracking studies mainly utilized image-matching based tracking method so that they focus on rigid tracking. Tracking-by-detection on the other hand treats a tracking problem as a detection problem using a classifier making it more suitable for non-rigid tracking. In this paper, we conducted the study analyzing and complementing Struck [1], a tracking-by-detection method that utilizes the structured output SVM. Struck shows good tracking performance in normal occasions; however, it can suffer drift from background clutter since it cannot cope with scale change and from occlusion since it forces learning even though there is no object presence in the scene. In this paper, to solve these issues for Struck, we propose “scale-adaptive tracking” method that automatically adjusts the size of the bounding box according to that of the object. As a future work, we propose “F score with threshold” method that can detect occlusion and prevents SVM from false-positive learning. Also, we propose various applications for non-rigid tracking.

Hand Tracking을 이용한 가상현실 전시관과 상호작용 콘텐츠 제작

신승훈(Shin, Seunghun),임수연(Lim, Sooyeon) 한국전시산업융합연구원 2021 한국과학예술융합학회 Vol.39 No.5

핸드트래킹은 마이런크루거의 미디어 파사드 형식으로 영상을 기초한 인공현실 개념을 적용한 비디오 플레이스와 제런레니어의 3D 그래픽을 적용한 가상현실 개념의 데이터 글러브와 HMD를 통해 사용자에게 널리 알려지게 되었다. 키넥트, 립모션 등 카메라와 심도 검출이 가능한 장비를 통해 더욱더 정교한 손동작을 컴퓨터 가상환경에 적용할 수 있게 되었고, 현재 오큘러스 퀘스트 등 가상현실 기구에 적용되면서 사용자와 가상현실을 직관적으로 연결하기 위한 인터페이스로 사용되고 있다. 가상현실 사용환경 발전으로 전시환경을 위한 다양한 시도가 이루어졌지만, 아티스트 기술한계와 사용자 진입장벽, 기구의 성능과 콘텐츠 다양성 등 다양한 문제로 가상현실은 예술 소재 활용에 한계가 있었다. 본 논문은 이런 콘텐츠 다양성 한계를 극복하기 위해 시작되었다. 본 연구의 목적은 가상현실을 사용자가 더쉽게 이해하고 경험할 수 있는 실제 전시관인 ‘대구미술관 어미홀’을 핸드트래킹을 이용한 가상현실 전시관과 작품을 제작하고 평가하는 것이다. 따라서 본 논문은 핸드트래킹 활용의 정당성을 확인하기 위해 가상현실 기술을 살펴보고 가상현실 사용환경과 인터페이스가 어떻게 발전하는지 확인하는 것이다. 콘텐츠 환경 중 핸드트래킹을 활용한 콘텐츠 보급상황을 확인하였다. 연구결과 및 내용은 다음과 같다. 첫째, 가상현실은 3D그래픽 환경과 핸드트래킹을 활용한 환경으로 발전하고 있음을 확인하였다. 둘째, 핸드트래킹을 활용한 전시환경과 콘텐츠는 부족하다. 셋째, 제작 콘텐츠 평가결과 핸드트래킹을 이용한 가상현실 전시관과 콘텐츠는 평가자에게 입체감과 현장감, 입체음 경험을 제공하였다. 넷째, 평가자는 핸드트래킹을 통해 직관적으로 콘텐츠와 상호작용하고 전시 관람을 할 수 있고 작품을 이해하였다. 이러한 연구를 바탕으로 핸드트래킹을 이용한 전시콘텐츠와 환경이 사용자에게 더욱 보급되고 더 나가 여러 사용자가 동시에 사용할 수 있는 핸드트래킹을 활용한 다중접속 전시 플랫폼 연구가 필요하다. Hand tracking has become widely known to users through video places applying the concept of artificial reality based on images in the form of Myron Krueger’s media facade and data gloves and HMD of virtual reality concepts applying Jaron Lanier’s 3D graphics. Through equipment capable of depth sensing with cameras such as Kinect and LipMotion, more sophisticated Hand Tracking can be applied to computer virtual environments, and are currently applied to virtual reality devices such as OculusQuest and is used as an interface to intuitively connect users and virtual reality. Various attempts have been made for the exhibition environment due to the development of the virtual reality use environment, but virtual reality has limitations in using art materials due to various problems such as artist technology limitations, user entry barriers, and device performance and content diversity. This paper was initiated to overcome these limitations of content diversity. The purpose of this study is to produce and evaluate virtual reality exhibition halls and works using hand tracking at the Daegu Museum of Art’s Mother Hall, an actual exhibition hall where users can understand and experience virtual reality more easily. Therefore, this paper examines virtual reality technology to confirm the legitimacy of the use of Hand Tracking and confirms how the virtual reality use environment and interface develop. The content distribution status using hand tracking among the content environments was confirmed. The research results and contents are as follows. First, it was confirmed that virtual reality is developing into a 3D graphic environment and an environment using hand tracking. Second, the exhibition environment and content using hand tracking are insufficient. Third, as a result of the production content evaluation, the virtual reality exhibition hall and content using hand tracking provided the evaluator with a three-dimensional feeling, realism, and three-dimensional sound experience. Fourth, evaluators can intuitively interact with content and watch exhibitions through hand tracking and understand works. Based on these studies, it is necessary to study a multi-access exhibition platform using hand tracking that can be used by multiple users at the same time as exhibition content and environment using hand tracking are further spread to users.

Electromagnetic Detection and Real-Time DMLC Adaptation to Target Rotation During Radiotherapy

Wu, Junqing,Ruan, Dan,Cho, Byungchul,Sawant, Amit,Petersen, Jay,Newell, Laurence J.,Cattell, Herbert,Keall, Paul J. Elsevier 2012 International journal of radiation oncology, biolo Vol.82 No.3

<P><B>Purpose</B></P> <P>Intrafraction rotation of more than 45° and 25° has been observed for lung and prostate tumors, respectively. Such rotation is not routinely adapted to during current radiotherapy, which may compromise tumor dose coverage. The aim of the study was to investigate the geometric and dosimetric performance of an electromagnetically guided real-time dynamic multileaf collimator (DMLC) tracking system to adapt to intrafractional tumor rotation.</P> <P><B>Materials/Methods</B></P> <P>Target rotation was provided by changing the treatment couch angle. The target rotation was measured by a research Calypso system integrated with a real-time DMLC tracking system employed on a Varian linac. The geometric beam-target rotational alignment difference was measured using electronic portal images. The dosimetric accuracy was quantified using a two-dimensional ion chamber array. For each beam, the following five delivery modes were tested: 1) nonrotated target (reference); 2) fixed rotated target with tracking; 3) fixed rotated target without tracking; 4) actively rotating target with tracking; and 5) actively rotating target without tracking. Dosimetric performance of the latter four modes was measured and compared to the reference dose distribution using a 3 mm/3% γ-test.</P> <P><B>Results</B></P> <P>Geometrically, the beam-target rotational alignment difference was 0.3° ± 0.6° for fixed rotation and 0.3° ± 1.3° for active rotation. Dosimetrically, the average failure rate for the γ-test for a fixed rotated target was 11% with tracking and 36% without tracking. The average failure rate for an actively rotating target was 9% with tracking and 35% without tracking.</P> <P><B>Conclusions</B></P> <P>For the first time, real-time target rotation has been accurately detected and adapted to during radiation delivery via DMLC tracking. The beam-target rotational alignment difference was mostly within 1°. Dose distributions to fixed and actively rotating targets with DMLC tracking were significantly superior to those without tracking.</P>

온라인 트래킹에 대한 소비자 인식과 정책적 시사점

이진명 ( Lee Jin Myong ),나종연 ( Rha Jong Youn ),김지혜 ( Kim Jihye ),박서니 ( Park Sunny ),이보한 ( Lee Bohan ),조은선 ( Cho Eunsun ) 한국소비자학회 2018 소비자학연구 Vol.29 No.2

본 연구의 목적은 온라인 트래킹에 대한 소비자들의 인식, 행태, 의견을 탐색하고 이를 바탕으로 온라인 트래킹으로부터 소비자를 보호할 수 있는 정책적 시사점을 도출하는 것이다. 일반 소비자 20명을 대상으로 표적집단면접을 실시하여 온라인 트래킹에 대한 반응을 정성적으로 탐색하고 설문지를 개발하였으며, 온라인 설문조사를 통해 수집된 총 645명의 응답 자료를 분석하여 그 결과를 양적으로 검증하였다. 본 연구의 주요 결과는 다음과 같다. 첫째, 소비자들은 다양한 맞춤형 광고나 서비스를 통해 온라인 트래킹을 경험하고 있었으나 온라인 트래킹의 목적, 방법 등 구체적 내용에 대해서는 피상적으로만 이해하고 있었다. 둘째, 소비자들은 정보유용성, 편의성, 유희성을 온라인 트래킹의 효용으로 인식하였으며, 프라이버시 위험, 통제권 제한, 불완전 기능을 비용으로 인식하였다. 대체적으로 효용보다 비용을 높게 지각하는 것으로 나타났다. 셋째, 온라인 트래킹에 대한 소비자의 태도와 수용의도는 낮은 편이었으며, 트래킹 차단 프로그램을 설치하거나 쿠키를 삭제하는 등 적극적인 방법으로 온라인 트래킹을 차단하려는 의향이 높은 것으로 나타났다. 넷째, 소비자들은 온라인 트래킹으로부터 소비자를 보호해야 할 책임이 사업자에게 가장 크다고 여겼으며, 정부, 소비자 개인, 소비자단체 및 학계, 언론 등 다양한 이해관계자들이 안전한 온라인 트래킹 환경 조성을 위하여 노력해야 한다고 인식하였다. 다섯째, 소비자들은 보다 강력한 온라인 트래킹 규제정책을 요구하고 있으나 동시에 이를 신경 쓰고 싶어 하지 않는 양가적 반응을 보였다. 이러한 결과는 정보주체인 소비자들의 무력감을 극복하고 선택권과 통제권을 강화할 수 있는 실효적 방안 모색이 요구됨을 시사한다. 또한 온라인 트래킹으로부터 소비자를 보호하기 위한 법과 정책이 소비자 권익을 보호하는 동시에 산업의 혁신을 저해하지 않는 적절한 조화점에 대한 고민이 요구된다. 본 연구는 안전하고 신뢰할 수 있는 온라인 트래킹 환경 마련을 위한 기초자료 및 논의의 단초를 제공했다는 점에서 학문적, 정책적 의의를 갖는다. Online tracking, which refers to practices that collect, store, and utilize behavioral information about consumers online, is essential to develop personalized and customized services. Rapid advances in tracking technology may provide considerable convenience and benefits to the consumer. However, consumers’ privacy concerns and actual security risks may have increased since it has become increasingly difficult to know how information about individuals is traded, aggregated, and utilized. Therefore, protecting consumer privacy is a subject that should be studied and discussed more deeply in the changing market environment. This study aims to analyze the perceptions and response to online tracking of Koreans, to draw up policy implications to protect consumers from online tracking, and to provide a basis for a cooperative dialogue between the government, corporations, and consumers so consumer privacy can be adequately protected. For this purpose, focus group interviews were conducted with 20 participants on June 2-3, 2017. Online surveys were also conducted to verify the validity and objectivity of the results of the qualitative research. A total of 645 completed responses were collected from June 30 to July 4, 2017. The major results and implications of this study are summarized as follows. First, consumers were not clearly aware of what information about themselves is being tracked and used by whom, where, and for what purpose. To develop and expand online tracking, consumer information must be utilized. Therefore, it is required to improve the perception and understanding of consumers about the concept, mechanism, and influence of online tracking. Second, consumers are emotionally and behaviorally negative about online tracking and intend to actively block online tracking by using ad-block software or by deleting cookies. This result suggests that it is necessary to reduce the perceived risk and anxiety of consumers about online tracking through efforts such as protecting consumer privacy and ensuring the right to control their personal information. Third, consumers regarded the right of choice and control as the basic principle of personal information in online tracking and as very important. However, they recognized that these rights were not really guaranteed and would be formal, even if guaranteed. Therefore, it is necessary to find an effective way to overcome consumers’ powerlessness about privacy protection and to strengthen their rights to control what and how information is used. In addition, considering the privacy paradox, it is necessary to discuss how to reflect consumers' preferences without demanding too much effort from them. Fourth, when setting up online tracking, consumers prefer to configure privacy preferences in the browser rather than going to individual sites, to opt-in rather than opt-out, legal and policy regulation rather than self-regulation, and pre-regulation rather than post-regulation. The policy for consumer protection from online tracking should not be too loose to infringe the interests of consumers, but it should not hinder the innovation of the industry by becoming a new entry barriers. Therefore, it is necessary to consider proper harmony between consumer protection and industrial innovation in preparing online tracking policy.

정보통신기기의 위치추적에 대한 헌법적 통제에 관한 소고

이상경 헌법재판연구원 2019 헌법재판연구 Vol.6 No.1

Recently, a so-called Location-Based Service (LBS) has been activated using geographical location information, which can lead to various constitutional problems as well as various beneficial services. In particular, there is a great deal of concern about infringement of fundamental rights in using such location information for investigation purposes. The conflicts occur between the basic rights, especially securing freedom of communication, privacy, protection of personal information, and the investigatory utilization of location information. Therefore, this paper discusses the key issues related to location tracking, which are currently in question, in the following three categories. First, this paper discusses the sorts of location information tracking methods, the second, tracking cell-site location information, and the third, tracking real time GPS location information. In addition to these discussions, this paper examines whether investigatory use of location information infringes search warrant, freedom of communication, and right to self -determination of personal information. Use of location information can be largely classified into tracking of cell-site location information and GPS location tracking. The cell-site location information tracking can be divided into two again. The first is a location tracking method through the use of mobile information and communication equipment, which is related to the request of the communication confirmation fact data in the recent constitutional case. The second is a form in which communication history and location information of all communication subscribers existing in a specific base station are collectively. The following is the tracking of GPS location information. The tracking of such GPS location information can be further divided into two. First, there is a way to continuously track by attaching a location tracking device. Second, there is a method of tracking real time GPS location information using a virtual cell-site location, namely, a cell-site simulator. Since tracking real time GPS location information is directly related to the privacy, freedom of communication, and right to self-determination of personal information, this papers suggests that search warrant issued by courts be strictly needed for investigatory use of real time GPS location information. 최근 개인의 위치정보(Location Information)를 활용하는 소위 “위치기반서비스(Location-Based Service)”가 활성화되었다. 이러한 위치정보의 활용은 다양한 편의를 제공함에도 불구하고 여러 가지 헌법적 문제를 발생시킨다. 특히 국가가 개인의 위치정보를 수사목적으로 활용하는 경우, 정보주체의 통신비밀, 사생활의 비밀 및 개인정보 등의 침해를 야기할 수 있다. 따라서 본 논문은 현재 문제 되고있는 위치추적과 관련된 핵심 쟁점을 다음 3가지로 구분하여 논의한다. 먼저 정보통신기기의 위치추적의 종류를 논의하고, 두 번째로 발신기지국 위치추적, 세 번째로 실시간 GPS위치정보 추적에 관해 순서대로 논의한다. 이러한 논의와 더불어 위치추적의 헌법적 통제문제로서 영장주의, 통신비밀의 보장 및 개인정보자기결정권 등 침해 여부에 관해 검토한다. 위치정보를 수사목적으로 활용하는 방법은 다양하다. 크게는 발신기지국 위치정보 추적과 실시간 GPS위치정보의 추적으로 구별할 수 있다. 발신기지국 위치정보 추적은 다시 2가지로 구별될 수 있다. 첫째는 이동정보통신기기의 사용을 통한 위치추적 방법으로 과거의 발신기지국 접속 정보를 통한 위치추적-우리의 경우 통신확인사실자료의 요청과 관련된 부분-이다. 둘째는 특정한 기지국 내에 존재하는 모든 통신 가입자들에 대한 통신내역과 위치정보를 일괄 제공받는 형태-소위. ‘기지국 수사’-의 위치정보 추적이다. 우리나라 헌법재판소와 미국의 연방법원의 판례를 통해 발신기지국 위치정보의 추적에 관한 헌법적 통제문제를 살펴본다. 다음은 실시간 GPS위치정보의 추적이다. GPS위치정보는 인공위성과 GPS장치 부착 단말기 사이를 신호가 이동하는 시간을 측정하여 단말기의 위치가 파악되는 것으로써, 기술적인 수단이나 추적범위, 추적의 용이성 등의 측면에서 ‘발신기지국 위치정보’와 구별된다. 실시간 GPS위치정보의 추적도 다시 2가지로 구별될 수 있다. 첫째는 GPS위치추적 장치를 부착하여 지속적으로 실시간 추적하는 방법이고, 둘째는 가상기지국을 이용한 실시간 GPS위치정보의 추적방법이다. 실시간 GPS위치정보의 활용은 명문의 근거 법률이 없다는 점에서 법률유보 위반 문제와 사생활의 비밀과 자유 등 침해문제를 야기하므로, 활용에 대한 법적 근거를 마련하되 법원의 영장주의를 요건으로 하는 등 엄격하게 인정되어야 한다. 이와 관련된 미국 연방법원의 판례를 고찰함으로써 우리에게 필요한 시사점을 얻고자 한다.

유전자 알고리즘을 이용한 트랙킹 진동량 추정 시스템

진경복,이문노 한국반도체디스플레이기술학회 2011 반도체디스플레이기술학회지 Vol.10 No.2

This paper presents a tracking vibration estimation system of the track-following system using a tracking loop gain adjustment algorithm and a genetic algorithm. The algorithms are introduced to estimate accurately the tracking vibration quantity in spite of the uncertainties of the tracking actuator. An estimated actuator model can be found by applying a genetic algorithm. Accordingly, the tracking vibration quantity can be estimated from the measured tracking error, the tracking controller and the estimated actuator model. The proposed tracking vibration estimation method is applied to the track-following system of an optical recording device and is evaluated through the experimental result.

Image Tracking Algorithm Improvement Based on TLD Frame

Lei Yu,Tao Zheng,Qiyun Shi 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.5

Image target tracking is an important part in computer vision field, and has a broad application prospect in modern society. Lack of online learning function, the traditional target tracking algorithm was based on the single track as long as possible. The target deformation and occlusion will lead to target tracking lost. TLD (tracking-learning-detection) is the long-term effective algorithm in tracking single target proposed. The algorithm requires less prior knowledge and can achieve long-term tracking, but when target encounter obstacles, there will be drift phenomenon in the short term. In order to overcome this shortcoming, the paper improve the tracking module of TLD. A method is proposed by using Harris feature point instead of the original Grid sampling method. The experimental results show that this method can effectively suppress the tracking drift, and improve tracking precision.

AMR를 이용한 가변적인 관심 대상 객체 추적을 위한 딥러닝 기반 프레임워크

곽정훈,양견모,구재완,서갑호 제어·로봇·시스템학회 2022 제어·로봇·시스템학회 논문지 Vol.28 No.12

AMR(Autonomous Mobile Robot) is being used to improve working environment through collaboration such as transporting goods between workers. For collaboration such as transporting goods, AMR tracks the workers and carries out goods transport. Object tracking is possible based on a deep learning model trained using big data, built as an object to be tracked. When the worker changes frequently, such as in a work environment, there is a problem in that big data construction and deep learning model learning are required whenever an object to be tracked is changed. There is a need for a method for tracking objects that change frequently while providing small amounts of data. This paper proposes a deep learning-based framework for tracking changeable object. An object to be tracked, such as a worker, is defined as a ToI (Target-of-Interest) object. The proposed framework utilizes a two-stage deep learning model to track a changeable ToI object. In the deep learning model of the first stage, an object of the same type as the ToI object is tracked. In the deep learning model of the second stage, the ToI object is found among the objects being tracked. The position of the ToI object is transformed into the coordinate system of the AMR so that the AMR can track the ToI object. In the experiment, the results of tracking the ToI object by using the proposed method were verified. When tracking ToI objects with a single-stage deep learning model with a small amount of data, the accuracy of tracking the ToI objects decreased according to the amount of data. In the case of the proposed method, the tracking of the ToI object was not affected by the amount of data. .

Real-time visual tracking by deep reinforced decision making

Choi, Janghoon,Kwon, Junseok,Lee, Kyoung Mu Elsevier 2018 Computer vision and image understanding Vol.171 No.-

<P><B>Abstract</B></P> <P>One of the major challenges of model-free visual tracking problem has been the difficulty originating from the unpredictable and drastic changes in the appearance of objects we target to track. Existing methods tackle this problem by updating the appearance model on-line in order to adapt to the changes in the appearance. Despite the success of these methods however, inaccurate and erroneous updates of the appearance model result in a tracker drift. In this paper, we introduce a novel real-time visual tracking algorithm based on a template selection strategy constructed by deep reinforcement learning methods. The tracking algorithm utilizes this strategy to choose the appropriate template for tracking a given frame. The template selection strategy is self-learned by utilizing a simple policy gradient method on numerous training episodes randomly generated from a tracking benchmark dataset. Our proposed reinforcement learning framework is generally applicable to other confidence map based tracking algorithms. The experiment shows that our tracking algorithm runs in real-time speed of 43 fps and the proposed policy network effectively decides the appropriate template for successful visual tracking.</P> <P><B>Highlights</B></P> <P> <UL> <LI> Using deep reinforced template update strategy is beneficial for visual tracking. </LI> <LI> Noteworthy performance gain over other naïve update strategies. </LI> <LI> Runs at real-time speed of 43 fps while maintaining a competitive performance compared to other real-time algorithms. </LI> </UL> </P>