CN105931263A - Target tracking method and electronic equipment - Google Patents

Target tracking method and electronic equipment Download PDF

Info

Publication number
CN105931263A
CN105931263A CN 201610201474 CN201610201474A CN105931263A CN 105931263 A CN105931263 A CN 105931263A CN 201610201474 CN201610201474 CN 201610201474 CN 201610201474 A CN201610201474 A CN 201610201474A CN 105931263 A CN105931263 A CN 105931263A
Authority
CN
Grant status
Application
Patent type
Prior art keywords
tracking
target
target point
template
point
Prior art date
Application number
CN 201610201474
Other languages
Chinese (zh)
Inventor
孙晓路
陈子冲
安宁
王野
蒲立
Original Assignee
纳恩博(北京)科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/20Analysis of motion
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/18Closed circuit television systems, i.e. systems in which the signal is not broadcast
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20092Interactive image processing based on input by user
    • G06T2207/20101Interactive definition of point of interest, landmark or seed

Abstract

The invention discloses a target tracking method, the method can be applied in electronic equipment, and the electronic equipment comprises a camera; the method comprises the steps: image data collected by the camera is sent to control equipment; position information of a target point transmitted by the control equipment is received, wherein the target point is a point chosen by a user in a frame when the control equipment outputs the frame of image data through a display screen, and the target point is any point on a tracking target; a tracking template corresponding to the tracking target is determined based on the position information of the target point; visual tracking is performed on the tracking target through a visual tracking algorithm based on the tracking template corresponding to the tracking target. According to the invention, in a online learning visual tracking algorithm in the prior art, a technical problem that a moving object cannot be visually tracked when a interaction mode of the tracking template is defined by a user appointed area can be solved. The invention also provides electronic equipment.

Description

一种目标跟踪方法及电子设备 Target tracking method and electronic equipment

技术领域 FIELD

[0001]本发明涉及视觉跟踪技术领域,尤其涉及一种目标跟踪方法及电子设备。 [0001] The present invention relates to a vision tracking technology, and more particularly, to a method and an electronic target tracking apparatus.

背景技术 Background technique

[0002] 视觉跟踪技术,是指对图像序列中的跟踪目标进行检测、提取、识别和跟踪,获得跟踪目标运动参数,如位置、速度、加速度和运动轨迹等,从而进行下一步的处理与分析,实现对跟踪目标的行为理解,以完成更高一级的检测任务。 [0002] visual tracking means for tracking a target sequence of images is detected, extraction, identification and tracking, to obtain the tracking target parameter, such as location, velocity, acceleration and the like trajectory so as to perform the next processing and analysis to achieve the goal of tracking the behavior of understanding to complete a higher level of detection tasks. 视觉跟踪技术主要目的是模仿生理视觉系统的运动感知功能,赋予机器辨识图像序列中物体运动及其相互关系的能力,为图像序列理解提供重要途径。 Visual tracking technology is mainly designed to mimic the physiological function of the visual system of motion sensing, giving the machine to identify the sequence of images of objects in motion and the ability to mutual relations, image sequence provides an important way to understand. 视觉跟踪技术具有广阔的应用前景,如视频监控、视频分析、视频检索、基于视频的运动分析和合成、基于运动信息的身份识别等。 Visual tracking technology has broad application prospects, such as video surveillance, video analysis, video search, video-based motion analysis and synthesis, and identity-based sports such information.

[0003]近几年,基于在线学习的视觉跟踪技术兴起,各种在线学习的视觉跟踪算法不断涌现,在没有任何离线学习的先验经验的情况下,根据在初始帧画面中定义的跟踪模板,训练模型用于后续视频中目标的跟踪,并在跟踪过程不断更新模型,以达到适应目标物体姿态变化,以及克服复杂背景干扰的目的。 [0003] In recent years, online learning based visual tracking the rise of technology, a variety of online learning is emerging visual tracking algorithm, without any prior knowledge of offline learning situation, according to tracking templates defined in the initial frame picture , subsequent video training model for tracking the target and continually updates the model in the tracking process, in order to achieve your target body attitude change, and overcome complex background purposes. 由于无需离线训练,使得在线学习的视觉跟踪技术具有很高的通用性,可以对用户指定的任何物体进行视觉跟踪。 Eliminating the need for off-line training, visual tracking technology makes online learning has high versatility, any object can be user-specified visual tracking.

[0004]现有的在线学习的视觉跟踪算法的交互模式,需要用户在视频画面中指定跟踪目标所在的区域(该区域通常为一个矩形区域,需要用户通过画框操作画出该区域),从而将该区域定义跟踪模板。 Interactive mode visual tracking algorithm [0004] Existing e-learning, the user needs to specify the tracking target area in the video picture is located (usually a rectangular region of the region, the region required by the user to draw frame operation), so that the area defined tracking template. 在线学习的视觉跟踪算法对跟踪模板的精度有较高的要求,过大的跟踪模板易包含较多的干扰背景,过小的跟踪模板不具有足够的区分度。 Online learning visual tracking algorithm has precision tracking template of higher demand, too much background interference tracking template contains more easily, too small tracking template does not have a sufficient degree of differentiation. 这种基于用户指定区域来定义跟踪模板的交互模式,要求在用户指定区域过程中,跟踪目标必须处于静止状态,以给用户足够的时间来准确指定该区域。 This is defined based on the user interaction mode specified area tracking template, requiring the user to specify the area of ​​the process, the target track must be at a standstill, to give the user sufficient time to accurately specify the region. 但是,若跟踪目标处于运动状态,用户则没有足够的时间来准确定义跟踪目标所在的区域,也就无法获得满足要求的跟踪模板,继而无法对运动中的跟踪目标进行视觉跟踪。 However, if the target is in motion tracking, users will not have enough time to accurately define the area where the target track, it can not meet the requirements to obtain the tracking template, which in turn can not track the movement of the visual target tracking.

[0005]综上,现有技术中的在线学习的视觉跟踪算法,由于采用用户指定区域来定义跟踪模板的交互模式,存在无法对运动中的物体进行视觉跟踪的技术问题。 [0005] In summary, the prior art online learning visual tracking algorithm, thanks to a user-specified area tracking templates to define the mode of interaction, there can not be an object in motion visual tracking of technical problems.

发明内容 SUMMARY

[0006]本发明实施例通过提供一种目标跟踪方法及电子设备,解决了现有技术中的在线学习的视觉跟踪算法,由于采用用户指定区域来定义跟踪模板的交互模式,存在无法对运动中的物体进行视觉跟踪的技术问题。 Example [0006] The present invention provides a method of tracking a target and an electronic device, the problem in the prior art visual online learning tracking algorithm, since the user specified area tracking template to define the interactive mode, the motion can not exist the objects visual tracking of technical problems.

[0007] —方面,本发明通过本发明的一实施例提供如下技术方案: [0007] - aspect, the present invention provides the following technical solution to an embodiment of the present invention:

[0008] —种目标跟踪方法,应用于电子设备中,所述电子设备具有一摄像头,所述目标跟踪方法包括: [0008] - the target species tracking method applied to an electronic device, the electronic device having a camera, the target tracking method comprising:

[0009]将所述摄像头采集到的图像数据发送给控制设备; [0009] The camera transmits the acquired image data to the control apparatus;

[0010]接收所述控制设备发来的目标点的位置信息,其中,所述目标点为在所述控制设备通过显示屏输出所述图像数据的画面时用户在所述画面上选中的点,所述目标点为跟踪目标上的任一点; [0010] The apparatus receives the control information sent by the location of the target point, wherein the target point is a point in the control device selected by the user on the screen of the output display screen in the image data, the target point is any point on the target track;

[0011 ]基于所述目标点的位置信息,确定所述跟踪目标对应的跟踪模板; [0011] location information based on the target point, to determine the tracking target track corresponding to the template;

[0012] 基于所述跟踪目标对应的跟踪模板,利用视觉跟踪算法对所述跟踪目标进行视觉跟踪。 [0012] corresponding to a target track based on the tracking template, the target tracking vision tracking with a visual tracking algorithm.

[0013]优选地,所述基于所述目标点的位置信息,确定所述跟踪目标对应的跟踪模板,包括: [0013] Preferably, the location-based information of the target point is determined corresponding to the tracking target tracking template, comprising:

[0014]基于所述目标点的位置信息,在所述画面中确定所述目标点; [0014] based on the location information of the target point, the target point is determined in the picture;

[0015]在所述目标点周围生成多个备选跟踪模板; [0015] Alternatively, a plurality of tracking template generated around the target point;

[0016]基于显著性算法,分别对所述多个备选跟踪模板进行分析,并从所述多个备选跟踪模板中选出一最佳备选跟踪模板,其中,所述最佳备选跟踪模板即为所述跟踪目标对应的跟踪模板。 [0016] Based on significant algorithm, each of the plurality of candidate templates to analyze the tracking, tracing and select a best option from the plurality of candidate template tracking template, wherein the optimal alternate tracking is the template corresponding to the tracking target tracking template.

[0017] 优选地,在所述基于所述跟踪模板,利用视觉跟踪算法对所述跟踪目标进行视觉跟踪过程中,还包括: [0017] Preferably, the template based on the tracking of the tracking target visual tracking process with a visual tracking algorithm, further comprising:

[0018]控制所述电子设备对准所述目标点前进,其中,所述电子设备为可移动电子设备。 [0018] The electronic control device at the target point proceeds, wherein the electronic device is a mobile electronic device.

[0019]优选地,所述控制所述电子设备对准所述目标点前进,包括: [0019] Preferably, the electronic device controls the aligned advancing the target point, comprising:

[0020] 基于等式Picth = arctan(dy/f),确定所述目标点与所述画面的中心在竖直方向上的竖直偏离角;其中,Picth为所述竖直偏离角,f为所述摄像头的焦距,dy为所述目标点到所述摄像头光轴的垂直偏移量; [0020] Based on the equation Picth = arctan (dy / f), determining the target point and the center of the screen vertical off-angle in the vertical direction; wherein, Picth is the vertical deviation angle, f is the focal length of the camera, dy is the target point of the camera optical axis to a vertical offset;

[0021 ]根据所述竖直偏离角,调整所述摄像头的俯仰角,以使所述目标点在竖直方向靠近所述画面的中心。 [0021] The vertical deviation angle, pitch angle adjustment of the camera according to the target point near the center of the screen in the vertical direction.

[0022]优选地,所述控制所述电子设备对准所述目标点前进,包括: [0022] Preferably, the electronic device controls the aligned advancing the target point, comprising:

[0023] 基于等式73¥ = 31"(^311((11/;0,确定所述目标点与所述画面的中心在水平方向上的水平偏移角;其中,yaw为所述水平偏移角,f为所述摄像头的焦距,dx为所述目标点到所述摄像头光轴的水平偏移量; [0023] Based on Equation 73 ¥ = 31 "(^ 311 ((11 /; 0, determining the target point and the center of the screen in the horizontal direction of the horizontal deviation angle; wherein, yaw biasing of the horizontal shift angle, f is the focal length of the camera, dx is the target point of the camera optical axis to the horizontal offset amount;

[0024]根据所述水平偏移角,确定所述电子设备的转动角速度; [0024] The offset angle to the horizontal, determining a rotation angular velocity of the electronic device;

[0025]基于所述转动角速度,控制所述电子设备转动,以使所述目标点在水平方向靠近所述画面的中心。 [0025] Based on the rotation angular velocity, the electronic control apparatus is rotated, so that the target point near the center of the screen in the horizontal direction.

[0026]优选地,所述控制所述电子设备对准所述目标点前进,包括: [0026] Preferably, the electronic device controls the aligned advancing the target point, comprising:

[0027]根据所述跟踪目标对应的跟踪模板在所述画面中的尺寸,确定所述电子设备的前进速度; [0027] The target tracking template size corresponding to the screen in the tracking, determining the forward speed of the electronic device;

[0028]基于所述前进速度,控制所述电子设备向所述跟踪目标前进。 [0028] proceeds to the target track based on the forward speed, the electronic control device.

[0029]另一方面,本发明通过本发明的一实施例,提供如下技术方案: [0029] another aspect, the present invention, by an embodiment of the invention, there is provided the following technical solutions:

[0030] —种电子设备,所述电子设备具有一摄像头,所述电子设备,还包括: [0030] - electronic device, said electronic device having a camera, the electronic apparatus further comprising:

[0031 ]发送单元,用于将所述摄像头采集到的图像数据发送给控制设备; [0031] The transmission unit for the camera to capture the image data to the control apparatus;

[0032]接收单元,用于接收所述控制设备发来的目标点的位置信息,其中,所述目标点为在所述控制设备通过显示屏输出所述图像数据的画面时用户在所述画面上选中的点,所述目标点为跟踪目标上的任一点; [0032] a receiving unit for receiving position information sent from the control device of the target point, wherein the target point when the display screen of the control device by outputting the image data of the user in the screen on the selected point, the target point is any point on the target track;

[0033]确定单元,用于基于所述目标点的位置信息,确定所述跟踪目标对应的跟踪模板; [0033] determination unit, a position information based on the target point, is determined corresponding to the tracking target tracking template;

[0034] 跟踪单元,用于基于所述跟踪目标对应的跟踪模板,利用视觉跟踪算法对所述跟踪目标进行视觉跟踪。 [0034] The tracking unit, corresponding to the target track based on the tracking template, the target tracking vision tracking with a visual tracking algorithm.

[0035]优选地,所述确定单元,包括: [0035] Preferably, the determining unit comprises:

[0036]第一确定模块,用于基于所述目标点的位置信息,在所述画面中确定所述目标点; [0036] The first determining module, based on the position information of the target point, the target point is determined in the picture;

[0037]生成模块,用于在所述目标点周围生成多个备选跟踪模板; [0037] The generating module, for generating a plurality of alternative tracking template around the target point;

[0038]分析模块,用于基于显著性算法,分别对所述多个备选跟踪模板进行分析,并从所述多个备选跟踪模板中选出一最佳备选跟踪模板,其中,所述最佳备选跟踪模板即为所述跟踪目标对应的跟踪模板。 [0038] The analysis module for significance based algorithm, each of the plurality of candidate templates to analyze the tracking, tracing and select a best option from the plurality of candidate template tracking template, wherein the said template tracking is the best option corresponding to the tracking target tracking template.

[0039] 优选地,所述电子设备,还包括: [0039] Preferably, the electronic apparatus further comprising:

[0040]控制单元,用于在所述基于所述跟踪模板,利用视觉跟踪算法对所述跟踪目标进行视觉跟踪过程中,控制所述电子设备对准所述目标点前进,其中,所述电子设备为可移动电子设备。 [0040] a control unit for the template based on the tracking of the tracking target visual tracking process with a visual tracking algorithm, the electronic control device at the target point proceeds, wherein said electronic device is a mobile electronic device.

[0041]优选地,所述控制单元,包括: [0041] Preferably, the control means comprising:

[0042]第二确定模块,用于基于等式Picth = arctan(dy/f),确定所述目标点与所述画面的中心在竖直方向上的竖直偏离角;其中,Picth为所述竖直偏离角,f为所述摄像头的焦距,dy为所述目标点到所述摄像头光轴的垂直偏移量; [0042] The second determining module, based on the equation Picth = arctan (dy / f), determining the target point and the center of the screen in the vertical direction of vertical deviation angle; wherein, Picth said the vertical deviation angle, f is the focal length of camera, dy of the target point to the camera optical axis is perpendicular to the offset;

[0043]调整模块,用于根据所述竖直偏离角,调整所述摄像头的俯仰角,以使所述目标点在竖直方向靠近所述画面的中心。 [0043] The adjustment means for the vertical deviation angle, pitch angle adjustment of the camera according to the target point near the center of the screen in the vertical direction.

[0044] 优选地,所述控制单元,包括: [0044] Preferably, the control means comprising:

[0045]第三确定模块,用于基于等式73¥ = 31"(^311((^/;0,确定所述目标点与所述画面的中心在水平方向上的水平偏移角;其中,yaw为所述水平偏移角,f为所述摄像头的焦距,dx为所述目标点到所述摄像头光轴的水平偏移量; [0045] The third determining module, based on the equation 73 ¥ = 31 "(^ 311 ((^ /; 0, determining the target point and the center of the screen in the horizontal direction of the horizontal offset angle; wherein , yaw angle to the horizontal offset, f is the focal length of the camera, dx is the target point of the camera optical axis to the horizontal offset amount;

[0046]第四确定模块,用于根据所述水平偏移角,确定所述电子设备的转动角速度; [0046] Fourth determination module, according to the horizontal deviation angle, determining a rotation angular velocity of the electronic device;

[0047]第一控制模块,用于基于所述转动角速度,控制所述电子设备转动,以使所述目标点在水平方向靠近所述画面的中心。 [0047] a first control module for based on the center of the rotation angular velocity, the electronic control apparatus is rotated, so that the target point is close to the screen in the horizontal direction.

[0048] 优选地,所述控制单元,包括: [0048] Preferably, the control means comprising:

[0049]第五确定模块,用于根据所述跟踪目标对应的跟踪模板在所述画面中的尺寸,确定所述电子设备的前进速度; [0049] The fifth determining means for tracking according to the tracking target template in a size corresponding to the screen, determining the forward speed of the electronic device;

[0050]第二控制模块,用于基于所述前进速度,控制所述电子设备向所述跟踪目标前进。 [0050] The second control module based on the advancing speed, the electronic control apparatus proceeds to the tracked object.

[0051]本发明实施例中提供的一个或多个技术方案,至少具有如下技术效果或优点: [0051] One or more of the technical solutions provided in the embodiments of the present invention, at least the following technical effects or advantages:

[0052] 1、在本实施例中,将用户通过点击操作来定义跟踪模板的这种交互模式与在线学习的视觉跟踪算法相融合,仅需要用户点击跟踪目标上的一个目标点,即可获得跟踪目标对应的跟踪模板,从而利用在线学习的视觉跟踪算法对所述跟踪目标进行视觉跟踪。 [0052] 1, in the present embodiment, the user visually tracking algorithm to define this interaction model with the online learning tracking template is fused by a click operation, the user need only click-tracking a target point on the target, can be obtained tracking corresponding target tracking templates, so the visual target tracking visual tracking algorithm to track the use of online learning. 由于无需耗费过多时间,用户瞬间即可完成该点击操作,从而完成对跟踪模板的定义,具有操作方便、快捷的优点。 Because without consuming too much time, the user can instantly click to complete the operation to complete the definition of tracking templates, easy to operate, fast advantages. 所以有效地解决了现有技术中的在线学习的视觉跟踪算法,由于采用用户指定区域来定义跟踪模板的交互模式,耗时较长,存在无法对运动中的物体进行视觉跟踪的技术问题。 So effectively solves the prior art online learning visual tracking algorithm, thanks to a user-specified area tracking templates to define the mode of interaction, time-consuming, can not exist on the movement of objects in visual tracking of technical problems. 实现了将用户通过点击操作来定义跟踪模板的这种交互模式与在线学习的视觉跟踪算法相融合,来对运动中的物体进行视觉跟踪的技术效果。 Implements the user to define a tracking template by clicking visual tracking algorithm operating this interaction model and the integration of online learning to visually track moving objects in technical effect.

[0053] 2、在本实施例中,用户可以通过控制设备监视电子设备是否出现目标跟丢的情况,在出现目标跟丢的情况时,可以通过点击操作及时对目标点进行修正,从而弥补了某些视觉跟踪算法(例如:长期跟踪算法)鲁棒性差的不足。 [0053] 2, in the present embodiment, the user may if there is the case with the lost object is achieved by the control device monitors the electronic device, when the case with the lost target appears, timely target point is corrected by the click operation, which make up the some visual tracking algorithm (for example: long-term tracking algorithm) quite robust enough.

[0054] 3、在本实施例中,将摄像头采集到的图像数据发送给控制设备,实现了将电子设备的视野与用户共享,使得用户可以方便地在控制设备所输出的画面中确定目标点,进而使得电子设备可以基于目标点确定跟踪目标的跟踪模板,并利用视觉跟踪算法对跟踪目标进行视觉跟踪。 [0054] 3, in the present embodiment, the camera captured the image data to the control device, to achieve a shared vision and a user of the electronic device, so that the user can easily determine a target point on the screen control device outputted , enabling the electronic device may be determined based on the target point tracking target tracking template and target tracking visual tracking using the visual tracking algorithm. 且在对跟踪目标进行视觉跟踪过程中,电子设备还可以自动对准目标点前进,这样,用户即可在控制设备输出的画面上点击任一目标点,来控制电子设备的行驶方向,同时,用户可以在控制设备上实时观看电子设备在行驶过程中的路况信息,并对电子设备的行驶方向进行调整,具有操控方便的优点。 In the process of tracking and for visual tracking target, the electronic device may also automatically proceeds at the target point, which lets the user on the screen of the control device to output a click on any of the target point to control the traveling direction of the electronic device, at the same time, the user can view the real-time traffic information on the electronic control device during driving of the apparatus, and adjusts the traveling direction of the electronic device, having the advantages of easy handling.

附图说明 BRIEF DESCRIPTION

[0055]为了更清楚地说明本发明实施例中的技术方案,下面将对实施例描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。 [0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings will be described below as required in the embodiment, a brief introduction Apparently, the drawings in the following description of the present invention, some embodiments, those of ordinary skill in the art is concerned, without creative efforts, can derive from these drawings other drawings.

[0056]图1为本发明实施例中一种目标跟踪方法的流程图; [0056] FIG. 1 is a flowchart illustrating a method of object tracking method of the present embodiment of the invention;

[0057]图2为本发明实施例中一种电子设备的结构图; [0057] Figure 2 embodiment a configuration diagram of an electronic apparatus of the embodiment of the present invention;

[0058]图3为本发明实施例中一种目标跟踪方法的流程图。 [0058] FIG 3 a flow diagram of one embodiment of the method for target tracking embodiment of the present invention.

具体实施方式 Detailed ways

[0059]本发明实施例通过提供一种目标跟踪方法及电子设备,解决了现有技术中的在线学习的视觉跟踪算法,由于采用用户指定区域来定义跟踪模板的交互模式,存在无法对运动中的物体进行视觉跟踪的技术问题。 Example [0059] The present invention provides a method of tracking a target and an electronic device, the problem in the prior art visual online learning tracking algorithm, since the user specified area tracking template to define the interactive mode, the motion can not exist the objects visual tracking of technical problems.

[0060]本发明实施例的技术方案为解决上述技术问题,总体思路如下: [0060] The technical solution of the embodiment of the present invention to solve the above problems, the general idea is as follows:

[0061] —种目标跟踪方法,应用于电子设备中,该电子设备具有一摄像头,该方法包括:将摄像头采集到的图像数据发送给控制设备;接收控制设备发来的目标点的位置信息,其中,目标点为在控制设备通过显示屏输出图像数据的画面时用户在画面上选中的点,目标点为跟踪目标上的任一点;基于目标点的位置信息,确定跟踪目标对应的跟踪模板;基于跟踪目标对应的跟踪模板,利用视觉跟踪算法对跟踪目标进行视觉跟踪。 [0061] - species target tracking method applied to an electronic device, the electronic device having a camera, the method comprising: transmitting the camera collects the image data to the control device; receiving location information device sent by the target control point, wherein, when the target point to the control device via the display screen of the image data output user selected point on the screen, the target point is any point on the target track; location information based on the target point, the target track corresponding to the track determined template; based on the corresponding tracking target tracking template, use visual target tracking algorithm for tracking visual tracking.

[0062]为了更好的理解上述技术方案,下面将结合说明书附图以及具体的实施方式对上述技术方案进行详细的说明。 [0062] For a better understanding of the above technical solutions, in conjunction with the following drawings and specific embodiments of the above technical solutions described in detail.

[0063] 实施例一 [0063] Example a

[0064]本实施例提供了一种目标跟踪方法,应用于电子设备中,所述电子设备具有一摄像头,如图1所示,所述目标跟踪方法,包括: [0064] The present embodiment provides a tracking method applied to an electronic device, the electronic device having a camera, a method of tracking the target, as shown in FIG comprising:

[0065]步骤SlOl:将摄像头采集到的图像数据发送给控制设备。 [0065] Step SlOl: transmitting the collected camera image data to the control device.

[0066]在具体实施过程中,所述电子设备可以是一可移动电子设备,其包括一动力系统,能够驱动电子设备行驶(例如:直行,转弯,倒退,曲线行驶,等等)。 [0066] In a specific implementation, the electronic device may be a mobile electronic device, comprising a power system, can be driven with the electronic device (for example: straight, turning, reverse, curve driving, etc.).

[0067]在具体实施过程中,在电子设备上设置有一摄像头,用于采集图像信息。 [0067] In a specific implementation, the electronic device provided with a camera for acquiring image information. 为了获得更为广阔的图像采集视角,对于地面移动电子设备而言,摄像头应尽量设置在靠近电子设备顶部的位置;对于空中移动电子设备(如无人机)而言,摄像头应尽量设置在靠近电子设备底部的位置。 In order to obtain a broader perspective image acquisition, for terrestrial mobile electronic device, the camera should be provided at a position near the top of the electronic device; air for mobile electronic devices (e.g., UAV), the camera should be arranged close to the position of the bottom of the electronic device.

[0068]在具体实施过程中,控制设备可以与该电子设备通过有线方式或无线方式连接,以使得控制设备可以与电子设备进行通信。 [0068] In a specific implementation, the control device may be connected to the electronic device through wired or wireless manner, so that the control device can communicate with the electronic device. 在电子设备通过摄像头采集到图像数据后,会将采集到的图像数据实时发送给控制设备。 After the electronic device to the image data acquired through the camera, it will capture the image data transmitted in real time to the control device.

[0069]在具体实施过程中,该控制设备可以是与电子设备为相互独立的设备(例如:智能手机、或平板电脑、或笔记本电脑、或台式机电脑、或智能电视、或智能钥匙、等等);或者,该控制设备还可以直接设置在电子设备上,作为电子设备的一部分。 [0069] In a specific implementation, the control device may be an electronic device for the independent device (example: a smartphone, or tablet computer, or a laptop, or desktop PC, or smart television, or a smart key, etc. etc.); or the control device can also be disposed directly on the electronic device, the electronic device as a part.

[0070]步骤S102:接收控制设备发来的目标点的位置信息,其中,目标点为在控制设备通过显示屏输出图像数据的画面时用户在画面上选中的点。 [0070] the step S102: the location information sent by the device receiving the control target point, wherein, when the target point to the control device via the display screen of the image data output user selected point on the screen.

[0071]在具体实施过程中,控制设备接收到电子设备发来的图像数据后,可以通过一触摸屏(例如:电容式触摸屏、或电阻式触摸屏)输出该图像数据对应的画面(即:传图画面),从而实现了将电子设备的视野与用户共享。 [0071] In a specific implementation, the control device after receiving the electronic device sent by the image data, (e.g.,: a capacitive touch screen, or a resistive touch screen) through a touch screen outputs the image data corresponding to a screen (i.e.: mass FIG. screen), enabling the electronic device to the user's vision and shared. 用户可以在控制设备输出的画面上寻找一跟踪目标(该跟踪目标可以是静止的物体,也可以是运动的物体),并通过点击操作点击跟踪目标上的任意一个像素点,这个像素点就是所述目标点。 The user can find a target tracking (the tracking target may be a stationary object, or may be a moving object) on the screen of the control device output, and through any one of the pixels on the click operation click tracking targets, the pixel is the above the target point. 控制设备获取到用户的点击操作后,即可将用户点击的目标点的位置信息(例如:目标点在屏幕上的二维坐标)发送给电子设备。 The control device obtains the user's click operation, the position information of the target point to the user clicks (e.g.,: the two-dimensional coordinates of the target point on the screen) to the electronic device. 对应地,电子设备接收控制设备发来的目标点的位置信息。 Correspondingly, the electronic control device receives the device information sent by the location of the target point.

[0072]步骤S103:基于目标点的位置信息,确定跟踪目标对应的跟踪模板。 [0072] Step S103: Based on the location information of the target point is determined corresponding to a target track tracking template.

[0073] 具体来讲,步骤S103,包括: [0073] Specifically, step S103, the comprising:

[0074]基于目标点的位置信息,在画面中确定目标点;在目标点周围生成多个备选跟踪模板;基于显著性算法,分别对多个备选跟踪模板进行分析,并从多个备选跟踪模板中选出一最佳备选跟踪模板,其中,最佳备选跟踪模板即为跟踪目标对应的跟踪模板。 [0074] Based on the position information of the target point, the target point is determined in the picture; generating a plurality of alternative points around the target tracking template; significance based algorithm, a plurality of alternative tracking templates were analyzed, and the plurality prepared from selected from the group selected from a tracking template best alternative tracking template, wherein the template tracking is the best alternative tracking template corresponding to a target track.

[0075]在具体实施过程中,可以获取目标点、以及目标点附近其它像素点的颜色信息(例如:色调参数、亮度参数,或RBG参数),并对这些像素点的颜色信息进行分析,由于构成跟踪目标的像素点可能具有相同或相近的颜色,所以可以将颜色相同或相近的像素点所组成的区域定义为一个备选跟踪模板,从而生成多个备选跟踪模板。 [0075] In a specific implementation, the target points can be acquired, and the color information of the other pixels in the vicinity of the target point (e.g.: hue parameter, a brightness parameter, or parameters RBG), and analyzes the color information of the pixel, since the pixels constituting the target track may have the same or similar color, it is possible to define a region composed of the same or similar color pixel as a tracking template Alternatively, thereby generating a plurality of alternative tracking template.

[0076]在具体实施过程中,可以对每个备选跟踪模板添加噪声和随机形变,生成每个备选跟踪模板的正样本;对每个备选跟踪模板周围的背景区域随机采样,生成每个备选跟踪模板的负样本;基于每个备选跟踪模板的正样本和每个备选跟踪模板的负样本,生成每个备选跟踪模板的校验集。 [0076] In a specific embodiment the process may be added for each of the candidate template tracking noise and random deformation, generates a positive sample for each candidate template of the track; random sampling around each candidate background region tracking template to generate each Alternatively, a negative samples tracking templates; negative samples based on the positive samples for each candidate template tracking and tracking each candidate template, generating a checksum for each candidate set of tracking template. 进一步,训练每个备选跟踪模板的跟踪模型;生成每个备选跟踪模板的校验集;再测试每个备选跟踪模板的跟踪模型在各自对应备选跟踪模板的检验集上的响应;基于正样本和负样本集上平均响应的比值,确定每个备选跟踪模板的跟踪模型的显著性;最后将显著性最高的跟踪模型对应的备选跟踪模板确定为最佳备选跟踪模板。 Further, each of the candidate model training track the tracking template; generating a set of alternative tracking each check template; re-trace test response model for each alternative track on each test template sets corresponding to the tracking alternative template; positive and negative samples based on the current ratio of the average response, determine the significance of each of the candidate model to track the tracking template; Finally, the most significant candidate corresponding to the tracking model as the optimum alternative tracking template tracking template.

[0077]在具体实施过程中,每个备选跟踪模板都为矩形区域,这样最终得到的最佳备选跟踪模板也为矩形区域,从而满足了在线学习的视觉跟踪算法对跟踪模板的要求,进而实现了将用户通过点击操作来定义跟踪模板的这种交互模式与在线学习的视觉跟踪算法相融合。 [0077] In a specific implementation, each candidate template tracking a rectangular area, so that the final tracking template best alternative also obtained as a rectangular area, to meet the online learning tracking algorithm requires visual tracking template, thus achieving a user to define a tracking template by clicking visual tracking algorithm operating this interaction model and online learning integration.

[0078] 步骤S104:基于跟踪目标对应的跟踪模板,利用视觉跟踪算法对跟踪目标进行视觉跟踪。 [0078] Step S104: corresponding to a target track based on the tracking template, visual tracking of the tracking target by using a visual tracking algorithm.

[0079]在具体实施过程中,视觉跟踪算在一定时间内的具有很高的鲁棒性(具体受限于应用环境的复杂程度,大概在几十秒到十几分钟之间),所以,视觉跟踪算法可以提供较高的自动化程度,在准确跟踪期间,无需用户控制,即可准确地对跟踪目标进行视觉跟踪。 [0079] In a specific implementation, the visual track count in a given time has a high robustness (particularly limited in the complexity of the application environment, probably between ten minutes to several tens of seconds), so that, visual tracking algorithm may provide a higher degree of automation, accurate tracking during, no user control, can accurately track a visual target tracking.

[0080]在具体实施过程中,所述视觉跟踪算法是指在线学习的视觉跟踪算法,此处不限定具体的视觉跟踪算法,任何短期跟踪算法(short-term tracking)和长期跟踪算法(long-term tracking)都可以采用。 [0080] In a specific implementation, the visual tracking algorithm refers to a visual tracking online learning algorithm, here is not limited particularly visual tracking algorithm, any short-term tracking algorithm (short-term tracking) and long-term tracking algorithm (Long- term tracking) can be used. 但是,鉴于短期跟踪算法具有更好的鲁棒性且算法更加成熟,应尽量选择短期跟踪算法,例如,可以选择采用协同滤波器(Correlat1n Filter)的跟踪算法,从而获得更好的鲁棒性,并且降低算法的复杂度。 However, in view of the short-term tracking algorithm more robust and more sophisticated algorithm, the short-term tracking algorithm should be chosen, for example, may be selected using the synergistic tracking algorithm filter (Correlat1n Filter), to obtain a better robustness, and reduce the complexity of the algorithm.

[0081]在具体实施过程中,在电子设备对跟踪目标进行视觉跟踪时,可以在摄像头采集到的图像数据中标记出跟踪目标,并将携带有标记的图像数据发送给控制设备。 [0081] In a specific implementation, when the electronic device for visually tracking a tracking target, may be collected in the camera image data marked in a tracking target, and transmits the image data carrying the marker to the control device. 在控制设备输出图像数据对应的画面时,用户即可根据画面中的标记和跟踪目标的位置关系,判断电子设备是否出现目标跟丢的情况。 When the control apparatus outputs the image data corresponding to the screen, the user according to the positional relationship between the screen and the tracking target marker, the target is determined with an electronic device is lost occurs. 例如,若画面中的标记与跟踪目标的位置重合,则表明没有跟丢;若画面中的标记与跟踪目标的位置不重合,甚至相距较远,则表明跟丢了。 For example, if the position of the overlapped screen tracking target flag, it means that no with the lost; marker if the screen position is not coincident with the target track, even far away, it indicates that with the lost. 在用户发现电子设备出现目标跟丢的情况时,可以在控制设备的显示屏上重新点击跟踪目标的任一点,从而确定一新的目标点,以使电子设备基于新的目标点,重新确定跟踪目标对应的跟踪模板,并利用视觉跟踪算法对跟踪目标进行视觉跟踪。 When users find the target with the lost electronic device fails, you can re-click the target track at any point on the control device display to determine a new target point, so that the electronic device based on the new target point, redefine tracking corresponding target tracking template and target tracking visual tracking using the visual tracking algorithm.

[0082]在本实施例中,用户可以通过控制设备监视电子设备是否出现目标跟丢的情况,在出现目标跟丢的情况时,可以通过点击操作及时对目标点进行修正,从而弥补了某些视觉跟踪算法(例如:长期跟踪算法)鲁棒性差的不足。 [0082] In the present embodiment, the user may be lost if there is the case with certain monitoring electronic device by the control device, with the case when the target appears lost, the target point in time can be corrected by a click operation, which make up some visual tracking algorithm (for example: long-term tracking algorithm) quite robust enough.

[0083]在本实施例中,将用户通过点击操作来定义跟踪模板的这种交互模式与在线学习的视觉跟踪算法相融合,仅需要用户点击跟踪目标上的一个目标点,即可获得跟踪目标对应的跟踪模板,从而利用在线学习的视觉跟踪算法对所述跟踪目标进行视觉跟踪。 [0083] In the present embodiment, the user defined template by clicking the track visual tracking algorithm operation this interaction model is fused with the online learning, the user only needs to click on a target track on the target point, the target track can be obtained corresponding tracking templates, so the visual target tracking visual tracking algorithm to track the use of online learning. 由于无需耗费过多时间,用户瞬间即可完成该点击操作,从而完成对跟踪模板的定义,具有操作方便、快捷的优点。 Because without consuming too much time, the user can instantly click to complete the operation to complete the definition of tracking templates, easy to operate, fast advantages. 所以有效地解决了在线学习的视觉跟踪算法,由于采用用户指定区域来定义跟踪模板的交互模式,耗时较长,存在无法对运动中的物体进行视觉跟踪的技术问题。 So effectively solve the visual tracking algorithm of online learning, thanks to a user-specified area tracking templates to define the mode of interaction, time-consuming, can not exist on the movement of objects in visual tracking of technical problems. 实现了利用在线学习的视觉跟踪算法对运动中的物体进行视觉跟踪的技术效果。 Achieve visual tracking algorithm using online learning to the movement of objects in visual tracking technical effect.

[0084]作为一种可选的实施方式,在执行步骤S104过程中,还可以同时执行步骤S105。 [0084] As an alternative embodiment, the process of step S104 is performed, step S105 may also be performed simultaneously.

[0085]步骤S105:控制电子设备对准目标点前进。 [0085] Step S105: the control electronics at the target point proceeds.

[0086]在具体实施过程中,可以根据目标点在画面中的位置,调整摄像头的俯仰角、以及控制电子设备转弯,使得目标点逐渐靠近画面的中心,从而控制电子设备对准目标点,再控制电子设备前进。 [0086] In a specific implementation, according to the position of the target point in the screen, adjust the camera's pitch angle, and the control electronics turns, so that the target point gradually approach the center of the screen, thereby controlling the electronic device at the target point, then control electronics forward.

[0087]在具体实施过程中,可以基于等式(I)确定目标点与画面的中心在竖直方向上的竖直偏离角: [0087] In a specific implementation may be based on the equation (I) determining the target point and the center of the screen vertical off-angle in the vertical direction:

[0088] Picth = arctan(dy/f)--等式(I) [0088] Picth = arctan (dy / f) - equation (I)

[0089]其中,Picth为竖直偏离角,f为摄像头的焦距,dy为目标点到摄像头光轴的垂直偏移量; [0089] wherein, Picth a vertical deviation angle, f is the focal length of the camera, dy target point to the vertical offset of the optical axis of the camera;

[0090]再根据竖直偏离角Picth,调整摄像头的俯仰角,使竖直偏离角Picth逐渐减小趋于0,最终使目标点在竖直方向靠近画面的中心。 [0090] According to another pitch angle Picth vertical deviation angle, to adjust the camera, so that the vertical deviation angle tends to 0 Picth gradually decreases, and finally to a point near the center of the target screen in the vertical direction.

[0091]在具体实施过程中,可以基于等式(2)确定目标点与画面的中心在水平方向上的水平偏移角: [0091] In a specific implementation may be based on the equation (2) determining the level of the target point and the center of the screen in the horizontal direction of the deviation angle:

[0092] yaw = arc tan (dx/f)--等式(2) [0092] yaw = arc tan (dx / f) - Eq. (2)

[0093]其中,yaw为水平偏移角,f为摄像头的焦距,dx为目标点到摄像头光轴的水平偏移量; [0093] wherein, yaw angle is a horizontal offset, f is the focal length of the camera, dx is the target point to the horizontal axis of the camera offset;

[0094]再根据水平偏移角,确定电子设备的转动角速度;基于转动角速度,控制电子设备转动,使得水平偏移角yaw逐渐减小趋于O,最终使目标点在水平方向靠近画面的中心。 [0094] The horizontal offset angle again, to determine rotational angular velocity of the electronic device; based on the rotation angular velocity, the rotation control electronics, so that the yaw angle offset level decreases tends O, and finally to a point near the center of the target screen in the horizontal direction .

[0095]其中,转动角速度与水平偏移角成正比例关系,这样,在水平偏移角越大时,转动角速度也会越大,可以使目标点在水平方向快速靠近画面的中心。 [0095] wherein the rotational angular velocity and the horizontal angular offset proportional relationship, so that when the level of the larger offset angle, rotation angular velocity will be greater, the target point can be made closer to the center of the screen quickly in a horizontal direction.

[0096]在竖直偏离角Picth和水平偏移角yaw都为O时(或都接近O时),目标点基本就位于画面的中心点,此时,即可控制电子设备前进,逐渐靠近目标点,从而实现对目标点的跟踪行驶。 [0096] When the off angle in the vertical and horizontal offset Picth yaw angle are O (or when the are close to O), the target point is located substantially center point of the screen, this time, to control the electronic device proceeds, gradually approach the target point, enabling the tracking of the target point of travel.

[0097]在具体实施过程中,可以根据跟踪目标对应的跟踪模板在画面中的尺寸,确定电子设备的前进速度;基于该前进速度,控制电子设备向跟踪目标前进。 [0097] In a specific implementation, the target can be tracked in accordance with the tracking template size corresponding to the screen, determining the forward speed of the electronic device; based on the forward speed, the electronic control apparatus proceeds to the tracking target. 其中,可以使用sigmoid函数制定速度衰减模型。 Among them, sigmoid function can be used to develop speed decay model.

[0098]在具体实施过程中,电子设备的前进速度与跟踪目标对应的跟踪模板在画面中的尺寸成反比例关系,这样,在跟踪目标对应的跟踪模板在画面中的尺寸越小时,说明跟踪目标与电子设备的距离越远,则控制电子设备的前进速度越快,从而控制电子设备快速靠近跟踪目标,而在跟踪目标对应的跟踪模板在画面中的尺寸越大时,说明跟踪目标与电子设备的距离越近,则控制电子设备的前进速度越慢,从而防止电子设备与跟踪目标碰撞。 [0098] In a specific implementation, the forward speed of the electronic device with the tracked object corresponding to the tracking template size inversely proportional to the screen, so that the track corresponding to the target tracking template size in the screen is smaller, indicating a tracking target and the farther away from the electronic device, the control proceeds faster the speed of the electronic device, thereby controlling the electronic flash device close to the target track, and tracking the corresponding target tracking template at the larger screen size, indicating the target track with the electronic device the closer the distance, the control electronics of the slower forward speed, thus preventing electronic equipment and tracking targets collision.

[0099]在本实施例中,将摄像头采集到的图像数据发送给控制设备,实现了将电子设备的视野与用户共享,使得用户可以方便地在控制设备所输出的画面中确定目标点,进而使得电子设备可以基于目标点确定跟踪目标的跟踪模板,并利用视觉跟踪算法对跟踪目标进行视觉跟踪。 [0099] In the present embodiment, the camera captured the image data to the control device, to achieve a shared vision and a user of the electronic device, so that the user can easily determine a target point on the screen control device outputted, and further so that the electronic device can be determined based on the target point tracking target tracking template and target tracking visual tracking using the visual tracking algorithm. 在对跟踪目标进行视觉跟踪过程中,电子设备还可以自动对准目标点前进,这样,用户即可在控制设备输出的画面上点击任一目标点,来控制电子设备的行驶方向,操作方便,并且用户可以在控制设备上实时观看电子设备在行驶过程中的路况信息,并对电子设备的行驶方向进行调整。 In the process of visually tracking a tracking target, the electronic device may also automatically proceeds at the target point, which lets the user on the screen of the control device to output a click on any of the target point to control the traveling direction of the electronic device, easy to operate, and the user can watch the real-time traffic information in the electronic device during running on the control device, and adjusting the traveling direction of the electronic device.

[0100]在具体实施过程中,用户可以在控制设备的触摸屏上,连续点击画面中的不同目标点,从而遥控电子设备自由行驶。 [0100] In a specific implementation, the user can control the device on a touch screen, a continuous click target different screen points to the electronic device remote control with freedom.

[0101]基于同一发明构思,本实施例该提供了一种电子设备,该电子设备具有一摄像头,如图2所示,该电子设备,还包括: [0101] Based on the same inventive concept, the present embodiment provides an electronic device, the electronic device having a camera, the electronic device in FIG. 2, further comprising:

[0102]发送单元201,用于将摄像头采集到的图像数据发送给控制设备; [0102] transmitting unit 201, captured by the camera for transmitting image data to the control apparatus;

[0103]接收单元202,用于接收控制设备发来的目标点的位置信息,其中,目标点为在控制设备通过显示屏输出图像数据的画面时用户在画面上选中的点,目标点为跟踪目标上的任一点; [0103] The receiving unit 202, the position information sent by the target device for receiving a control point, wherein, when the target point to the control device via the display screen of the image data output user selected point on the screen, the target point for the tracking either on the target one o'clock;

[0104]确定单元203,用于基于目标点的位置信息,确定跟踪目标对应的跟踪模板; [0104] determination unit 203, a position information based on the target point, the target template is determined corresponding to the track to track;

[0105] 跟踪单元204,用于基于跟踪目标对应的跟踪模板,利用视觉跟踪算法对跟踪目标进行视觉跟踪。 [0105] Tracking unit 204, corresponding to the target track based on the tracking template, visual tracking using a tracking algorithm to track a target visually.

[0106]作为一种可选的实施方式,确定单元203,包括: [0106] As an alternative embodiment, the determination unit 203, comprising:

[0107]第一确定模块,用于基于目标点的位置信息,在画面中确定目标点; [0107] a first determining module, based on the position information for the target point, the target point is determined in the picture;

[0108]生成模块,用于在目标点周围生成多个备选跟踪模板; [0108] generating module, for generating a plurality of candidate points around the target tracking template;

[0109]分析模块,用于基于显著性算法,分别对多个备选跟踪模板进行分析,并从多个备选跟踪模板中选出一最佳备选跟踪模板,其中,最佳备选跟踪模板即为跟踪目标对应的跟踪丰旲板。 [0109] Analysis module, based on significant algorithm, respectively, a plurality of alternative tracking templates for analysis, and selects a best option from a plurality of alternative tracking template tracking template, wherein the optimal alternate track tracking tracking template is the abundance Dae plate corresponding to the target.

[0110]作为一种可选的实施方式,电子设备还包括: [0110] As an alternative embodiment, the electronic device further comprising:

[0111] 控制单元205,用于在基于跟踪模板,利用视觉跟踪算法对跟踪目标进行视觉跟踪过程中,控制电子设备对准目标点前进,其中,电子设备为可移动电子设备。 [0111] The control unit 205, based on the tracking template for, for visually tracking a target tracking process with a visual tracking algorithm, the control proceeds electronic device at the target point, wherein the electronic device is a mobile electronic device.

[0112]作为一种可选的实施方式,控制单元205包括: [0112] As an alternative embodiment, the control unit 205 comprises:

[0113] 第二确定模块,用于基于等式Picth = arctan(dy/f),确定目标点与画面的中心在竖直方向上的竖直偏离角;其中,Picth为竖直偏离角,f为摄像头的焦距,dy为目标点到摄像头光轴的垂直偏移量; [0113] The second determining module, based on the equation Picth = arctan (dy / f), determining the center point of the target screen in the vertical direction of the vertical deviation angle; wherein, Picth a vertical deviation angle, f the focal length of the camera, dy target point to the vertical offset of the optical axis of the camera;

[0114]调整模块,用于根据竖直偏离角,调整摄像头的俯仰角,以使目标点在竖直方向靠近画面的中心。 [0114] The adjustment module, according to a vertical deviation angle, pitch angle adjustment of the camera, so that the target point near the center of the screen in the vertical direction.

[0115]作为一种可选的实施方式,控制单元205,包括: [0115] As an alternative embodiment, the control unit 205, comprising:

[0116] 第三确定模块,用于基于等式yaw = arctan(dx/f),确定目标点与画面的中心在水平方向上的水平偏移角;其中,yaw为水平偏移角,f为摄像头的焦距,dx为目标点到摄像头光轴的水平偏移量; [0116] The third determining module, based on the equation for the yaw = arctan (dx / f), determining the level of the target point and the center of the screen in the horizontal direction of the deviation angle; wherein, Yaw is the horizontal offset angle, f is the focal length of the camera, dx is the target point to the horizontal axis of the camera offset;

[0117]第四确定模块,用于根据水平偏移角,确定电子设备的转动角速度; [0117] Fourth determination module, an offset angle from the horizontal, to determine rotational angular velocity of the electronic device;

[0118]第一控制模块,用于基于转动角速度,控制电子设备转动,以使目标点在水平方向靠近画面的中心。 [0118] The first control module, based on the rotational angular velocity of a central control electronics rotated to a point near the target screen in the horizontal direction.

[0119]作为一种可选的实施方式,控制单元205,包括: [0119] As an alternative embodiment, the control unit 205, comprising:

[0120]第五确定模块,用于根据跟踪目标对应的跟踪模板在画面中的尺寸,确定电子设备的前进速度; [0120] Fifth determination module for tracking the target tracking template size corresponding to the screen, determining the forward speed of the electronic device;

[0121]第二控制模块,用于基于前进速度,控制电子设备向跟踪目标前进。 [0121] The second control module based on the advancing speed, the electronic control apparatus proceeds to the tracking target.

[0122]由于本实施例所介绍的电子设备为实施本发明实施例中目标跟踪方法所采用的电子设备,故而基于本发明实施例中所介绍的目标跟踪方法,本领域所属技术人员能够了解本实施例的电子设备的具体实施方式以及其各种变化形式,所以在此对于该电子设备如何实现本发明实施例中的方法不再详细介绍。 [0122] Since the electronic apparatus according to the present embodiment is described for the embodiment of the present invention, an electronic apparatus in target tracking method employed embodiment, the target tracking method embodiments described therefore based on the present invention, those skilled in the art to understand the present dETAILED dESCRIPTION Example embodiments of the electronic apparatus as well as various variations, so in this embodiment of the method not described in detail how to implement the electronic apparatus of the present invention. 只要本领域所属技术人员实施本发明实施例中目标跟踪方法所采用的电子设备,都属于本发明所欲保护的范围。 Those skilled in the art as long as the implementation of the electronic target tracking apparatus employed in the embodiment of the present invention, are within the scope of protection of the present invention is desired.

[0123]上述本发明实施例中的技术方案,至少具有如下的技术效果或优点: [0123] Technical solutions in the embodiments of the present invention has at least the following technical effects or advantages:

[0124] 1、在本发明实施例中,将用户通过点击操作来定义跟踪模板的这种交互模式与在线学习的视觉跟踪算法相融合,仅需要用户点击跟踪目标上的一个目标点,即可获得跟踪目标对应的跟踪模板,从而利用在线学习的视觉跟踪算法对所述跟踪目标进行视觉跟踪。 [0124] 1, in the embodiment of the present invention, the user to define this interaction model visual tracking algorithm with the online learning tracking template is fused by a click operation, the user need only click on a target track on the target point, to to obtain the corresponding tracking target tracking templates, so the visual target tracking visual tracking algorithm to track the use of online learning. 由于无需耗费过多时间,用户瞬间即可完成该点击操作,从而完成对跟踪模板的定义,具有操作方便、快捷的优点。 Because without consuming too much time, the user can instantly click to complete the operation to complete the definition of tracking templates, easy to operate, fast advantages. 所以有效地解决了在线学习的视觉跟踪算法,由于采用用户指定区域来定义跟踪模板的交互模式,耗时较长,存在无法对运动中的物体进行视觉跟踪的技术问题。 So effectively solve the visual tracking algorithm of online learning, thanks to a user-specified area tracking templates to define the mode of interaction, time-consuming, can not exist on the movement of objects in visual tracking of technical problems. 实现了将用户通过点击操作来定义跟踪模板的这种交互模式与在线学习的视觉跟踪算法相融合,来对运动中的物体进行视觉跟踪的技术效果。 Implements the user to define a tracking template by clicking visual tracking algorithm operating this interaction model and the integration of online learning to visually track moving objects in technical effect.

[0125] 2、在本发明实施例中,用户可以通过控制设备监视电子设备是否出现目标跟丢的情况,在出现目标跟丢的情况时,可以通过点击操作及时对目标点进行修正,从而弥补了某些视觉跟踪算法(例如:长期跟踪算法)鲁棒性差的不足。 [0125] 2, in the embodiment of the invention, a user may be the case with the lost certain whether there by the control device monitors the electronic device, when the case with the lost target appears, timely target point is corrected by the click operation, which make some visual tracking algorithms (for example: long-term tracking algorithm) quite robust enough.

[0126] 3、在本发明实施例中,将摄像头采集到的图像数据发送给控制设备,实现了将电子设备的视野与用户共享,使得用户可以方便地在控制设备所输出的画面中确定目标点,进而使得电子设备可以基于目标点确定跟踪目标的跟踪模板,并利用视觉跟踪算法对跟踪目标进行视觉跟踪。 [0126] 3, in the embodiment of the present invention, the camera captured the image data to the control device, to achieve a shared vision and a user of the electronic device, so that the user can easily determine a target screen control device outputted point, enabling the electronic device may be determined based on the target point tracking template tracking goals and targets for visual tracking using the tracking visual tracking algorithm. 且在对跟踪目标进行视觉跟踪过程中,电子设备还可以自动对准目标点前进,这样,用户即可在控制设备输出的画面上点击任一目标点,来控制电子设备的行驶方向,同时,用户可以在控制设备上实时观看电子设备在行驶过程中的路况信息,并对电子设备的行驶方向进行调整,具有操控方便的优点。 In the process of tracking and for visual tracking target, the electronic device may also automatically proceeds at the target point, which lets the user on the screen of the control device to output a click on any of the target point to control the traveling direction of the electronic device, at the same time, the user can view the real-time traffic information on the electronic control device during driving of the apparatus, and adjusts the traveling direction of the electronic device, having the advantages of easy handling.

[0127]实施例二 [0127] Second Embodiment

[0128]本实施例提供了 一种目标跟踪方法,应用于自平衡车中,所述自平衡车具有一摄像头,如图3所示,所述目标跟踪方法,包括: [0128] The present embodiment provides a method for tracking targets, self-balancing vehicle is applied, the self-balancing vehicle with a camera, as shown, the target tracking method 3, as shown in FIG comprising:

[0129]步骤S301:将摄像头采集到的图像数据发送给控制设备。 [0129] Step S301: the camera to capture the image data to the control device.

[0130]在具体实施过程中,所述自平衡车主要有独轮和双轮两类,其运作原理主要是建立在一种被称为“动态稳定” (Dynamic Stabilizat1n)的基本原理上,利用车体内部的陀螺仪和加速度传感器,来检测车体姿态的变化,并利用伺服控制系统,精确地驱动电机进行相应的调整,以保持系统的平衡。 [0130] In a specific implementation, the two-wheeled self-balanced and have unicycle owner, its operational principle is based on the basic principle is called a "dynamic stabilization" (Dynamic Stabilizat1n), the use of the interior of the vehicle body acceleration sensor and a gyroscope, to detect a change in posture of the vehicle body, and the servo control system to accurately adjust the drive motor accordingly, to maintain balance of the system. 自平衡车中包括一套动力系统,能够驱动自平衡车在路面上行驶(例如:直行,转弯,倒退,曲线行驶,等等)。 A self-balancing vehicle includes a power system capable of driving a self-balancing vehicle traveling on the road (for example: straight, turning, reverse, curve driving, etc.).

[0131]在具体实施过程中,在自平衡车上设置有一摄像头,用于采集图像信息。 [0131] In a specific implementation, the self-balancing in a car provided with a camera for acquiring image information. 为了获得更为广阔的图像采集视角,摄像头应尽量设置在靠近自平衡车顶部的位置。 In order to obtain a broader perspective image acquisition, the camera should be provided at a position near the top of the self-balancing vehicle.

[0132]在具体实施过程中,控制设备可以与自平衡车通过有线方式或无线方式连接,以使得控制设备可以与自平衡车进行通信。 [0132] In a specific implementation, the control device may be connected via a wired or wireless manner to the vehicle self-balancing, so that the control device may communicate with the self-balancing vehicle. 在自平衡车通过摄像头采集到图像数据后,会将采集到的图像数据实时发送给控制设备。 After the self-balancing vehicle image data acquired through the camera, it will capture the image data transmitted in real time to the control device.

[0133]在具体实施过程中,该控制设备可以是与自平衡车为相互独立的设备(例如:智能手机、或平板电脑、或笔记本电脑、或台式机电脑、或智能电视、或智能钥匙等等);或者,该控制设备还可以直接设置在自平衡车上,作为自平衡车的一部分。 [0133] In a specific implementation, the control device may be a self-balancing vehicle of independent devices (for example: a smartphone, or tablet computer, or a laptop, or desktop PC, or smart television, or smart keys, etc. etc.); or the control device may also be provided directly from the balance of the car, as a self-balancing vehicle part. 该控制设备在为智能钥匙时,可以控制自平衡车锁车、开锁,或开启防盗报警。 The control device when a smart key, you can control the self-balancing vehicle lock, unlock, or open the burglar alarm.

[0134]步骤S302:接收控制设备发来的目标点的位置信息,其中,目标点为在控制设备通过显示屏输出图像数据的画面时用户在画面上选中的点。 [0134] Step S302: the location information sent by the device receiving the control target point, wherein, when the target point to the control device via the display screen of the image data output user selected point on the screen.

[0135]在具体实施过程中,控制设备接收到自平衡车发来的图像数据后,可以通过一触摸屏(例如:电容式触摸屏、或电阻式触摸屏)输出该图像数据对应的画面(即:传图画面),从而实现了将自平衡车的视野与用户共享。 [0135] In a specific implementation, the control device after receiving the self-balancing vehicle sent image data can be (e.g.: capacitive touch screen, or a resistive touch screen) through a touch screen outputs the image data corresponding to a screen (i.e.: Chuan FIG screen), thereby realizing a shared vision and self-balancing vehicle user. 用户可以在控制设备输出的画面上寻找一跟踪目标(该跟踪目标可以是静止的物体,也可以是运动的物体),并通过点击操作点击跟踪目标上的任意一个像素点,这个像素点就是所述目标点。 The user can find a target tracking (the tracking target may be a stationary object, or may be a moving object) on the screen of the control device output, and through any one of the pixels on the click operation click tracking targets, the pixel is the above the target point. 控制设备获取到用户的点击操作后,即可将用户点击的目标点的位置信息(例如:坐标信息)发送给自平衡车。 After obtaining control device to the user's click operation, the user can click on the position information of the target point (e.g.: coordinate information) to a self-balancing vehicle. 对应地,自平衡车接收控制设备发来的目标点的位置信息。 Correspondingly, the balance of the vehicle from the position information receiving apparatus sent from the control target point.

[0136]步骤S303:基于目标点的位置信息,确定跟踪目标对应的跟踪模板。 [0136] Step S303: Based on the location information of the target point is determined corresponding to a target track tracking template.

[0137] 具体来讲,步骤S303,包括: [0137] Specifically, step S303, the comprising:

[0138]基于目标点的位置信息,在画面中确定目标点;在目标点周围生成多个备选跟踪模板;基于显著性算法,分别对多个备选跟踪模板进行分析,并从多个备选跟踪模板中选出一最佳备选跟踪模板,其中,最佳备选跟踪模板即为跟踪目标对应的跟踪模板。 [0138] Based on the position information of the target point, the target point is determined in the picture; generating a plurality of alternative points around the target tracking template; significance based algorithm, a plurality of alternative tracking templates were analyzed, and the plurality prepared from selected from the group selected from a tracking template best alternative tracking template, wherein the template tracking is the best alternative tracking template corresponding to a target track.

[0139]在具体实施过程中,可以获取目标点、以及目标点附近其它像素点的颜色信息(例如:色调参数、亮度参数,或RBG参数),并对这些像素点的颜色信息进行分析,由于构成跟踪目标的像素点可能具有相同或相近的颜色,所以可以将颜色相同或相近的像素点所组成的区域定义为一个备选跟踪模板,从而生成多个备选跟踪模板。 [0139] In a specific implementation, the target points can be acquired, and the color information of the other pixels in the vicinity of the target point (e.g.: hue parameter, a brightness parameter, or parameters RBG), and analyzes the color information of the pixel, since the pixels constituting the target track may have the same or similar color, it is possible to define a region composed of the same or similar color pixel as a tracking template Alternatively, thereby generating a plurality of alternative tracking template.

[0140]在具体实施过程中,可以对每个备选跟踪模板添加噪声和随机形变,生成每个备选跟踪模板的正样本;对每个备选跟踪模板周围的背景区域随机采样,生成每个备选跟踪模板的负样本;基于每个备选跟踪模板的正样本和每个备选跟踪模板的负样本,生成每个备选跟踪模板的校验集。 [0140] In a specific embodiment the process may be added for each of the candidate template tracking noise and random deformation, generates a positive sample for each candidate template of the track; random sampling around each candidate background region tracking template to generate each Alternatively, a negative samples tracking templates; negative samples based on the positive samples for each candidate template tracking and tracking each candidate template, generating a checksum for each candidate set of tracking template. 进一步,训练每个备选跟踪模板的跟踪模型;生成每个备选跟踪模板的校验集;再测试每个备选跟踪模板的跟踪模型在各自对应备选跟踪模板的检验集上的响应;基于正样本和负样本集上平均响应的比值,确定每个备选跟踪模板的跟踪模型的显著性;最后将显著性最高的跟踪模型对应的备选跟踪模板确定为最佳备选跟踪模板。 Further, each of the candidate model training track the tracking template; generating a set of alternative tracking each check template; re-trace test response model for each alternative track on each test template sets corresponding to the tracking alternative template; positive and negative samples based on the current ratio of the average response, determine the significance of each of the candidate model to track the tracking template; Finally, the most significant candidate corresponding to the tracking model as the optimum alternative tracking template tracking template.

[0141]在具体实施过程中,每个备选跟踪模板都为矩形区域,这样最终得到的最佳备选跟踪模板也为矩形区域,从而满足了在线学习的视觉跟踪算法对跟踪模板的要求,进而实现了将用户通过点击操作来定义跟踪模板的这种交互模式与在线学习的视觉跟踪算法相融合。 [0141] In a specific implementation, each candidate template tracking a rectangular area, so that the final tracking template best alternative also obtained as a rectangular area, to meet the online learning tracking algorithm requires visual tracking template, thus achieving a user to define a tracking template by clicking visual tracking algorithm operating this interaction model and online learning integration.

[0142] 步骤S304:基于跟踪目标对应的跟踪模板,利用视觉跟踪算法对跟踪目标进行视觉跟踪。 [0142] Step S304: corresponding to a target track based on the tracking template, visual tracking of the tracking target by using a visual tracking algorithm.

[0143]在具体实施过程中,视觉跟踪算在一定时间内的具有很高的鲁棒性(具体受限于应用环境的复杂程度,大概在几十秒到十几分钟之间),所以,视觉跟踪算法可以提供较高的自动化程度,在准确跟踪期间,无需用户控制,即可准确地对跟踪目标进行视觉跟踪。 [0143] In a specific implementation, the visual track count in a given time has a high robustness (particularly limited in the complexity of the application environment, probably between ten minutes to several tens of seconds), so that, visual tracking algorithm may provide a higher degree of automation, accurate tracking during, no user control, can accurately track a visual target tracking.

[0144]在具体实施过程中,所述视觉跟踪算法是指在线学习的视觉跟踪算法,此处不限定具体的视觉跟踪算法,任何短期跟踪算法(short-term tracking)和长期跟踪算法(long-term tracking)都可以采用。 [0144] In a specific implementation, the visual tracking algorithm refers to a visual tracking online learning algorithm, here is not limited particularly visual tracking algorithm, any short-term tracking algorithm (short-term tracking) and long-term tracking algorithm (Long- term tracking) can be used. 但是,鉴于短期跟踪算法具有更好的鲁棒性且算法更加成熟,应尽量选择短期跟踪算法,例如,可以选择采用协同滤波器(Correlat1n Filter)的视觉跟踪算法,从而获得更好的鲁棒性,并且降低算法的复杂度。 However, in view of the short-term tracking algorithm more robust and more sophisticated algorithm, the short-term tracking algorithm should be chosen, for example, may be selected using the synergistic visual tracking algorithm filter (Correlat1n Filter), to obtain a better robustness and reduces the complexity of the algorithm.

[0145]在具体实施过程中,在自平衡车对跟踪目标进行视觉跟踪时,可以在摄像头采集到的图像数据中标记出该跟踪目标,并将携带有标记的图像数据发送给控制设备。 [0145] In a specific implementation, when the balance of the vehicle from the tracking target visual tracking, can be collected in the camera image data of the marked target track and carrying the mark image data to the control device. 在控制设备输出图像数据对应的画面时,用户即可根据画面中的标记和跟踪目标的位置关系,判断自平衡车是否出现目标跟丢的情况。 When the control apparatus outputs the image data corresponding to the screen, the user according to the positional relationship between the screen and the tracking target flag, it is determined whether the vehicle is self-balancing with the target appears lost. 例如,若画面中的标记与跟踪目标的位置重合,则表明没有跟丢;若画面中的标记与跟踪目标的位置不重合,甚至相距较远,则表明跟丢了。 For example, if the position of the overlapped screen tracking target flag, it means that no with the lost; marker if the screen position is not coincident with the target track, even far away, it indicates that with the lost. 在用户发现自平衡车出现目标跟丢的情况时,可以在控制设备的显示屏上重新点击跟踪目标的任一点,从而确定一新的目标点,以使自平衡车基于新的目标点,重新确定跟踪目标对应的跟踪模板,并利用视觉跟踪算法对跟踪目标进行视觉跟踪。 When users find the target with the lost of self-balancing vehicle occurs, you can re-click on the control device's display screen to track the target at any point, to determine a new target point, so self-balancing vehicle based on the new target point, again tracking to determine the corresponding target tracking template and target tracking visual tracking using the visual tracking algorithm.

[0146]在本实施例中,用户可以通过控制设备监视自平衡车是否出现目标跟丢的情况,在出现目标跟丢的情况时,可以通过点击操作及时对目标点进行修正,从而弥补了某些视觉跟踪算法(例如:长期跟踪算法)鲁棒性差的不足。 [0146] In the present embodiment, the user may if there is the case with the lost object is achieved by the control device monitors the self-balancing vehicle, while with the case of losing the target appears, timely target point is corrected by the click operation, which make up a these visual tracking algorithm (for example: long-term tracking algorithm) quite robust enough.

[0147]在本实施例中,将用户通过点击操作来定义跟踪模板的这种交互模式与在线学习的视觉跟踪算法相融合,仅需要用户点击跟踪目标上的一个目标点,即可获得跟踪目标对应的跟踪模板,从而利用在线学习的视觉跟踪算法对所述跟踪目标进行视觉跟踪。 [0147] In the present embodiment, the user defined template by clicking the track visual tracking algorithm operation this interaction model is fused with the online learning, the user only needs to click on a target track on the target point, the target track can be obtained corresponding tracking templates, so the visual target tracking visual tracking algorithm to track the use of online learning. 由于无需耗费过多时间,用户瞬间即可完成该点击操作,从而完成对跟踪模板的定义,具有操作方便、快捷的优点。 Because without consuming too much time, the user can instantly click to complete the operation to complete the definition of tracking templates, easy to operate, fast advantages. 所以有效地解决了在线学习的视觉跟踪算法,由于采用用户指定区域来定义跟踪模板的交互模式,耗时较长,存在无法对运动中的物体进行视觉跟踪的技术问题。 So effectively solve the visual tracking algorithm of online learning, thanks to a user-specified area tracking templates to define the mode of interaction, time-consuming, can not exist on the movement of objects in visual tracking of technical problems. 实现了利用在线学习的视觉跟踪算法对运动中的物体进行视觉跟踪的技术效果。 Achieve visual tracking algorithm using online learning to the movement of objects in visual tracking technical effect.

[0148]作为一种可选的实施方式,在执行步骤S304过程中,还可以同时执行步骤S305。 [0148] As an alternative embodiment, the process at step S304 is performed, step S305 may also be performed simultaneously.

[0149]步骤S305:控制自平衡车对准目标点前进。 [0149] Step S305: control self-balancing vehicle at the target point forward.

[0150]在具体实施过程中,可以根据目标点在画面中的位置,调整摄像头的俯仰角、以及控制自平衡车转弯,使得目标点逐渐靠近画面的中心,从而控制自平衡车对准目标点,再控制自平衡车前进。 [0150] In a specific implementation, according to the position of the target point in the screen, adjust the pitch angle of the camera, and control self-balancing vehicle turns, so that the target point gradually approach the center of the screen, thereby controlling the self-balancing vehicle at the target point , and then control the self-balancing vehicle forward.

[0151]在具体实施过程中,可以基于等式(I)确定目标点与画面的中心在竖直方向上的竖直偏离角: [0151] In a specific implementation may be based on the equation (I) determining the target point and the center of the screen vertical off-angle in the vertical direction:

[0152] Picth = arctan(dy/f)--等式(I) [0152] Picth = arctan (dy / f) - equation (I)

[0153]其中,Picth为竖直偏离角,f为摄像头的焦距,dy为目标点到摄像头光轴的垂直偏移量; [0153] wherein, Picth a vertical deviation angle, f is the focal length of the camera, dy target point to the vertical offset of the optical axis of the camera;

[0154]再根据竖直偏离角Picth,调整摄像头的俯仰角,使竖直偏离角Picth逐渐减小趋于0,最终使目标点在竖直方向靠近画面的中心。 [0154] According to another pitch angle Picth vertical deviation angle, to adjust the camera, so that the vertical deviation angle tends to 0 Picth gradually decreases, and finally to a point near the center of the target screen in the vertical direction.

[0155]在具体实施过程中,可以基于等式(2)确定目标点与画面的中心在水平方向上的水平偏移角: [0155] In a specific implementation may be based on the equation (2) determining the level of the target point and the center of the screen in the horizontal direction of the deviation angle:

[0156] yaw = arc tan (dx/f)--等式(2) [0156] yaw = arc tan (dx / f) - Eq. (2)

[0157]其中,yaw为水平偏移角,f为摄像头的焦距,dx为目标点到摄像头光轴的水平偏移量; [0157] wherein, yaw angle is a horizontal offset, f is the focal length of the camera, dx is the target point to the horizontal axis of the camera offset;

[0158]再根据水平偏移角,确定自平衡车的转动角速度;基于转动角速度,控制自平衡车转动,使得水平偏移角yaw逐渐减小趋于O,最终使目标点在水平方向靠近画面的中心。 [0158] and then the deviation angle from the horizontal, the rotation angular velocity is determined from the balance of the vehicle; based on the rotation angular velocity, the rotation control self-balancing vehicle, yaw angle such that the horizontal deviation tends O decreases, and finally to a point near the target screen in the horizontal direction center of.

[0159]其中,转动角速度与水平偏移角成正比例关系,这样,在水平偏移角越大时,转动角速度也会越大,可以使目标点在水平方向快速靠近画面的中心。 [0159] wherein the rotational angular velocity and the horizontal angular offset proportional relationship, so that when the level of the larger offset angle, rotation angular velocity will be greater, the target point can be made closer to the center of the screen quickly in a horizontal direction.

[0160]在竖直偏离角Picth和水平偏移角yaw都为O时(或都接近O时),目标点基本就位于画面的中心点,此时,即可控制自平衡车前进,逐渐靠近目标点,从而实现对目标点的跟踪行驶。 When [0160] the vertical and horizontal deviation angle Picth yaw angle offset are O (or when the are close to O), the target point is located substantially center point of the screen, this time, to control the self-balancing vehicle forward, gradually approach target point, enabling the tracking of the target point of travel.

[0161]在具体实施过程中,可以根据跟踪目标对应的跟踪模板在画面中的尺寸,确定自平衡车的前进速度;基于该前进速度,控制自平衡车向跟踪目标前进。 [0161] In a specific embodiment of the process, according to the target track corresponding to the track in the template screen dimensions, the forward speed is determined from the balance of the vehicle; based on the forward speed, the control proceeds to a self-balancing vehicle tracking target. 其中,可以使用sigmoid函数制定速度衰减模型。 Among them, sigmoid function can be used to develop speed decay model.

[0162]在具体实施过程中,自平衡车的前进速度与跟踪目标对应的跟踪模板在画面中的尺寸成反比例关系,这样,在跟踪目标对应的跟踪模板在画面中的尺寸越小时,说明跟踪目标与自平衡车的距离越远,则控制自平衡车的前进速度越快,从而控制自平衡车快速靠近跟踪目标,而在跟踪目标对应的跟踪模板在画面中的尺寸越大时,说明跟踪目标与自平衡车的距离越近,则控制自平衡车的前进速度越慢,从而防止自平衡车与跟踪目标碰撞。 [0162] In a specific implementation, since the advancing speed balancing vehicle and tracking the target corresponding to the tracking template size inversely proportional to the screen, so that the size of the screen is smaller in track corresponding to a target tracking template described tracking and the farther the distance from the target vehicle equilibrium, then control proceeds from the faster speed of the vehicle balanced, thereby controlling the self-balancing vehicle quick approach to track the target, and tracking the corresponding target tracking template at the larger screen size, track description since the target and the closer the car balance, self-control, the slower the forward speed of the car balance, so as to prevent self-balancing vehicle collision and tracking targets.

[0163]在本实施例中,将摄像头采集到的图像数据发送给控制设备,实现了将自平衡车的视野与用户共享,使得用户可以方便地在控制设备所输出的画面中确定目标点,进而使得自平衡车可以基于目标点确定跟踪目标的跟踪模板,并利用视觉跟踪算法对跟踪目标进行视觉跟踪。 [0163] In the present embodiment, the camera captured the image data to the control apparatus, achieved a self-balancing vehicle vision and users to share, so that the user can easily determine a target point on the screen control device outputted, thus making the self-balancing vehicle can be determined based on the target point tracking target tracking template and target tracking visual tracking using the visual tracking algorithm. 在对跟踪目标进行视觉跟踪过程中,自平衡车还可以自动对准目标点前进,这样,用户即可在控制设备输出的画面上点击任一目标点,来控制自平衡车的行驶方向,操作方便,并且用户可以在控制设备上实时观看自平衡车在行驶过程中的路况信息,并对自平衡车的行驶方向进行调整。 In the process of visually tracking a tracking target, from the balance of the vehicle at the target point may also be automatically proceeds so that the user can control the device output on the screen of a click on any target point to control the self-balancing vehicle traveling direction, the operation convenient, and the user can view real-time traffic information from the car balance in the process of moving on the control device, and adjust the balance of the car from the direction of travel.

[0164]在具体实施过程中,用户可以在控制设备的触摸屏上,连续点击画面中的不同目标点,从而遥控自平衡车自由行驶。 [0164] In a specific implementation, the user can control the device on a touch screen, a continuous click different target point picture, thereby balancing the vehicle remote from the free travel.

[0165]基于同一发明构思,本实施例该提供了一种自平衡车,该自平衡车具有一摄像头,该自平衡车还包括图2中所示的发送单元201、接收单元202、确定单元203和跟踪单元204。 [0165] Based on the same inventive concept, the present embodiment provides a self-balancing of the vehicle, the vehicle having a balance from the camera, the self-balancing vehicle further includes a transmitting unit 2201 shown in FIG., The receiving unit 202, determination unit 203 and tracking unit 204. 其中, among them,

[0166]发送单元201,用于将摄像头采集到的图像数据发送给控制设备; [0166] transmitting unit 201, captured by the camera for transmitting image data to the control apparatus;

[0167]接收单元202,用于接收控制设备发来的目标点的位置信息,其中,目标点为在控制设备通过显示屏输出图像数据的画面时用户在画面上选中的点,目标点为跟踪目标上的任一点; [0167] The receiving unit 202, the position information sent by the target device for receiving a control point, wherein, when the target point to the control device via the display screen of the image data output user selected point on the screen, the target point for the tracking either on the destination point;

[0168]确定单元203,用于基于目标点的位置信息,确定跟踪目标对应的跟踪模板; [0168] determination unit 203, a position information based on the target point, the target template is determined corresponding to the track to track;

[0169] 跟踪单元204,用于基于跟踪目标对应的跟踪模板,利用视觉跟踪算法对跟踪目标进行视觉跟踪。 [0169] Tracking unit 204, corresponding to the target track based on the tracking template, visual tracking using a tracking algorithm to track a target visually.

[0170]作为一种可选的实施方式,确定单元203,包括: [0170] As an alternative embodiment, the determination unit 203, comprising:

[0171 ]第一确定模块,用于基于目标点的位置信息,在画面中确定目标点; [0171] a first determining module, based on the position information for the target point, the target point is determined in the picture;

[0172]生成模块,用于在目标点周围生成多个备选跟踪模板; [0172] generating module, for generating a plurality of candidate points around the target tracking template;

[0173]分析模块,用于基于显著性算法,分别对多个备选跟踪模板进行分析,并从多个备选跟踪模板中选出一最佳备选跟踪模板,其中,最佳备选跟踪模板即为跟踪目标对应的跟踪丰旲板。 [0173] Analysis module, based on significant algorithm, respectively, a plurality of alternative tracking templates for analysis, and selects a best option from a plurality of alternative tracking template tracking template, wherein the optimal alternate track tracking tracking template is the abundance Dae plate corresponding to the target.

[0174]作为一种可选的实施方式,自平衡车,还包括: [0174] As an alternative embodiment, the self-balancing vehicle, further comprising:

[0175] 控制单元205,用于在基于跟踪模板,利用视觉跟踪算法对跟踪目标进行视觉跟踪过程中,控制自平衡车对准目标点前进,其中,自平衡车为可移动自平衡车。 [0175] The control unit 205, based on the tracking template for, for visually tracking a target tracking process, self-balancing vehicle control proceeds at the target point, wherein the vehicle is self-balancing movable self-balancing vehicle with a visual tracking algorithm.

[0176]作为一种可选的实施方式,控制单元205包括: [0176] As an alternative embodiment, the control unit 205 comprises:

[0177]第二确定模块,用于基于等式Picth = arctan(dy/f),确定目标点与画面的中心在竖直方向上的竖直偏离角;其中,Picth为竖直偏离角,f为摄像头的焦距,dy为目标点到摄像头光轴的垂直偏移量; [0177] The second determining module, based on the equation Picth = arctan (dy / f), determining the center point of the target screen in the vertical direction of the vertical deviation angle; wherein, Picth a vertical deviation angle, f the focal length of the camera, dy target point to the vertical offset of the optical axis of the camera;

[0178]调整模块,用于根据竖直偏离角,调整摄像头的俯仰角,以使目标点在竖直方向靠近画面的中心。 [0178] The adjustment module, according to a vertical deviation angle, pitch angle adjustment of the camera, so that the target point near the center of the screen in the vertical direction.

[0179]作为一种可选的实施方式,控制单元205,包括: [0179] As an alternative embodiment, the control unit 205, comprising:

[0180] 第三确定模块,用于基于等式yaw = arctan(dx/f),确定目标点与画面的中心在水平方向上的水平偏移角;其中,yaw为水平偏移角,f为摄像头的焦距,dx为目标点到摄像头光轴的水平偏移量; [0180] The third determining module, based on the equation for the yaw = arctan (dx / f), determining the level of the target point and the center of the screen in the horizontal direction of the deviation angle; wherein, Yaw is the horizontal offset angle, f is the focal length of the camera, dx is the target point to the horizontal axis of the camera offset;

[0181]第四确定模块,用于根据水平偏移角,确定自平衡车的转动角速度; [0181] Fourth determination module, an offset angle from the horizontal, the rotation angular velocity is determined from the balance of the vehicle;

[0182]第一控制模块,用于基于转动角速度,控制自平衡车转动,以使目标点在水平方向靠近画面的中心。 [0182] The first control module, based on the rotation angular velocity, since the balance control of the vehicle is rotated, so that the target point near the center of the screen in the horizontal direction.

[0183]作为一种可选的实施方式,控制单元205,包括: [0183] As an alternative embodiment, the control unit 205, comprising:

[0184]第五确定模块,用于根据跟踪目标对应的跟踪模板在画面中的尺寸,确定自平衡车的前进速度; [0184] Fifth determination module for tracking the target tracking template size corresponding to the screen, the forward speed is determined from the balance of the vehicle;

[0185]第二控制模块,用于基于前进速度,控制自平衡车向跟踪目标前进。 [0185] The second control module based on forward speed, self-balancing vehicle control proceeds to the tracking target.

[0186]由于本实施例所介绍的自平衡车为实施本发明实施例中目标跟踪方法所采用的可移动电子设备,故而基于本发明实施例中所介绍的目标跟踪方法,本领域所属技术人员能够了解本实施例的自平衡车的具体实施方式以及其各种变化形式,所以在此对于该自平衡车如何实现本发明实施例中的方法不再详细介绍。 [0186] Since the present embodiment described self-balancing vehicle to embodiments of the present invention may be a mobile electronic apparatus in the target tracking method employed embodiment, the target tracking method embodiments described therefore based on the present invention, those skilled in the art dETAILED dESCRIPTION able to understand the self-balancing vehicle of the present embodiment and its various variations, so this car to balance implemented embodiment of the method of the present invention not described in detail for the self. 只要本领域所属技术人员实施本发明实施例中目标跟踪方法所采用的自平衡车,都属于本发明所欲保护的范围。 Those skilled in the art as long as the embodiment of the self balancing vehicle target tracking method employed in embodiments of the present invention, are within the scope of protection of the present invention is desired.

[0187]上述本发明实施例中的技术方案,至少具有如下的技术效果或优点: [0187] Technical solutions in the embodiments of the present invention has at least the following technical effects or advantages:

[0188] 1、在本发明实施例中,将用户通过点击操作来定义跟踪模板的这种交互模式与在线学习的视觉跟踪算法相融合,仅需要用户点击跟踪目标上的一个目标点,即可获得跟踪目标对应的跟踪模板,从而利用在线学习的视觉跟踪算法对所述跟踪目标进行视觉跟踪。 [0188] 1, in the embodiment of the present invention, the user to define this interaction model visual tracking algorithm with the online learning tracking template is fused by a click operation, the user need only click on a target track on the target point, to to obtain the corresponding tracking target tracking templates, so the visual target tracking visual tracking algorithm to track the use of online learning. 由于无需耗费过多时间,用户瞬间即可完成该点击操作,从而完成对跟踪模板的定义,具有操作方便、快捷的优点。 Because without consuming too much time, the user can instantly click to complete the operation to complete the definition of tracking templates, easy to operate, fast advantages. 所以有效地解决了在线学习的视觉跟踪算法,由于采用用户指定区域来定义跟踪模板的交互模式,耗时较长,存在无法对运动中的物体进行视觉跟踪的技术问题。 So effectively solve the visual tracking algorithm of online learning, thanks to a user-specified area tracking templates to define the mode of interaction, time-consuming, can not exist on the movement of objects in visual tracking of technical problems. 实现了将用户通过点击操作来定义跟踪模板的这种交互模式与在线学习的视觉跟踪算法相融合,来对运动中的物体进行视觉跟踪的技术效果。 Implements the user to define a tracking template by clicking visual tracking algorithm operating this interaction model and the integration of online learning to visually track moving objects in technical effect.

[0189] 2、在本发明实施例中,用户可以通过控制设备监视自平衡车是否出现目标跟丢的情况,在出现目标跟丢的情况时,可以通过点击操作及时对目标点进行修正,从而弥补了某些视觉跟踪算法(例如:长期跟踪算法)鲁棒性差的不足。 [0189] 2, in the embodiment of the invention, a user may be the target with lost if there by the control device monitors the self-balancing vehicle, while with the case of losing the target appears, timely target point is corrected by the click operation, thereby to make up for some visual tracking algorithms (for example: long-term tracking algorithm) quite robust enough.

[0190] 3、在本发明实施例中,将摄像头采集到的图像数据发送给控制设备,实现了将自平衡车的视野与用户共享,使得用户可以方便地在控制设备所输出的画面中确定目标点,进而使得自平衡车可以基于目标点确定跟踪目标的跟踪模板,并利用视觉跟踪算法对跟踪目标进行视觉跟踪。 [0190] 3, in the embodiment of the present invention, the camera captured the image data to the control apparatus, achieved a self-balancing vehicle vision and users to share, so that the user can easily determine the picture control device outputted target point, thus making the self-balancing vehicle can be determined based on the target point tracking target tracking template and target tracking visual tracking using the visual tracking algorithm. 且在对跟踪目标进行视觉跟踪过程中,自平衡车还可以自动对准目标点前进,这样,用户即可在控制设备输出的画面上点击任一目标点,来控制自平衡车的行驶方向,同时,用户可以在控制设备上实时观看自平衡车在行驶过程中的路况信息,并对自平衡车的行驶方向进行调整,具有操控方便的优点。 In the process of tracking and for visual tracking target, from the balance of the vehicle at the target point may also be automatically proceeds so that the user can control the device output on the screen of a click on any target point to control the self-balancing vehicle traveling direction, at the same time, users can view real-time control device on self-balancing vehicle traffic information in the process of moving, and adjust the balance of the car from the direction of travel, with easy handling advantages.

[0191]本领域内的技术人员应明白,本发明的实施例可提供为方法、系统、或计算机程序产品。 [0191] skilled in the art should understand that the embodiments of the present invention may provide a method, system, or computer program product. 因此,本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。 Thus, embodiments of the present invention may be employed entirely hardware embodiment, an entirely software embodiment, or an embodiment in conjunction with the form of software and hardware aspects. 而且,本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。 Further, the present invention may take the form of a computer program product embodied in one or more of which comprises a computer usable storage medium having computer-usable program code (including but not limited to, disk storage, CD-ROM, optical memory, etc.).

[0192]本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。 [0192] The present invention has been described in accordance with the method of Example of the present invention, apparatus (systems) and computer program products flowchart and / or block diagrams described. 应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。 It should be understood and implemented by computer program instructions and block, and the flowchart / or block diagrams each process and / or flowchart illustrations and / or block diagrams of processes and / or blocks. 可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。 These computer program instructions may be provided to a processor a general purpose computer, special purpose computer, embedded processor or other programmable data processing apparatus to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing apparatus generating in a device for implementing the flow chart or more flows and / or block diagram block or blocks in a specified functions.

[0193]这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。 [0193] These computer program instructions may also be stored in a computer can direct a computer or other programmable data processing apparatus to function in a particular manner readable memory produce an article of manufacture such that the storage instruction means comprises a memory in the computer-readable instructions the instruction means implemented in a flowchart or more flows and / or block diagram block or blocks in a specified function.

[0194]这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。 [0194] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps on the computer or other programmable apparatus to produce a computer implemented so that the computer or other programmable apparatus execute instructions to provide processes for implementing a process or flows and / or block diagram block or blocks a function specified step.

[0195]尽管已描述了本发明的优选实施例,但本领域内的技术人员一旦得知了基本创造性概念,则可对这些实施例作出另外的变更和修改。 [0195] While the present invention has been described with preferred embodiments, but those skilled in the art from the underlying inventive concept can make other modifications and variations to these embodiments. 所以,所附权利要求意欲解释为包括优选实施例以及落入本发明范围的所有变更和修改。 Therefore, the appended claims are intended to explain embodiments including the preferred embodiment as fall within the scope of the invention and all changes and modifications.

[0196]显然,本领域的技术人员可以对本发明进行各种改动和变型而不脱离本发明的精神和范围。 [0196] Obviously, those skilled in the art can make various modifications and variations to the invention without departing from the spirit and scope of the invention. 这样,倘若本发明的这些修改和变型属于本发明权利要求及其等同技术的范围之内,则本发明也意图包含这些改动和变型在内。 Thus, if these modifications and variations of the present invention fall within the claims of the invention and the scope of equivalents thereof, the present invention intends to include these modifications and variations.

Claims (12)

  1. 1.一种目标跟踪方法,应用于电子设备中,所述电子设备具有一摄像头,其特征在于,所述目标跟踪方法包括: 将所述摄像头采集到的图像数据发送给控制设备; 接收所述控制设备发来的目标点的位置信息,其中,所述目标点为在所述控制设备通过显示屏输出所述图像数据的画面时用户在所述画面上选中的点,所述目标点为跟踪目标上的任一点; 基于所述目标点的位置信息,确定所述跟踪目标对应的跟踪模板; 基于所述跟踪目标对应的跟踪模板,利用视觉跟踪算法对所述跟踪目标进行视觉跟足示O An object tracking method applied to an electronic device, the electronic device having a camera, characterized in that the target tracking method comprising: the camera to capture the image data to the control apparatus; receiving the the control device position information sent by the target point, wherein the target point when the display screen of the control device by outputting the image data of the user on the screen of the selected point, the target point for the tracking on the target according to any one o'clock; location information based on the target point, is determined corresponding to the tracking target tracking template; corresponding to a target track based on the tracking template, the target tracking vision with a visual tracking algorithm is shown with the foot O
  2. 2.如权利要求1所述的目标跟踪方法,其特征在于,所述基于所述目标点的位置信息,确定所述跟踪目标对应的跟踪模板,包括: 基于所述目标点的位置信息,在所述画面中确定所述目标点; 在所述目标点周围生成多个备选跟踪模板; 基于显著性算法,分别对所述多个备选跟踪模板进行分析,并从所述多个备选跟踪模板中选出一最佳备选跟踪模板,其中,所述最佳备选跟踪模板即为所述跟踪目标对应的跟踪丰旲板。 2. A target tracking method according to claim 1, wherein the location-based information of the target point, determining the tracking template corresponding to the target track, comprising: a position information based on the target point, the the screen determining the target point; generating a plurality of alternative tracking template around the target point; significance based on the algorithm, each of the plurality of candidate templates trace analysis, and from the plurality of candidate selecting an optimum tracking template Alternatively tracking template, wherein the template that is the best alternative trace trace trace Dae abundance corresponding to a target plate.
  3. 3.如权利要求1或2所述的目标跟踪方法,其特征在于,在所述基于所述跟踪模板,利用视觉跟踪算法对所述跟踪目标进行视觉跟踪过程中,还包括: 控制所述电子设备对准所述目标点前进,其中,所述电子设备为可移动电子设备。 3. A target tracking method according to claim 1, wherein said template based on the tracking, the tracking algorithm with a visual target tracking vision tracking process, further comprising: controlling the electronic advancing device at the target point, wherein the electronic device is a mobile electronic device.
  4. 4.如权利要求3所述的目标跟踪方法,其特征在于,所述控制所述电子设备对准所述目标点前进,包括: 基于等式Picth = arctan(dy/f),确定所述目标点与所述画面的中心在竖直方向上的竖直偏离角;其中,Picth为所述竖直偏离角,f为所述摄像头的焦距,dy为所述目标点到所述摄像头光轴的垂直偏移量; 根据所述竖直偏离角,调整所述摄像头的俯仰角,以使所述目标点在竖直方向靠近所述画面的中心。 4. The target tracking method according to claim 3, characterized in that the control of the electronic device at the target point forward, comprising: based on the equation Picth = arctan (dy / f), determining the target the center point of the screen vertically off-angle in the vertical direction; wherein, Picth is the vertical deviation angle, f is the focal length of the camera, dy is the target point to the camera optical axis vertical offset; offset from the vertical angle, pitch angle adjustment of the camera according to the target point near the center of the screen in the vertical direction.
  5. 5.如权利要求3所述的目标跟踪方法,其特征在于,所述控制所述电子设备对准所述目标点前进,包括: 基于等式yaw = arctan(dx/f),确定所述目标点与所述画面的中心在水平方向上的水平偏移角;其中,yaw为所述水平偏移角,f为所述摄像头的焦距,dx为所述目标点到所述摄像头光轴的水平偏移量; 根据所述水平偏移角,确定所述电子设备的转动角速度; 基于所述转动角速度,控制所述电子设备转动,以使所述目标点在水平方向靠近所述画面的中心。 5. A target tracking method according to claim 3, characterized in that the control of the electronic device at the target point forward, comprising: based on the equation yaw = arctan (dx / f), determining the target the center point of the screen in the horizontal direction of the horizontal deviation angle; wherein, yaw angle to the horizontal offset, f is the focal length of the camera, dx is the target point to the camera optical axis horizontal offset; offset angle according to the level, determining a rotation angular velocity of the electronic device; center, based on the rotation angular velocity, the rotation control of the electronic device, so that the target point is close to the screen in the horizontal direction.
  6. 6.如权利要求3所述的目标跟踪方法,其特征在于,所述控制所述电子设备对准所述目标点前进,包括: 根据所述跟踪目标对应的跟踪模板在所述画面中的尺寸,确定所述电子设备的前进速度; 基于所述前进速度,控制所述电子设备向所述跟踪目标前进。 6. A target tracking method according to claim 3, characterized in that the control of the electronic device at the target point forward, comprising: a size of the target track corresponding to the screen template in accordance with the tracking determining the advance speed of the electronic device; advancing to the target track based on the forward speed, the electronic control device.
  7. 7.一种电子设备,所述电子设备具有一摄像头,其特征在于,所述电子设备,还包括: 发送单元,用于将所述摄像头采集到的图像数据发送给控制设备; 接收单元,用于接收所述控制设备发来的目标点的位置信息,其中,所述目标点为在所述控制设备通过显示屏输出所述图像数据的画面时用户在所述画面上选中的点,所述目标点为跟踪目标上的任一点; 确定单元,用于基于所述目标点的位置信息,确定所述跟踪目标对应的跟踪模板; 跟踪单元,用于基于所述跟踪目标对应的跟踪模板,利用视觉跟踪算法对所述跟踪目标进行视觉跟踪。 An electronic device, said electronic device having a camera, wherein said electronic device, further comprising: transmitting means for transmitting the image captured by the camera to the control device data; receiving means, with receiving position information sent from the control device of the target point, wherein the target point when the display screen of the control device by outputting the image data of the user on the screen of the selected point, the target point is any point on the target track; determining means, information based on a position of the target point is determined corresponding to the tracking target tracking template; tracking unit, corresponding to the target track based on the tracking template, visual tracking algorithm for tracking a tracking target visually.
  8. 8.如权利要求7所述的电子设备,其特征在于,所述确定单元,包括: 第一确定模块,用于基于所述目标点的位置信息,在所述画面中确定所述目标点; 生成模块,用于在所述目标点周围生成多个备选跟踪模板; 分析模块,用于基于显著性算法,分别对所述多个备选跟踪模板进行分析,并从所述多个备选跟踪模板中选出一最佳备选跟踪模板,其中,所述最佳备选跟踪模板即为所述跟踪目标对应的跟踪模板。 The electronic apparatus as claimed in claim 7, wherein the determining unit comprises: a first determining module, based on information of a position of the target point, the target point is determined in the picture; generating means for generating a plurality of alternative tracking template around the target point; analysis module for significance based algorithm on each of the plurality of candidate templates trace analysis, and from the plurality of candidate selecting an optimum tracking template Alternatively tracking template, wherein the template is the best alternative track corresponding to the tracking target tracking template.
  9. 9.如权利要求7或8所述的电子设备,其特征在于,所述电子设备,还包括: 控制单元,用于在所述基于所述跟踪模板,利用视觉跟踪算法对所述跟踪目标进行视觉跟踪过程中,控制所述电子设备对准所述目标点前进,其中,所述电子设备为可移动电子设备。 9. The electronic apparatus of claim 7 or claim 8, wherein said electronic apparatus further comprising: a control unit for performing the tracking of the tracking target based on the template, with a visual tracking algorithm visual tracking process, the electronic control device at the target point proceeds, wherein the electronic device is a mobile electronic device.
  10. 10.如权利要求9所述的电子设备,其特征在于,所述控制单元,包括: 第二确定模块,用于基于等式? 10. The electronic apparatus according to claim 9, wherein said control means comprises: a second determining module, based on the equation? :!^1:11 = 31'(^311((17/;0,确定所述目标点与所述画面的中心在竖直方向上的竖直偏离角;其中,PiCth为所述竖直偏离角,f为所述摄像头的焦距,dy为所述目标点到所述摄像头光轴的垂直偏移量; 调整模块,用于根据所述竖直偏离角,调整所述摄像头的俯仰角,以使所述目标点在竖直方向靠近所述画面的中心。 !: 1:11 = 31 ^ '(^ 311 ((17 /; 0, determining the target point and the center of the screen in the vertical direction of vertical deviation angle; wherein, PiCth is offset from the vertical angle, f is the focal length of the camera, dy is the target point to the camera optical axis vertical offset; adjusting module according to the vertical deviation angle, to adjust the pitch angle of the camera, to the target point near the center of the screen in the vertical direction.
  11. 11.如权利要求9所述的电子设备,其特征在于,所述控制单元,包括: 第三确定模块,用于基于等式yaw = arctan(dx/f),确定所述目标点与所述画面的中心在水平方向上的水平偏移角;其中,yaw为所述水平偏移角,f为所述摄像头的焦距,dx为所述目标点到所述摄像头光轴的水平偏移量; 第四确定模块,用于根据所述水平偏移角,确定所述电子设备的转动角速度; 第一控制模块,用于基于所述转动角速度,控制所述电子设备转动,以使所述目标点在水平方向靠近所述画面的中心。 11. The electronic device according to claim 9, wherein said control means comprises: a third determining module, based on the equation for the yaw = arctan (dx / f), determining the target point and the center of the screen in the horizontal direction of the horizontal deviation angle; wherein, yaw angle to the horizontal offset, f is the focal length of the camera, dx is the target point of the camera optical axis to the horizontal offset amount; fourth determining means for, according to the level of the offset angle, determining a rotation angular velocity of the electronic device; a first control module, based on the rotation angular velocity, the electronic control apparatus is rotated, so that the target point near the center of the screen in the horizontal direction.
  12. 12.如权利要求9所述的电子设备,其特征在于,所述控制单元,包括: 第五确定模块,用于根据所述跟踪目标对应的跟踪模板在所述画面中的尺寸,确定所述电子设备的前进速度; 第二控制模块,用于基于所述前进速度,控制所述电子设备向所述跟踪目标前进。 12. The electronic device according to claim 9, wherein said control means includes: fifth determining means for target tracking according to the tracking template size corresponding to the screen, determining the forward speed of the electronic device; a second control module based on the advancing speed, the electronic control apparatus proceeds to the tracked object.
CN 201610201474 2016-03-31 2016-03-31 Target tracking method and electronic equipment CN105931263A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201610201474 CN105931263A (en) 2016-03-31 2016-03-31 Target tracking method and electronic equipment

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN 201610201474 CN105931263A (en) 2016-03-31 2016-03-31 Target tracking method and electronic equipment
PCT/CN2017/079030 WO2017167282A1 (en) 2016-03-31 2017-03-31 Target tracking method, electronic device, and computer storage medium

Publications (1)

Publication Number Publication Date
CN105931263A true true CN105931263A (en) 2016-09-07

Family

ID=56840484

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201610201474 CN105931263A (en) 2016-03-31 2016-03-31 Target tracking method and electronic equipment

Country Status (2)

Country Link
CN (1) CN105931263A (en)
WO (1) WO2017167282A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106683123A (en) * 2016-10-31 2017-05-17 纳恩博(北京)科技有限公司 Method and device for tracking targets
CN106672345A (en) * 2016-12-30 2017-05-17 华南智能机器人创新研究院 Automatic sorting method and system of industrial robot
WO2017167282A1 (en) * 2016-03-31 2017-10-05 纳恩博(北京)科技有限公司 Target tracking method, electronic device, and computer storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102074016A (en) * 2009-11-24 2011-05-25 杭州海康威视软件有限公司 Device and method for automatically tracking motion target
CN102411368A (en) * 2011-07-22 2012-04-11 北京大学 Active vision human face tracking method and tracking system of robot
CN104700415A (en) * 2015-03-23 2015-06-10 华中科技大学 Method of selecting matching template in image matching tracking

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9305365B2 (en) * 2013-01-24 2016-04-05 Kineticor, Inc. Systems, devices, and methods for tracking moving targets
CN105931263A (en) * 2016-03-31 2016-09-07 纳恩博(北京)科技有限公司 Target tracking method and electronic equipment

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102074016A (en) * 2009-11-24 2011-05-25 杭州海康威视软件有限公司 Device and method for automatically tracking motion target
CN102411368A (en) * 2011-07-22 2012-04-11 北京大学 Active vision human face tracking method and tracking system of robot
CN104700415A (en) * 2015-03-23 2015-06-10 华中科技大学 Method of selecting matching template in image matching tracking

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘松松: "基于HRM特征提取和SVM的目标检测方法", 《理论与方法》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017167282A1 (en) * 2016-03-31 2017-10-05 纳恩博(北京)科技有限公司 Target tracking method, electronic device, and computer storage medium
CN106683123A (en) * 2016-10-31 2017-05-17 纳恩博(北京)科技有限公司 Method and device for tracking targets
CN106672345A (en) * 2016-12-30 2017-05-17 华南智能机器人创新研究院 Automatic sorting method and system of industrial robot

Also Published As

Publication number Publication date Type
WO2017167282A1 (en) 2017-10-05 application

Similar Documents

Publication Publication Date Title
US20120197464A1 (en) Interfacing with a mobile telepresence robot
US8860760B2 (en) Augmented reality (AR) system and method for tracking parts and visually cueing a user to identify and locate parts in a scene
Mur-Artal et al. Visual-inertial monocular SLAM with map reuse
US20100201808A1 (en) Camera based motion sensing system
Nikolic et al. A UAV system for inspection of industrial facilities
Ligorio et al. Extended Kalman filter-based methods for pose estimation using visual, inertial and magnetic sensors: Comparative analysis and performance evaluation
Schmid et al. Autonomous vision‐based micro air vehicle for indoor and outdoor navigation
US20160031559A1 (en) Systems and methods for target tracking
US20140118479A1 (en) Method, system, and computer program product for gamifying the process of obtaining panoramic images
Weiss Vision based navigation for micro helicopters
Wenzel et al. Low-cost visual tracking of a landing place and hovering flight control with a microcontroller
Wang et al. Online high-precision probabilistic localization of robotic fish using visual and inertial cues
US20140300704A1 (en) Automatic rectification of stereo imaging cameras
US20130156296A1 (en) Three Dimensional Gesture Recognition in Vehicles
US20140051513A1 (en) Interactive augmented reality using a self-propelled device
JP2003280813A (en) Pointing device, pointer controller, pointer control method and recording medium with the method recorded thereon
Fabian et al. Integrating the microsoft kinect with simulink: Real-time object tracking example
Dijkshoorn Simultaneous localization and mapping with the ar. drone
WO2013027628A1 (en) Information processing device, information processing method, and program
US20160148367A1 (en) Operating a computing device by detecting rounded objects in an image
US20100149337A1 (en) Controlling Robotic Motion of Camera
Heng et al. Self-calibration and visual slam with a multi-camera system on a micro aerial vehicle
US9086724B2 (en) Display control system, display control method, computer-readable storage medium having stored thereon display control program, and display control apparatus
US9129400B1 (en) Movement prediction for image capture
US20140226024A1 (en) Camera control in presence of latency

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination