CN102004548A - System and method of inputting information by using image collecting equipment - Google Patents

System and method of inputting information by using image collecting equipment Download PDF

Info

Publication number
CN102004548A
CN102004548A CN 201010550092 CN201010550092A CN102004548A CN 102004548 A CN102004548 A CN 102004548A CN 201010550092 CN201010550092 CN 201010550092 CN 201010550092 A CN201010550092 A CN 201010550092A CN 102004548 A CN102004548 A CN 102004548A
Authority
CN
China
Prior art keywords
motion vector
information
motion
input
direction
Prior art date
Application number
CN 201010550092
Other languages
Chinese (zh)
Other versions
CN102004548B (en
Inventor
高飞
Original Assignee
无锡中星微电子有限公司
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
Application filed by 无锡中星微电子有限公司 filed Critical 无锡中星微电子有限公司
Priority to CN 201010550092 priority Critical patent/CN102004548B/en
Publication of CN102004548A publication Critical patent/CN102004548A/en
Application granted granted Critical
Publication of CN102004548B publication Critical patent/CN102004548B/en

Links

Abstract

The invention provides system and method of inputting information by using image collecting equipment, wherein the method comprises the following steps: obtaining a motion vector of each block by dividing an image into blocks; carrying out length filtering to the obtained motion vector; obtaining main motion vectors of image motion; carrying out time de-noising on the main motion vectors, thus obtaining effective motion vectors; combining the effective motion vectors; and decoding the information of the vector combination by retrieving the corresponding relationship between input information stored by an information presentation storage unit and the vector combination so as to obtain the input information of the specific presentation.

Description

利用图像采集设备进行信息输入的系统及其方法 System and method for using an image acquisition device for information input

【技术领域】 TECHNICAL FIELD

[0001] 本发明涉及信息输入领域,特别是关于利用图像采集设备进行信息输入的系统及其方法。 [0001] The present invention relates to the field of input information, in particular information about the system and method using an input image acquisition device.

【背景技术】 【Background technique】

[0002] 现有的电子设备,以手机为例,进行信息输入的方式一种是键盘输入方式,另外一种是触摸屏输入方式。 [0002] The conventional electronic device, mobile phone as an example, the way the information input keyboard input mode, another mode is a touch screen input. 由于触摸屏输入方式符合人们的书写习惯,因此逐渐成为输入方式的主流。 Since the touch-screen input methods in line with people's writing habits, thus gradually become the mainstream input method.

[0003] 但现有的手写板和触摸屏,由于成本问题难以普及。 [0003] However, a conventional tablet and the touch screen, since the cost is difficult to spread. 而现有的手机中通常都包含摄像头,如果能利用摄像头代替手写板或者触摸屏来进行信息的输入则能够在很多地方提供便捷的输入。 The existing phones typically include a camera, if the camera instead of using the tablet or a touch screen to input information input can be provided in many places easily.

【发明内容】 [SUMMARY]

[0004] 本发明的目的在于提供一种利用图像采集设备进行信息输入的方法。 [0004] The object of the present invention is to provide a method for using an image acquisition device for information input.

[0005] 本发明的另一目的在于提供一种利用图像采集设备进行信息输入的系统。 [0005] Another object of the present invention is to provide an image acquisition system using the information input device.

[0006] 为达成前述目的,本发明一种利用图像采集设备进行信息输入的方法;其包括: [0006] To achieve the above object, the present invention provides a method of using information inputted image pickup apparatus; comprising:

[0007] 对图像进行分块获取每个分块的运动矢量; [0007] The image acquisition block motion vector of each block;

[0008] 对获取的运动矢量进行长度滤波; [0008] The motion vectors obtained by filtering the length;

[0009] 获取图像运动的主要运动矢量; [0009] The main moving image acquired motion vector;

[0010] 对主要运动矢量进行时间去噪,获取有效的运动矢量; [0010] The main time denoising motion vectors, to obtain a valid motion vector;

[0011] 对所述有效运动矢量进行信息的译码获取其具体表征的输入信息。 [0011] The input information of the valid motion vector decoding information acquired specific representation.

[0012] 进一步地,在进行输入信息检测之前还包括首先定义输入信息的起始和终止时间段的步骤。 Before [0012] Further, the input information is detected during the first defining step further comprises the starting and ending time information input.

[0013] 进一步地,所述对获取的运动矢量进行长度滤波包括:设定运动矢量阀值,小于运动矢量阀值的运动矢量判断为扰动,滤除判断为扰动的运动矢量。 [0013] Further, the length of said filtering comprises motion vector obtained: setting the motion vector threshold value, the motion vector is less than the threshold value is determined disturbance, filtering out the motion vector is determined disturbance.

[0014] 进一步地,所述获取图像运动的主要运动矢量包括:对长度滤波后的运动矢量的方向建立直方图,横轴表征方向,纵轴表征该方向运动矢量的个数;获取直方图的峰值,该峰值的方向表示当前图像中目标运动的方向,该方向的运动矢量为主要运动矢量。 [0014] Furthermore, the acquisition of primary motion vector of the motion picture comprising: a motion vector for establishing the length of the filtered histogram, the horizontal axis represents the direction, the direction of the vertical axis represents the number of motion vectors; obtaining histograms peak, the peak direction indicates the direction of motion of the current object in the image, the motion vector of the direction of the main motion vectors.

[0015] 进一步地,所述对主要运动矢量进行时间去噪,获取有效的运动矢量包括:设定运动矢量的时间阀值,连续存在时间小于时间阀值的运动矢量判断为扰动,连续存在时间大于所述时间阀值的运动矢量的运动方向为有效运动方向。 [0015] Further, the main time denoising motion vector, to obtain a valid motion vector comprising: a motion vector set threshold time, continuous presence time is less than the time threshold is determined motion vector perturbation, continuous presence time the direction of motion of the motion vector is greater than a time threshold as an active movement direction.

[0016] 进一步地,对所述有效运动矢量进行信息的译码包括:通过调取信息表征存储单元存储的输入信息和运动矢量的对应关系确定运动矢量具体表征的输入信息。 Coding [0016] Furthermore, the effective motion vector information comprises: a correspondence relationship storage unit stores characterized by the input information and the retrieved information to determine the motion vector characterizing a motion vector of the specific input information.

[0017] 进一步地,如果输入时间段内有多个有效运动矢量,对多个有效运动矢量按时间顺序排列形成有效运动矢量组合,前述信息表征存储单元存储的为输入信息和运动矢量组合的对应关系。 [0017] Further, if the input period has a plurality of motion vectors efficiently, motion vectors for the plurality of effective chronological order to form an effective combination of the motion vector, the information stored in the storage unit for the characterization of the input information and the motion vector corresponding to a combination of relationship. [0018] 为达成前述另一目的,本发明一种利用图像采集设备进行信息输入的系统,其包括: [0018] To achieve the above another object, the present invention utilizing an image acquisition device for information input system, comprising:

[0019] 运动估计单元,其用于对图像中分块进行运动搜索获取运动矢量; [0019] The motion estimation unit for image acquisition equatorial blocks motion search motion vector;

[0020] 长度滤波单元,用于对运动估计单元获取的运动矢量进行长度滤波排除扰动; [0020] The length of the filter unit, the motion estimation unit configured to acquire motion vectors for filtering negative perturbation length;

[0021] 主要运动矢量计算单元,用于计算当前图像的运动目标的主要运动矢量; [0021] The main motion vector calculation unit for calculating a current motion vector of the main moving target image;

[0022] 时间滤波单元,用于对所述主要运动矢量进行时间上的去噪,最终获取有效的运 [0022] Time filtering means for performing denoising of time on the primary motion vector, obtaining the final effective operation

动矢量; Motion vectors;

[0023] 运动矢量译码单元,用于对所述有效运动矢量进行信息译码获取其具体表征的输入fe息。 [0023] The motion vector coding unit for coding information acquiring specific information characterizing the input fe effective motion vector.

[0024] 进一步地,所述系统还包括输入片断确定单元,用于定义输入信息的起始和终止时间段。 [0024] Preferably, the system further comprises an input segment determination unit for inputting information and define the starting period terminates.

[0025] 进一步地,长度滤波单元设定运动矢量阀值,小于运动矢量阀值的运动矢量判断为扰动,滤除判断为扰动的运动矢量。 [0025] Further, the filtering unit sets the motion vector length threshold value, the motion vector is less than the threshold value it determines that the motion vector perturbation, filtered motion vector is determined disturbance.

[0026] 进一步地,主要运动矢量计算单元对长度滤波单元长度滤波后的运动矢量的方向建立直方图,横轴表征方向,纵轴表征该方向运动矢量的个数;然后获取直方图的峰值,该峰值的方向表示当前图像中目标运动的方向,该方向的运动矢量为主要运动矢量。 [0026] Further, the primary motion vector calculation unit direction vectors establish the length of the length of the filtering unit filtering the histogram, the horizontal axis represents the direction, the direction of the vertical axis represents the number of motion vectors; then obtaining the histogram peak, the direction of the peak indicates the direction of motion of the current object in the image, the motion vector of the direction of the main motion vectors.

[0027] 进一步地,所述时间滤波单元设定运动矢量的时间阀值,连续存在时间小于时间阀值的运动矢量判断为扰动,连续存在时间大于所述时间阀值的运动矢量的运动方向为有效运动方向。 [0027] Furthermore, the time filtering unit setting a motion vector threshold time, continuous presence time is less than the time threshold is determined motion vector perturbation, there is a time greater than the continuous motion vector direction threshold of the time effective direction of movement.

[0028] 进一步地,所述运动矢量译码单元还包括一个存储运动矢量和对应信息表征的存储单元,通过调取信息表征存储单元存储的输入信息和运动矢量的对应关系确定运动矢量具体表征的输入信息。 [0028] Further, the motion vector coding unit further comprises a storage unit storing the motion vector and characterized correspondence information, a motion vector is determined by the transfer of information that indicates a correspondence relationship storage unit stores the input information and the motion vector of the specific representation Enter information.

[0029] 所述系统进一步包括一个有效组合单元,当输入时间段内有多个有效运动矢量时,所述有效组合单元对多个有效运动矢量按时间顺序排列形成有效运动矢量组合,前述信息表征存储单元存储的为输入信息和运动矢量组合的对应关系。 [0029] The system further comprises an effective combination unit, when a plurality of effective period of the input motion vectors, the effective combination of a plurality of unit effective motion vectors in chronological order to form an effective combination of the motion vector, the information characterized by storage means for storing correspondence relationship between the input information and the motion vector combinations.

[0030] 本发明的利用图像采集设备进行信息输入的系统及其方法,利用图像采集设备采集运动图像,并对图像进行分块,分别获取每一分块的运动矢量,然后对运动矢量进行长度滤波、获取主运动矢量以及进行时间滤波获取有效运动矢量,再利用预先存储的运动矢量与输入信息的对应关系获得运动矢量表示的输入信息,从而实现利用图像采集设备即可实现信息的输入,可以代替手写板或触摸屏实现信息输入,能够降低产品成本。 [0030] With the image pickup apparatus of the present invention is an information input system and method, the image acquisition device using the moving image capture, and image block, the motion vectors are acquired for each sub-block, then the motion vector length filtering, motion vector, and obtaining the master time acquisition effective filtering motion vectors, then motion vector with the corresponding relationship between the input information stored in advance to obtain the input information indicated by the motion vector, thereby achieving image capture device can be realized by using input information, can be Instead of tablet or touch screen enables inputting product cost can be reduced.

【附图说明】 BRIEF DESCRIPTION

[0031] 图1是利用图像采集设备进行信息输入的方法的流程示意图。 [0031] FIG. 1 is a schematic flow diagram of a method of using an image acquisition device for information input.

[0032] 图2是利用图像采集设备进行信息输入的系统的结构框图。 [0032] FIG. 2 is a block diagram showing a configuration using an image acquisition device for information input system.

【具体实施方式】 【Detailed ways】

[0033] 此处所称的“一个实施例”或“实施例”是指可包含于本发明至少一个实现方式中的特定特征、结构或特性。 [0033] referred to herein to "one embodiment" or "an embodiment" means that a particular feature may be included in the present invention, at least one implementation, structure, or characteristic. 在本说明书中不同地方出现的“在一个实施例中”并非均指同一个实施例,也不是单独的或选择性的与其他实施例互相排斥的实施例。 In various places in the present specification, "in one embodiment" we are not referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments of the embodiment. 此外,表示一个或多个实施例的方法、流程图或功能框图中的单元顺序并非固定的指代任何特定顺序,也不构成对本发明的限制。 Further, means one or more embodiments of the method, the order of units in the flowcharts or diagrams are not inherently indicate any particular order nor limit the present invention.

[0034] 本发明是关于向电子设备,例如手机、PDA或平板电脑等进行信息输入的系统和方法,其中这些电子设备中均配备有图像采集设备,例如摄像头。 [0034] The present invention relates to a system and method for information input to the electronic device, such as mobile phones, PDA or a tablet computer, wherein the electronic devices are equipped with image capture devices such as cameras. 下面将以手机为例,以向手机内输入中文汉字信息为具体实例对本发明的系统和方方进行说明。 Here an example will be a mobile phone, to input the Chinese character information into the mobile phone as a specific example of the system of the present invention and the square will be described.

[0035] 因为有的汉字可能只有一个笔画,而有的汉字笔画比较多,对于多笔画的汉字可以将汉字拆解成不同笔画进行输入信息检测,然后将各笔画组合成一个完整的汉字。 [0035] Because some characters may be a stroke, while others are more strokes of Chinese characters, for the multi-stroke kanji may be disassembled into different input stroke information detection, and the combinations of characters into a complete stroke. 单笔画的汉字作为多笔画汉字的一个特例。 Single strokes of Chinese characters as a special case of multi-stroke characters. 下面以输入的信息为多个笔画的汉字为例对本发明的信息输入系统和方法进行说明。 The following input information to a plurality of strokes of Chinese characters as an example of information input system and method of the present invention will be described.

[0036] 请参阅图1所示,其显示本发明的利用摄像头进行信息输入的方法的流程图,其中输入的信息为多笔画的汉字。 [0036] Please refer to FIG. 1, a flowchart of a method of inputting information using the camera of the present invention showing, wherein the input information is multi-stroke characters. 如图1所示,本发明的利用摄像头进行信息输入的方法其包括: 1, the information input using the camera of the present invention is a method comprising:

[0037] 步骤Sll :在向手机内输入信息时,首先需要定义一次进行输入信息检测的输入时间,也可以称为定义输入片断,在输入片断内进行输入信息的检测。 [0037] Step Sll: when entering information into the phone, you first need to define the time for the detected input time information, may also be referred to define the input clip, for detecting input information in the input segment. 在定义输入片断时可以是设定某个按键按下到弹起的时间,也可以是直接定义一次输入的时间。 When the input segment may be set to define a key is pressed to bounce time, or may be directly input a defined time. 在输入片断定义的时间内完成的输入才是一个输入信息,如果定义的输入时间片断还未结束,则可以继续输入笔画,在输入片断定义的时间结束之后才进行输入信息的最终判断。 Completed in the time entry is a fragment defined input information input, if the input clip defined time has not been completed, you can continue to enter strokes before the final judgment entered information after the end of the input clip defined period of time.

[0038] 步骤S12 :在输入片断内,摄像头采集输入的图像,例如是通过手指运动进行汉字的书写,则摄像头采集手指运动的图像,对图像进行分块进行运动估计,获取每一个分块的运动矢量。 [0038] Step S12: in the input clip, the camera image acquisition input, for example, to write characters by finger movement, the camera image acquisition finger movement, the image block motion estimation, obtaining for each block of motion vector. 关于视频图像中运动检测的技术可以采用现有的各种运动检测的方法,例如帧间差分法、背景相减法、统计平均法、中值滤波器法等等,关于运动检测的方法的具体原理及内容本说明书不再一一列举详细说明。 About video image motion detection techniques may be of various conventional motion detection method using, for example, inter-frame difference, background subtraction, the statistical average, median filter method and the like, particularly relates to a method of motion detection principle of The present specification and will not be enumerated in detail.

[0039] 步骤S13 :对获取的运动矢量进行长度滤波。 [0039] Step S13: obtaining the motion vector length is filtered. 因为在输入过程中可能有时候是操作者并未进行输入动作,而是一些扰动因素被摄像头捕捉到,例如手指的弯曲或者抖动等其他小动作。 Since in the input process may sometimes be an operator input operation is not performed, but a number of other tricks disturbance factors are captured by the camera, such as a finger is bent or jitter. 为避免这些扰动因素对输入信息的干扰,可以设置一个运动矢量长度的阀值, 当运动矢量的长度大于该长度阀值时才认为是操作者在进行信息输入,如果运动矢量的长度小于该长度阀值,则认为该运动矢量是扰动,滤除该运动矢量。 To avoid these disturbance factors interfere with the input information may be provided a motion vector length threshold, only when the length of the motion vector is greater than the length threshold that an operator performing the information input, if the length of the motion vector is smaller than the length threshold is considered the motion vector is disturbing, to filter out the motion vector.

[0040] 步骤S14 :获取图像运动的主要运动矢量。 [0040] Step S14: acquiring image motion vector of the primary motion. 对经过长度滤波之后的运动矢量的方向建立直方图,横轴表征方向,纵轴表征该方向运动矢量的个数;获取直方图的峰值,该峰值的方向表示当前图像中目标运动的方向,该方向的运动矢量为主要运动矢量。 Establishing a histogram, the horizontal axis represents the direction through the motion vector length after filtering, the vertical axis represents the number of the motion vector; obtaining a histogram peak, the peak direction represents the direction of motion of the current object in the image, the motion vector direction of the main motion vectors.

[0041] 步骤S15 :对主要运动矢量进行时间去噪,获取有效的运动矢量。 [0041] Step S15: The main time denoising motion vectors, to obtain a valid motion vector. 因为有些运动矢量虽然长度满足长度的阀值,但有可能是操作者的误操作,比如手指从摄像头前偶然的滑动,可能运动矢量也很长。 Because some of the motion vector meet the threshold length although the length, but there may be an erroneous operation of the operator, such as sliding the finger from the front of the camera by chance, the motion vector may be very long. 为确定确实是操作者在输入信息,可以设定运动矢量的存在时间阀值,当运动矢量的存在时间小于该预定的时间阀值时,判断该运动矢量为扰动,对其进行滤波去除,当运动矢量的连续存在时间超过该预定的时间阀值时判断该运动矢量的运动方向为有效运动方向,该运动矢量为有效运动矢量。 To determine indeed the operator to input information, there is a time threshold may be set motion vector, when the motion vector is present in less than the predetermined time threshold value, determining that the motion vector perturbation, filters it is removed, when Analyzing motion vector exists continuously for more than a predetermined time threshold of the motion direction of the motion vector for the effective direction of movement, the motion vector is a motion vector is valid.

[0042] 步骤S16 :对各有效运动矢量进行组合。 [0042] Step S16: combining the motion vector for each valid. 因为每一笔画对应一个运动矢量,为表示整个汉字,需要对各有效运动矢量进行组合,例如对多个有效运动矢量按时间顺序排列形成有效运动矢量组合。 Since each stroke corresponds to a motion vector representing the entire Chinese character, the need for effective combination for each motion vector, for example, a plurality of valid motion vectors in chronological order to form an effective combination of a motion vector. [0043] 步骤S17 :对输入的有效运动矢量组合进行译码。 [0043] Step S17: the motion vector decoding valid input combinations. 可以提前预先设定输入信息(例如汉字输入的笔画)与运动矢量组合的对应关系,在对运动矢量组合进行译码时,通过调取预先存储的输入信息和运动矢量组合的对应关系确定运动矢量组合具体表征的输入信肩、ο Can input information set in advance in advance (e.g. Chinese character strokes entered) correspondence between a combination of motion vector, when the motion vector decoded in combination, the correspondence relationship stored in advance by the transfer of input information and determining the motion vector of the motion vector is a combination of combination of input signals characterized shoulder particular, ο

[0044] 对于单笔画的汉字的输入可以将运动矢量组合的步骤看作是单个笔画自己的组合,也可以理解为不需要进行运动矢量组合,相应地,预先设定的输入信息是与运动矢量的对应关系,在对运动矢量进行译码时,通过调取预先存储的输入信息和运动矢量的对应关系确定运动矢量具体表征的输入信息。 [0044] For a single-stroke input Chinese characters can be considered as a combined step of the motion vector is a combination of a single stroke of its own, can be understood as the combination does not require a motion vector, respectively, the input information is set in advance the motion vector correspondence between motion vector when decoding the correspondence relationship between the input information and the retrieved motion vectors by the motion vector stored in advance to determine the specific information characterizing input.

[0045] 请参阅图2所示,其显示本发明的利用图像采集设备进行信息输入的系统1的一个实施例的结构框图。 [0045] Please refer to FIG. 2, which shows the use of the image pickup apparatus of the present invention is a block diagram showing an embodiment of information input system. 如图2所示,本发明的利用图像采集设备进行信息输入的系统1其包括运动估计单元11、长度滤波单元12、主要运动矢量计算单元13、时间滤波单元14、有效组合单元15以及组合译码单元16。 As shown, the information input apparatus using an image acquisition system of the present invention which includes a motion estimation unit 11, the length of the filter unit 12, the motion vector calculation is mainly 13, 14, combining unit 15, and an effective combination of translation unit time filtering unit 2 code unit 16.

[0046] 运动估计单元11,其用于对图像中分块进行运动搜索获取运动矢量。 [0046] The motion estimation unit 11, an image for which the equatorial blocks motion search motion vector is acquired. 在一个实施例中,例如是通过手指运动进行汉字的书写,则摄像头采集手指运动的图像,运动估计单元11对图像进行分块进行运动估计,获取每一个分块的运动矢量。 In one embodiment, for example, to write characters by finger movement, the camera capture an image of the finger movement, the motion estimation unit 11 divides the image block motion estimation, a block of each acquired motion vector. 关于视频图像中运动检测的技术可以采用现有的各种运动检测的方法,例如帧间差分法、背景相减法、统计平均法、 中值滤波器法等等,关于运动检测的方法的具体原理及内容本说明书不再一一列举详细说明。 About video image motion detection techniques may be of various conventional motion detection method using, for example, inter-frame difference, background subtraction, the statistical average, median filter method and the like, particularly relates to a method of motion detection principle of The present specification and will not be enumerated in detail.

[0047] 长度滤波单元12,用于对运动估计单元11获取的运动矢量进行长度滤波排除扰动。 [0047] The length of the filter unit 12, a unit 11 acquires the length of the filter to exclude the motion vectors of the motion estimation disturbance. 因为在输入过程中可能有时候是操作者并未进行输入动作,而是一些扰动因素被摄像头捕捉到,例如手指的弯曲或者抖动等其他小动作。 Since in the input process may sometimes be an operator input operation is not performed, but a number of other tricks disturbance factors are captured by the camera, such as a finger is bent or jitter. 为避免这些扰动因素对输入信息的干扰,可以设置一个运动矢量长度的阀值,当运动矢量的长度大于该长度阀值时才认为是操作者在进行信息输入,如果运动矢量的长度小于该长度阀值,则认为该运动矢量是扰动,滤除该运动矢量。 To avoid these disturbance factors interfere with the input information may be provided a motion vector length threshold, only when the length of the motion vector is greater than the length threshold that an operator performing the information input, if the length of the motion vector is smaller than the length threshold is considered the motion vector is disturbing, to filter out the motion vector.

[0048] 主要运动矢量计算单元13,用于计算当前图像的运动目标的主要运动矢量。 [0048] The main motion vector calculating unit 13 for calculating a current motion vector of the main moving target image. 主要运动矢量计算单元13对经过长度滤波单元12长度滤波之后的运动矢量的方向建立直方图,横轴表征方向,纵轴表征该方向运动矢量的个数;然后获取直方图的峰值,该峰值的方向就表示当前图像中目标运动的方向,该方向的运动矢量为主要运动矢量。 The main motion vector calculation unit 13 after establishment of the motion vector length of the filtering unit 12 after the filter length histogram, the horizontal axis represents the direction of the vertical axis represents the number of direction vectors; then obtaining the histogram peak, the peak It indicates a direction to the target direction of motion of the current image, the motion vector of the direction of the main motion vectors.

[0049] 时间滤波单元14,用于对所述主要运动矢量计算单元13计算出的主要运动矢量进行时间上的去噪,最终获取有效的运动矢量。 [0049] The temporal filtering unit 14 for de-noising the time of the primary motion vector calculation unit 13 calculates the motion vector of the main, to obtain a valid final motion vector. 因为有些运动矢量虽然长度满足长度的阀值,但有可能是操作者的误操作,比如手指从摄像头前偶然的滑动,可能运动矢量也很长。 Because some of the motion vector meet the threshold length although the length, but there may be an erroneous operation of the operator, such as sliding the finger from the front of the camera by chance, the motion vector may be very long. 为确定确实是操作者在输入信息,可以设定运动矢量的存在时间阀值,当运动矢量的存在时间小于该预定的时间阀值时,判断该运动矢量为扰动,对其进行滤波去除,当运动矢量的连续存在时间超过该预定的时间阀值时判断该运动矢量的运动方向为有效运动方向,该运动矢量为有效运动矢量。 To determine indeed the operator to input information, there is a time threshold may be set motion vector, when the motion vector is present in less than the predetermined time threshold value, determining that the motion vector perturbation, filters it is removed, when Analyzing motion vector exists continuously for more than a predetermined time threshold of the motion direction of the motion vector for the effective direction of movement, the motion vector is a motion vector is valid.

[0050] 有效组合单元15,在本实施例中输入信息是多笔画的汉字输入,每一个笔画对应一个有效运动矢量,当输入时间段内有多个有效运动矢量时,所述有效组合单元15对多个有效运动矢量按时间顺序排列形成有效运动矢量组合。 [0050] Effective combination unit 15, in the present embodiment, the input information is a character input multiple strokes, each stroke corresponds to a valid motion vectors, when a plurality of effective period of the input motion vectors, the active combination unit 15 a plurality of motion vectors for effective chronological form an effective combination of a motion vector.

[0051] 组合译码单元16用于对前述有效组合单元15组合后的有效运动矢量组合进行译码,获取其具体表征的输入信息。 [0051] composition information coding unit 16 for inputting a combination of motion vectors of the valid combinations of the active combination unit 15 decodes the acquired specific representation. 在组合译码单元16内包括一个存储运动矢量组合和对应信息表征的存储单元161,在译码时,组合译码单元16调取存储单元161内储存的运动矢量和对应信息表征的对应关系,则可以获取该运动矢量组合具体表征的输入信息。 In the combination of the decoding unit 16 comprises a combination of a motion vector storage unit 161 stores correspondence information, and characterized, in decoding, the decoding unit 16 in combination retrieved motion vector stored in the storage unit 161 and the correspondence relationship characterized correspondence information, the input information can be acquired motion vector characterized particular combination.

[0052] 在前述实施例中是包含有效组合单元,将多笔画组合成一个汉字,如果是单笔画汉字,可以看作是有效组合单元的特例,只对一个笔画进行组合或者理解为不需要该有效组合单元。 [0052] In the foregoing embodiment, the combination comprising an effective unit, combined into a multi-stroke characters, if single stroke characters, can be considered as a special case of an effective combination unit, only one or combination of stroke is understood to be unnecessary for the effective combination unit.

[0053] 在本发明的实施例中,其还可以包括一个输入片断定义单元(未图示),用来定义每次输入的起始和终止的时间段。 [0053] In an embodiment of the present invention may further comprise a clip defined input unit (not shown), it is used to define the start time and the termination of each entry. 在输入片断定义的时间内完成的输入才是一个输入信息,超过该时间的输入则无法记入本次输入,如果没有输完,则需要重新输入。 Completed in the time entry is a fragment defined input input information, than the time of input can not be credited to this input, if no losers, you will need to re-enter.

[0054] 上述说明已经充分揭露了本发明的具体实施方式。 [0054] The above description has been fully disclosed specific embodiments of the present invention. 需要指出的是,熟悉该领域的技术人员对本发明的具体实施方式所做的任何改动均不脱离本发明的权利要求书的范围。 It should be noted that any changes to the art skilled in the art the specific embodiments of the invention made without departing from the scope of the invention as claimed in claims. 相应地,本发明的权利要求的范围也并不仅仅局限于前述具体实施方式。 Accordingly, the present invention requires the claimed scope is not limited to the foregoing detailed description.

Claims (14)

1. 一种利用图像采集设备进行信息输入的方法;其包括: 对图像进行分块获取每个分块的运动矢量;对获取的运动矢量进行长度滤波;获取图像运动的主要运动矢量;对主要运动矢量进行时间去噪,获取有效的运动矢量;对所述有效运动矢量进行信息的译码获取其具体表征的输入信息。 1. A method of using the image capture information input apparatus; comprising: obtaining the image block motion vector for each block; the motion vector is acquired filter length; main motion vectors acquired image motion; major time denoising motion vector, the motion vector to obtain valid; the decoded information of the motion vector obtaining effective specific input information representation.
2.如权利要求1所述的利用图像采集设备进行信息输入的方法,其特征在于:在进行输入信息检测之前还包括首先定义输入信息的起始和终止时间段的步骤。 2. The use of the image pickup apparatus as claimed in claim 1, an information input method, which is characterized in that: further comprising a first detecting input information prior to the step of defining the starting and ending time information input.
3.如权利要求1所述的利用图像采集设备进行信息输入的方法,其特征在于:所述对获取的运动矢量进行长度滤波包括:设定运动矢量长度阀值,小于运动矢量长度阀值的运动矢量判断为扰动,滤除判断为扰动的运动矢量。 3. The use of the image pickup apparatus as claimed in claim 1, an information input method, which is characterized in that: said motion vectors for filtering the acquired length comprising: setting a motion vector length threshold is less than the motion vector length threshold motion vector is determined disturbance, filtering out the motion vector is determined disturbance.
4.如权利要求1所述的利用图像采集设备进行信息输入的方法,其特征在于:所述获取图像运动的主要运动矢量包括:对长度滤波后的运动矢量的方向建立直方图,横轴表征方向,纵轴表征该方向运动矢量的个数;获取直方图的峰值,该峰值的方向表示当前图像中目标运动的方向,该方向的运动矢量为主要运动矢量。 4. The use of the image pickup apparatus as claimed in claim 1, an information input method, which is characterized in that: said acquiring primary motion vector of the motion picture comprising: establishing a histogram, the horizontal axis represents the direction of the motion vector length filter direction, the vertical axis represents the number of the motion vector; acquiring histogram peak, the peak direction indicates the direction of motion of the current object in the image, the motion vector of the direction of the main motion vectors.
5.如权利要求1所述的利用图像采集设备进行信息输入的方法,其特征在于:所述对主要运动矢量进行时间去噪,获取有效的运动矢量包括:设定运动矢量的时间阀值,所述主要运动矢量连续存在时间小于时间阀值的运动矢量判断为扰动,所述主要运动矢量连续存在时间大于所述时间阀值的运动矢量的运动方向为有效运动方向。 5. The use of the image pickup apparatus as claimed in claim 1, an information input method, which is characterized in that: said main time denoising motion vectors, to obtain a valid motion vector comprising: a motion vector set time threshold, continuous presence of the primary motion vector is less than the time threshold is determined motion vector perturbation, the primary motion vector is greater than the continuous presence time of the motion vector direction threshold time valid direction of movement.
6.如权利要求1所述的利用图像采集设备进行信息输入的方法,其特征在于:对所述有效运动矢量进行信息的译码包括:预先设定每一输入信息和运动矢量的对应关系,将其储存于信息表征存储单元内,通过调取预先存储的输入信息和运动矢量的对应关系确定运动矢量具体表征的输入信息。 6. The image pickup apparatus using the method of claim 1, wherein the input information, wherein: the decoded information of the valid motion vectors comprising: a corresponding relationship set in advance for each input information and the motion vector, the information which is stored in the storage unit characterized correspondence relationship between the input information and the retrieved motion vector by the input information stored in advance to determine the motion vector specific characterization.
7.如权利要求6所述的利用图像采集设备进行信息输入的方法,其特征在于:如果输入时间段内有多个有效运动矢量,对多个有效运动矢量按时间顺序排列形成有效运动矢量组合,前述信息表征存储单元存储的为输入信息和运动矢量组合的对应关系。 7. The image pickup apparatus using the method of claim 6, wherein the input information, wherein: if the input period has a plurality of motion vectors efficiently, motion vectors for the plurality of effective chronological order to form an effective combination of motion vectors , characterizing the information storage unit for storing the input information and the motion vector cOMBINATIONS.
8. 一种利用图像采集设备进行信息输入的系统,其包括:运动估计单元,其用于对图像中分块进行运动搜索获取运动矢量; 长度滤波单元,用于对运动估计单元获取的运动矢量进行长度滤波排除扰动; 主要运动矢量计算单元,用于计算当前图像的运动目标的主要运动矢量; 时间滤波单元,用于对所述主要运动矢量进行时间上的去噪,最终获取有效的运动矢量;运动矢量译码单元,用于对所述有效运动矢量进行信息译码获取其具体表征的输入信息。 An image pickup apparatus using an information input system, comprising: a motion estimation unit for image acquisition equatorial blocks motion search motion vector; length filtering unit for motion estimation unit obtaining motion vectors filtering the length negative disturbance; main motion vector calculation unit for calculating a current motion vector of the main moving target image; time filtering unit for the primary motion vector of the temporal denoising, the final motion vector acquired effective ; motion vector decoding unit for decoding said motion vector information decoded efficiently obtain specific information characterizing input.
9.如权利要求8所述的利用图像采集设备进行信息输入的系统,其特征在于:其还包括输入片断确定单元,用于定义输入信息的起始和终止时间段。 9. The use of the image pickup apparatus as claimed in claim 8, an information input system, characterized in that: it further comprises a start and stop time input segment determining means, for defining the input information.
10.如权利要求8所述的利用图像采集设备进行信息输入的系统,其特征在于:长度滤波单元设定运动矢量长度阀值,小于运动矢量长度阀值的运动矢量判断为扰动,滤除判断为扰动的运动矢量。 10. The use of the image pickup apparatus as claimed in claim 8, the input system information, wherein: the filtering unit length motion vector length threshold is set, the motion vector is less than the threshold value is determined as the motion vector length disturbance, filtered Analyzing motion vector perturbation.
11.如权利要求8所述的利用图像采集设备进行信息输入的系统,其特征在于:主要运动矢量计算单元对长度滤波后的运动矢量的方向建立直方图,横轴表征方向,纵轴表征该方向运动矢量的个数;获取直方图的峰值,该峰值的方向表示当前图像中目标运动的方向, 该方向的运动矢量为主要运动矢量。 11 using image acquisition apparatus according to claim 8, wherein the input system information, wherein: the main motion vector calculation unit to establish a histogram, the horizontal axis represents the direction of the motion vector length of the filter, the vertical axis represents the the number of directions of motion vectors; obtaining the histogram peak, the peak direction indicates the direction of motion of the current object in the image, the motion vector of the direction of the main motion vectors.
12.如权利要求8所述的利用图像采集设备进行信息输入的系统,其特征在于:所述时间滤波单元设定运动矢量的时间阀值,主运动矢量连续存在时间小于时间阀值的运动矢量判断为扰动,主运动矢量连续存在时间大于所述时间阀值的运动矢量的运动方向为有效运动方向。 12. The use of the image pickup apparatus as claimed in claim 8, the input system information, wherein: said filtering unit time motion vector set time threshold, the threshold time less than the time of the primary motion vector of the motion vectors exist continuously disturbance is determined, the motion vector of the main direction of continuous motion of the motion vector is longer than the time threshold is present in an effective direction of movement.
13.如权利要求8所述的利用图像采集设备进行信息输入的系统,其特征在于:所述运动矢量译码单元还包括一个存储运动矢量和对应输入信息的存储单元,通过调取信息表征存储单元存储的输入信息和运动矢量的对应关系确定运动矢量具体表征的输入信息。 13. The use of the image pickup apparatus as claimed in claim 8, the input system information, wherein: the motion vector coding unit further includes a storage unit storing a motion vector corresponding to the input information and, characterized by the transfer of information storage means for storing correspondence relationship between the input information and the motion vector of the motion vector is determined characterizing the specific input information.
14.如权利要求13所述的利用图像采集设备进行信息输入的系统,其特征在于:其进一步包括一个有效组合单元,当输入时间段内有多个有效运动矢量时,所述有效组合单元对多个有效运动矢量按时间顺序排列形成有效运动矢量组合,前述信息表征存储单元存储的为输入信息和运动矢量组合的对应关系。 14. The use of the image pickup apparatus as claimed in claim 13, an information input system, characterized in that: it further comprises an effective combination unit, when a plurality of effective period of the input motion vectors, a combination of the active unit a plurality of valid motion vectors in chronological order to form an effective combination of the motion vector, the information stored in the storage unit for the characterization of the input information and the motion vector cOMBINATIONS.
CN 201010550092 2010-11-18 2010-11-18 System and method of inputting information by using image collecting equipment CN102004548B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201010550092 CN102004548B (en) 2010-11-18 2010-11-18 System and method of inputting information by using image collecting equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201010550092 CN102004548B (en) 2010-11-18 2010-11-18 System and method of inputting information by using image collecting equipment

Publications (2)

Publication Number Publication Date
CN102004548A true CN102004548A (en) 2011-04-06
CN102004548B CN102004548B (en) 2013-02-13

Family

ID=43811952

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201010550092 CN102004548B (en) 2010-11-18 2010-11-18 System and method of inputting information by using image collecting equipment

Country Status (1)

Country Link
CN (1) CN102004548B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5113452A (en) * 1988-08-23 1992-05-12 Sony Corporation Hand-written character recognition apparatus and method
JPH09102013A (en) * 1995-10-04 1997-04-15 Nec Corp Handwriting character/graphic reader
CN1881994A (en) * 2006-05-18 2006-12-20 北京中星微电子有限公司 Method and apparatus for hand-written input and gesture recognition of mobile apparatus
CN101539994A (en) * 2009-04-16 2009-09-23 西安交通大学 Mutually translating system and method of sign language and speech

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5113452A (en) * 1988-08-23 1992-05-12 Sony Corporation Hand-written character recognition apparatus and method
JPH09102013A (en) * 1995-10-04 1997-04-15 Nec Corp Handwriting character/graphic reader
CN1881994A (en) * 2006-05-18 2006-12-20 北京中星微电子有限公司 Method and apparatus for hand-written input and gesture recognition of mobile apparatus
CN101539994A (en) * 2009-04-16 2009-09-23 西安交通大学 Mutually translating system and method of sign language and speech

Also Published As

Publication number Publication date
CN102004548B (en) 2013-02-13

Similar Documents

Publication Publication Date Title
KR100883065B1 (en) Apparatus and method for record control by motion detection
WO2017032086A1 (en) Photograph capturing control method and terminal
US8379098B2 (en) Real time video process control using gestures
KR20150067160A (en) Video scene detection
CN103353935B (en) A kind of 3D dynamic gesture identification method for intelligent domestic system
CN101689394A (en) Method and system for video indexing and video synopsis
CN102257511A (en) Method, apparatus and computer program product for providing adaptive gesture analysis
CN103249352A (en) Adaptive displays using gaze tracking
US9690388B2 (en) Identification of a gesture
WO2014075582A1 (en) Method and apparatus for storing webpage access records
CN102369729A (en) Tracking judgment device, tracking judgment method, and tracking judgment program
CN101281593A (en) Method and system for researching intelligent video monitoring case
CN102982527A (en) Methods and systems for image segmentation
WO2015058381A1 (en) Method and terminal for selecting image from continuous images
US20090141936A1 (en) Object-Tracking Computer Program Product, Object-Tracking Device, and Camera
US9128528B2 (en) Image-based real-time gesture recognition
US9357117B2 (en) Photographing device for producing composite image and method using the same
CN103793657B (en) System and method for hiden application on mobile terminals
WO2017005149A1 (en) Game acceleration method and device
US20090174674A1 (en) Apparatus and methods for a touch user interface using an image sensor
CN103092520A (en) Method and device of screen image clipping and touch screen mobile device
KR20130025944A (en) Method, apparatus and computer program product for providing object tracking using template switching and feature adaptation
KR101718373B1 (en) Video play method, terminal, and system
CN102859534A (en) Viewpoint detector based on skin color area and face area
JP2007265125A (en) Content display

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination
C14 Grant of patent or utility model
CP01 Change in the name or title of a patent holder