CN102932638A - 3D video monitoring method based on computer modeling - Google Patents

3D video monitoring method based on computer modeling Download PDF

Info

Publication number
CN102932638A
CN102932638A CN2012104987155A CN201210498715A CN102932638A CN 102932638 A CN102932638 A CN 102932638A CN 2012104987155 A CN2012104987155 A CN 2012104987155A CN 201210498715 A CN201210498715 A CN 201210498715A CN 102932638 A CN102932638 A CN 102932638A
Authority
CN
China
Prior art keywords
image
subsystem
system
3d
information
Prior art date
Application number
CN2012104987155A
Other languages
Chinese (zh)
Other versions
CN102932638B (en
Inventor
田学东
刘哲
李秀云
梁浚
郭中豪
杨子鹏
孙裕昌
邢文武
王兴楠
Original Assignee
天津市电视技术研究所
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 天津市电视技术研究所 filed Critical 天津市电视技术研究所
Priority to CN201210498715.5A priority Critical patent/CN102932638B/en
Publication of CN102932638A publication Critical patent/CN102932638A/en
Application granted granted Critical
Publication of CN102932638B publication Critical patent/CN102932638B/en

Links

Abstract

The invention relates to a 3D (Three Dimensional) video monitoring method based on computer modeling. A hardware used in the method comprises a front-end image acquisition system and a transmission system. The method is characterized in that a monitoring camera is used for acquiring video image information; a computer is used as a processing platform so as to finish the conversion from images to a 3D model, and the 3D modeling, and update the content of the 3D modeling according to real-time video image information acquired by the camera; and simultaneously, the virtual monitoring is executed on a model by a simulated camera in the computer. The method has the beneficial effects of being capable of carrying out the 3D modeling by the computer, modeling historical records according to normal recorded videos, realizing the simulation on monitoring regions by combining with a digital sand table, finishing the bake simulation on complex environments with a small number of acquisition front ends, and being applied to detection in the complex environments.

Description

基于计算机建模的3D视频监控方法 3D computer modeling method based on video surveillance

技术领域 FIELD

[0001] 本发明涉及视频监控技术领域,特别涉及一种基于计算机建模的3D视频监控方法。 [0001] The present invention relates to a video monitoring technology, and more particularly relates to a 3D video monitoring method is based on computer modeling.

背景技术 Background technique

[0002] 监控系统是由前端采集系统、传输系统和显示系统组成的,以远程观看所监控区域实时状况和进行录像回放为主要功能的弱电系统。 [0002] The monitoring system is composed of the front end of the acquisition system, display system, and a transmission system to remote viewing area monitored in real time and for health as the main function of the video playback system weak. 目前在市面上的监控系统的显示均采用2维图像显示,具有无法适应高温条件下近距离监控,无法在不具备安装条件的监控角度进行监控等诸多不足之处,随着我国视频监控技术的发展,需要一种新的技术方案来弥补现有技术的不足。 Display monitoring system currently on the market are made of 2-dimensional image display, has not adapt to high temperatures close range, the angle can not be monitored in a monitoring installation conditions do not have many other deficiencies, as the art of video surveillance development, a new technical solution to make up for the deficiencies of the prior art.

发明内容 SUMMARY

[0003] 本发明的目的就是针对上述方法的不足,提出一种基于计算机建模的3D视频监控方法,由监控摄像采集视频图像信息,由计算机处理处理完成由图像向3D模型的转换,在计算机内完成3D建模,并根据摄像机采集的实时视频图像信息实时更新3D模型的状况,如运行轨迹、色彩变化、形体变化等信息。 [0003] The object of the present invention is insufficient for the above-described method, provides a method of 3D video monitoring computer modeling based on information collected by the surveillance video camera, the image to complete the conversion from the 3D model by computer processing, the computer information in complete 3D modeling, 3D models and real-time updates based on real-time video image information captured by the camera's status, such as running tracks, color changes, body changes. 同时通过计算机内被模拟的摄像机对模型进行虚拟的监控模式。 While the virtual monitor mode model being simulated by a computer camera.

[0004] 这样我们就能实现在空间上模拟出一个摄像机,在高速的计算机处理能力的基础上,最终会得到接近于现实的3D模型,实现3D监控。 [0004] In this way we can achieve in space to simulate a camera, on the basis of high-speed computer processing power based on the final 3D model will be closer to reality, to achieve 3D monitor.

[0005] 本发明中的设备所采用的技术方案是:一种基于计算机建模的3D视频监控方法,其利用的硬件包括前端图像采集系统、传输系统,其特征在于,由监控摄像机采集视频图像信息,以计算机为处理平台,由计算机处理完成由图像向3D模型的转换和3D建模,根据摄像机采集的实时视频图像信息实时更新3D模型的内容,包括运行轨迹、色彩变化、形体变化信息,同时通过计算机内模拟摄像机对模型进行虚拟监控;所述方法包括如下次序步骤: [0005] aspect of the present invention is employed in the device is: A method for monitoring a 3D video based on computer modeling, using hardware which includes a front end image acquisition system, transmission system, characterized in that the image acquisition by a video surveillance camera information, computer processing platform, complete content processed by a computer to convert 3D models and 3D modeling, real-time video image information captured by the camera is updated in real time by the image of a 3D model, including a running track, color changes, physical changes in information, simultaneously monitoring a virtual computer model mimics camera; the method comprising the following sequence of steps:

(O建立前端图像采集系统,前端图像采集系统和传输系统包括监控摄像机,云台、监控网络; (O create a front end image acquisition system, the front end of the image acquisition system and transport system comprises a surveillance camera, PTZ, monitoring network;

(2)在计算机中建立图像距离处理系统,图像距离处理系统由帧图像提取子系统、帧图像对比子系统、数据运算处理子系统和数据接口子系统组成,实现对不同前端采集到的图像进行距离运算; (2) create an image from the computer processing system, an image processing system different from the front end acquired image extracted by the image sub-frames, the frame image matching subsystem, processing subsystem, and data arithmetic data interface subsystem, implemented for distance calculation;

帧图像提取系统通过对针对同一物体或环境进行采集的不同采集前端同一时间点采集到的图像进行帧提取,并把提取到的帧信息提供给帧图像对比子系统; Frame image extracted by the extraction system of different acquisition frame front end for the acquisition of the same object at the same time or environmental point captured image, and supplies the extracted frame image frame information to the comparison subsystem;

帧图像对比子系统主要对比帧图像提取子系统提供的帧数据信息,以校对采集到的图像信息是否属于同一物体或环境以及对比不同采集前端采集到的信息之间差异; Comparative main frame image matching subsystem to extract frame image data sub-frame is provided to the image information acquired proofreading belong to the same object or a different environment and a comparison between the information collection difference distal collected;

在帧图像对比子系统确认不同采集前端采集到的图像信息属于同一物体或环境之后,数据运算子系统通过采集前端之间的距离信息和同一物体或环境由不同采集前端采集的图像信息进行运算处理,得到需要的3D用以表达物体的多边形与采集前端之间的距离 After comparison of different acquisition subsystem acknowledges distal captured image information belonging to the same object or environment, the operation processing data computing subsystem information and the image information of the same object or the distance between the front end environment acquired by the different acquisition frame image acquisition distal to give the desired expression for the distance between the 3D polygonal object with the distal end gathering

信息; information;

数据接口子系统则完成数据由图像距离处理系统向3D建模系统的数据输出; Data interface subsystem is completed by the image data output from the data processing system to a 3D modeling system;

图像距离处理系统对采集到的图像进行多边形面片处理,计算每个多边形面片的顶点距离信息,把运算的数据传送给3D建模系统,采用“偏光原理”运算; The image processing system from the collected image processing polygon patches, calculates the distance information of each vertex of the polygonal face sheet, transfer data to the 3D modeling system operation, a "polarizing principle" operation;

对不同的采集前端所采集到的不同的图像信息进行运算分析,得到图像信息点与不同的采集前端之间的距离信息以及各个采集前端采集到的图像的色彩、色调、灰度和饱和度信息,将信息数据传送给3D建模系统; The front end of the different acquisition the acquired image information different calculation analysis, the collected information and distance between the front end of each of the image information acquired with a different acquisition point distal to the color image, hue, saturation, and gray-scale information the information data to the 3D modeling system;

(3)在计算机中建立图像位移处理系统:图像位移处理系统由帧图像提取子系统、帧图像位移对比子系统和运行轨迹分析处理子系统组成,实现对运动目标运行轨迹的运算和处理; (3) create an image displacement in a computer processing system: image shift processing system frame image extracted by the subsystem, subsystem frame image contrast and displacement trajectory analysis processing subsystem, and the processing operation to realize the target trajectory of the motion;

这里的帧图像提取子系统和图像距离处理子系统离得帧图像处理子系统不同,它主要提取的帧图像,此处帧图像指的是同一采集前端在不同时间轴上提取的; Here the frame image extraction subsystem and the image processing subsystem from the frame image obtained from the different processing subsystem, it is mainly the extracted frame image, here referring to the same frame image acquired at the front end of the extracted different axis;

帧图像位移对比子系统根据帧图像提取子系统提供的帧信息,通过处理运算得出表示物体的多边形各个顶点的位移量。 Comparative subsystem extracts frame image displacement provided by the sub-frame information frame image represented by the obtained displacement amount calculation processing of each vertex of the polygon.

[0006] 运行轨迹分析处理子系统把3D建模标识物体的多边形的运行轨迹运算出来,结合3D模型以动画的形式展示出来; [0006] The processing subsystem to analyze the running track running track identification polygonal 3D modeling objects out of operation, in conjunction with the 3D model in the form of animation display;

(4)在计算机中建立3D建模系统,3D建模系统由建模子系统、色彩生成子系统和模拟摄像机生成子系统组成;通过在计算机中对模型进行不同角度的图像输出来模拟生成虚拟摄像机的监控画面,达到对模型进行多方位的显示的过程; (4) established in the computer 3D modeling system, generated by the 3D modeling system modeling subsystem, color camera subsystem and to generate an analog subsystem; simulated by the model image output at different angles in a computer generated virtual the camera monitor screen, to show the process of the model of multi-faceted;

(5)由3D建模子系统建立的3D模型和图像位移子系统运算出的模型各个部位表示的多边形的时间线上的运行轨迹进行结合生成3D模型的动画形式,以实现模拟监控系统。 Polygon running track timeline (. 5) and the image of the 3D model by the 3D modeling subsystem displacement subsystem calculated to establish the various parts are combined to generate a model representation of a 3D model animation for analog monitoring system.

[0007] 本发明的有益效果是:基于计算机建模的3D视频监控方法,以传统监控模式运行,对现场进行实时监控,对现场进行传统监控模式的录像、查找和回等功能,通过计算机3D建模可以对实时监控的区域进行3D建模,可以根据普通录像对历史记录进行建模,配合使用数字沙盘可以实现监控区域模拟化,完成以较少的采集前端对复杂环境的模拟复制,本发明应于复杂环境的检测,如水文检测,地下矿井建模,高灵敏性和准确的还原事物的实时状态,实现动态的数据处理,动态的选择阀值进行区域复制,可广泛应用厂矿企业的生产区域,特别是在人员无法接近的高温区域,更适宜采用此技术进行监控,本发明也可应用于全系视频会议,在世界的任何地方做到真正面对面的商讨。 [0007] the advantages are: 3D video monitoring method based on computer modeling, run the traditional monitoring mode, on-site real-time monitoring, on-site traditional video monitor mode, find and return functions, 3D computer region may be modeled 3D modeling real-time monitoring, can be modeled according to the normal recording history, with the sandbox may be implemented using a digital simulation of the monitor area, the completion of the analog copy with less complex environment acquisition front-end, according to the present invention to detecting a complex environment, such as hydrological detection, modeling underground mines, high sensitivity and accurate real-time status of things reduction, dynamic data processing, the dynamic threshold value for the selected replication region can be widely used industrial enterprises production areas, especially in the high-temperature region inaccessible personnel, more appropriate use of this technology for monitoring, the present invention can also be applied to a full line of video conferencing, truly face to face to discuss anywhere in the world.

附图说明 BRIEF DESCRIPTION

[0008]图I是基于计算机建模的3D监控系统框架图; [0008] Figure I is a 3D monitor of FIG framework based on computer modeling;

图2是人眼偏光原理不意图。 Figure 2 is a polarizing human eye principle is not intended.

具体实施方式 detailed description

[0009] 下面结合附图和实施例对本发明进一步说明。 Figures and examples further illustrate the present invention [0009] The following binding.

[0010] 如图I、图2所示,一种基于计算机建模的3D视频监控方法,采用的硬件包括前端图像采集系统、传输系统,由监控摄像采集视频图像信息,以计算机为处理平台,由计算机处理完成由图像向3D模型的转换和3D建模,根据摄像机采集的实时视频图像信息实时更新3D模型的内容,包括运行轨迹、色彩变化、形体变化信息,同时通过计算机软件模拟摄像机对模型进行虚拟的监控, [0010] FIG. I, as shown in FIG. 2, the video surveillance method based on 3D computer modeling, using the hardware includes a front end image acquisition system, transmission system, information is collected by the video surveillance camera, computer processing platform, by computer processing contents to convert the 3D model and 3D modeling, real-time video image information is updated in real time by a camera collecting images of the 3D model, comprising a running track, color changes, physical changes in information, through computer simulation software model of the camera virtual monitoring,

实施例一: Example One:

1、建立前端图像采集系统,前端图像采集系统和传输系统包括摄像机,云台、监控网 1, create a front end image acquisition system, the front end of the image acquisition system and the transmission system includes a camera, head, monitoring network

络; Network;

2、在计算机中建立图像距离处理系统:图像距离处理系统由帧图像提取子系统、帧图像对比子系统、数据运算处理子系统和数据接口子系统组成,实现对前端采集到的图像进行距离运算; 2, create an image from the computer processing system: image extracted from the frame image processing system subsystems, comparison subsystems frame image data and data interface subsystem arithmetic processing subsystem, to realize the front collected image distance calculation ;

图像距离处理系统的处理过程:通过对不同采集前端针对同一物体或环境的采集图像信息的处理来进行对监控物体或环境与采集点之间的距离运算,以3D模型的表示方法,将具有复杂外形的物体其表面由多边形面片来近似表示; The image processing from the processing system: the front end by different acquisition process to acquire image information for the same object or environment to the distance between the operation and monitoring of the environment or object collection point, to represent a 3D model having a complicated the surface profile of the object is approximated by a polygon represented facets;

对采集到得图像进行多边形面片处理,计算每个多边形面片的顶点距离信息,把运算的数据传送给3D建模系统,采用“偏光原理”运算; To give the collected image processing polygonal patches, calculates the distance information of each vertex of the polygonal face sheet, transfer data to the 3D modeling system operation, a "polarizing principle" operation;

就像我们的视觉以能分辨远近一样,采集前端就像人的双眼,靠不同的采集前端之间的距离差,对不同的采集前端所采集到的不同的图像信息进行运算分析,得到图像信息点与不同的采集前端之间的距离信息以及各个采集前端采集到的图像的色彩、色调、灰度和饱和度信息,将信息数据传送给3D建模系统; As we can distinguish between near and far vision as to collect the distal end like the human eyes, by the distance between the different acquisition difference distal end, the distal end of the different acquisition the acquired image information different calculation analysis, image information and collecting information from the respective gathering point between the front end and the front end to the different acquisition of color images, color, saturation, and gray-scale information, the transmitting information data to a 3D modeling system;

如图2所示,以我们人眼为例阐述偏光原理:设注视点为M,它在两眼视网膜中心的构像分别为ml和m2。 2, the human eye with our example to explain the principles of polarization: the gaze point set M, the constellation in which the center of the retina are two ml and m2. 当注视M点时,其它物点A、B也会在视网膜上构像,分别为al、bl和a2、b2,左右相应像点分别到相应视网膜中心的横向弧长之差,称为生理视差。 When the gaze point M, the other object points A, B on the retina will constellation, respectively, al, bl, and a2, b2, respectively, about the corresponding image point of the arc length corresponding to the difference between the lateral center of the retina, known as the physiological parallax .

[0011] 以M点的构像ml、m2为准,像点在其左侧的为正,反之为负。 [0011] In ml M constellation points, m2 subject, its left dot is positive, otherwise it is negative. 那么A、B两点的生理视差为:A=mlal — m2a2 < O, B= mlbl-m2b2 > O。 Then A, B physiological parallax two points: A = mlal - m2a2 <O, B = mlbl-m2b2> O. 显然,M点的生理视差为零。 Obviously, the disparity physiological point M is zero. 由此可见,当物点比注视点远时,其生理视差小于零,反之大于零。 Thus, when the object point than the gazing point is far, the disparity is less than zero physiological, on the contrary greater than zero. 这种由于物点远近所形成的生物视差,经过大脑的处理,便产生空间物体远近不同的立体感觉。 Because of this disparity biological object point distance of the formed, treated brain, they produce different spatial distance object three-dimensional feel.

[0012] 3、在计算机中建立图像位移处理系统:图像位移处理系统由帧图像提取子系统、帧图像位移对比子系统和运行轨迹分析处理子系统组成,主要实现对运动目标运行轨迹的运算和处理; [0012] 3, the establishment of image shift processing in a computer system: the image shift processing sub-system extracted from the frame image and the frame image matching subsystem displacement trajectory analysis processing subsystem, the main achievement of the operation target moving trajectory and deal with;

图像位移处理系统处理过程:通过对相同的采集前端对同一物体或环境在不同时间段采集到的信息进行处理来计算物体或环境在时间轴上的位移量; The image processing system processes the displacement: calculating a displacement amount of the object or the environment on the time axis by processing the same object or environment information collected at different times for the same collection front end;

当每一个物体在其局部坐标系中被建立起来之后,就需要将其放置到将要绘制的场景之中,组成场景的每个物体都有自己独立的局部坐标系; After each object is set up in its local coordinate system, needs to be placed into the scene to be drawn, each object has its own separate constituent scene local coordinate system;

整个场景的坐标系采用世界坐标系,场景中的所有物体都必须从自己的局部坐标系中变换到世界坐标系中以定义场景中物体之间的空间相对关系; Whole scene coordinate system using the world coordinate system, all objects in the scene have to be converted from its own local coordinate system to the world coordinate system to define a space between the objects in the scene relative relationship;

如果一个物体在场景中是运动的,则必须为该物体定义一个随时间变化的变换序列以便在每一帧将该物体变换到世界坐标系中的不同位置。 If a sequence of transformations for object motion in the scene, it must be for a time varying definitions for object into a different position in the world coordinate system of the object in each frame.

[0013] 图像位移处理系统通过物体或环境在坐标系上的变化对物体或环境的运行轨迹进行分析运算。 [0013] The processing system analyzes the image displacement calculation of the running track by a change in the environment or the object or objects on the coordinate system environment.

[0014] 接收图像距离处理系统的数据信息对物体或环境进行NURBS建模生成和色彩生成处理,由于接收到的是3D表示方法的多边形的面片的顶点信息,所以存储量和运算量都大大的减少了,采用局部坐标系、世界坐标系或相机坐标系来建立现实世界的模拟3D场 [0014] The data processing system receives an image from an object or environment to generate NURBS modeling and color generation processing, since the received vertex information of the polygon is a 3D representation of the surface of the sheet, so the amount of computation and the storage are greatly reduced, using a local coordinate system, world coordinate system or camera coordinate system to create a 3D simulation of real-world field

Day

ο ο

[0015] 同时色彩处理阶段可以对实现纹理映射、透明以及雾化(大气效应)等真实感效果。 [0015] Also color processing stage can achieve texture mapping, fogging and transparency (atmospheric effects) and so realistic effect. 物体表面纹理的定义是在世界坐标系中进行的,通过预处理,每个带有纹理的多边形在其顶点数据中建立了与相应纹理图的映射关系。 Surface texture of the object is defined in the world coordinate system is performed by the pretreatment, each polygon with texture mapping relationship established in the texture map corresponding to its apex data. 在绘制带有纹理的多边形时,其相应的纹理图也同时被加载到纹理存储器中,在求出物体上象素坐标的同时其相应的纹理坐标也被计算出来。 When drawing a polygon with a texture, which texture map corresponding also be loaded into the texture memory, while the pixel coordinates on the object to obtain its corresponding texture coordinates is also calculated. 用该纹理坐标从纹理存储器中读出相应纹理象素的值,将其与明暗处理的结果进行混合就得到要显示的象素值。 Value of a corresponding pixel texture readout from the texture memory, the result of shading processing performed by mixing the pixel texture coordinate value is obtained to be displayed. 雾化(大气效应)则是在计算出的象素值上乘上一个与深度有关的裳减因子。 Atomizing (atmospheric effects) on the pixel value is calculated by multiplying a depth-related reduction factor Sang.

[0016] 对落在同一屏幕位置的象素点的象素值按其所属物体的透明系数进行加权融合就可以产生透明效果。 [0016] The pixel value of pixel dots on the same screen position falls weighting coefficients belongs fusion its transparent object can produce the effect of transparency. 得到采集前端现场的3D模型后,我们可以通过建立虚拟摄像机可以再模型任意角度对模型进行图像采样处理。 After obtaining acquisition front-end 3D model of the scene, we can then model the model at any angle image sampling process by creating a virtual camera.

[0017] 4、在计算机中建立3D建模系统,3D建模系统包括建模子系统、色彩生成子系统和模拟摄像机生成子系统组成;由3D建模子系统和图像位移子系统运算生成模拟监控系统。 [0017] 4, the establishment of 3D modeling in a computer system, including 3D modeling system modeling subsystem, generating color camera subsystem and to generate an analog subsystem; manufactured by 3D modeling subsystem and to generate an analog image shift calculation subsystem surveillance system.

[0018] 基于计算机建模的3D监控系统可广泛应用厂矿企业的生产区域,如人员无法接近的高温区域,可采用此技术进行监控。 [0018] 3D-based monitoring system for monitoring a computer modeling can be widely applied to production zone mining enterprises, such as for inaccessible high temperature region, this technique may be employed. 也可应用于全系视频会议,让我们可以在世界的任何地方做到真正面对面的商讨。 It can also be applied to a full line of video conferencing, so that we can really do discuss face to face anywhere in the world.

[0019] 基于计算机建模的3D监控系统首先需要建模才能实现监控,在建模的基础上我们可以应用的方位将非常宽广,无论从军事还是科考层面来说,都可以通过建模获取我们所需的地形、建筑设备等形体状况及其变化等方面的信息。 [0019] Based on computer modeling of 3D modeling monitoring system first needs to implement monitoring, modeling on the basis of the position that we can apply will be very broad, both from a military expedition or level, can be obtained through modeling physical condition aspects of information we need terrain, construction equipment and change. 我们同样可以采用非图像形式的采集前端,诸如海底勘测的声纳、工业探伤的射线和X光等作为前端以实现我们对诸如海床的测绘、工业产品及其内部建模和人体结构等的实时建模。 We can also adopt the form of non-image acquisition front-end, such as submarine sonar survey of industrial flaw detection and X-rays, etc. as a front end to achieve our surveying and mapping, modeling and industrial products and its internal structure of the human body such as the seabed, etc. real-time modeling.

[0020] 根据上述说明,结合本领域技术可实现本发明的方案。 [0020] According to the above description, those skilled in conjunction with the present invention may be implemented.

Claims (2)

1. 一种基于计算机建模的3D视频监控方法,其利用的硬件包括前端图像采集系统、传输系统,其特征在于,由监控摄像机采集视频图像信息,以计算机为处理平台,由计算机处理完成由图像向3D模型的转换和3D建模,根据摄像机采集的实时视频图像信息实时更新3D模型的内容,包括运行轨迹、色彩变化、形体变化信息,同时通过计算机内模拟摄像机对模型进行虚拟监控;所述方法包括如下次序步骤:(O建立前端图像采集系统,前端图像采集系统和传输系统包括监控摄像机,云台、监控网络;(2)在计算机中建立图像距离处理系统,图像距离处理系统由帧图像提取子系统、帧图像对比子系统、数据运算处理子系统和数据接口子系统组成,实现对不同前端采集到的图像进行距离运算;帧图像提取系统通过对针对同一物体或环境进行采集的不同采集前端同一时 A method of 3D video monitoring computer modeling based hardware comprising a front end utilizing an image acquisition system, transmission system, wherein the image information collected by the monitoring video cameras, computer processing platform, by the computer processing is performed by image conversion to 3D modeling and 3D models, real-time video image information captured by the camera in real-time 3D model updates, including a running track, color changes, physical changes in information, and monitor virtual model by computer simulation within the camera; the said method comprising the following sequence of steps: (O create a front end image acquisition system, the front end of the image acquisition system and transport system comprises a surveillance camera, PTZ, monitoring network; (2) to establish an image processing system from a computer, from the image processing system by a frame image extracting subsystems, comparison subsystems frame image data and data interface subsystem arithmetic processing subsystem, to achieve different distal acquired image distance calculation; frame image capture system for the collection of the different objects or the same environment when the acquisition front-end same 间点采集到的图像进行帧提取,并把提取到的帧信息提供给帧图像对比子系统;帧图像对比子系统主要对比帧图像提取子系统提供的帧数据信息,以校对采集到的图像信息是否属于同一物体或环境以及对比不同采集前端采集到的信息之间差异;在帧图像对比子系统确认不同采集前端采集到的图像信息属于同一物体或环境之后, 数据运算子系统通过采集前端之间的距离信息和同一物体或环境由不同采集前端采集的图像信息进行运算处理,得到需要的3D用以表达物体的多边形与采集前端之间的距离信息;数据接口子系统则完成数据由图像距离处理系统向3D建模系统的数据输出;图像距离处理系统对采集到的图像进行多边形面片处理,计算每个多边形面片的顶点距离信息,把运算的数据传送给3D建模系统,采用“偏光原理”运算;对不同的采集前端所采集 Between points acquired image frame extraction, and the extracted frame image frame information to the comparison subsystem; Comparative main frame image matching subsystem to extract frame image data sub-frame is provided to the image information acquired proofreading belong to the same object or environment and the difference between the information collected to compare different distal collected; after confirmation frame image contrast different acquisition subsystem distal captured image information belonging to the same object or environment, the data acquisition subsystem operation between the distal end performs arithmetic processing information and image information from the same object or different acquisition environment acquired by the front end, to give the desired 3D information for expressing the distance between the polygon and the capture of the distal end of the object; data interface subsystem processes the image data is completed from the data output system to a 3D modeling system; an image processing system from the collected image processing polygon patches, calculates the distance information of each vertex of the polygonal patches, the data transfer operation to the 3D modeling system, a "polarization principle "operation; collected different collecting distal 到的不同的图像信息进行运算分析,得到图像信息点与不同的采集前端之间的距离信息以及各个采集前端采集到的图像的色彩、色调、灰度和饱和度信息,将信息数据传送给3D建模系统;(3)在计算机中建立图像位移处理系统:图像位移处理系统由帧图像提取子系统、帧图像位移对比子系统和运行轨迹分析处理子系统组成,实现对运动目标运行轨迹的运算和处理;这里的帧图像提取子系统和图像距离处理子系统离得帧图像处理子系统不同,它主要提取的帧图像,此处帧图像指的是同一采集前端在不同时间轴上提取的;帧图像位移对比子系统根据帧图像提取子系统提供的帧信息,通过处理运算得出表示物体的多边形各个顶点的位移量。 The different image information analysis calculation to obtain distance information, and gathering between the front end of the respective image information acquired with a different acquisition point distal to the color image, hue, saturation, and gray-scale information, the information data is transmitted to 3D modeling system; (3) create an image displacement in a computer processing system: image shift processing system extracts the sub frame image and the frame image matching subsystem displacement trajectory analysis processing subsystem, to achieve operation of the trajectory of the moving object and processing; where the frame image extraction subsystem and a processing subsystem from the image obtained from the frame image processing subsystem different, it is mainly the extracted frame image, here referring to the same frame image acquired at the front end of the extracted different axis; Comparative subsystem extracts frame image displacement provided by the sub-frame information frame image represented by the obtained displacement amount calculation processing of each vertex of the polygon.
2.运行轨迹分析处理子系统把3D建模标识物体的多边形的运行轨迹运算出来,结合3D模型以动画的形式展示出来;(4)在计算机中建立3D建模系统,3D建模系统由建模子系统、色彩生成子系统和模拟摄像机生成子系统组成;通过在计算机中对模型进行不同角度的图像输出来模拟生成虚拟摄像机的监控画面,达到对模型进行多方位的显示的过程;(5)由3D建模子系统建立的3D模型和图像位移子系统运算出的模型各个部位表示的多边形的时间线上的运行轨迹进行结合生成3D模型的动画形式,以实现模拟监控系统。 2. Handling Subsystem trajectory analysis 3D modeled objects identified polygonal trajectory out operation, in conjunction with the 3D model in the form of animation display; (4) the establishment of 3D modeling in a computer system, 3D modeling system built by the mold system, color generation subsystem generates analog cameras and subsystems; generating a simulated virtual camera monitor screen image output by the model at different angles in a computer, to process the model of the multi-directional display; (5 ) trajectory by a polygonal line time 3D modeling and 3D model image displacement calculated subsystem subsystem established model representation of the various parts are combined to generate animated 3D model, in order to achieve analog control system.
CN201210498715.5A 2012-11-30 2012-11-30 3D video monitoring method based on computer modeling CN102932638B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210498715.5A CN102932638B (en) 2012-11-30 2012-11-30 3D video monitoring method based on computer modeling

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210498715.5A CN102932638B (en) 2012-11-30 2012-11-30 3D video monitoring method based on computer modeling

Publications (2)

Publication Number Publication Date
CN102932638A true CN102932638A (en) 2013-02-13
CN102932638B CN102932638B (en) 2014-12-10

Family

ID=47647323

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210498715.5A CN102932638B (en) 2012-11-30 2012-11-30 3D video monitoring method based on computer modeling

Country Status (1)

Country Link
CN (1) CN102932638B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106162144A (en) * 2016-07-21 2016-11-23 触景无限科技(北京)有限公司 A kind of visual pattern processing equipment, system and intelligent machine for overnight sight
CN106373173A (en) * 2016-08-31 2017-02-01 北京首钢自动化信息技术有限公司 Monitoring method and monitoring system
CN108810517A (en) * 2018-07-05 2018-11-13 盎锐(上海)信息科技有限公司 Image processor with monitoring function and method
CN108848366A (en) * 2018-07-05 2018-11-20 盎锐(上海)信息科技有限公司 Information acquisition device and method based on 3D video camera

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101208723A (en) * 2005-02-23 2008-06-25 克雷格·萨默斯 Automatic scene modeling for the 3D camera and 3D video
CN101419499A (en) * 2008-11-14 2009-04-29 东南大学 Multimedia human-computer interaction method based on cam and mike
CN101951502A (en) * 2010-10-19 2011-01-19 北京硅盾安全技术有限公司 Three-dimensional intelligent video monitoring method
JP4710081B2 (en) * 2004-11-24 2011-06-29 株式会社国際電気通信基礎技術研究所 Image creating system and image creating method
CN102608920A (en) * 2012-03-15 2012-07-25 中国计量学院 Method for monitoring bridge inspection van through three-dimensional (3D) simulation on basis of Android system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4710081B2 (en) * 2004-11-24 2011-06-29 株式会社国際電気通信基礎技術研究所 Image creating system and image creating method
CN101208723A (en) * 2005-02-23 2008-06-25 克雷格·萨默斯 Automatic scene modeling for the 3D camera and 3D video
CN101419499A (en) * 2008-11-14 2009-04-29 东南大学 Multimedia human-computer interaction method based on cam and mike
CN101951502A (en) * 2010-10-19 2011-01-19 北京硅盾安全技术有限公司 Three-dimensional intelligent video monitoring method
CN102608920A (en) * 2012-03-15 2012-07-25 中国计量学院 Method for monitoring bridge inspection van through three-dimensional (3D) simulation on basis of Android system

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106162144A (en) * 2016-07-21 2016-11-23 触景无限科技(北京)有限公司 A kind of visual pattern processing equipment, system and intelligent machine for overnight sight
CN106373173A (en) * 2016-08-31 2017-02-01 北京首钢自动化信息技术有限公司 Monitoring method and monitoring system
CN108810517A (en) * 2018-07-05 2018-11-13 盎锐(上海)信息科技有限公司 Image processor with monitoring function and method
CN108848366A (en) * 2018-07-05 2018-11-20 盎锐(上海)信息科技有限公司 Information acquisition device and method based on 3D video camera

Also Published As

Publication number Publication date
CN102932638B (en) 2014-12-10

Similar Documents

Publication Publication Date Title
Plankers et al. Articulated soft objects for video-based body modeling
Varol et al. Learning from synthetic humans
CN104011788B (en) For strengthening and the system and method for virtual reality
Balan et al. Detailed human shape and pose from images
CN103247075B (en) Based on the indoor environment three-dimensional rebuilding method of variation mechanism
CN102959616B (en) Interactive reality augmentation for natural interaction
Loper et al. OpenDR: An approximate differentiable renderer
US20100257252A1 (en) Augmented Reality Cloud Computing
US8933931B2 (en) Distributed asynchronous localization and mapping for augmented reality
US20080204453A1 (en) Method and apparatus for generating three-dimensional model information
WO2017133009A1 (en) Method for positioning human joint using depth image of convolutional neural network
CN100504299C (en) Method for obtaining three-dimensional information of space non-cooperative object
CN105160310A (en) 3D (three-dimensional) convolutional neural network based human body behavior recognition method
CN102317973A (en) Fusion of a 2d electro-optical image and 3d point cloud data for scene interpretation and registration performance assessment
CN1617174A (en) Human limb three-dimensional model building method based on image cutline
CN101794349B (en) Experimental system and method for augmented reality of teleoperation of robot
CN105144247B (en) The generation of the three dimensional representation of user
Shapiro et al. Rapid avatar capture and simulation using commodity depth sensors
CN104933718B (en) A kind of physical coordinates localization method based on binocular vision
Joseph Tan et al. Fits like a glove: Rapid and reliable hand shape personalization
Turner et al. Fast, automated, scalable generation of textured 3d models of indoor environments
Ribeiro et al. Auditory augmented reality: Object sonification for the visually impaired
Li et al. Monocular depth estimation with hierarchical fusion of dilated cnns and soft-weighted-sum inference
Bray et al. Fast stochastic optimization for articulated structure tracking
CN101877143A (en) Three-dimensional scene reconstruction method of two-dimensional image group

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination
C14 Grant of patent or utility model
C41 Transfer of patent application or patent right or utility model