JP2003329448A - Three-dimensional site information creating system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To construct a three-dimensional model capable of sharply distinguishing a construction machine and land features by picking up images of a construction work site by a plurality of stereo cameras. <P>SOLUTION: A plurality of camera poles 1 respectively comprising the stereo camera 3 configurated by a plurality of cameras 2, are respectively installed on different places, and each camera 2 picks up the images of the construction work site 5. Each stereo camera 3 performs the stereo-processing on the picked-up images to obtain a distance image, and detects position coordinates of a marker pair 61, 62 mounted on the construction machine 6. A host device 4 acquiring the distance image data from each of the stereo cameras 3 integrates the distance images and creates the three-dimensional model data of the construction work site 5. Further a position and the direction of the construction machine 6 are specified on the basis of position coordinates of the marker pair 61, 62. <P>COPYRIGHT: (C)2004,JPO

Description

Detailed Description of the Invention

[0001]

TECHNICAL FIELD The present invention relates to a technique for obtaining three-dimensional information of a construction site such as a construction site.

[0002]

2. Description of the Related Art For example, as a technique for measuring topography or measuring the position of a construction machine at a construction site where the construction machine works, a tracking type total station as disclosed in Japanese Patent Laid-Open No. 11-237244 is disclosed. Also, RTK-GPS is known.

[0003]

However, the tracking type total station cannot be used if there is a shield between the surveying instrument and the target, and the position measuring target 1
Therefore, there are many practical problems such as one set being required.

In addition, in RTK-GPS, GPS (Glob
Since the antenna must receive the signal from the artificial satellite, there is a problem that the antenna cannot be used unless it can receive the signal from the artificial satellite.

Therefore, an object of the present invention is to provide a practical system for obtaining three-dimensional information on the spot.

[0006] Another object of the present invention is to provide a system capable of distinguishing various objects existing on site, such as construction machinery and terrain.

Still another object of the present invention is to provide a system capable of obtaining the three-dimensional information even in the field where the sky is closed.

[0008]

A three-dimensional information generation system for a scene according to one embodiment of the present invention uses a plurality of images obtained by viewing the scene from different predetermined places, and presents various information existing in the scene. On-site three-dimensional data generation means for generating data on the three-dimensional position of the object, and specific object three-dimensional data detection means for obtaining data on the three-dimensional position of the specific object from the data on the three-dimensional positions of the various objects on the site. Other-object three-dimensional data detection means for obtaining data on the three-dimensional positions of other objects other than the specific object from the data on the three-dimensional positions of the various objects on the spot.

In a preferred embodiment, there is provided data output means for outputting the obtained data regarding the three-dimensional position of the specific object and the data regarding the three-dimensional position of an object other than the specific object separately or together. Further prepare.

In a preferred embodiment, a plurality of stereo cameras arranged at predetermined different places are provided, and the on-site three-dimensional data generating means uses images captured by each of the plurality of stereo cameras. To generate a range image of the scene, and to generate three-dimensional model data of the scene using the range images from the plurality of stereo cameras. Each of the stereo cameras is a pole type having a plurality of cameras arranged in a line in the vertical direction.

In a preferred embodiment, the plurality of images are moving images, and the on-site three-dimensional data generation means uses the plurality of moving images to dynamically change the motion images. The specific object three-dimensional data detecting means obtains dynamic data regarding the three-dimensional position of the specific object from the dynamic three-dimensional model data.

[0012] In a preferred embodiment, the detecting means detects the three-dimensional model data of the work site and a marker installed on the construction machine to detect the position and orientation of the construction machine.

In a preferred embodiment, a site image of the site viewed from a predetermined viewpoint is displayed by using the 3D model data of the site and the data regarding the 3D position of the specific object. There is.

[0014]

DETAILED DESCRIPTION OF THE INVENTION A three-dimensional information generation system according to an embodiment in which the present invention is applied to a construction work site will be described below with reference to the drawings.

FIG. 1 shows a third embodiment according to the present invention.
It is a figure which shows arrangement | positioning etc. of the camera installed in the construction work site in a dimensional information generation system.

The present system has a plurality (here, three) of camera poles 1, and each camera pole 1 is arranged at a different position in order to photograph the construction work site 5. Each camera pole 1 can be fixed to the ground, or can be mounted on a vehicle or the like to be movable. The position at which each camera pole 1 is arranged is arranged at a position where a blind spot cannot be made in order to photograph the entire construction work site 5, and its three-dimensional coordinates are measured in advance.
The number of camera poles 1 does not necessarily have to be three.

Each camera pole 1 includes a plurality of (five in this case) moving image cameras 2 arranged at different predetermined relative positions.
It has a stereo camera 3 which is a combination of (for example, a video camera). 5 included in one stereo camera 3
The cameras 2 in a row are arranged in a line in the height direction, but this does not necessarily have to be the case. For example, the cameras 2 may be arranged in a row of 5's on the dice or other arrangements. Well, the number of cameras 2 does not have to be 5, and may be more or less than 5 as long as it is 2 or more. Then, all the cameras 2 of each camera pole 1 simultaneously photograph the construction work site 5 of the construction work site. As will be described later, distance images are independently generated from the five moving images from each camera pole 1, and a dynamic three-dimensional model of the construction work site 5 is synthesized from these distance images. Become.

The construction work site 5 is provided with stakes 7 at a plurality of points, and a construction machine (hereinafter referred to as a construction machine) 6 performs a predetermined work according to the stakes 7. Each of the construction machines 6 includes a plurality of (here, two) markers 61 and 62 having a specific shape (here, spherical) at a predetermined location (here, a predetermined position on the roof of the driver's seat) that can be viewed from the stereo camera 3. The markers 61 and 62 are colored in mutually different colors, for example, and can be identified by image processing from an image captured by the camera 2. This marker pair is used when detecting the position and direction of the construction machine 6, as described later.

Next, the functional configuration of this system will be described with reference to FIGS.

FIG. 2 illustrates the basic functions of this system.

As shown in FIG. 2, by using images of the construction work site viewed from a plurality of different places, all the objects (terrain, construction equipment, timbers, people, etc.) existing on the construction work site 5 are simultaneously examined. The measured three-dimensional position-related data 100 is obtained. Here, the simultaneously measured three-dimensional position-related data 100 is, for example, a distance image from each stereo camera 5 in this embodiment, but this is an example, and it does not necessarily have to be so, in short. Any type of data may be used as long as the data can determine the three-dimensional positions of various objects in the scene. Next, from the simultaneously measured three-dimensional position-related data 100 at the construction work site, a pre-registered specific object (here, for example, each construction machine 6)
The three-dimensional position-related data 102 and 103 and the three-dimensional position-related data 101 of the object other than the specific object (here, for example, the terrain other than the construction machine 6 or the siding) are separated and extracted. Here, the three-dimensional position-related data 10 of the specific object
In this embodiment, 2 and 103 are the three-dimensional positions of the representative parts (for example, the markers or the driver's seat) of the individual construction machines 6, or the three-dimensional positions of the individual construction machines 6, as will be understood from the description below. Not only the three-dimensional model data that also represents a three-dimensional shape, but this is also an example, and data in other formats may be used. In addition, the three-dimensional position-related data 101 of an object other than the specific object means the terrain (including the marking) in this embodiment.
However, this is also an example, and data of other formats may be used. The three-dimensional position-related data 101 to 103 of the individual objects separated and extracted in this way may be output separately and used, or may be output together and used in combination. In this embodiment,
The specific object is a construction machine, but this is not limited to the example and does not have to be the case, and an arbitrary object such as a person, a building, a siding, equipment or the ground can be the specific object.

FIG. 3 is a diagram showing the overall functional configuration of this system. The present system includes a stereo camera 3 installed on each camera pole 1 and a host device 4 for integrating a range image synthesized by each stereo camera 3 to obtain a three-dimensional model of a construction work site 5.

As shown in FIG. 3, each stereo camera 3
Are 5 cameras 2 and 5 cameras 2 respectively
An image processing unit 31 that generates a distance moving image by a stereo image processing method using the luminance moving image captured by the image capturing unit, and a wireless transmission / reception unit 32 that wirelessly transmits the processing result of the image processing unit 31 to the host device 4. (In this embodiment, each stereo camera 3 generates a distance moving image and transmits the distance moving image to the host device 4, and the host device 4 generates a three-dimensional model of the construction site 5 from a plurality of collected distance moving images. It is intended to generate, but does not necessarily have to be.
Then, without performing complicated image processing, the luminance moving images of the five cameras 2 are transmitted to the host device 4, and the host device 4
A distance moving image for each stereo camera 3 may be generated by the stereo image processing method, and a three-dimensional model may be generated from the distance moving images. Since various variations can be adopted for the sharing of processing between the stereo camera 3 and the host device 4 as described above, the following description is merely one example. )

FIG. 4 shows a detailed functional configuration of the image processing unit 31 for each stereo camera 3.

As shown in FIG. 4, the image processing section 31 includes a construction machine position recognition section 33, a stereo processing section 34, and a coordinate conversion processing section 35.

Here, in order to perform a stereo image process to obtain a range image, 5 included in one stereo camera 3
One of the two cameras 2 is the reference camera 2a, and the remaining four are the comparison cameras 2b. And the reference camera 2a
And each of the comparison cameras 2b form one camera pair. That is, four camera pairs are configured in this embodiment.

The stereo processing unit 34 includes a LoG (Laplacian of Gaussian) processing unit 341 for removing noise and enhancing edges of images captured by the reference camera 2a and the comparison camera 2b, and each camera pair. For each, pattern matching is performed between the image from the reference camera 2a (hereinafter referred to as the reference image) and the image from each comparison camera 2b (hereinafter referred to as the comparison image) to obtain the SAD (Sum of Absolute Distance). An SAD processing unit 342 for calculating, an SSAD (Sum of SAD) processing unit 343 for totaling SADs of four camera pairs, and a distance image combining unit 344 for combining distance images are provided.

When each LoG processing section 341 performs LoG processing on the image from each camera 2, the difference in image quality between different cameras can be reduced. As a result, it is possible to make the pattern matching process between the images of different cameras succeeding to each other with high accuracy.

Each SAD processing section 342 and SSAD processing section 343, for example, perform processing in the following procedure,
A so-called corresponding point search is performed.

(1) Select one pixel as a target of distance measurement from the reference image. A certain distance is assumed as the distance to the object in the construction work site corresponding to this target pixel. Then, the position of the pixel (hereinafter referred to as “corresponding candidate pixel”) in each comparison image corresponding to the coordinate point in the construction work site space separated by the assumed distance is obtained.

(2) A matching window (pixel block) having a size of, for example, 3 pixels × 3 pixels (hereinafter referred to as a “reference window”) centered on the position of the target pixel is set in the reference image. Within each comparison image, a matching window (hereinafter referred to as “comparison window”) of the same size centered on the position of the corresponding candidate pixel is set.

(3) For each camera pair, the pixel value of each pixel in the reference window on the standard image and the pixel value of each corresponding pixel in the comparison window on the comparison image are compared, and “Dissimilarity” is calculated. As the “degree of difference”, the absolute value of the difference between pixel values, the square of the difference between pixel values, or the like is used.

(4) The "difference" is calculated for all the pixels in the reference window, and the "difference" is summed up for all the pixels in the reference window (hereinafter referred to as window addition) to obtain "difference obtained by window addition". Degree ”for each camera pair. This “window added difference” is “SA
D ".

The SSAD processing unit 343 acquires the “SAD” of each camera pair from each SAD processing unit 342, and sums the “SAD” of the four camera pairs that have been gathered to obtain the “final sum of dissimilarities”. Is asked. This "final total of dissimilarity" is "SSAD".

Each SAD processing unit 342 further assumes a plurality of distances as the distance to the object in the construction work site corresponding to the target pixel, and each of these distances is also " “SAD” is obtained, and in response to this, the SSAD processing unit 343 performs the above-described processing to obtain “SSAD” for each distance. Then, the SSAD processing unit 343 estimates one assumed distance at which “SSAD” is the minimum as the distance to the object corresponding to the target pixel, and outputs the target pixel and the estimated distance to the distance image synthesis unit 344.

Here, the minimum "SSAD" means that the image pattern in the reference window of the standard image is
This means that the comparison image is most similar to the image pattern in the comparison window.

Then, all pixels in the reference image are used as target pixels to perform the above-described processing to estimate the distance, and the distance image synthesizing unit 344 accumulates the distance to obtain a distance image corresponding to the reference image. To be

In this embodiment, in order to grasp the movement of the construction machine 6 in real time, each camera 2 is basically a moving image camera (for example, a video camera), and each output from the moving image camera 2. Corresponding point search is performed for each frame image at the time point. As a result, the image output from the stereo processing unit 34 is also a moving image in which the frame image at each time point is a distance image.

By performing the above-mentioned corresponding point search for each stereo camera 3, a range image is obtained for each stereo camera 3, but the three-dimensional coordinate value () of the target area 5 obtained from the range image of each stereo camera 3 ( That is, the x and y coordinate values of the pixel in the image and the distance value (z coordinate value) indicated by the pixel value)
Is expressed in a camera coordinate system based on the location and direction of the stereo camera 3. Therefore, the coordinate conversion processing unit 35 performs a process of converting the coordinate value of each camera coordinate system obtained from the distance image of each stereo camera 3 into a predetermined common reference coordinate system.

As a specific device for performing the coordinate conversion process, for example, the device disclosed in Japanese Patent Laid-Open No. 2002-32744 can be applied.

The construction machine position recognition unit 33 includes a marker coordinate detection unit 331 that detects a marker attached to the construction machine in the image from the reference camera, and a marker distance determination unit that determines the distance from the camera pole 1 to the marker. 332.

The marker coordinate detector 331 receives a reference image from one of the five cameras 2, for example, the reference camera 2a. Since the markers 61 and 62 attached to the construction machine 6 are shown as circles in the image,
It is extracted by pattern recognition, and each marker 61, 6 is extracted.
2. Determine the x, y coordinate values on the two reference images.

The marker distance determining unit 332 corresponds to the x and y coordinates of the markers 61 and 62 detected by the marker coordinate detecting unit 331 from the distance image corresponding to the reference image combined by the distance image combining unit 344. The z coordinate value is obtained, and the distance from the camera pole 1 to the markers 61 and 62 is obtained.

The marker distance determination unit 332 notifies the coordinate conversion processing unit 35 of the coordinate values of the markers 61 and 62 on the reference image and the distances from the camera pole 1 to the markers 61 and 62. The coordinate conversion processing unit 35, similarly to the conversion of the distance image, three-dimensional coordinate values indicating the position of each marker (x and y coordinate values of pixels in the image and distance value to the marker (z coordinate value)).
Is converted into a predetermined common reference coordinate system.

The coordinate conversion processing unit 35 passes the three-dimensional coordinate values of each marker and the distance image to the wireless transmission / reception unit 32, and the wireless transmission / reception unit 32 transmits them to the host device 4. (Note that as a modification, the coordinate conversion processing unit 35 is provided in the host device 4,
You may make it transmit the marker coordinate value and distance image of the camera coordinate system before coordinate conversion from each stereo camera 3 to the host device 4. )

Next, returning to FIG. 3, the host device 4 will be described.

As shown in FIG. 3, the host device 4 is composed of, for example, a general-purpose computer system, and each component or function in the host device 4 described below is, for example, to execute a computer program. It is realized by.

The host device 4 has, as its internal functions, a radio transmitter / receiver 41 for receiving a radio signal from the stereo camera 3 and an individual construction machine based on the three-dimensional coordinate values of the markers from the plurality of stereo cameras 3. Of a construction machine, which detects the position and direction of the construction machine, a terrain generation section 43 which statistically processes distance images from a plurality of stereo cameras 3 to generate three-dimensional model data of the terrain of a construction work site, GIS data including position and direction and 3D model data of topography
A GIS data storage unit 44 for storing as (Geographic Information System) data and a GIS data output unit 45 for outputting the GIS data to the outside are provided.

Detailed structures of the construction machine detection section 42 and the terrain generation section 43 will be described with reference to FIG.

As shown in FIG. 5, the construction machine detecting section 42 further identifies a pair of markers corresponding to each construction machine based on the positions of the markers estimated by the three stereo cameras 3, respectively, and A construction machine position determination unit 421 that determines the position and direction of the construction machine from the position of the marker pair, a construction machine recognition unit 422 that recognizes the three-dimensional model of each construction machine from the three-dimensional model of the terrain, and each construction machine And a construction machine pattern storage unit 423 that stores the characteristic pattern of the three-dimensional model.

The construction machine position determining unit 421 uses a predetermined statistical process (for example, the average of the coordinate values from the three stereo cameras 3) for the three-dimensional coordinate values of the markers estimated by the three stereo cameras 3, for example. The majority of the coordinate values from the three stereo cameras 3 is calculated, or the most reliable value among the coordinate values from the three stereo cameras 3 is selected. The specific position coordinate value. Then, by classifying the plurality of fixed-position markers into a pair of markers having a predetermined mutual positional relationship, the pair of markers 61 and 62 attached to each construction machine are detected, and Pair marker 6
The representative position of 1, 62 is set as the position of the construction machine, and the direction of the construction machine is determined based on the arrangement direction of the markers 61, 62 of the pair. To determine this position and direction,
Do this for all construction equipment (that is, markers for all pairs).

The construction machine recognizing unit 422 is used by the construction machine position determining unit 42.
The distance image integration processing unit 431, which will be described later, creates using the position and direction of each construction machine from 1 and the three-dimensional characteristic patterns of construction machines of various models accumulated in the construction machine pattern storage unit 423. From the three-dimensional model data of the terrain,
The 3D model part corresponding to each construction machine is extracted. For example, from the three-dimensional model data of the terrain, the three-dimensional model portion of the area estimated to be the individual construction machine determined by the position and direction of the individual construction machine from the construction machine position determination unit 421 is extracted and taken out. By comparing the three-dimensional shape features of the three-dimensional model portion with the three-dimensional feature patterns of various types of construction equipment stored in the construction equipment pattern storage unit 423, the three-dimensional model portion of each construction equipment can be further improved. Accurately index and identify what model the construction machine is. The position and direction of each construction machine and the three-dimensional model thus obtained are stored in the GIS data storage unit 44 as elements of GIS data. (Note that the construction machine recognition unit 42
The process of extracting the three-dimensional model data of the construction machine by 2 may be omitted. In this case, the construction machine-related data included in the GIS data is only the position and direction of the construction machine from the construction machine position determination unit 421. )

The terrain generation unit 43 statistically processes the distance images from the three stereo cameras 3 and integrates the distance image integration processing unit 431, the processing result of the distance image integration processing unit 431, and the construction machine recognition unit 422 described above. And a terrain determination unit 432 that determines a three-dimensional model of the terrain at the construction work site based on the processing result of 1.

The range image integration processing unit 431 performs a predetermined statistical process on the range images from the three stereo cameras 3 (for example, the majority decision of the coordinate values from the three stereo cameras 3, or three). The most reliable value among the coordinate values from the stereo camera 3 is selected, and the final three-dimensional coordinate value of the terrain (including construction machinery) (that is, three-dimensional model data of the terrain) is applied. ).

A more specific method of the above statistical processing is the method disclosed in Japanese Patent Laid-Open No. 2002-32744, that is, voxel data in three-dimensional space based on distance images from a plurality of stereo cameras. Can be applied to apply the method of integration.

The terrain determining unit 432 removes the 3D model of the construction machine determined by the construction machine recognizing unit 422 from the 3D model data of the terrain (including the construction machine) from the distance image integration processing unit 431. , Generates three-dimensional model data of pure terrain (including stakes) that does not include construction machinery at the construction work site. This pure terrain 3D model data is GIS
It is stored in the GIS data storage unit 44 as a data element. (Note that when the construction machine recognition unit 422 is omitted as described above, the terrain determination unit 432 is also omitted. In that case, the three-dimensional topography including the construction machine from the distance image integration processing unit 431 is also included. The model data is the GIS data storage unit 44.
Stored in. )

The GIS data output section 45 outputs the GIS data in the GIS data storage section 44 to the outside. As an output mode, for example, the GIS data is provided to an external information processing device through a communication network, or the GIS data is used to draw and display an image of a construction work site viewed from a predetermined viewpoint. A mode such as “Yes” can be considered. Since the topography of the construction work site is three-dimensional model data, it is possible to display an image viewed from an arbitrary viewpoint. Further, since the position and direction of the construction machine are known, it is possible to display the construction machine and the terrain other than the construction machine by different colors in the image. In particular, when the three-dimensional model data of the construction machine is extracted, the construction machine can be clearly displayed in distinction from other topography. The 3D model of the terrain and the position, direction and 3D model of the construction machine are
Since it is a dynamic one that follows the movement of a moving image captured by a camera, it is possible to dynamically display an image based on those data.

Next, a constructional three-dimensional information generation system of a simpler construction according to the second embodiment will be described.

The system according to the present embodiment is a system for generating a distance image of a target area by using a still image using a digital camera or the like, and its configuration is shown in FIG.

The present system is composed of an image processing device 8. The image processing device 8 is composed of, for example, a general-purpose computer system, and the individual constituent elements or functions in the image processing device 8 described below are as follows. For example, it is realized by executing a computer program.

The image processing device 8 has, as its internal function,
The image input reception unit 81, the feature extraction unit 82, the stereo processing unit 84, the construction machine recognition unit 85, the coordinate conversion unit 86, and the data storage unit 87 are provided.

In this embodiment, still images taken by a digital camera or the like from a plurality of different shooting locations are used at the construction work site. At least two of the plurality of still images include a reference point such as stitching. Then, the image input receiving unit 81 captures the image data from each shooting location one by one in a fixed order for the plurality of shooting locations.

The feature extraction unit 82 extracts feature points from each of the captured images, compares the patterns of the extracted feature points, and specifies a region commonly included in at least two images.

The stereo processing unit 84 performs a stereo processing method for each of the specified common areas by using two or more images that share the common areas, thereby performing the terrain of the common areas (construction machines and sidings). The distance image of (including) is calculated, and the three-dimensional coordinates (three-dimensional model data) of the landform are determined from this distance image.

The construction machine recognizing unit 85 performs pattern matching between each part of the three-dimensional model data of the terrain from the stereo processing unit 84 and the characteristic pattern of the three-dimensional model of the construction machine prepared in advance, to thereby obtain the terrain. The 3D model portion of the construction machine is recognized and extracted from the 3D model data. Alternatively, as an alternative, a feature pattern of the construction machine image when the construction machine is viewed from various directions is prepared in advance, and each part of the distance image calculated by the stereo processing unit 84 and the construction machine image are prepared. By performing pattern matching with the feature pattern of
The image portion of the construction machine is recognized from the distance image, and the three-dimensional position coordinates of the construction machine are obtained from the image portion.

Then, the coordinate conversion unit 86 includes the three-dimensional model data of the terrain from the stereo processing unit 84 and the three-dimensional model data of the construction machine or the three-dimensional position coordinates from the construction machine recognition unit 85 in the input image. Convert to the coordinate value of the reference coordinate system in the construction work site with the reference point such as the tensioning as the reference. The coordinate-converted data is stored in the data storage unit 87 and is output to the outside as in the first embodiment.

The above-described embodiments of the present invention are examples for explaining the present invention, and are not intended to limit the scope of the present invention only to those embodiments. Those skilled in the art can implement the present invention in various other modes without departing from the gist of the present invention.

For example, in the above embodiment, the position and direction of the construction machine are detected from the two markers provided on the construction machine, but this is merely an example, and only one marker provided on the construction machine is detected. It is also possible to detect the position and direction of the construction machine from the marker (the direction can be detected from the shape of the marker), 3
The position and direction may be detected using more than one marker.
Alternatively, instead of or in combination with the method of using the marker installed on the construction machine, the pattern matching with the construction machine image, the detection method using the color information unique to the construction machine, or the like is used. It is also possible to detect the position and orientation of the machine.

Further, in the above embodiment, the distance images are combined for each stereo camera and the integration processing is performed by the host device. However, all the images captured by the cameras are transmitted to the host device, and the host device Can do all the processing consistently.

In the above embodiment, a plurality of multi-lens stereo cameras installed in different places are used, but instead of this, a plurality of monocular cameras are installed in different places, and the plurality of mono-eye cameras are installed. It is also possible to grasp the three-dimensional shape of the scene from the image from the camera.

In the above embodiment, the shape information of the construction machine is used.
(Marker or shape feature pattern of the construction machine itself) is registered in advance, and the construction information is used to detect the construction machine from the initially obtained 3D position data of the entire site. However, the registration target for such object detection is not limited to the construction machine. Information of a desired type of object such as a person or a building is pre-registered together with or instead of the construction machine, and the desired object is detected by a method such as pattern matching using the registered information. You can On the contrary, it is also possible to pre-register the information of the terrain and the background, and use the registered information to detect an object other than the terrain and the background, and to detect the movement of the object. The method will be useful in applications such as security systems).

Further, the finally output data is GI.
The data need not be S data, and may be data in other formats.

The image source does not necessarily have to be a camera as in the above-described embodiment, and an image acquired from a network or an image read by an image scanner may be input.

The site to which the present invention can be applied is not limited to the construction work site. It can be applied to various 3D real spaces.

[Brief description of drawings]

FIG. 1 is a diagram showing an arrangement of cameras in a three-dimensional information generation system according to a first embodiment of the present invention.

FIG. 2 is a diagram showing basic functions of the three-dimensional information generation system according to the first embodiment of the present invention.

FIG. 3 is a diagram showing a functional configuration of a three-dimensional information generation system according to the first embodiment of the present invention.

FIG. 4 is a diagram illustrating a detailed functional configuration of an image processing unit.

FIG. 5 is a diagram showing a detailed functional configuration of a host device.

FIG. 6 is a diagram showing a configuration of an image processing device of a three-dimensional information generation system according to a second embodiment of the present invention.

[Explanation of symbols]

1 ... Camera pole 2 ... camera 3 ... Stereo camera 4 ... Host device 5 ... Construction work site 6 ... Construction machinery 7 ... 8 ... Image processing device

   ─────────────────────────────────────────────────── ─── Continued front page    (72) Inventor Hiroshi Miwa             1200 Manda, Hiratsuka-shi, Kanagawa Made by Komatsu Ltd.             Seisakusho Institute (72) Inventor Hiroyoshi Yamaguchi             1200 Manda, Hiratsuka-shi, Kanagawa Made by Komatsu Ltd.             Seisakusho Institute F term (reference) 5B057 AA20 BA02 DA08 DB03 DB06                       DB09 DC03 DC09 DC25 DC32                       DC36

Claims (3)

[Claims] 1. A site three-dimensional data generation means for generating data relating to the three-dimensional positions of various objects existing on the site by using a plurality of images obtained by viewing the site from predetermined different places, and Specific object three-dimensional data detection means for obtaining data on the three-dimensional position of a specific object from data on the three-dimensional positions of various objects; A three-dimensional information generation system in the field, comprising another object three-dimensional data detection means for obtaining data on a three-dimensional position. 2. The system according to claim 1, wherein the obtained data on the three-dimensional position of the specific object and the data on the three-dimensional position of another object other than the specific object are stored.
An on-site three-dimensional information generation system further comprising data output means for outputting separately or together. 3. A step of generating data regarding a three-dimensional position of various objects existing on the scene using a plurality of images obtained by viewing the scene from predetermined different places, and a three-dimensional shape of the objects on the scene. Obtaining data on the three-dimensional position of the specific object from the data on the position, and obtaining data on the three-dimensional position of the object other than the specific object from the data on the three-dimensional position of the objects on the scene. A method of generating three-dimensional information on site.