CN110009985B - Sand table making devices based on machine learning - Google Patents
Sand table making devices based on machine learning Download PDFInfo
- Publication number
- CN110009985B CN110009985B CN201910239479.7A CN201910239479A CN110009985B CN 110009985 B CN110009985 B CN 110009985B CN 201910239479 A CN201910239479 A CN 201910239479A CN 110009985 B CN110009985 B CN 110009985B
- Authority
- CN
- China
- Prior art keywords
- landform
- sand table
- data
- projection
- prediction model
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 239000004576 sand Substances 0.000 title claims abstract description 130
- 238000010801 machine learning Methods 0.000 title claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 49
- 238000004519 manufacturing process Methods 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 19
- 230000000694 effects Effects 0.000 claims abstract description 13
- 238000003384 imaging method Methods 0.000 claims abstract description 10
- 230000008859 change Effects 0.000 claims description 23
- 238000012544 monitoring process Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 8
- 230000008054 signal transmission Effects 0.000 claims description 8
- 239000013589 supplement Substances 0.000 claims description 8
- 230000001502 supplementing effect Effects 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 7
- 238000004088 simulation Methods 0.000 description 7
- 238000012937 correction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000004033 plastic Substances 0.000 description 4
- 229920003023 plastic Polymers 0.000 description 4
- 238000002360 preparation method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000010146 3D printing Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000001746 injection moulding Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000002991 molded plastic Substances 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000002407 reforming Methods 0.000 description 1
- 238000007634 remodeling Methods 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000004148 unit process Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B25/00—Models for purposes not provided for in G09B23/00, e.g. full-sized devices for demonstration purposes
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09F—DISPLAYING; ADVERTISING; SIGNS; LABELS OR NAME-PLATES; SEALS
- G09F19/00—Advertising or display means not otherwise provided for
- G09F19/12—Advertising or display means not otherwise provided for using special optical effects
- G09F19/18—Advertising or display means not otherwise provided for using special optical effects involving the use of optical projection means, e.g. projection of images on clouds
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Accounting & Taxation (AREA)
- Marketing (AREA)
- Holo Graphy (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a sand table manufacturing device based on machine learning, belongs to the technical field of sand table manufacturing, and solves the problems that the existing sand table is long in manufacturing period, poor in authenticity in display and incapable of being adjusted in real time. The method comprises the following steps: the control terminal is used for constructing a prediction model and solving the projection parameters and complete landform data of the laser holographic projector in real time; the laser holographic projector is used for carrying out sand table projection imaging; the mechanical arm is used for manufacturing the landform of the sand table; the binocular camera, the laser ranging sensor and the three-dimensional scanner are used for collecting data required by model training. In the device, laser holographic projection can truly show the state of landform, and the mechanical arm rapidly stacks and adjusts the landform; the model trained by machine learning can be used for solving the optimal projection parameters and the landform information in real time, the projection state and the landform are corrected and adjusted automatically in real time, and the manufactured sand table achieves the optimal projection size and effect.
Description
Technical Field
The invention relates to the technical field of sand table manufacturing, in particular to a sand table manufacturing device based on machine learning.
Background
Military sand tables typically contain two main parts: one is a bottom tray and the other is a simulation of a mountain river. At present, the manufacture of mountains and rivers mainly adopts two materials, one is a plastic simulation product, and the other is sand.
The sand table that uses plastic simulation article as the owner needs to take the form of special customization, at first carries out the drawing of 3D drawing to true physiognomy, carries out the shape that 3D printed or moulded plastics to the drawing after that, makes out simulation article preparation, puts these simulation articles on the tray again for show the physiognomy to other people. On one hand, the sand table is long in preparation period, and the preparation of landforms needs to be carried out in a 3D printing or injection molding mode and needs to prepare scenes; in a sudden state, the landform is not prepared in time, cannot be adjusted in time, and cannot meet the condition of tracking the change of a real scene. On the other hand, the exhibition area is limited, as the landform is manufactured by 3D printing or injection molding glue, the size of the plastic part is required to a certain extent, the cost is correspondingly increased for the size exceeding the conventional size, the reusability is lacked after the plastic part is used, each landform is unique, and the existing landform cannot be applied to other areas for exhibition, so that the waste is caused.
The sand table mainly using sand is characterized in that required sand is covered on a tray firstly, then each characteristic is measured and marked according to an existing drawing (such as a mountain and a river), finally, the sand is piled or dug according to a marking point, the piled part represents a mountain, and the dug part represents a river. On one hand, the sand table is long in preparation and manufacturing period, real landforms need to be scaled in equal proportion, and marking is carried out in the sand table; meanwhile, the whole process of the production needs manual work for producing landform, such as sand piling to represent mountains and sand digging to represent lakes. On the other hand, in the use stage of the scene, firstly, the accuracy is lacked, different landforms can be represented in the same display mode, and people are prone to causing mishaps, for example, a lake and a mountain depression terrain can be simultaneously represented in a sand pit form, and the marking is needed for distinguishing; secondly, the reality is lacked, the color of the sand is single, and the real scene cannot be displayed; finally, the adjustment is inconvenient, the sand needs to be adjusted manually when the landform is changed in use, the difficulty is increased and the efficiency is low according to the complexity of the change and the increase of the size.
Disclosure of Invention
In view of the above analysis, the present invention aims to provide a sand table making device based on machine learning, so as to solve the problems of long making period, lack of authenticity in display and incapability of real-time adjustment of the prior sand table.
The purpose of the invention is mainly realized by the following technical scheme:
provided is a sand table making device based on machine learning, including:
the control terminal is used for constructing a laser holographic projection prediction model and a landform information prediction model, training the models, and solving the projection parameters and complete landform data of the laser holographic projector in real time through the trained models;
the laser holographic projector is used for carrying out sand table projection imaging according to the numerical value of the projection parameter;
the mechanical arm is used for manufacturing the landform of the sand table according to the complete landform data;
the binocular camera and the laser ranging sensor are both suspended right above the sand table, are connected with the control terminal and are used for collecting data required by training of the laser holographic projection prediction model;
and the three-dimensional scanner is used for scanning the real landform and acquiring data required by training the landform information prediction model.
The invention has the following beneficial effects: the sand table manufacturing process of the device is fast and efficient, and the instantaneity problem and the authenticity problem of the traditional sand table can be effectively solved through machine learning, laser holographic projection and mechanical arm manufacturing; laser holographic projection can be more real show the state of simulation landform (for example, mountain river etc.), uses the arm can be quick pile up the topography and adjust. Simultaneously through constantly monitoring external environment, when sand table size and outside show environment change, utilize the model that machine learning trained to seek optimum projection parameter and landform information in real time, carry out automatic correction and adjustment to the state of projection and landform, the sand table of making reaches best projection size and effect.
On the basis of the scheme, the invention is further improved as follows:
further, the robot arm includes: moving arms, a chassis, a laser distance sensor and a dexterous hand;
one end of the moving arm is provided with a dexterous hand, the other end of the moving arm is arranged on the chassis, and the moving arm rotates by taking a connecting point with the chassis as an axis;
the chassis is provided with a moving assembly for moving the position of the mechanical arm;
the dexterous hand rotates by taking a connecting point with the moving arm as an axis and is used for stacking landforms;
the number of the laser distance sensors is at least two, and the laser distance sensors are respectively arranged on the dexterous hand and the chassis and used for monitoring obstacles in the moving process.
Further, the control terminal includes:
the data acquisition module is used for acquiring a data set required by a training laser holographic projection prediction model and a landform information prediction model;
the prediction model construction and training module is used for constructing a laser holographic projection sand table prediction model and a landform information prediction model, and respectively training the two models by using the data set acquired by the data acquisition module to obtain the trained laser holographic projection sand table prediction model and the trained landform information prediction model;
the projection parameter and complete landform data solving module is used for inputting the length, width, height and depth information of the sand table into the trained laser holographic projection prediction model to obtain projection parameters; the landform information prediction model is also used for inputting the contour of the landform into the trained landform information prediction model to obtain complete landform data;
the signal transmission module is used for transmitting the projection parameters and the projection parameters obtained by the complete landform data obtaining module to the laser holographic projector; and simultaneously transmitting the obtained complete landform data to the mechanical arm.
Further, a calibration tool with a cross cursor for position calibration is also included; the data acquisition module comprises: the device comprises a region dividing unit, a length and width dimension collecting unit and a depth and shallow dimension collecting unit;
the area dividing unit is used for dividing the internal area of the sand table and taking the intersection point of each divided sub-area as a reference point;
the length and width collecting unit and the depth and depth collecting unit are used for being matched with a binocular camera, a laser ranging sensor, a laser holographic projector and a calibration tool to collect data of all reference points to obtain a data set required by a training model;
the data set includes a planar position coordinate, a vertical position coordinate, a focus range, and a sharpness of the fiducial.
Further, the data acquisition module further comprises: the system comprises an outline scanning unit, a key point grabbing unit and a data supplementing unit;
the contour scanning unit receives the landform contour scanned by the three-dimensional scanner and collects corners appearing in the contour;
the key point grabbing unit grabs the length, width and height information of the landform key points according to the positions of the corners;
and the data supplement unit is used for decomposing the parts between the adjacent key points, acquiring the length, width and height data of each decomposed part, and obtaining complete landform data for training a landform information prediction model.
Further, the data acquisition of the reference points includes:
the long and wide size collection unit controls the laser holographic projector to project cross-shaped cursors, the cross-shaped cursors are sequentially projected at the positions of the reference points, the position of the calibration tool is adjusted until the cross-shaped cursors in the calibration tool are overlapped with the cross-shaped cursors of the cursors, the long and wide size collection unit records the plane position coordinates of the reference points at the moment, and long and wide size collection of the sand table is completed;
the depth size collection unit controls the laser holographic projector to project cross-shaped cursors, the cross-shaped cursors are sequentially projected at the positions of the reference points, the calibration tool is moved upwards/downwards under the condition that the positions of the cross-shaped cursors in the calibration tool and the cross-shaped cursors of the cursors are overlapped, until the cross-shaped cursors in a binocular camera display interface achieve the best display effect, the depth size collection unit records the vertical height, the focusing range and the definition information of the positions as the vertical position coordinates, the focusing range and the definition of the reference points, and the depth size collection of the sand table is completed.
Further, the prediction model building and training module comprises:
the parameter initialization unit is used for initializing the network weight and the bias and randomly selecting a first input sample in the training data set;
the parameter processing unit is used for carrying out neuron activation forward propagation, carrying out weight and bias processing on the first input sample through a hidden layer and solving a result and an error of an output layer;
a parameter adjusting unit, which performs back propagation according to the error and adjusts the network weight and the bias;
and the training monitoring unit judges whether the training is finished according to a preset finishing condition.
Further, the module for calculating the projection parameters and the complete landform data comprises:
the high-complexity area marking unit is used for comparing the high-complexity area in the real landform with the area of the current sand table and marking the point location area which accords with the high complexity in the sand table;
a weight determination unit for determining the position, number and weight of the demand degree of the marked high-complexity point location region;
and the projection parameter calculating unit is used for calculating the focusing range and definition by utilizing the trained model according to the length, width, height and depth information of the sand table and the determined weight.
Further, the projection parameter and complete landform data obtaining module searches and matches in the established existing data set after obtaining the length, width, height and depth information of the sand table, directly selects the corresponding focusing range and definition information when matching is consistent, and obtains the focusing range and definition information by adopting a trained laser holographic projection sand table prediction model when matching is inconsistent; after the landform outline is obtained, searching and matching are carried out in the established existing database, and when the matching is consistent, corresponding complete landform data is directly selected; and when the matching is inconsistent, obtaining complete landform data by adopting the trained landform information prediction model.
The device further comprises a landform monitoring sensor, a control terminal and a display, wherein the landform monitoring sensor is used for monitoring real landform information in real time and transmitting the information to the control terminal, the control terminal compares the interval time of the change of the landform with a preset reference when judging that the landform changes, and ignores the interval time of the change of the landform when the interval time of the change of the landform is smaller than the reference; when the interval time of the landform change is larger than the reference, on one hand, the projection parameter and complete landform data solving module carries out parameter prediction again on the whole region or high-complexity region of the landform to obtain a new focusing range and a new definition parameter; on the other hand, the projection parameter and complete landform data solving module carries out key point collection and landform supplement on a new landform change area to obtain complete landform data.
In the invention, the technical schemes can be combined with each other to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
FIG. 1 is a diagram of a sand table making apparatus based on machine learning according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a sand table area partitioning and calibrating tool according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating the gathering of geomorphic data according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating a neural network structure according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating training a constructed prediction model according to an embodiment of the present invention;
FIG. 6 is a flowchart illustrating a method for determining projection parameters according to an embodiment of the present invention;
FIG. 7 is a diagram illustrating a method for obtaining topographic data in accordance with an embodiment of the present invention;
FIG. 8 is a diagram illustrating a key point merge result according to an embodiment of the present invention;
FIG. 9 is a schematic diagram of a laser projector according to an embodiment of the present invention;
FIG. 10 is a schematic view of a robotic arm according to an embodiment of the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
The invention discloses a sand table manufacturing device based on machine learning, which comprises a control terminal and a sand table manufacturing device, wherein the control terminal is used for constructing a laser holographic projection prediction model and a landform information prediction model, training the models and solving projection parameters and complete landform data of a laser holographic projector in real time through the trained models, as shown in figure 1;
the laser holographic projector is used for carrying out sand table projection imaging according to the numerical value of the projection parameter;
the mechanical arm is used for manufacturing the landform of the sand table according to the complete landform data;
the binocular camera and the laser ranging sensor are both suspended right above the sand table, are connected with the control terminal and are used for collecting data required by training of the laser holographic projection prediction model;
and the three-dimensional scanner is used for scanning the real landform and acquiring data required by training the landform information prediction model.
Compared with the prior art, the sand table manufacturing device based on machine learning provided by the embodiment has the advantages that all the devices are matched with each other, the sand table manufacturing process is fast and efficient, and the instantaneity problem and the authenticity problem of the traditional sand table can be effectively solved through machine learning, laser holographic projection and mechanical arm manufacturing; laser holographic projection can be more real show the state of simulation landform (for example, mountain river etc.), uses the arm can be quick pile up the topography and adjust. Simultaneously through constantly monitoring external environment, when sand table size and outside show environment change, utilize the model that machine learning trained to seek optimum projection parameter and landform information in real time, carry out automatic correction and adjustment to the state of projection and landform, the sand table of making reaches best projection size and effect.
Specifically, the device gives full play to the advantages of artificial intelligence, a laser holographic projection technology and mechanical arm manufacturing, the control terminal automatically and immediately obtains an optimal parameter solution through machine learning, laser holographic projection simulates and shows an actual scene more truly, and the mechanical arm replaces manual work to automatically perform terrain manufacturing and adjustment. The control terminal includes: the system comprises a data acquisition module, a prediction model construction and training module, a projection parameter and complete landform data solving module and a signal transmission module; wherein,
the data acquisition module is used for acquiring a data set required by a training laser holographic projection prediction model and a landform information prediction model;
the prediction model building and training module is used for building a laser holographic projection sand table prediction model and a landform information prediction model, and training by using the data set obtained by the data acquisition module to obtain the trained laser holographic projection sand table prediction model and the landform information prediction model;
the projection parameter and complete landform data solving module is used for inputting the information of the sand table such as length, width, height, depth and the like into the trained laser holographic projection prediction model to obtain projection parameters (such as a focusing range, a definition value and the like); the landform information prediction model is also used for inputting the contour of the landform into the trained landform information prediction model to obtain complete landform data;
the signal transmission module is used for transmitting signals between the laser holographic projector, the binocular camera, the laser ranging sensor, the mechanical arm, the three-dimensional scanner and the control terminal, and transmitting projection parameters such as the focusing range, the definition value and the like obtained by the projection parameter and complete landform data obtaining module to the laser holographic projector for projection imaging; meanwhile, the obtained complete landform data is transmitted to the mechanical arm, and the landform is piled up and adjusted.
Further, the data acquisition module is divided into two parts: a laser projection data acquisition submodule and a landform manufacturing data acquisition submodule; the laser projection data acquisition submodule is used for acquiring a data set required by a training laser holographic projection sand table prediction model, and the landform making data acquisition submodule is used for acquiring a data set required by a training landform information prediction model.
The laser projection data acquisition submodule comprises: the system comprises an area dividing unit, a length and width collecting unit and a depth and shallow collecting unit, wherein each unit is matched with a laser holographic projector, a binocular camera, a laser ranging sensor and a calibration tool to collect data and acquire a data set containing a large amount of data (the data set has a target value). When actual data acquisition is performed: the region dividing unit divides the internal region of the sand table and takes the intersection point of each divided sub-region as a reference point; the method comprises the following steps that a binocular camera, a laser ranging sensor and a laser holographic projector are used for locking the whole area of the sand table and positioning all datum points; and finally, the length-width dimension collection unit and the depth-width dimension collection unit respectively control the binocular camera, the laser ranging sensor and the laser holographic projector, and cooperate with a calibration tool to sequentially collect data of all the reference points to obtain a data set required by the training model.
Specifically, the area dividing unit divides the area inside the sand table, and takes the intersection point of each divided sub-area as a reference point. In this embodiment, a rectangular sand table is taken as an example, and as shown in fig. 2, a sand table frame prepared in advance is laid (when the sand table frame is not prepared, bricks can be used for piling or digging 15 to 25 CM down on the flat ground) and is matched with the current place as much as possible, sand soil with appropriate humidity of 3 to 5CM is laid in the sand table frame (the sand soil is picked up by hand to be easy to grasp into a cluster and to be loose when being thrown down), and the sand table frame is flattened and compacted by a wood plate to be used as a reference surface of the sand table. The region dividing unit automatically divides the sand table region, the dividing mode can be selected according to the shape of the sand table and the projection display precision requirement, illustratively, a rectangular sand table is divided into 20 sub-rectangles according to a 4-by-5 matrix, and 12 intersection points of the sub-rectangles in the sand table are used as reference points.
After the area division is completed, a binocular camera, a laser ranging sensor and a laser holographic projector are installed at a position capable of covering a sand table, the binocular camera is used for locking the whole area of the sand table (generally installed right above the central point of the rectangular sand table), the 12 datum points are located, the control terminal controls the laser holographic projector (generally installed at a position forming an angle of 45 degrees with the plane of the sand table), so that the projection definition on the datum plane of the sand table is optimal, a calibration tool is matched to collect and record sand table size data (including length, width and depth dimensions), and a data set of 'sand table size-12 point positions-focusing power/definition' is obtained in a summary mode.
The long and wide size collecting unit is matched with the binocular camera, the laser ranging sensor, the laser holographic projector and the calibration tool to complete the long and wide size collection of the sand table; specifically, the laser holographic projector is controlled to project a cross cursor, the cross cursor is projected at the position of a point 1, and the color of the cursor to be calibrated at the time is red. A calibrator holds the calibration tool by hand, the cross positions of the cursor and the cross positions of the cross in the calibration tool are overlapped, the focal length value of the binocular camera is kept fixed, a laser ranging sensor (installed right above a sand table) is controlled to calibrate, and the position coordinate of the point 1 is recorded (the surface of the sand table is used as a reference surface). It should be noted that, the laser ranging sensor is used for further calibration, so that the size data on the local details can be corrected, and the acquired position information of the reference is more accurate; if the position of the 1 point is calibrated, the color of the cursor is changed to green, which indicates that the position of the point is collected. And when the position of the point 1 is calibrated, controlling the cross cursor of the laser holographic projector to move to the position of the point 2, and repeating the above calibration mode until all the data of the 12 reference points are collected, and then completing the collection of the length and the width of the sand table.
And the depth size collecting unit is matched with the binocular camera, the laser holographic projector and the calibration tool on the basis of completing the collection of the length and the width sizes to collect the height and the depth of the sand table. The control terminal controls the laser holographic projector to project a cross cursor, the cross cursors are sequentially projected at the positions of the reference points, an operator keeps the state that the cross positions of the cross cursors in the calibration tool are overlapped with the cross positions of the cursors, the calibration tool is moved upwards/downwards until the cross cursors in the binocular camera display interface achieve the best display effect, and the depth size collection unit records the vertical height (relative to a reference surface), the focusing range and the definition information of the positions as the vertical position coordinates, the focusing range and the definition of the reference points.
In a specific working process, depth collection can be divided into two situations of height collection and depth collection, and when the height collection is carried out: the light and dark size collecting unit controls the laser projector to project a cross cursor, the cross cursor is projected at the position of a 1 point, and the color of the cursor to be calibrated is red. The calibration staff holds the calibration tool by hand, overlaps the position of the cross in the calibration tool and the position of the cross of the cursor and moves upwards at the same time, and notes that the cross and the cursor are required to keep an overlapped state in the process of moving upwards. With the 'ten' in the calibration tool being continuously lifted up, the position of the '1' point is calibrated and positioned through the binocular camera, the best display effect (the clearest display) is found on the height, and the obtained height value of the point is the height coordinate of the '1' point (the binocular camera is automatically positioned); at this time, the light and dark size gathering unit changes the cursor color from red to green, indicating that the data gathering at the "1" dot height is completed. And when the height of the position of the point 1 is collected, controlling the cursor to move to the position of the point 2, and repeating the above collecting mode until the data of the point 12 are completely collected, and then the height of the sand table is collected. In performing depth collection: the light and dark size collecting unit controls the laser projector to project a cross cursor, the cross cursor is projected at the position of a 1 point, and the color of the cursor to be calibrated is red. The operator digs a pit in the area of the point 1, then holds the calibration tool, overlaps the cross in the calibration tool with the cross of the cursor, and moves downwards towards the bottom of the pit, and the operator needs to keep the overlapping state of the cross and the cursor in the process of moving downwards. As the "ten" in the calibration tool is moved down continuously, the best display effect is found in depth by the position of the binocular camera at the "1" point. The light and dark size gathering unit changes the cursor color from red to green at this time, indicating that data gathering of the "1" dot depth is completed. When the position depth of the point 1 is collected, the cursor moves to the position of the point 2, the collection mode is the same as the above, and so on, and the depth collection of the sand table is finished until the data of the point 12 are completely collected; after acquiring the height or depth signal, the depth size collecting unit combines the focusing range and the definition of the laser projector on the reference surface to obtain the focusing range and the definition information of the optimal display position as the focusing range and the definition of the corresponding reference point. In addition, when the laser projector performs real environment display, red light, green light and blue light information at the above reference points can be recorded, and data collection statistics are shown in table 1.
Table 1 data collection statistics table:
the landform making data acquisition submodule is matched with the three-dimensional scanner to acquire data and acquire a data set (the data set has a target value) containing a large amount of data; in the actual acquisition process, the model can be established according to the existing landform or the data of the existing sand table landform model, such as mountains and rivers, can be directly acquired. Specific data are shown in table 2 and table 3; after the three-dimensional scanner scans the landform outline, the landform outline is sent to a landform making data acquisition submodule, and the submodule comprises: the system comprises an outline scanning unit, a key point grabbing unit and a data supplementing unit; wherein the contour scanning unit: automatically collecting corners appearing in the contour; the key point grabbing unit: according to the positions of the corners, capturing length, width and height information of landform key points (vertexes of the corners); a data supplement unit: as shown in fig. 3, according to the real landform state, the length, width and height of the landform are decomposed into small parts (which can be decomposed according to the complexity of the actual landform and the requirement of the display precision), and further, the length, width and height data of the small parts between the corners are collected, i.e. more detailed landform data are obtained to be used as a landform sample of the mountain, so that the prediction model can be learned.
TABLE 2 mountain data
TABLE 3 river data
The prediction model construction and training module comprises a prediction model construction unit and is used for constructing a laser holographic projection prediction model and a landform information prediction model; through the constructed model, when the size of the sand table and the external environment are changed, optimal laser holographic projection parameter data are obtained in real time, and the optimal display effect is achieved; when the landform is changed, the contour of the landform can be rapidly analyzed, details in the landform can be automatically supplemented, and complete landform data can be obtained. The two prediction models constructed by the prediction model construction unit both adopt a supervised machine learning algorithm, and the prediction models can be constructed through various machine learning algorithms, in the embodiment, the constructed neural network is as shown in fig. 3, and numerical information of focusing power/definition can be automatically obtained in the model by inputting the size of a sand table; the complete landform data can be automatically obtained by inputting the landform outline.
The prediction model construction and training module further comprises: the device comprises a parameter initialization unit, a parameter processing unit, a parameter adjusting unit and a training monitoring unit; respectively training the two prediction models constructed by the prediction model construction unit by utilizing a training data set obtained by a data acquisition module, and continuously adjusting the weight of the characteristics in the training process until the value returned by the prediction model meets the precision requirement in order to make the value returned by the prediction model approach to a target value as much as possible; in particular, as shown in figure 4,
and the parameter initialization unit sets a random number for the network weight and the bias in the initialization stage and randomly selects a first input sample in the data set. During the machine learning process, this portion of the network weights and biases are continually adjusted as the actual values differ from the target values.
The parameter processing unit is used for carrying out neuron activation forward propagation, carrying out weight and bias processing on the input samples through a hidden layer, and solving the result and expected error of an output layer; in the neural network of figure 3 of the drawings,
represents the weight between the ith node of the L-th layer and the jth node of the L + 1-th layer, and the weight between the L1 and the L2 layer is expressed as Ll
The weight between the L2 and L3 layers is
A bias term representing the ith node of the l +1 th layer; by using
Represents the input value of the jth node of the l +1 th layer. When l is equal to 1, the ratio of the total of the two,
and represents the output value of the jth node of the l +1 th layer after the jth node is subjected to the activation function theta (x). The formula is as follows:
thus, one training is completed, and an output result h is obtainedW,b(x)。
And the parameter adjusting unit is used for performing back propagation according to the error and adjusting the network weight and the bias. Wherein, for the output layer, Errj＝Oj(1-Oj)(Tj-Oj) For the hidden layer, Errj＝Oj(1-Oj)∑Errkwjk(ii) a Weight update, Δ Wij＝(l)ErrjOj，Wij’＝Wij+ΔWij(ii) a Offset update, Δ θj＝(l)Errj，θj＝j+Δθj。
The training monitoring unit is used for judging whether the training is finished or not, judging whether the training is finished or not according to a preset training finishing condition, illustratively finishing the training when the updating of the weight is lower than a certain threshold, the predicted error rate is lower than a certain threshold, a preset certain cycle number is reached and other conditions, and otherwise, continuously selecting a new sample for training.
The projection parameter and complete landform data solving module can be further divided into: the laser holographic projector projection parameter solving submodule and the relief integrity data solving submodule; wherein,
the projection parameter obtaining submodule of the laser holographic projector is used for obtaining the imaging parameters of the laser imager by utilizing a trained model after inputting the length, width, height and depth information of the sand table, as shown in figure 5, when the length, width, height and depth of the sand table are changed, only the size information of the sand table or the length, width, height and depth data of 12 datum points need to be input, and the projection parameter obtaining submodule of the laser holographic projector can automatically calculate the parameters of the focusing range and the definition, such as the parameters of x2 and y2 in table 1; and packing the projection parameters (red light, green light, blue light, focusing range and definition), transmitting the packed projection parameters to a laser holographic projector through a signal transmission module, and projecting the laser holographic projector on a sand table according to the projected parameter data.
In order to improve the authenticity of the display of the laser projection sand table, before the trained model obtains the projection parameters such as the focusing power and the definition, the projection parameter calculation submodule of the laser holographic projector can select a high-complexity area and carry out weighting so as to improve the prediction effect of the prediction model, and the submodule further can comprise: the system comprises a high-complexity area marking unit, a high-complexity area weight determining unit and a projection parameter solving unit; in particular, the amount of the solvent to be used,
and the high-complexity area marking unit is used for comparing the high-complexity area of the real landform to be simulated with the area of the current sand table and marking the point location area which accords with the high complexity in the sand table. For example, the high complexity region is 1 point or 4, 5 points … (note that if a specific region is required, the region is marked as a high complexity region by human before the processing terminal performs automatic alignment).
And the weight determining unit is used for determining the weight of key factors such as the position, the number, the requirement degree and the like of the high-complexity point location area. Considering that the complexity of each region in the simulated real environment is different, corresponding key factors need to be synthesized so as to confirm a certain point or certain points with the highest requirements on definition and focusing range, and achieve the best projection effect.
And the projection parameter calculation unit processes the focus range and the definition value contained in the covered area by utilizing the trained prediction model according to the length, width, height and depth of the sand table and the determined weight to find the most suitable focus range and definition value. For example, if the weighted selected regions are the locations of point 1 and point 2, as shown in Table 4, then the X1, X2, and Y1, Y2 values are processed to obtain the corresponding X and Y values.
TABLE 4 Focus Range and sharpness solution
It should be noted that, in order to improve the real-time performance, when the length, width, height, and depth of the sand table change, the projection parameter obtaining unit first searches and matches in the existing constructed database, and when the matches are consistent, directly selects the corresponding focusing range and definition information.
The complete landform data acquiring submodule analyzes the contour of the landform by utilizing the trained landform information prediction model when the landform changes, selects data of a plurality of key points, and captures landform data to be presented in the established landform information database or automatically supplements details in the landform information database according to the landform information prediction model to achieve the effect of being the same as the real landform environment.
During actual work, in order to improve the real-time performance, the submodule can further screen the extracted key points, and unnecessary key point input is reduced. Specifically, firstly, determining key points of a contour, collecting corners in the scanned contour, and taking the vertexes of all the corners as the key points; as shown in fig. 7, coordinates of point 1 to point N are collected; starting from the first corner, the distances between all adjacent corners are calculated, for example, the distance 1-2, the distance 2-3 …; then, screening the key points according to the distances, presetting a distance value x as a reference by the geomorphic integrity data acquisition submodule, comparing all the distances with the reference, if the distances are smaller than the reference value, giving up the distances, and if the distances are larger than the reference value, keeping the distances; for example, if the distance 4-5 is less than the reference value x, point 5 is discarded. Then taking the distance 4-6, comparing with the reference value x, if the distance 4-6 is smaller than the reference value x, abandoning … and so on. And after screening, when the obtained key points are discontinuous, merging the key points, and correspondingly processing discontinuous parts for merging. For example, in fig. 8, point 5 is discarded, and points 4 and 6 are processed on the x and y axes to yield a new point 6 position. After merging, the positions of all points are reordered in order, as shown in fig. 8, for example, the position of a new point 6 is changed to a point 5, and the sorted continuous key points are ready for the next adjustment. Finally, inputting the screened and combined key points into a trained landform information prediction model, automatically supplementing missing details in the contour among the key points, and supplementing missing data of x2, x4, x6, x8 and h2 by using the prediction model; and the complete landform data obtained after the supplement is sent to the mechanical arm in real time through the receiving signal transmission module.
And the laser holographic projector receives the projection parameter values sent by the signal transmission module in real time to perform sand table projection imaging. As shown in fig. 9, the laser holographic projector in this embodiment adopts a three-primary-color laser technology, and uses laser beams to transmit pictures, wherein the optical components of the laser projector mainly include red, green and blue three-color light valves, a beam combining X-prism, a projection lens and a driving light valve. There are three colors of red, green and blue lasers in the laser holographic projector. The laser is expanded by the corresponding optical element and the processing chip in the machine and then transmitted to the X prism to integrate the three beams of laser, and then the integrated laser is transmitted to the projection curtain by the projection objective, so that the projection display process of the whole laser holographic projector is completed.
The mechanical arm receives complete landform data sent by the signal transmission module in real time, and the mechanical arm quickly piles up and adjusts landforms according to the complete landform data, so that the time for manually establishing a model for the landforms is saved. The robot arm, as shown in fig. 10, includes: moving arms, a chassis, a laser distance sensor and a dexterous hand; wherein, one end of the movable arm is provided with a dexterous hand, the other end is arranged on the chassis, and the movable arm carries out omnibearing rotation by taking a connecting point with the chassis as an axis; the chassis is provided with a moving component (such as a wheel); the dexterous hand can realize the all-round rotation; the number of the laser distance sensors is at least two, and the laser distance sensors are respectively arranged on the dexterous hand and the chassis and used for monitoring obstacles in the moving process.
During specific work, firstly, a base point of the mechanical arm is determined: before the mechanical arm works, the mechanical arm is placed at a certain position on the periphery of the sand table, and the coordinate of the position is recorded into the control terminal to be used as a position base point of the mechanical arm. Then, the moving position of the mechanical arm is determined, the control terminal calculates the complexity of the whole sand table landform, arranges the sand table landform according to the complexity, and sends the positions of the complexity area to the mechanical arm in sequence (the complexity is high- > low). Finally, the mechanical arm moves through the chassis moving part according to the sequence of the base point position, the high-complexity region position and the high-low complexity region position; at the in-process that removes, measure the barrier through the range finding inductor, prevent the collision, when every removes a assigned position, carry out the piling task through dexterous hand, finish until all position landforms pile up, then the arm playback, remove original reference position, to this, the piling up work of landform is accomplished to the arm.
It should be noted that, in the process of stacking landforms, the sand table can be more efficiently and accurately stacked by using dexterous hands. The smart hand is provided with a laser distance sensor for avoiding obstacles, and during stacking, in the process of moving from the outside of the sand table to the inside of the sand table, the smart hand continuously detects whether an obstacle exists in the front, such as a stacked mountain …, and stops moving if the obstacle is detected, adjusts the position of the smart hand, changes the smart hand into an upward movement and continues moving to a target position.
It should be noted that, in order to solve the problems that the traditional sand table has poor instantaneity, and when the landform changes, real-time adjustment cannot be performed, and the real landform cannot be reflected. The device in the embodiment further comprises a landform monitoring sensor (for example, video or image acquisition and transmission equipment), wherein the landform monitoring sensor monitors real landform information in real time and transmits the real landform information to the control terminal, the control terminal judges whether the landform information changes or not, and when the landform information changes, whether the constructed landform information and projection are updated or not is judged according to preset conditions; specifically, a time interval is preset as a reference (the time interval can be set according to actual precision requirements, hardware conditions, sand table scale and the like), when the change of the landform is monitored, the interval time of the landform change is compared with the reference, and if the interval time of the landform change is smaller than the reference, the interval time of the landform change is ignored; if the interval time of the change of the landform is greater than the reference, on one hand, the projection parameter solving submodule carries out parameter prediction again on the whole region or the high-complexity region of the landform to obtain a new focusing range and definition parameters and sends the new focusing range and definition parameters to the laser holographic projector for projection imaging; on the other hand, the geomorphic integrity data acquisition submodule collects key points of a new geomorphic change area, supplements geomorphic data, and sends the geomorphic data to the mechanical arm for stacking;
considering the time cost required by the mechanical arm to re-stack the terrain, wherein the interval time of change of the terrain is greater than a reference, after collecting key points of a new terrain, the control terminal adopts different stacking modes according to the change degree of the terrain, and specifically, the collected new key points and recently collected key point parameters are compared in a preset error range (specific numerical values can be set according to conditions such as actual display effect, hardware equipment and real-time requirement); when the updated key point parameter is larger than the error range, the mode of 'reforming' is adopted, and when the updated key point parameter is smaller than the error range, the mode of 'small-range correction' is adopted.
In the remodeling mode, the landform is smoothed and remodeled, and the mechanical arm firstly smoothes the landform of the area into an initial state according to initial parameters (a height Z coordinate in the initial state and an X, Y axis coordinate); then, the obtained latest geomorphic information is utilized to be re-tiled (step S202 is executed). In the small-range correction mode, the region with changed landform is further taken as a reference, the key points of the contour in a certain range around the region are collected, the latest landform information is obtained, and the new landform information is piled up again.
The device adds artificial intelligence, laser holographic imaging technology and mechanical arm landform manufacturing in military sand table manufacturing, and can solve the problems brought by the prior sand table; the laser holographic imaging technology and the rapid automatic manufacturing of the landform of the mechanical arm can solve the problems of accuracy and authenticity. On the basis, the device also has the interactive functions of distance measurement, position marking and the like, the distance between two points in the sand table can be obtained through the laser ranging sensor, the point of interest is calibrated, and more information on the battlefield can be obtained in real time.
Those skilled in the art will appreciate that all or part of the flow of the method implementing the above embodiments may be implemented by hardware associated with computer program instructions, and the program may be stored in a computer readable storage medium. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (8)
1. A sand table making device based on machine learning is characterized by comprising:
the control terminal is used for constructing a laser holographic projection prediction model and a landform information prediction model, training the models, and solving the projection parameters and complete landform data of the laser holographic projector in real time through the trained models;
the laser holographic projector is used for carrying out sand table projection imaging according to the numerical value of the projection parameter;
the mechanical arm is used for manufacturing the landform of the sand table according to the complete landform data;
the binocular camera and the laser ranging sensor are both suspended right above the sand table, are connected with the control terminal and are used for collecting data required by training of the laser holographic projection prediction model;
the three-dimensional scanner is used for scanning real landform and collecting data required by training the landform information prediction model;
the control terminal includes:
the data acquisition module is used for acquiring a data set required by a training laser holographic projection prediction model and a landform information prediction model;
the prediction model construction and training module is used for constructing a laser holographic projection sand table prediction model and a landform information prediction model, and respectively training the two models by using the data set acquired by the data acquisition module to obtain the trained laser holographic projection sand table prediction model and the trained landform information prediction model;
the projection parameter and complete landform data solving module is used for inputting the length, width, height and depth information of the sand table into the trained laser holographic projection prediction model to obtain projection parameters; the landform information prediction model is also used for inputting the contour of the landform into the trained landform information prediction model to obtain complete landform data;
the signal transmission module is used for transmitting the projection parameters and the projection parameters obtained by the complete landform data obtaining module to the laser holographic projector; meanwhile, the obtained complete landform data is transmitted to the mechanical arm;
the device also comprises a landform monitoring sensor, a control terminal and a display, wherein the landform monitoring sensor is used for monitoring real landform information in real time and transmitting the information to the control terminal, when the control terminal judges that the landform changes, the interval time of the landform change is compared with a preset reference, and when the interval time of the landform change is smaller than the reference, the interval time of the landform change is ignored; when the interval time of the landform change is larger than the reference, on one hand, the projection parameter and complete landform data solving module carries out parameter prediction again on the whole region or high-complexity region of the landform to obtain a new focusing range and a new definition parameter; on the other hand, the projection parameter and complete landform data solving module carries out key point collection and landform supplement on a new landform change area to obtain complete landform data.
2. The apparatus of claim 1, wherein the robotic arm comprises: moving arms, a chassis, a laser distance sensor and a dexterous hand;
one end of the moving arm is provided with a dexterous hand, the other end of the moving arm is arranged on the chassis, and the moving arm rotates by taking a connecting point with the chassis as an axis;
the chassis is provided with a moving assembly for moving the position of the mechanical arm;
the dexterous hand rotates by taking a connecting point with the moving arm as an axis and is used for stacking landforms;
the number of the laser distance sensors is at least two, and the laser distance sensors are respectively arranged on the dexterous hand and the chassis and used for monitoring obstacles in the moving process.
3. The apparatus of claim 1, further comprising a calibration tool having a cross cursor for positional calibration; the data acquisition module comprises: the device comprises a region dividing unit, a length and width dimension collecting unit and a depth and shallow dimension collecting unit;
the area dividing unit is used for dividing the internal area of the sand table and taking the intersection point of each divided sub-area as a reference point;
the length and width collecting unit and the depth and depth collecting unit are used for being matched with a binocular camera, a laser ranging sensor, a laser holographic projector and a calibration tool to collect data of all reference points to obtain a data set required by a training model;
the data set includes a planar position coordinate, a vertical position coordinate, a focus range, and a sharpness of the fiducial.
4. The apparatus of claim 3, wherein the data acquisition module further comprises: the system comprises an outline scanning unit, a key point grabbing unit and a data supplementing unit;
the contour scanning unit receives the landform contour scanned by the three-dimensional scanner and collects corners appearing in the contour;
the key point grabbing unit grabs the length, width and height information of the landform key points according to the positions of the corners;
and the data supplement unit is used for decomposing the parts between the adjacent key points, acquiring the length, width and height data of each decomposed part, and obtaining complete landform data for training a landform information prediction model.
5. The apparatus of claim 4, wherein the data acquisition for each fiducial point comprises:
the long and wide size collection unit controls the laser holographic projector to project cross-shaped cursors, the cross-shaped cursors are sequentially projected at the positions of the reference points, the position of the calibration tool is adjusted until the cross-shaped cursors in the calibration tool are overlapped with the cross-shaped cursors of the cursors, the long and wide size collection unit records the plane position coordinates of the reference points at the moment, and long and wide size collection of the sand table is completed;
the depth size collection unit controls the laser holographic projector to project cross-shaped cursors, the cross-shaped cursors are sequentially projected at the positions of the reference points, the calibration tool is moved upwards/downwards under the condition that the positions of the cross-shaped cursors in the calibration tool and the cross-shaped cursors of the cursors are overlapped, until the cross-shaped cursors in a binocular camera display interface achieve the best display effect, the depth size collection unit records the vertical height, the focusing range and the definition information of the positions as the vertical position coordinates, the focusing range and the definition of the reference points, and the depth size collection of the sand table is completed.
6. The apparatus of claim 5, wherein the predictive model building and training module comprises:
the parameter initialization unit is used for initializing the network weight and the bias and randomly selecting a first input sample in the training data set;
the parameter processing unit is used for carrying out neuron activation forward propagation, carrying out weight and bias processing on the first input sample through a hidden layer and solving a result and an error of an output layer;
a parameter adjusting unit, which performs back propagation according to the error and adjusts the network weight and the bias;
and the training monitoring unit judges whether the training is finished according to a preset finishing condition.
7. The apparatus of claim 6, wherein the projection parameters and complete topographic data determining module comprises:
the high-complexity area marking unit is used for comparing the high-complexity area in the real landform with the area of the current sand table and marking the point location area which accords with the high complexity in the sand table;
a weight determination unit for determining the position, number and weight of the demand degree of the marked high-complexity point location region;
and the projection parameter calculating unit is used for calculating the focusing range and definition by utilizing the trained model according to the length, width, height and depth information of the sand table and the determined weight.
8. The device of claim 7, wherein the projection parameter and complete geomorphic data obtaining module searches and matches in the existing built data set after obtaining the information of the length, width, height and depth of the sand table, and directly selects the corresponding focusing range and definition information when the matching is consistent, and obtains the focusing range and definition information by using a trained laser holographic projection sand table prediction model when the matching is inconsistent; after the landform outline is obtained, searching and matching are carried out in the established existing database, and when the matching is consistent, corresponding complete landform data is directly selected; and when the matching is inconsistent, obtaining complete landform data by adopting the trained landform information prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910239479.7A CN110009985B (en) | 2019-03-27 | 2019-03-27 | Sand table making devices based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910239479.7A CN110009985B (en) | 2019-03-27 | 2019-03-27 | Sand table making devices based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110009985A CN110009985A (en) | 2019-07-12 |
| CN110009985B true CN110009985B (en) | 2020-12-25 |
Family
ID=67168421
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910239479.7A Active CN110009985B (en) | 2019-03-27 | 2019-03-27 | Sand table making devices based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110009985B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111291729B (en) * | 2020-03-26 | 2023-09-01 | 北京百度网讯科技有限公司 | Human body posture estimation method, device, equipment and storage medium |
| CN112785949B (en) * | 2021-01-22 | 2022-07-12 | 北京邮电大学 | Three-dimensional scene projection method and device and three-dimensional sand table |
| CN114782901B (en) * | 2022-06-21 | 2022-09-09 | 深圳市禾讯数字创意有限公司 | Sand table projection method, device, equipment and medium based on visual change analysis |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699237A (en) * | 2009-11-20 | 2010-04-28 | 中国航空工业空气动力研究院 | Three-dimensional model attitude angle video measuring system for wind tunnel model test |
| FR2970663A1 (en) * | 2011-01-26 | 2012-07-27 | Snecma | Processing a metal part by sintering and laser fusion for reducing its roughness, comprises automatically sanding a surface of the metal part with grains having different diameters, where the sanding process is defined by a program |
| CN103389076A (en) * | 2013-07-24 | 2013-11-13 | 国家海洋局第二海洋研究所 | Submarine topography change detection and analysis method based on mesh reconstruction |
| CN104134389A (en) * | 2014-08-19 | 2014-11-05 | 福建四创软件有限公司 | Interactive sand table demonstration system and method |
| CN104259669A (en) * | 2014-09-11 | 2015-01-07 | 苏州菲镭泰克激光技术有限公司 | Precise three-dimensional curved surface laser marking method |
| CN105045389A (en) * | 2015-07-07 | 2015-11-11 | 深圳水晶石数字科技有限公司 | Demonstration method for interactive sand table system |
| CN105894945A (en) * | 2016-04-13 | 2016-08-24 | 苏州育龙科教设备有限公司 | Digital sand table having landform teaching demonstration function |
| CN106094721A (en) * | 2016-07-01 | 2016-11-09 | 西安工业大学 | The processing method of three-dimensional live topography sand table |
| CN106980366A (en) * | 2017-02-27 | 2017-07-25 | 合肥安达创展科技股份有限公司 | Landform precisely catches system and fine high definition projection imaging system |
| CN107886826A (en) * | 2017-11-22 | 2018-04-06 | 上海未石影视文化有限公司 | A kind of laser induced interactive digital sand table model |
| CN108789414A (en) * | 2018-07-17 | 2018-11-13 | 五邑大学 | Intelligent machine arm system based on three-dimensional machine vision and its control method |
| CN208422342U (en) * | 2018-08-08 | 2019-01-22 | 深圳市大峡谷科技发展有限公司 | The projection of dual-projection three-dimensional imaging digital sand table controls equipment |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104567546B (en) * | 2014-12-23 | 2016-02-17 | 哈尔滨工业大学 | A kind of IR Scene sand table system for infrared seeker test |
| CN206594941U (en) * | 2016-05-06 | 2017-10-27 | 柳州铁道职业技术学院 | A kind of indoor digital mapping teaching platform device |
| US10599098B2 (en) * | 2017-01-26 | 2020-03-24 | The Charles Stark Draper Laboratory, Inc. | Method and apparatus for light field generation |
| CN108510592B (en) * | 2017-02-27 | 2021-08-31 | 亮风台（上海）信息科技有限公司 | Augmented reality display method of real physical model |
| CN107545788B (en) * | 2017-10-17 | 2019-07-30 | 北京华如科技股份有限公司 | Goods electronic sand map system is deduced based on the operation that augmented reality is shown |
| CN108320311B (en) * | 2018-01-19 | 2020-10-09 | 杭州映墨科技有限公司 | AR sand table calibration model calculation method capable of automatically correcting deviation |
-
2019
- 2019-03-27 CN CN201910239479.7A patent/CN110009985B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699237A (en) * | 2009-11-20 | 2010-04-28 | 中国航空工业空气动力研究院 | Three-dimensional model attitude angle video measuring system for wind tunnel model test |
| FR2970663A1 (en) * | 2011-01-26 | 2012-07-27 | Snecma | Processing a metal part by sintering and laser fusion for reducing its roughness, comprises automatically sanding a surface of the metal part with grains having different diameters, where the sanding process is defined by a program |
| CN103389076A (en) * | 2013-07-24 | 2013-11-13 | 国家海洋局第二海洋研究所 | Submarine topography change detection and analysis method based on mesh reconstruction |
| CN104134389A (en) * | 2014-08-19 | 2014-11-05 | 福建四创软件有限公司 | Interactive sand table demonstration system and method |
| CN104259669A (en) * | 2014-09-11 | 2015-01-07 | 苏州菲镭泰克激光技术有限公司 | Precise three-dimensional curved surface laser marking method |
| CN105045389A (en) * | 2015-07-07 | 2015-11-11 | 深圳水晶石数字科技有限公司 | Demonstration method for interactive sand table system |
| CN105894945A (en) * | 2016-04-13 | 2016-08-24 | 苏州育龙科教设备有限公司 | Digital sand table having landform teaching demonstration function |
| CN106094721A (en) * | 2016-07-01 | 2016-11-09 | 西安工业大学 | The processing method of three-dimensional live topography sand table |
| CN106980366A (en) * | 2017-02-27 | 2017-07-25 | 合肥安达创展科技股份有限公司 | Landform precisely catches system and fine high definition projection imaging system |
| CN107886826A (en) * | 2017-11-22 | 2018-04-06 | 上海未石影视文化有限公司 | A kind of laser induced interactive digital sand table model |
| CN108789414A (en) * | 2018-07-17 | 2018-11-13 | 五邑大学 | Intelligent machine arm system based on three-dimensional machine vision and its control method |
| CN208422342U (en) * | 2018-08-08 | 2019-01-22 | 深圳市大峡谷科技发展有限公司 | The projection of dual-projection three-dimensional imaging digital sand table controls equipment |
Non-Patent Citations (1)
| Title |
|---|
| 基于增强实境的地形设计沙盘系统研究;蔡凌豪;《西部人居环境学刊》;20160913;第26-33页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110009985A (en) | 2019-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109994036B (en) | Sand table manufacturing method based on machine learning | |
| CN110009985B (en) | Sand table making devices based on machine learning | |
| WO2022142759A1 (en) | Lidar and camera joint calibration method | |
| US7196730B2 (en) | Method and system for complete 3D object and area digitizing | |
| CN100573388C (en) | The robot control method of real-time color auto acquisition and robot | |
| CN112132972A (en) | Three-dimensional reconstruction method and system for fusing laser and image data | |
| CN110334701B (en) | Data acquisition method based on deep learning and multi-vision in digital twin environment | |
| KR102027932B1 (en) | Space image drawing system based on high precision aerial image | |
| JP2012533222A (en) | Image-based surface tracking | |
| CN110202573A (en) | Full-automatic hand and eye calibrating, working face scaling method and device | |
| CA2705254A1 (en) | Arrangement and method for providing a three dimensional map representation of an area | |
| CN110146099A (en) | A kind of synchronous superposition method based on deep learning | |
| CN113963044A (en) | RGBD camera-based intelligent loading method and system for cargo box | |
| CN109709977B (en) | Method and device for planning movement track and moving object | |
| CN109856946B (en) | Method for manufacturing laser holographic projection sand table | |
| CN114359406A (en) | Calibration of auto-focusing binocular camera, 3D vision and depth point cloud calculation method | |
| CN116758234A (en) | Mountain terrain modeling method based on multipoint cloud data fusion | |
| CN115965790A (en) | Oblique photography point cloud filtering method based on cloth simulation algorithm | |
| CN116625258A (en) | Chain spacing measuring system and chain spacing measuring method | |
| US6999072B2 (en) | Data processing method, data processing program and recording medium | |
| CN114608522A (en) | Vision-based obstacle identification and distance measurement method | |
| CN114529585A (en) | Mobile equipment autonomous positioning method based on depth vision and inertial measurement | |
| CN113932712A (en) | Melon and fruit vegetable size measuring method based on depth camera and key points | |
| CN109856945B (en) | Laser holographic projection sand table manufacturing device | |
| CN106384331A (en) | High-definition image synthetic method based on precision displacement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |