CN111768361B - Underground space quality evaluation and visual presentation method and system thereof - Google Patents
Underground space quality evaluation and visual presentation method and system thereof Download PDFInfo
- Publication number
- CN111768361B CN111768361B CN202010386869.XA CN202010386869A CN111768361B CN 111768361 B CN111768361 B CN 111768361B CN 202010386869 A CN202010386869 A CN 202010386869A CN 111768361 B CN111768361 B CN 111768361B
- Authority
- CN
- China
- Prior art keywords
- picture
- underground space
- pictures
- space
- place
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/021—Optical sensing devices
- B25J19/023—Optical sensing devices including video camera means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J5/00—Manipulators mounted on wheels or on carriages
- B25J5/005—Manipulators mounted on wheels or on carriages mounted on endless tracks or belts
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/0009—Constructional details, e.g. manipulator supports, bases
- B25J9/0027—Means for extending the operation range
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
- H04W4/026—Services making use of location information using location based information parameters using orientation information, e.g. compass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method and a system for evaluating underground space quality and visually presenting the underground space quality, wherein the method comprises the following steps of: collecting pictures of the existing underground space by a picture collecting robot; putting the collected pictures into a data collection platform, and collecting evaluation results of four indexes of space brightness, space comfort, space richness and environment artistry of each picture through a crowdsourcing mechanism; obtaining a model for deducing the grading data of the picture according to the features of the picture through a deep learning algorithm; repeating the steps until the accuracy of the model meets the requirement; obtaining pictures and coordinates of the underground space to be evaluated, and grading each picture by using the trained model; and marking each place on the underground space plane graph by different colors according to the grade to form a grade result plane distribution graph and displaying the grade result plane distribution graph. The invention solves the problem of the current underground space picture missing, and realizes high-accuracy underground space quality evaluation and visual presentation thereof.
Description
Technical Field
The invention relates to the technical field of spatial quality evaluation, in particular to a method and a system for underground spatial quality evaluation and visual presentation thereof.
Background
At present, a platform related to spatial perception mainly takes Place Pulse of MIT as a main part, a Google street view picture and a corresponding coordinate of the picture are intercepted through a crawler algorithm, the picture is placed on a webpage platform, and grading data of a network user on the picture are collected. However, place Pulse has a great limitation, firstly, because its picture is taken from google street view, which also means that it cannot reach underground space, and no people currently provide corresponding space pictures in the underground space. Secondly, the collection mode of the scoring data of Place Pulse is carried out through a public webpage platform, and the collection mode is a collection mode without any incentive mechanism, and the related data is insufficient, so that the scoring is not accurate enough.
In view of the above, it is desirable to provide a method and a system for evaluating the quality of the underground space and visually presenting the evaluation.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides a method and a system for evaluating underground space quality and visually presenting the underground space quality.
The invention is realized by the following steps:
in one aspect, the invention provides a method for evaluating underground space quality and visually presenting the underground space quality, which comprises the following steps:
s1, collecting pictures of a plurality of directions of each place of the existing underground space through a picture collecting robot;
s2, putting the collected pictures into a data collection platform, collecting results of evaluation of four indexes of space brightness, space comfort, space richness and environment artistry of each picture by a network user through a crowdsourcing mechanism, and analyzing to obtain grading data of each picture;
s3, training by combining the grading data and the characteristic information of each picture through a deep learning algorithm to obtain a model for deducing the grading data of the pictures according to the picture characteristics;
s4, repeating the steps S1-S3 until the accuracy of the model meets the requirement;
s5, obtaining pictures and coordinates of multiple directions of each place of the underground space to be evaluated, grading each picture by using a trained model, and obtaining the grade value of each place by using the grade data of the pictures of the multiple directions of each place;
and S6, marking each place on the underground space plane graph with different colors according to the grade of each place to form a grade result plane distribution graph and displaying the grade result plane distribution graph.
Further, the step S2 specifically includes:
the method comprises the steps of putting two photos with the same position in different places or two photos with the same position and different positions in different places into a data collection platform for display each time, collecting a result of comparing and selecting the two given pictures by a network user in a preset problem about space brightness, space comfort, space richness and environment artistry by using a data collection mode with a reward mechanism, and obtaining scoring data of each picture according to picture sequencing by adopting TrueSkill algorithm.
Further, the step S3 specifically includes:
and extracting semantic features and color features of each picture, and training the obtained grading data of each picture and the semantic features and the color features by adopting a full convolution neural network to obtain a model capable of deducing the grading data of the picture according to the semantic features and the color features of the picture.
Further, the step S5 of obtaining the pictures and coordinates of the multiple orientations of each location in the underground space to be evaluated specifically includes: if the underground space field needing to be evaluated is established, pictures and coordinates of multiple directions of each place of the underground space field are collected through the picture collecting robot, and if the underground space field needing to be evaluated is not established, screenshot of the multiple directions of each place is conducted according to the BIM model of the underground space field, and the coordinates of the screenshot place are recorded.
Further, the method for collecting the coordinates of each place of the underground space field through the picture collecting robot comprises the following steps:
the picture collecting robot judges the signal angle of each base station by acquiring signals of at least two base stations distributed in the underground space, determines the current coordinate of the robot relative to the base stations through an AOA algorithm, and calculates by combining the map absolute coordinate of the base stations and the coordinate of the picture collecting robot relative to the base stations to obtain the absolute coordinate of the current position of the robot, namely the coordinate of the corresponding place of the underground space field.
On the other hand, the invention also provides a system for evaluating the quality of the underground space and visually presenting the evaluation, which is used for realizing the method and comprises a picture collecting robot and an intelligent perception platform of the underground space;
the image collecting robot is used for collecting images of a plurality of directions of all places of the existing underground space;
the underground space intelligent perception platform comprises:
the data collection module is used for putting the collected pictures into a data collection platform, collecting results of evaluation of four indexes of space brightness, space comfort, space richness and environment artistry of each picture by a network user through a crowdsourcing mechanism, and analyzing to obtain grading data of each picture;
the quality evaluation module is used for training by combining the grading data and the characteristic information of each picture through a deep learning algorithm to obtain a model for deducing the grading data of the pictures according to the picture characteristics; grading the pictures of multiple directions of each place of the underground space to be evaluated by using the trained model, and obtaining the grade value of each place by using the grade data of the pictures of multiple directions of each place;
and the visual presentation module is used for marking each place on the underground space plane graph by different colors according to the grade of each place to form a grade result plane distribution graph and displaying the grade result plane distribution graph.
Further, the picture collecting robot comprises a shell, a central processing unit, a rotary lifting device, a shooting device and a moving device, wherein the central processing unit is located in the shell, the moving device is fixed at two ends of the shell, the rotary lifting device is fixed above the shell, the shooting device is fixed on the rotary lifting device, and the moving device, the rotary lifting device and the shooting device are all electrically connected with the central processing unit.
Furthermore, the shooting device comprises two cameras, and the distance between the two cameras is the distance between human eyes
Further, the moving device adopts a crawler drive.
Further, the rotary lifting device comprises a lifting mechanism and a rotating mechanism fixed on the lifting mechanism, the rotating mechanism comprises a horizontal rotating block which horizontally rotates relative to the lifting mechanism and a vertical rotating block which vertically rotates relative to the horizontal rotating block, and the shooting device is fixed with the vertical rotating block.
Compared with the prior art, the invention has the following beneficial effects:
according to the method and the system for evaluating the quality of the underground space and visually presenting the quality of the underground space, pictures of multiple directions of each place of the existing underground space are collected through the picture collecting robot, the problem that the pictures of the existing underground space are missing is solved, the grading data of the pictures are collected through a crowdsourcing mechanism, a model for deducing the grading data of the pictures according to the picture characteristics is obtained through deep learning algorithm training, the pictures are graded through the model, the grading accuracy can be improved, the evaluation is convenient, the grading result plane distribution graph is formed by marking each place on the underground space plane graph with different colors according to the grading height of each place and displayed, the visual presentation of the evaluation result is realized, and a user can conveniently obtain the information of the evaluation result. The invention provides corresponding picture data of the underground space, which can provide picture data for the navigation of the corresponding underground space later, and the collected grading data can provide a data basis for the related work of quantitative evaluation of the quality of the underground space.
Drawings
Fig. 1 is a flowchart of a method for evaluating quality of an underground space and visually presenting the evaluation according to an embodiment of the present invention;
FIG. 2 is a block diagram of a system for evaluating the quality of a subsurface space and visually presenting the evaluation according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an image capturing robot according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a lifting mechanism provided in an embodiment of the present invention;
fig. 5 is a control schematic diagram of an image capturing robot according to an embodiment of the present invention.
Description of reference numerals: the system comprises an image acquisition robot, 11 a central processing unit, 12 a lifting mechanism, 13 a shooting device, 14 a horizontal rotating block, 15 a vertical rotating block, 16 a mobile device, 2 an underground space intelligent sensing platform, 21 a data collection module, 22 a quality evaluation module and 23 a visual presentation module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a method for evaluating quality of an underground space and visually presenting the evaluation, which can be applied to an intelligent sensing platform of the underground space, and the method includes the following steps:
s1, collecting pictures of a plurality of directions of each place of the existing underground space through a picture collecting robot;
specifically, a path is set for the picture collecting robot, a shooting distance is set, the picture collecting robot runs at a preset speed, the picture collecting robot stops moving when a certain distance is reached, photos of the front, the rear, the left, the right and the upper five directions of the place are shot, and the picture collecting robot continues to move after the shooting is finished until the picture shooting of each place is finished.
S2, putting the collected pictures into a data collection platform, collecting results of evaluation of four indexes of space brightness, space comfort, space richness and environment artistry of each picture by a network user through a crowdsourcing mechanism, and analyzing to obtain grading data of each picture;
specifically, collected picture groups corresponding to each place are numbered, two pictures in the same position of different places or two pictures in different positions of the same place and different positions are put into a data collection platform for display each time, and the results of comparing and selecting the two given pictures by a network user under the preset problems about space brightness, space comfort, space richness and environment artistry are collected by using a data collection mode with a reward mechanism. The comparison between two pictures can be represented by a form (Xi, xj, Y), wherein Xi and Xj respectively represent two pictures, and Y is 0 or 1; if Y is 0, it means Xi is worse than Xj at the index, and if Y is 1, it means Xi is better than Xj at the index. And then, adopting TrueSkill algorithm to obtain the scoring data of each picture according to picture sequencing.
The data collection mode with the reward mechanism includes: (1) A tree game that can be combined with a small program, the more questions answered, the more nutrients the tree receives. (2) The questions are used as a revival means of a certain game, and the questions are answered and then revived. (3) And taking the question as a verification question of the login of a certain webpage interface. And (4) making the questions into psychological test questions. By means of a data collection mode with a reward mechanism, a large amount of evaluation data can be collected, data collection time is shortened, and evaluation accuracy is improved.
S3, training by combining the grading data and the characteristic information of each picture through a deep learning algorithm to obtain a model for deducing the grading data of the pictures according to the picture characteristics;
specifically, semantic features and color features of each picture are extracted, and the obtained scoring data of each picture and the semantic features and the color features are trained by adopting a full convolution neural network (FCN) to obtain a model capable of deducing the scoring data of the picture according to the semantic features and the color features of the picture.
S4, repeating the steps S1-S3 until the accuracy of the model meets the requirement; therefore, the image evaluation result with higher accuracy can be obtained through the model.
S5, obtaining pictures and coordinates of multiple directions of each place of the underground space to be evaluated, grading each picture by using the trained model, and obtaining the grade value of each place by using the grade data of the pictures of the multiple directions of each place;
specifically, if the underground space field needing to be evaluated is built, pictures and coordinates of multiple directions of each place of the underground space field are collected through a picture collecting robot, and if the underground space field needing to be evaluated is not built, screenshots of multiple directions of each place are conducted according to a BIM (building information modeling) model of the underground space field, and the coordinates of the screenshot place are recorded.
The method for collecting the pictures of the multiple directions of each place of the underground space field through the picture collecting robot is consistent with the method for collecting the pictures of the multiple directions of each place of the existing underground space through the picture collecting robot, and the method is not repeated herein.
Preferably, the method for collecting the coordinates of each place of the underground space field by the picture collecting robot comprises the following steps:
the method comprises the steps that at least two UWB (ultra wide band) positioning base stations are arranged in an underground space field in advance, the positioning base stations are ceiling type or flat type positioning base stations and can be installed at the top of the underground space field or the top area of a column, a picture collecting robot judges the signal angle of each base station by acquiring signals of the at least two base stations distributed in the underground space, the current coordinate of the robot relative to the base stations is determined through an AOA (angle of arrival) algorithm, and the absolute coordinate of the map of the base stations and the coordinate of the picture collecting robot relative to the base stations are combined for calculation to obtain the absolute coordinate of the current position of the robot, namely the coordinate of the corresponding place of the underground space field.
And S6, marking each place on the underground space plane graph with different colors according to the grade of each place to form a grade result plane distribution graph and displaying the grade result plane distribution graph.
Specifically, the scoring values of all the sites are combined with the coordinates of all the sites collected before, all the sites on the underground space plane graph are labeled with different colors according to the scoring levels of all the sites aiming at different problems, a scoring result plane distribution graph is formed, each problem corresponds to one index of space brightness, space comfort, space richness and environment artistry and corresponds to one scoring result plane distribution graph, the scoring result plane distribution graph is displayed, and a user can click all the sites on the scoring result plane distribution graph to obtain the scoring values of all the sites.
The related pictures and the grading data can be opened for the user according to actual needs, and different researchers can download the pictures and the grading data according to own needs.
According to the method for evaluating the quality of the underground space and visually presenting the quality of the underground space, the pictures of multiple directions of each place of the existing underground space are collected through the picture collecting robot, the problem that the pictures of the existing underground space are missing is solved, the grading data of the pictures are collected through a crowdsourcing mechanism, a model for deducing the grading data of the pictures according to the picture characteristics is obtained through deep learning algorithm training, the pictures are graded through the model, the grading accuracy can be improved, the evaluation is convenient, the grading result plane distribution diagram is formed by marking each place on the underground space plane diagram with different colors according to the grading height of each place and is displayed, the visual presentation of the evaluation result is realized, and a user can conveniently obtain the evaluation result information. The invention provides corresponding picture data of the underground space, which can provide picture data for the navigation of the corresponding underground space later, and the collected grading data can provide a data basis for the related work of quantitative evaluation of the quality of the underground space.
As shown in fig. 2, an embodiment of the present invention further provides a system for evaluating quality of an underground space and visually presenting the same, for implementing the method, where the system includes a picture collecting robot and an underground space intelligent sensing platform 2;
the image collecting robot is used for collecting images of a plurality of directions of all places of the existing underground space;
the underground space intelligent perception platform 2 comprises:
the data collection module 21 is configured to put the collected pictures into a data collection platform, collect, through a crowdsourcing mechanism, results of evaluation performed by a network user on four indexes of space brightness, space comfort, space richness and environmental artistry of each picture, and analyze the results to obtain scoring data of each picture;
the quality evaluation module 22 is used for training by combining the grading data and the feature information of each picture through a deep learning algorithm to obtain a model for deducing the grading data of the pictures according to the features of the pictures; grading the pictures of multiple directions of each place of the underground space to be evaluated by using the trained model, and obtaining the grading value of each place by using the grading data of the pictures of multiple directions of each place;
and the visual presentation module 23 is used for labeling each place on the underground space plane graph with different colors according to the grade of each place to form a grade result plane distribution graph and displaying the grade result plane distribution graph.
As shown in fig. 3 to 5, the robot for collecting pictures 1 includes a housing, a central processing unit 11, a rotary lifting device, a shooting device 13, and a moving device 16, wherein the central processing unit 11 is located in the housing, the moving device 16 is fixed at two ends of the housing, the rotary lifting device is fixed above the housing, the shooting device 13 is fixed on the rotary lifting device, and the moving device 16, the rotary lifting device, and the shooting device 13 are all electrically connected to the central processing unit 11. After the image acquisition robot 1 arrives at the shooting place, the central processing unit 11 controls the moving device 16 to stop moving, and simultaneously starts the rotary lifting device and the shooting device 13, and when shooting is carried out each time, the rotary lifting device is lifted to a position where the shooting device 13 is 1.70m away from the ground, so that the height of a human is simulated. Preferably, the shooting device 13 includes two cameras, and the distance between the two cameras is the human eye distance, simulating the space seen by human eyes. The moving device 16 adopts crawler transmission and moves stably. Further preferably, the rotary lifting device includes a lifting mechanism 12 and a rotating mechanism fixed on the lifting mechanism 12, the rotating mechanism includes a horizontal rotating block 14 horizontally rotating with respect to the lifting mechanism 12 and a vertical rotating block 15 vertically rotating with respect to the horizontal rotating block 14, the photographing device 13 is fixed with the vertical rotating block 15, the lifting of the photographing device 13 is realized through the lifting mechanism 12, the rotation of the photographing device 13 in the horizontal direction is realized through the horizontal rotating block 14, and the vertical rotation of the photographing device 13 is realized through the vertical rotating block 15, so that pictures of each position and each orientation of each point in the underground space can be photographed.
Since the principle of the system for solving the technical problem is similar to that of the embodiment of the method, the implementation of the system can refer to the implementation of the method, and repeated parts are not described again.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A method for evaluating underground space quality and visually presenting the underground space quality is characterized by comprising the following steps:
s1, collecting pictures of a plurality of directions of each place of the existing underground space through a picture collecting robot;
s2, putting the collected pictures into a data collection platform, collecting results of evaluation of four indexes of space brightness, space comfort, space richness and environment artistry of the network users on the pictures through a crowdsourcing mechanism, and analyzing the results to obtain scoring data of the pictures, wherein the results specifically comprise the following steps: the method comprises the steps of numbering collected picture groups corresponding to each place, putting two pictures in the same position of different places or two pictures in different positions of the same place into a data collection platform for display each time, collecting a result of comparing and selecting the two given pictures by a network user in a preset problem about space brightness, space comfort, space richness and environmental artistry by using a data collection mode with a reward mechanism, and respectively representing the two pictures by using a form table (Xi, xj and Y) for comparison of every two pictures, wherein Y is 0 or 1; if Y is 0, the index of Xi is inferior to Xj, if Y is 1, the index of Xi is superior to Xj, and then the scoring data of each picture is obtained by adopting TrueSkill algorithm according to the picture ordering;
s3, training by combining the grading data and the characteristic information of each picture through a deep learning algorithm to obtain a model for deducing the grading data of the pictures according to the picture characteristics;
s4, repeating the steps S1-S3 until the accuracy of the model meets the requirement;
s5, obtaining pictures and coordinates of multiple directions of each place of the underground space to be evaluated, grading each picture by using a trained model, and obtaining the grade value of each place by using the grade data of the pictures of the multiple directions of each place;
and S6, marking each place on the underground space plane graph with different colors according to the grade of each place to form a grade result plane distribution graph and displaying the grade result plane distribution graph.
2. The method for evaluating the quality of a subsurface space according to claim 1 and visually presenting the same, wherein the step S3 specifically comprises:
and extracting semantic features and color features of each picture, and training the obtained grading data of each picture and the semantic features and the color features by adopting a full convolution neural network to obtain a model capable of deducing the grading data of the picture according to the semantic features and the color features of the picture.
3. The method for evaluating the quality of underground space according to claim 1 and visually presenting the same, wherein: the step S5 of obtaining the pictures and coordinates of the plurality of directions of each location in the underground space to be evaluated specifically includes: if the underground space field needing to be evaluated is established, pictures and coordinates of multiple directions of each place of the underground space field are collected through the picture collecting robot, and if the underground space field needing to be evaluated is not established, screenshot of the multiple directions of each place is conducted according to the BIM model of the underground space field, and the coordinates of the screenshot place are recorded.
4. The method for evaluating the quality of underground space and visually presenting the same as claimed in claim 3, wherein the method for collecting the coordinates of each location of the underground space field by the picture collecting robot comprises the following steps:
the picture collecting robot judges the signal angle of each base station by acquiring signals of at least two base stations distributed in the underground space, determines the current coordinate of the robot relative to the base stations through an AOA algorithm, and calculates by combining the map absolute coordinate of the base stations and the coordinate of the picture collecting robot relative to the base stations to obtain the absolute coordinate of the current position of the robot, namely the coordinate of the corresponding place of the underground space field.
5. A system for evaluating the quality of underground space and visually presenting the same, for implementing the method according to any one of claims 1 to 4, wherein: the intelligent sensing system comprises a picture collecting robot and an underground space intelligent sensing platform;
the image collecting robot is used for collecting images of a plurality of directions of all places of the existing underground space;
the underground space intelligent perception platform comprises:
the data collection module is used for putting the collected pictures into a data collection platform, collecting results of evaluation of four indexes of space brightness, space comfort, space richness and environment artistry of each picture by a network user through a crowdsourcing mechanism, and analyzing to obtain grading data of each picture;
the quality evaluation module is used for training by combining the grading data and the characteristic information of each picture through a deep learning algorithm to obtain a model for deducing the grading data of the pictures according to the picture characteristics; grading the pictures of multiple directions of each place of the underground space to be evaluated by using the trained model, and obtaining the grading value of each place by using the grading data of the pictures of multiple directions of each place;
and the visual presentation module is used for marking each place on the underground space plane graph with different colors according to the grade of each place to form a grade result plane distribution graph and displaying the grade result plane distribution graph.
6. The system for visually representing and evaluating the quality of a subsurface space according to claim 5, wherein: the picture collecting robot comprises a shell, a central processing unit, a rotary lifting device, a shooting device and a moving device, wherein the central processing unit is located in the shell, the moving device is fixed at two ends of the shell, the rotary lifting device is fixed above the shell, the shooting device is fixed on the rotary lifting device, and the moving device, the rotary lifting device and the shooting device are electrically connected with the central processing unit.
7. The system for visually representing and evaluating the quality of a subsurface space according to claim 6, wherein: the shooting device comprises two cameras, and the distance between the two cameras is the distance between human eyes.
8. The system for underground space quality evaluation and visual presentation thereof according to claim 6, wherein: the moving device adopts crawler transmission.
9. The system for visually representing and evaluating the quality of a subsurface space according to claim 6, wherein: the rotary lifting device comprises a lifting mechanism and a rotating mechanism fixed on the lifting mechanism, the rotating mechanism comprises a horizontal rotating block and a vertical rotating block, the horizontal rotating block horizontally rotates relative to the lifting mechanism, the vertical rotating block vertically rotates relative to the horizontal rotating block, and the shooting device is fixed with the vertical rotating block.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010386869.XA CN111768361B (en) | 2020-05-09 | 2020-05-09 | Underground space quality evaluation and visual presentation method and system thereof |
| PCT/CN2021/088812 WO2021227805A1 (en) | 2020-05-09 | 2021-04-21 | Underground space quality evaluation and visualized presentation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010386869.XA CN111768361B (en) | 2020-05-09 | 2020-05-09 | Underground space quality evaluation and visual presentation method and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111768361A CN111768361A (en) | 2020-10-13 |
| CN111768361B true CN111768361B (en) | 2022-12-02 |
Family
ID=72719097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010386869.XA Active CN111768361B (en) | 2020-05-09 | 2020-05-09 | Underground space quality evaluation and visual presentation method and system thereof |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111768361B (en) |
| WO (1) | WO2021227805A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111768361B (en) * | 2020-05-09 | 2022-12-02 | 中铁第四勘察设计院集团有限公司 | Underground space quality evaluation and visual presentation method and system thereof |
| CN112417556A (en) * | 2020-11-18 | 2021-02-26 | 同济大学 | BIM forward design method based on image measurable intelligent evaluation |
| CN112905257A (en) * | 2021-01-15 | 2021-06-04 | 珠海新势力创建筑设计有限公司 | Software plug-in based on BIM model automated inspection basement air shaft and fan room generate condition |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106598081A (en) * | 2016-10-27 | 2017-04-26 | 纳恩博（北京）科技有限公司 | Image acquisition method and electronic devices |
| CN107392252A (en) * | 2017-07-26 | 2017-11-24 | 上海城诗信息科技有限公司 | Computer deep learning characteristics of image and the method for quantifying perceptibility |
| CN110926479A (en) * | 2019-12-20 | 2020-03-27 | 杜明利 | Method and system for automatically generating indoor three-dimensional navigation map model |
| CN111080167A (en) * | 2019-12-30 | 2020-04-28 | 南京慧龙城市规划设计有限公司 | Underground space resource quality assessment method for urban planning |
| CN111093145A (en) * | 2019-11-15 | 2020-05-01 | 垒途智能教科技术研究院江苏有限公司 | Positioning system and positioning method of mowing robot |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105147198A (en) * | 2015-08-10 | 2015-12-16 | 深圳先进技术研究院 | Indoor mapping system and method based on sweeping robot |
| CN111126864A (en) * | 2019-12-26 | 2020-05-08 | 中国地质大学（武汉） | Street quality assessment method based on man-machine confrontation score |
| CN111768361B (en) * | 2020-05-09 | 2022-12-02 | 中铁第四勘察设计院集团有限公司 | Underground space quality evaluation and visual presentation method and system thereof |
-
2020
- 2020-05-09 CN CN202010386869.XA patent/CN111768361B/en active Active
-
2021
- 2021-04-21 WO PCT/CN2021/088812 patent/WO2021227805A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106598081A (en) * | 2016-10-27 | 2017-04-26 | 纳恩博（北京）科技有限公司 | Image acquisition method and electronic devices |
| CN107392252A (en) * | 2017-07-26 | 2017-11-24 | 上海城诗信息科技有限公司 | Computer deep learning characteristics of image and the method for quantifying perceptibility |
| CN111093145A (en) * | 2019-11-15 | 2020-05-01 | 垒途智能教科技术研究院江苏有限公司 | Positioning system and positioning method of mowing robot |
| CN110926479A (en) * | 2019-12-20 | 2020-03-27 | 杜明利 | Method and system for automatically generating indoor three-dimensional navigation map model |
| CN111080167A (en) * | 2019-12-30 | 2020-04-28 | 南京慧龙城市规划设计有限公司 | Underground space resource quality assessment method for urban planning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111768361A (en) | 2020-10-13 |
| WO2021227805A1 (en) | 2021-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111768361B (en) | Underground space quality evaluation and visual presentation method and system thereof | |
| CN104781849B (en) | Monocular vision positions the fast initialization with building figure (SLAM) simultaneously | |
| CN105094335B (en) | Situation extracting method, object positioning method and its system | |
| CN110619777B (en) | Criminal investigation and experiment intelligent training and assessment system creation method based on VR technology | |
| KR102377561B1 (en) | Apparatus and method for providing taekwondo movement coaching service using mirror dispaly | |
| CN108921203A (en) | A kind of detection and recognition methods of pointer-type water meter | |
| CN108520197A (en) | A kind of Remote Sensing Target detection method and device | |
| CN107256082B (en) | Throwing object trajectory measuring and calculating system based on network integration and binocular vision technology | |
| CN107229329A (en) | For the method and system of the virtual sensor data generation annotated with depth ground truth | |
| CN112700545B (en) | Simulation display system and method for remote sensing data | |
| CN108376198B (en) | Crowd simulation method and system based on virtual reality | |
| CN110110445B (en) | Sunshine analysis method, device, equipment and storage medium | |
| CN106558051A (en) | A kind of improved method for detecting road from single image | |
| CN109410275A (en) | Position predicting method, device, equipment and readable storage medium storing program for executing | |
| CN109545003A (en) | A kind of display methods, device, terminal device and storage medium | |
| CN110135277A (en) | A kind of Human bodys' response method based on convolutional neural networks | |
| CN110427998A (en) | Model training, object detection method and device, electronic equipment, storage medium | |
| CN105631849B (en) | The change detecting method and device of target polygon | |
| CN109934129A (en) | A kind of man face characteristic point positioning method, device, computer equipment and storage medium | |
| CN117333644A (en) | Virtual reality display picture generation method, device, equipment and medium | |
| CN103761011A (en) | Method, system and computing device of virtual touch screen | |
| CN111540056A (en) | AR intelligent navigation method and AR intelligent navigation system | |
| CN110909648B (en) | People flow monitoring method implemented on edge computing equipment by using neural network | |
| CN116229001A (en) | Urban three-dimensional digital map generation method and system based on spatial entropy | |
| CN108040239B (en) | Knowledge training system and method based on image recognition |
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 |