CN112683169A - Object size measuring method, device, equipment and storage medium - Google Patents
Object size measuring method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112683169A CN112683169A CN202011502470.XA CN202011502470A CN112683169A CN 112683169 A CN112683169 A CN 112683169A CN 202011502470 A CN202011502470 A CN 202011502470A CN 112683169 A CN112683169 A CN 112683169A
- Authority
- CN
- China
- Prior art keywords
- world
- dimensional
- image
- feature points
- coordinates
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000002159 abnormal effect Effects 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims description 19
- 238000012216 screening Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 abstract description 15
- 238000012549 training Methods 0.000 description 17
- 239000011159 matrix material Substances 0.000 description 14
- 238000012360 testing method Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 238000000691 measurement method Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000002354 daily effect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241001464837 Viridiplantae Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Abstract
The embodiment of the application provides an object size measuring method, an object size measuring device, computer equipment and a storage medium. And (3) converting the coordinates of the image feature points from a 3D world coordinate system to a two-dimensional coordinate system so as to screen the image feature points, and then removing abnormal feature points according to the deviation distribution of the feature points. And finally, calculating object parameters such as length, width, height and volume through the 3D coordinates of the residual characteristic points. According to the invention, the characteristic points of the object to be measured are subjected to 3D modeling and converted into the two-dimensional coordinate system, the characteristic points of the object to be measured are intelligently screened, and the measurement reliability and accuracy are high, so that the object size measuring device can more conveniently and quickly measure the size of the object, and the measurement reliability and accuracy are high.
Description
Technical Field
The application relates to the technical field of intelligent measurement objects, in particular to a method, a device, equipment and a storage medium for measuring body dimensions.
Background
In daily life, we are often faced with the need to measure the dimensions of some objects, but measuring tools are not necessarily present around. With the provision of the scientific and technological level and the living level, various intelligent terminals are integrated into the daily life of people, and the geometric dimension of an object to be detected can be quickly obtained through the visual detection of the intelligent terminals and the like. In some scenarios, for example, there is a need to identify the type and size of an object, which facilitates accurate selection of a suitable vehicle type or packaging box during moving and shipping.
The intelligent size measuring scheme in the prior art mainly comprises three steps: 1. acquiring an image formed by a camera assembly, and manually selecting a measuring point of an object to be measured on the image; 2. the obtained object coordinate is a two-dimensional coordinate, and the coordinate of the selected object point to be measured is converted into a three-dimensional coordinate system from the two-dimensional coordinate through a conversion algorithm; 3. and estimating the length to be measured according to the three-dimensional coordinates. Although this method can make the measurement result accurate by selecting the point to be measured, the manually selected point may be difficult to calibrate, and the point to be measured may not be touched precisely, and a position deviation may be generated, thereby causing a deviation in the measurement result. And the measurement can be carried out only after the detection point is selected, the automatic measurement cannot be carried out, the operation is complex, and the user experience is poor.
Disclosure of Invention
The embodiment of the application aims to provide an object dimension measuring method, an object dimension measuring device, object dimension measuring equipment and a storage medium, and aims to solve the technical problems that in the prior art, a measuring point is required to be selected, calibration is difficult, the point to be measured cannot be accurately touched, position deviation is possibly generated, and accordingly a measuring result is deviated.
In order to solve the above technical problem, an embodiment of the present application provides an object dimension measuring method, including the following steps:
acquiring an image of an object to be detected;
acquiring characteristic points of the image and calculating world three-dimensional coordinates of the characteristic points;
converting the world three-dimensional coordinates into two-dimensional plane coordinates;
screening characteristic points according to the two-dimensional plane coordinates;
and calculating the size of the object to be measured according to the world three-dimensional coordinates of the screened feature points.
Further, the obtained image of the object to be detected is a continuously obtained offset image, and the world three-dimensional coordinates of the feature points of the image are calculated according to a VIO algorithm.
Further, the screening of feature points according to the two-dimensional plane coordinates includes:
acquiring the boundary of the object to be detected based on a deep learning target detection model;
and screening the characteristic points of the object to be detected in the boundary.
Further, the object dimension measuring method further includes: and identifying the object to be detected, and acquiring the boundary of each identified object to be detected.
Further, the step of calculating the size of the object to be measured according to the world three-dimensional coordinates of the screened feature points comprises
Rejecting abnormal feature points within the boundary;
and calculating the size of the object to be measured according to the world three-dimensional coordinates of the remaining characteristic points.
Further, the removing the abnormal feature points in the boundary includes:
and taking the center of the two-dimensional image enclosed by the boundary as the starting point of the line segment, connecting all the characteristic points and the starting point into the line segment, calculating the length, acquiring the median of the length of all the line segments, and removing the characteristic points of the line segments which deviate from the length greatly.
Further, the step of calculating the size of the object to be measured according to the world three-dimensional coordinates of the remaining feature points comprises
And obtaining the maximum value and the minimum value of each dimension coordinate of the eliminated abnormal feature points, and calculating the size length of the object to be measured according to the maximum value and the minimum value of each dimension coordinate.
In order to solve the above technical problem, an embodiment of the present application further provides an object dimension measuring apparatus, including:
the image acquisition module is used for acquiring an image of an object to be detected;
the characteristic point three-dimensional coordinate calculation module is used for acquiring the characteristic points of the image and calculating the world three-dimensional coordinates of the characteristic points;
the two-dimensional coordinate conversion module is used for converting the world three-dimensional coordinate into a two-dimensional plane coordinate;
the characteristic point screening module is used for screening characteristic points according to the two-dimensional plane coordinates;
and the size calculation module is used for calculating the size of the object to be measured according to the screened world three-dimensional coordinates of the feature points.
Further, in order to solve the above technical problem, embodiments of the present application further provide an object dimension measuring apparatus,
in order to solve the above technical problem, an embodiment of the present application further provides a computer device, which adopts the following technical solutions:
a computer device comprising a memory, a processor and a network interface, the memory having stored therein a computer program, the processor implementing the steps of the object dimension measuring method described above when executing the computer program.
In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:
a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the object dimension measuring method described above.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects:
the embodiment of the application provides an object size measuring method, which comprises the steps of obtaining characteristic points of an object to be measured according to an obtained image of the object to be measured, carrying out 3D modeling on the characteristic points, and calculating world three-dimensional coordinates of the characteristic points. And (3) converting the coordinates of the image feature points from a 3D world coordinate system to a two-dimensional coordinate system so as to screen the image feature points, and then removing abnormal feature points according to the deviation distribution of the feature points. And finally, calculating object parameters such as length, width, height and volume through the 3D coordinates of the residual characteristic points. According to the invention, the characteristic points of the object to be measured are subjected to 3D modeling and converted into the two-dimensional coordinate system, the characteristic points of the object to be measured are intelligently screened, and the measurement reliability and accuracy are high, so that the object size measuring device can more conveniently and quickly measure the size of the object, and the measurement reliability and accuracy are high.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is a flow chart of one embodiment of an object dimension measurement method of the present application;
FIG. 2 is an exemplary sample of the object dimension measurement method of the present application;
FIG. 3 is a schematic structural view of one embodiment of an object dimension measuring device of the present application;
FIG. 4 is a schematic block diagram of one embodiment of a computer device according to the present application.
Reference numerals:
| 3 | object size |
301 | |
| 302 | Feature point three-dimensional |
303 | Two-dimensional |
| 304 | Characteristic point screening die | 305 | Size calculation module |
| 4 | |
41 | |
| 42 | Processor with a memory having a plurality of |
43 | Network interface |
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
With the increasing functionality of mobile devices (e.g., mobile phones, tablet computers, etc.), users carry mobile devices with them every day, but do not necessarily carry tools such as measuring scales with them. For example, sometimes, if an object is placed in a certain place, but the placing space is not enough, the specific length or volume of the object needs to be known. Or sometimes it is also desirable to know what the person's height is in order to fill in information, etc. However, the user does not have a tool for measuring the length of the object, and when the user does not have a measuring scale or other tools for measuring the length and other dimensions of the object or the size of the object is too large to be measured directly by the measuring scale, a method for easily and conveniently measuring the size information of the object by using a portable mobile device is needed, so that the user can conveniently and quickly know the size of the object to be known.
In view of the problems in the background art, the following technical solutions are proposed in the present application. Referring to FIG. 1, a flow chart of one embodiment of a method of measuring dimensions of an object according to the present application is shown. The object size measuring method comprises the following steps:
101: and acquiring an image of the object to be detected.
In the embodiment of the invention, the image of the object to be detected can be acquired through a mobile terminal, such as a mobile phone camera, a tablet personal computer and other equipment with a camera shooting function.
102: and acquiring the characteristic points of the image and calculating the world three-dimensional coordinates of the characteristic points.
In the embodiment of the present invention, the detection and acquisition of the feature points are obtained by using an algorithm such as a VIO (Visual Inertial odometer) and the like by sensors such as an accelerometer, a gyroscope, a camera and the like on the mobile device. Specifically, when the image of the object to be measured is obtained in step 101, it is necessary to slowly move a mobile device such as a mobile phone, obtain the image of the object to be measured as a continuously obtained offset image, and then obtain all feature points around the target object through a VIO algorithm, as shown in fig. 2, hashed points in the graph are feature points of the object to be measured, store coordinates of all the feature points, perform 3D modeling on the feature points, and calculate world three-dimensional coordinates of each feature point in a world coordinate system, where the world coordinates are coordinates using a certain set "reference point" of a virtual world as an origin.
Specifically, when the feature point is subjected to 3D modeling, the feature point world three-dimensional coordinates obtained through calculation are 3D world coordinates with the mobile terminal which has finished shooting as the origin. And the world coordinate system abstractly expresses the virtual scene of the object to be detected and the position relation of the object in the image.
103: and converting the world three-dimensional coordinates into two-dimensional plane coordinates.
In the embodiment of the present invention, since the acquired image of the object to be measured is a two-dimensional image, when the feature points of the two-dimensional image are screened to calculate the size, the 3D world coordinates of the feature points acquired in step 102 need to be converted into two-dimensional coordinates, so that the two-dimensional coordinates and the object to be measured are in the same coordinate system, and the measurement result is more accurate and precise.
In the embodiment of the invention, the 3D world coordinates of the feature points are converted into two-dimensional coordinates by matrix multiplication, which is a dimension reduction operation. According to the embodiment of the invention, the 3D world coordinate of the characteristic point is directly calculated and obtained, and the process of converting the 3D world coordinate into the two-dimensional coordinate mainly comprises the processes of observing space conversion and projection space conversion. The observation space conversion is to convert the 3D world coordinates of the feature points into camera space coordinates, the camera space coordinates are a coordinate system with the shooting equipment as an origin and with the observer as a center, so that the content shot by the shooting equipment in the processing process is presented by the position relation of the vertex of the object to be detected relative to the observer. The observation space transformation is to calculate the transformation of world coordinates to the camera, and the matrix of the camera is to transform to world coordinates, so that when the observation space is transformed, the inverse matrix of the camera that is actually multiplied by the 3D world coordinates is to calculate the transformation of the world to the camera. The projection space conversion is to convert the three-dimensional coordinates of the object to be measured into two-dimensional coordinates, the image of the object to be measured acquired in step 101 depends on the relative positions of the object to be measured and the mobile terminal, the closer the object to be measured is to the mobile terminal shooting device, the larger the imaging is, and otherwise, the smaller the imaging is, and the projection conversion depends on the maximum observed angle, the farthest distance and the closest distance.
Specifically, when the world three-dimensional coordinate is converted into a two-dimensional plane coordinate, the embodiment of the present invention performs matrix multiplication on the 3D coordinate of the feature point, the scale coordinate, the projection matrix acquired by the mobile terminal, and the observation matrix to obtain the two-dimensional coordinate of the object to be measured, where the scale coordinate is generally an identity matrix, and the observation matrix is an internal parameter of the mobile terminal.
104: and screening the characteristic points according to the two-dimensional plane coordinates.
After the 3D world coordinates of all the feature points acquired from the image are converted into two-dimensional coordinates in step 103, the feature points are screened according to the two-dimensional coordinates to calculate the size of the object to be measured. Specifically, when feature points are screened, firstly, a boundary of the object to be detected is obtained through a target detection model based on deep learning, and the boundary and the feature points of the object to be detected in the boundary are screened.
The target detection model based on deep learning is a lightweight detection model, the target detection includes 2 tasks of target classification and target positioning, the target positioning generally uses a rectangular bounding box to frame the position of the object, and the target classification can quickly detect the target object to be detected.
Specifically, the object classification is based on image detection, and a class label of an image is output. The target positioning can be realized by detecting two key points of the upper left corner and the lower right corner of the object to be detected to completely predict the boundary frame of the object to be detected, or by detecting the central point of the object to be detected and then predicting the width and the height of the object frame to generate the boundary frame of the object to be detected. For example, by first obtaining the image reshape of the object to be measured (a function that can readjust the number of rows, columns, and dimensions of the matrix) obtained in step 101 to 448x448, and then dividing the image of the object to be measured into 7x7 cells, each cell predicting 2 bounding boxes, and the position coordinates of each bounding box are 4, x, y, w, and h, respectively. Where x, y is the offset of the bounding box with respect to the cell in which it is located (typically, the offset with respect to the coordinate point at the upper left corner of the cell, where the side length of each square cell is taken to be 1, so x, y is between [0,1 ]); w, h are the ratio of the predicted bounding box width, height to the entire picture width, height, respectively, also between [0,1 ]. And determining the positions of the angular points of the object to be detected, finding the upper left angular point and the lower right angular point which belong to the same target, wherein the angular distance of a pair of angular points of the same prediction frame is short, and finely adjusting the angular points to ensure that the prediction frame is more accurate.
Further, the target detection model is trained, and the training of the target detection model is completed by acquiring a large number of target data sets, and performing training steps such as data labeling, dividing the data sets into a training set, a test set and a verification set, configuring an SSD (Single Shot multi box Detector), selecting a training model, and the like. The boundary of the object to be detected can be rapidly obtained through the trained target detection model.
Optionally, the target detection model is a mobileNet-SSD detection model, and a training process thereof is as follows:
1. and marking the acquired data and establishing data set soft connection. The test sample data set collected in this embodiment is in a VOC format, the data set includes a training verification set train _ lmdb file (lmdb, which is called a Lightning Memory-Mapped Database, a Lightning Memory mapping Database file, which includes a data file and a lock file) and a test set test _ lmdb file, the training verification set train _ lmdb file includes training data and verification data, and the test _ lmdb file includes test data. Establishing soft connection between the training verification set train _ lmdb file and the test set test _ lmdb file.
2. Creating a label file, which labels data, such as the file name of a picture, the name of a labeled object, the position of the object, and the like, and is used for defining the category of a training sample, and the training sample is placed under a project folder.
3. And configuring the SSD, wherein the SSD is a unified framework for performing object detection tasks by using a single network, and SSD codes can be directly downloaded.
4. And downloading a pre-training model, wherein the pre-training model is subjected to preliminary debugging of the VOC data set.
And 5, starting training, modifying and running the training script, and continuously adjusting parameters in the middle. And after training is finished, running a training script and testing the precision value of the network.
Further, the target detection model based on deep learning has an object recognition function, can recognize all objects to be detected in the acquired image, and acquires the boundary of each recognized object to be detected. As shown in fig. 2, the object to be measured has two pots of plants, and frames are acquired for the two pots of plants respectively. The larger frame is the boundary of the plant 1, the smaller frame is the boundary of the plant 2, all the detected feature points of the two pots of plants are screened, all the feature points in the larger frame are screened by calculating the green plant 1, and only all the feature points in the smaller frame are screened by calculating the smaller plant 2.
105: and calculating the size of the object to be measured according to the world three-dimensional coordinates of the screened feature points.
In the embodiment of the invention, according to the maximum value and the minimum value of each dimension coordinate in the 3D world coordinates of the screened feature points, the size of the object to be measured is calculated by subtracting the minimum value from the maximum value of each dimension, for example, the length of the object to be measured is calculated according to the maximum value and the minimum value of an x axis, the width is calculated according to the maximum value and the minimum value of a y axis, and the height is calculated according to the maximum value and the minimum value of a z axis.
It can be understood that, in order to make the measurement result more accurate, the feature points in the boundary can be further screened, abnormal points in the feature points are removed, and the size of the object to be measured is calculated according to the world three-dimensional coordinates of the remaining feature points.
Specifically, when the abnormal feature points are removed, the center of the two-dimensional image enclosed by the boundary is used as the starting point of the line segment, all the feature points and the starting point are connected into the line segment, the length is calculated, the median of the length of all the line segments is obtained, and the feature points of the line segments with larger deviation from the length are removed.
The embodiment of the application provides an object size measuring method, which comprises the steps of obtaining characteristic points of an object to be measured according to an obtained image of the object to be measured, carrying out 3D modeling on the characteristic points, and calculating world three-dimensional coordinates of the characteristic points. And (3) converting the coordinates of the image feature points from a 3D world coordinate system to a two-dimensional coordinate system so as to screen the image feature points, and then removing abnormal feature points according to the deviation distribution of the feature points. And finally, calculating object parameters such as length, width, height and volume through the 3D coordinates of the residual characteristic points. According to the invention, the characteristic points of the object to be measured are subjected to 3D modeling and converted into the two-dimensional coordinate system, the characteristic points of the object to be measured are intelligently screened, and the measurement reliability and accuracy are high, so that the object size measuring device can more conveniently and quickly measure the size of the object, and the measurement reliability and accuracy are high.
In order to solve the above technical problem, as shown in fig. 3, an object dimension measuring apparatus 3 is further provided in the embodiment of the present application.
An object dimension measuring apparatus 3, comprising:
an image acquisition module 301, configured to acquire an image of an object to be detected;
a feature point three-dimensional coordinate calculation module 302, configured to obtain a feature point of the image and calculate a world three-dimensional coordinate of the feature point;
a two-dimensional coordinate conversion module 303, configured to convert the world three-dimensional coordinate into a two-dimensional plane coordinate;
a feature point screening module 304, configured to screen feature points according to the two-dimensional plane coordinates;
and a size calculation module 305, configured to calculate the size of the object to be measured according to the filtered world three-dimensional coordinates of the feature points.
In the embodiment of the application, through the image of the object to be detected acquired by the image acquisition module 301, the feature point three-dimensional coordinate calculation module 302 acquires the feature points of the image, performs 3D modeling on the feature points, and calculates the world three-dimensional coordinates of all the feature points. The two-dimensional coordinate conversion module 303 converts the coordinates of the image feature points from a 3D world coordinate system to a two-dimensional coordinate system, the feature point screening module 304 performs target positioning and target classification on the image of the object to be detected acquired by the image acquisition module 301, and then eliminates abnormal feature points according to the deviation distribution of the feature points. And finally, the length, width, height and volume of the identified object to be detected are calculated by the size calculation module 305 according to the 3D coordinates of the residual characteristic points. According to the invention, the characteristic points of the object to be measured are subjected to 3D modeling and converted into the two-dimensional coordinate system, the characteristic points of the object to be measured are intelligently screened, and the measurement reliability and accuracy are high, so that the object size measuring device can more conveniently and quickly measure the size of the object, and the measurement reliability and accuracy are high.
Further, when acquiring the image of the object to be detected, the feature point three-dimensional coordinate calculation module 302 needs to slowly move a mobile device such as a mobile phone, acquire the image of the object to be detected as a continuously acquired offset image, and then obtain all feature points around the target object through a VIO algorithm.
When the world three-dimensional coordinate is converted into a two-dimensional plane coordinate, the two-dimensional coordinate conversion module 303 performs matrix multiplication on the 3D coordinate of the feature point, the scale coordinate, the projection matrix acquired by the mobile terminal, and the observation matrix to obtain the two-dimensional coordinate of the object to be measured, where the scale coordinate is generally an identity matrix and the observation matrix is an internal parameter of the mobile terminal.
The feature point screening module 304 includes a light-weight detection model based on a deep learning target detection model, which includes 2 tasks of target classification and target positioning, where the target positioning generally uses a rectangular bounding box to frame the position of an object, and the target classification can quickly detect the target object to be detected.
In some embodiments, the feature point filtering module 304 fully predicts the bounding box of the object to be tested by detecting two key points at the upper left corner and the lower right corner of the object to be tested.
It should be noted that the apparatus of this embodiment and the method embodiment belong to the same concept, and specific implementation processes thereof are detailed in the method embodiment, and technical features in the method embodiment are all correspondingly applicable in this embodiment, which is not described herein again.
In order to solve the above technical problem, the embodiment of the present application further provides a computer device 4. Referring to fig. 4, (Application Specific Integrated Circuit, ASIC), Programmable Gate Array (FPGA), Digital Signal Processor (DSP), embedded device, etc.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 41 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 4. Of course, the memory 41 may also include both internal and external storage devices of the computer device 4. In this embodiment, the memory 41 is generally used for storing an operating fund system installed in the computer device 4 and various types of application software, such as program codes of an object dimension measuring method. Further, the memory 41 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 42 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute the program code stored in the memory 41 or process data, for example, execute the program code of the object dimension measuring method.
The network interface 43 may comprise a wireless network interface or a wired network interface, and the network interface 43 is generally used for establishing communication connection between the computer device 4 and other electronic devices.
The present application provides yet another embodiment, which provides a computer-readable storage medium storing an object dimension measurement program executable by at least one processor to cause the at least one processor to perform the steps of the object dimension measurement method as described above.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. A method of measuring the dimensions of an object, comprising the steps of:
acquiring an image of an object to be detected;
acquiring characteristic points of the image and calculating world three-dimensional coordinates of the characteristic points;
converting the world three-dimensional coordinates into two-dimensional plane coordinates;
screening characteristic points according to the two-dimensional plane coordinates;
and calculating the size of the object to be measured according to the world three-dimensional coordinates of the screened feature points.
2. The object dimension measuring method according to claim 1, wherein the acquired image of the object to be measured is a continuously acquired offset image, a characteristic point of the image is acquired according to a visual-inertial-mileage calculation method, and the acquired characteristic point is subjected to 3D modeling to acquire world three-dimensional coordinates of the characteristic point.
3. The object dimension measuring method according to claim 2, wherein the screening of the feature points based on the two-dimensional plane coordinates includes:
acquiring the boundary of the object to be detected based on a deep learning target detection model;
and screening the characteristic points of the object to be detected in the boundary.
4. The object dimension measuring method according to claim 3, characterized by further comprising:
and identifying the object to be detected, and acquiring the boundary of each identified object to be detected.
5. The method according to claim 3, wherein the calculating the dimension of the object to be measured from the world three-dimensional coordinates of the feature points includes
Rejecting abnormal feature points within the boundary;
and calculating the size of the object to be measured according to the world three-dimensional coordinates of the remaining characteristic points.
6. The object dimension measuring method according to claim 5, wherein the eliminating of the abnormal feature points within the boundary includes:
and taking the center of the two-dimensional image enclosed by the boundary as the starting point of the line segment, connecting all the characteristic points and the starting point into the line segment, calculating the length, acquiring the median of the length of all the line segments, and removing the characteristic points of the line segments which deviate from the length greatly.
7. The method according to claim 6, wherein the calculating the size of the object to be measured from the world three-dimensional coordinates of the remaining feature points comprises
And acquiring the maximum value and the minimum value of each dimension coordinate of the eliminated abnormal feature points, and calculating the size length of the object to be measured according to the difference value of the maximum value and the minimum value of each dimension coordinate.
8. An object dimension measuring apparatus, comprising:
the image acquisition module is used for acquiring an image of an object to be detected;
the characteristic point three-dimensional coordinate calculation module is used for acquiring the characteristic points of the image and calculating the world three-dimensional coordinates of the characteristic points;
the two-dimensional coordinate conversion module is used for converting the world three-dimensional coordinate into a two-dimensional plane coordinate;
the characteristic point screening module is used for screening characteristic points according to the two-dimensional plane coordinates;
and the size calculation module is used for calculating the size of the object to be measured according to the screened world three-dimensional coordinates of the feature points.
9. A computer device, characterized by comprising a memory in which a computer program is stored, a processor and a network interface, the processor implementing the steps of the object dimension measuring method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, carries out the steps of the object dimension measuring method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011502470.XA CN112683169A (en) | 2020-12-17 | 2020-12-17 | Object size measuring method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011502470.XA CN112683169A (en) | 2020-12-17 | 2020-12-17 | Object size measuring method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112683169A true CN112683169A (en) | 2021-04-20 |
Family
ID=75449545
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011502470.XA Pending CN112683169A (en) | 2020-12-17 | 2020-12-17 | Object size measuring method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112683169A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113192202A (en) * | 2021-05-14 | 2021-07-30 | 广联达科技股份有限公司 | Method for representing vector diagram of building model and computer-readable storage medium |
| CN113688846A (en) * | 2021-08-24 | 2021-11-23 | 成都睿琪科技有限责任公司 | Object size recognition method, readable storage medium, and object size recognition system |
| CN115248017A (en) * | 2022-09-21 | 2022-10-28 | 江苏新恒基特种装备股份有限公司 | Rapid detection method and detection system for geometric dimension of branch pipe fitting |
| CN117685881A (en) * | 2024-01-31 | 2024-03-12 | 成都建工第七建筑工程有限公司 | Sensing and detecting system for concrete structure entity position and size deviation |
| CN113192202B (en) * | 2021-05-14 | 2024-04-30 | 广联达科技股份有限公司 | Method for representing vector diagram of building model and computer readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150125034A1 (en) * | 2013-11-05 | 2015-05-07 | Canon Kabushiki Kaisha | Information processing apparatus, information processing method, and storage medium |
| JP2016096988A (en) * | 2014-11-20 | 2016-05-30 | 学校法人金沢医科大学 | Body height measurement method, body height measurement apparatus, and body height measurement program |
| CN106570476A (en) * | 2016-10-28 | 2017-04-19 | 黑龙江省科学院自动化研究所 | Key size automatic extraction method in three dimensional human body measurement |
| CN108627092A (en) * | 2018-04-17 | 2018-10-09 | 南京阿凡达机器人科技有限公司 | A kind of measurement method, system, storage medium and the mobile terminal of package volume |
| CN110006343A (en) * | 2019-04-15 | 2019-07-12 | Oppo广东移动通信有限公司 | Measurement method, device and the terminal of object geometric parameter |
| CN111179152A (en) * | 2018-11-12 | 2020-05-19 | 阿里巴巴集团控股有限公司 | Road sign identification method and device, medium and terminal |
| CN111986250A (en) * | 2019-05-22 | 2020-11-24 | 顺丰科技有限公司 | Object volume measuring method, device, measuring equipment and storage medium |
| CN112001962A (en) * | 2020-07-24 | 2020-11-27 | 北京驭光科技发展有限公司 | Ship height measuring and calculating method and system |
-
2020
- 2020-12-17 CN CN202011502470.XA patent/CN112683169A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150125034A1 (en) * | 2013-11-05 | 2015-05-07 | Canon Kabushiki Kaisha | Information processing apparatus, information processing method, and storage medium |
| JP2016096988A (en) * | 2014-11-20 | 2016-05-30 | 学校法人金沢医科大学 | Body height measurement method, body height measurement apparatus, and body height measurement program |
| CN106570476A (en) * | 2016-10-28 | 2017-04-19 | 黑龙江省科学院自动化研究所 | Key size automatic extraction method in three dimensional human body measurement |
| CN108627092A (en) * | 2018-04-17 | 2018-10-09 | 南京阿凡达机器人科技有限公司 | A kind of measurement method, system, storage medium and the mobile terminal of package volume |
| CN111179152A (en) * | 2018-11-12 | 2020-05-19 | 阿里巴巴集团控股有限公司 | Road sign identification method and device, medium and terminal |
| CN110006343A (en) * | 2019-04-15 | 2019-07-12 | Oppo广东移动通信有限公司 | Measurement method, device and the terminal of object geometric parameter |
| CN111986250A (en) * | 2019-05-22 | 2020-11-24 | 顺丰科技有限公司 | Object volume measuring method, device, measuring equipment and storage medium |
| CN112001962A (en) * | 2020-07-24 | 2020-11-27 | 北京驭光科技发展有限公司 | Ship height measuring and calculating method and system |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113192202A (en) * | 2021-05-14 | 2021-07-30 | 广联达科技股份有限公司 | Method for representing vector diagram of building model and computer-readable storage medium |
| CN113192202B (en) * | 2021-05-14 | 2024-04-30 | 广联达科技股份有限公司 | Method for representing vector diagram of building model and computer readable storage medium |
| CN113688846A (en) * | 2021-08-24 | 2021-11-23 | 成都睿琪科技有限责任公司 | Object size recognition method, readable storage medium, and object size recognition system |
| CN113688846B (en) * | 2021-08-24 | 2023-11-03 | 成都睿琪科技有限责任公司 | Object size recognition method, readable storage medium, and object size recognition system |
| CN115248017A (en) * | 2022-09-21 | 2022-10-28 | 江苏新恒基特种装备股份有限公司 | Rapid detection method and detection system for geometric dimension of branch pipe fitting |
| CN115248017B (en) * | 2022-09-21 | 2022-11-29 | 江苏新恒基特种装备股份有限公司 | Rapid detection method and detection system for geometric dimension of branch pipe fitting |
| CN117685881A (en) * | 2024-01-31 | 2024-03-12 | 成都建工第七建筑工程有限公司 | Sensing and detecting system for concrete structure entity position and size deviation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108038474B (en) | Face detection method, convolutional neural network parameter training method, device and medium | |
| CN112683169A (en) | Object size measuring method, device, equipment and storage medium | |
| CN111476827B (en) | Target tracking method, system, electronic device and storage medium | |
| CN110910445B (en) | Object size detection method, device, detection equipment and storage medium | |
| CN111144398A (en) | Target detection method, target detection device, computer equipment and storage medium | |
| CN109345460B (en) | Method and apparatus for rectifying image | |
| CN112966711A (en) | Pointer instrument indicating number identification method and system based on convolutional neural network | |
| CN111144372A (en) | Vehicle detection method, device, computer equipment and storage medium | |
| CN111798521A (en) | Calibration method, calibration device, storage medium and electronic equipment | |
| CN111815576A (en) | Method, device, equipment and storage medium for detecting corrosion condition of metal part | |
| CN113899367B (en) | Positioning method and device for unmanned aerial vehicle landing, computer equipment and storage medium | |
| CN105654138A (en) | Orthogonal projection and dimensionality reduction classification method and system for multidimensional data | |
| CN112529836A (en) | High-voltage line defect detection method and device, storage medium and electronic equipment | |
| CN112669382A (en) | Image-based distance determination method and device | |
| CN113673288A (en) | Idle parking space detection method and device, computer equipment and storage medium | |
| CN111476144A (en) | Pedestrian attribute identification model determination method and device and computer readable storage medium | |
| CN115063473A (en) | Object height detection method and device, computer equipment and storage medium | |
| CN113989632A (en) | Bridge detection method and device for remote sensing image, electronic equipment and storage medium | |
| CN112308061B (en) | License plate character recognition method and device | |
| CN115424000A (en) | Pointer instrument identification method, system, equipment and storage medium | |
| CN112381773B (en) | Key cross section data analysis method, device, equipment and storage medium | |
| CN115035481A (en) | Image object distance fusion method, device, equipment and storage medium | |
| CN114399729A (en) | Monitoring object movement identification method, system, terminal and storage medium | |
| CN114022658A (en) | Target detection method, device, storage medium and terminal | |
| CN112950568A (en) | Scale length calculation method and device, computer equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210420 |
|
| RJ01 | Rejection of invention patent application after publication |