CN116148806A - Method and device for determining depth of target object and electronic equipment - Google Patents
Method and device for determining depth of target object and electronic equipment Download PDFInfo
- Publication number
- CN116148806A CN116148806A CN202310164928.2A CN202310164928A CN116148806A CN 116148806 A CN116148806 A CN 116148806A CN 202310164928 A CN202310164928 A CN 202310164928A CN 116148806 A CN116148806 A CN 116148806A
- Authority
- CN
- China
- Prior art keywords
- target
- information
- target object
- preset
- depth
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Image Processing (AREA)
Abstract
A method, a device and electronic equipment for determining the depth of a target object, wherein the method comprises the following steps: object information corresponding to the target object is obtained, the object information is converted into a multidimensional feature vector based on the data preprocessing model, and the multidimensional feature vector is input into a preset depth model to obtain length information corresponding to the target object. According to the method, the object information of the target object is input into the data preprocessing model to obtain the multidimensional feature vector corresponding to the object information, the multidimensional feature vector is input into the trained preset depth model to determine the depth information of the target object, and the data preprocessing model and the preset depth model are both models trained in advance, so that the accuracy of the depth information of the target object determined based on the data preprocessing model and the preset depth model can be ensured.
Description
Technical Field
The application relates to the technical field of intelligent driving, in particular to a method and device for determining the depth of a target object and electronic equipment.
Background
In the development process of the automatic driving technology, the software architecture of the automatic driving can be divided into a perception module and a decision module, the perception module acquires data outside the vehicle through a sensor in the vehicle system, the sensor can be a laser radar, an image acquisition device and the like, and the decision module issues instructions based on the data acquired by the perception module.
When the sensor in the sensing module described above is a laser radar, the laser radar can determine the position of the target object in the three-dimensional space based on the transmitting time, the returning time, the transmitting angle and the returning angle of the transmitted pulse signal, and the data collected by the laser radar is used as the point cloud data, so the processing of the point cloud data collected by the laser radar is as follows:
when a target object is detected based on a laser radar, the laser radar can acquire all first point cloud data in a scene containing the target object, and process the first point cloud data based on a PointNet algorithm to acquire second point cloud data corresponding to the target object, wherein the point cloud data is a scene formed by a plurality of points or a point cloud set of the object, each point can be represented by coordinates in a space rectangular coordinate system, and the minimum value and the maximum value of x are required to be determined from x of all points of the target object, so that the range in the x direction is acquired; determining the minimum value and the maximum value of y from y of all points of the target object to obtain a range in the y direction; and determining the minimum value and the maximum value of z from the z of all points of the target object, and obtaining the range in the z direction.
Based on the obtained 6 values, a 3D frame of the target object can be determined, and based on the 3D frame, the height information, the width information and the depth information of the target object can be obtained.
Disclosure of Invention
The application provides a method, a device and electronic equipment for determining the depth of a target object, which are used for improving the accuracy of depth information of the target object.
In a first aspect, the present application provides a method of determining a depth of a target object, the method comprising:
obtaining object information corresponding to a target object, wherein the object information comprises: the height information, the width information and the target type of the target object;
converting the object information into a multi-dimensional target feature vector based on a data preprocessing model;
and inputting the multi-dimensional target feature vector into a preset depth model to obtain depth information corresponding to the target object.
According to the method, the object information of the target object is processed through the data preprocessing model to obtain the multi-dimensional target feature vector corresponding to the target object, and the multi-dimensional target feature vector is processed through the preset depth model to obtain the depth information of the target object.
In one possible design, before obtaining the object information corresponding to the target object, the method includes:
obtaining test object information corresponding to m test objects, wherein the test object information is the height information, the width information and the depth information of the test objects and the type information of the test objects, and m is a positive integer;
training based on the m test objects to obtain training models corresponding to the m test objects;
and determining a preset depth model corresponding to the m test objects in response to the training model meeting preset conditions.
Through the method, the m test objects are trained, training models of the m test objects are obtained, when the training models meet preset conditions, the determined preset depth model is selected, and accuracy of predicting depth information of the preset depth model is improved.
In one possible design, training is performed based on the m test objects, to obtain training models corresponding to the m test objects, including:
determining the maximum value of all height information, width information and depth information corresponding to the m test objects and category feature vectors corresponding to the m test objects respectively;
normalizing the height information and the width information corresponding to each test object based on the maximum value to obtain two-dimensional feature vectors corresponding to each test object;
splicing the two-dimensional feature vectors of each test object and the corresponding class feature vectors to obtain the multidimensional feature vectors of each test object;
training is carried out based on the depth information corresponding to each test object and the multidimensional feature vectors, and training models corresponding to the m test objects are obtained.
By the method, the multi-dimensional feature vector of the target object is obtained through the splicing of the two-dimensional feature vector and the category feature vector of the target object, model training is carried out based on the multi-dimensional feature vector and the depth information of each test object, and the accuracy of the training model is ensured.
In one possible design, responding to the training model meeting a preset condition includes:
obtaining total training times corresponding to the m test objects, and determining a loss value of a training model corresponding to each training of the m test objects, wherein the loss value represents the difference between a model prediction depth value and an actual training sample depth value;
when the total training times reach preset training times, responding to the training model to accord with preset conditions; and
and when the loss value is smaller than a preset loss threshold value, responding to the training model to meet preset conditions.
Through the method, the training model after the m test objects are trained each time is detected, so that the obtained training model is ensured to meet the preset condition, and the accuracy of the training model is improved.
In one possible design, obtaining object information corresponding to the target object includes:
determining a three-dimensional detection frame of the target object, and obtaining a target type of the target object based on a preset classification algorithm;
responding to the target type in a preset category set, and reading out the height information and the width information of the target object based on the three-dimensional detection frame, wherein the preset category set comprises a plurality of categories corresponding to preset objects;
and taking the target type, the height information and the width information as object information corresponding to the target object.
According to the method, the width information and the height information of the target object are obtained through the three-dimensional detection frame, and the target type of the target object is determined to be consistent with the type of the preset object in the preset type set, so that the accuracy of the obtained object information of the target object is ensured.
In one possible design, obtaining the target type of the target object based on a preset classification algorithm includes:
extracting a plurality of target characteristics corresponding to the target object;
matching the plurality of target features with a preset category feature set to determine a plurality of similarity values corresponding to the plurality of target feature sets, wherein the preset category feature set comprises feature sets corresponding to each preset object;
and determining a preset category of the preset object corresponding to the maximum similarity from the plurality of similarity values, and taking the preset category as the target type of the target object.
By the method, the preset category of the preset object corresponding to the maximum similarity is determined, and the preset category is used as the target type of the target object, so that the accuracy of determining the target type of the target object is improved.
In one possible design, converting the object information into a multi-dimensional target feature vector based on a data preprocessing model includes:
inputting the object information corresponding to the target object into the data preprocessing model to obtain a target two-dimensional feature vector and a target category vector of the target object;
and combining the target two-dimensional feature vector and the target category vector to obtain a multi-dimensional target feature vector corresponding to the target object.
According to the method, the object information of the target object is converted into the multidimensional target feature vector through the data preprocessing model, and the object information of the target object is preprocessed, so that the accuracy of determining the depth information of the target object is improved.
In a second aspect, the present application provides an apparatus for determining a depth of a target object, the apparatus comprising:
the device comprises an obtaining module, a processing module and a processing module, wherein the obtaining module is used for obtaining object information corresponding to a target object, and the object information comprises: the height information, the width information and the target type of the target object;
the conversion module is used for converting the object information into a multidimensional target feature vector based on a data preprocessing model;
and the depth module is used for inputting the multi-dimensional target feature vector into a preset depth model to obtain depth information corresponding to the target object.
In one possible design, the obtaining module is specifically configured to obtain test object information corresponding to each of m test objects, perform training based on the m test objects, obtain training models corresponding to the m test objects, and determine a preset depth model corresponding to the m test objects in response to the training models meeting preset conditions.
In one possible design, the obtaining module is further configured to determine a maximum value of all height information, width information and depth information corresponding to the m test objects, and class feature vectors corresponding to the m test objects, normalize the height information and the width information corresponding to each test object based on the maximum value, obtain two-dimensional feature vectors corresponding to each test object, splice the two-dimensional feature vectors corresponding to each test object and the class feature vectors corresponding to each test object, obtain multidimensional feature vectors corresponding to each test object, and train based on the depth information corresponding to each test object and the multidimensional feature vectors, so as to obtain training models corresponding to the m test objects.
In one possible design, the obtaining module is further configured to obtain a total training number corresponding to the m test objects, determine a loss value of a training model corresponding to each training of the m test objects, respond to the training model meeting a preset condition when the total training number reaches a preset training number, and respond to the training model meeting a preset condition when the loss value is less than a preset loss threshold.
In one possible design, the obtaining module is further configured to determine a three-dimensional detection frame of the target object, obtain a target type of the target object based on a preset classification algorithm, read height information and width information of the target object based on the three-dimensional detection frame in response to the target type being in a preset classification set, and use the target type, the height information and the width information as object information corresponding to the target object.
In one possible design, the obtaining module is further configured to extract a plurality of target features corresponding to the target object, match the plurality of target features with a preset category feature set, determine a plurality of similarity values corresponding to the plurality of target feature sets, determine a preset category of the preset object corresponding to the maximum similarity from the plurality of similarity values, and use the preset category as the target type of the target object.
In one possible design, the transformation module is specifically configured to input the object information corresponding to the target object into the data preprocessing model, obtain a target two-dimensional feature vector and a target class vector of the target object, and combine the target two-dimensional feature vector and the target class vector to obtain a multi-dimensional target feature vector corresponding to the target object.
In a third aspect, the present application provides an electronic device, including:
a memory for storing a computer program;
and the processor is used for realizing the method steps for determining the depth of the target object when executing the computer program stored in the memory.
In a fourth aspect, a computer readable storage medium has stored therein a computer program which, when executed by a processor, performs one of the above-described method steps of determining a depth of a target object.
The technical effects of each of the first to fourth aspects and the technical effects that may be achieved by each aspect are referred to above for the technical effects that may be achieved by the first aspect or the various possible aspects of the first aspect, and are not repeated here.
Drawings
FIG. 1 is a flowchart of method steps for determining a depth of a target object provided herein;
FIG. 2 is a schematic diagram of object information of a target object processed based on a data preprocessing model provided by the present application;
fig. 3 is a schematic diagram of obtaining depth information of a target object based on a preset depth model provided in the present application;
FIG. 4 is a schematic structural view of an apparatus for determining the depth of a target object provided in the present application;
fig. 5 is a schematic structural diagram of an electronic device provided in the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings. The specific method of operation in the method embodiment may also be applied to the device embodiment or the system embodiment. It should be noted that "a plurality of" is understood as "at least two" in the description of the present application. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. A is connected with B, and can be represented as follows: both cases of direct connection of A and B and connection of A and B through C. In addition, in the description of the present application, the words "first," "second," and the like are used merely for distinguishing between the descriptions and not be construed as indicating or implying a relative importance or order.
In the prior art, a specific method for acquiring depth information of a target object based on a laser radar comprises the steps of acquiring all first point cloud data in a scene containing the target object based on the laser radar, processing the first point cloud data based on a PointNet algorithm, and acquiring second point cloud data corresponding to the target object, wherein each point in the second point cloud data can be represented by coordinates in a space rectangular coordinate system, and determining the minimum value and the maximum value of x from x of all points of the target object to obtain a range in the x direction; determining the minimum value and the maximum value of y from y of all points of the target object to obtain a range in the y direction; and determining the minimum value and the maximum value of z from the z of all points of the target object, and obtaining the range in the z direction.
Based on the obtained 6 values, a 3D frame of the target object can be determined, and based on the 3D frame, the height information, the width information and the depth information of the target object can be obtained.
In order to solve the above-described problems, the present application provides a method for determining a depth of a target object, so as to accurately determine depth information of the target object. The method and the device according to the embodiments of the present application are based on the same technical concept, and because the principles of the problems solved by the method and the device are similar, the embodiments of the device and the method can be referred to each other, and the repetition is not repeated.
Embodiments of the present application are described in detail below with reference to the accompanying drawings.
Referring to fig. 1, the present application provides a method for determining a depth of a target object, where the method can accurately determine depth information of the target object, and the implementation flow of the method is as follows:
step S1: object information corresponding to the target object is obtained.
In order to obtain accurate depth information of a target object, first, the target object needs to be detected based on a laser radar to obtain point cloud data corresponding to the target object, and although the accuracy of the laser radar in obtaining the depth information of the target object is low, the width information and the height information of the target object can be obtained based on the laser radar.
In order to obtain accurate width information and height information of a target object, clustering processing needs to be performed on the obtained point cloud data, in this embodiment of the present application, the clustering processing may be performed by using a PointNet algorithm, after clustering processing is performed on the point cloud data, a 3D frame corresponding to the target object is generated, after the 3D frame is obtained, filtering and correction are further required for removing noise data and other interferences in the 3D frame, and correction is used for obtaining accurate height information and width information based on the point cloud data.
Specifically, the filtering and correcting method is generally to detect whether the height and width of the 3D frame are smaller than a preset value, and when both the height and the width are smaller than the preset value, the 3D frame is considered to be caused by noise, an outlier detection method is adopted to correct, and the outlier is removed by performing outlier detection on the point cloud data in the 3D frame, and then the 3D frame is regenerated, and since outlier detection is a technology known to those skilled in the art, too much description is not given here.
Based on the processed 3D frame, determining whether the target type of the target object is in a preset category set or not in order to obtain accurate depth information of the target object, and performing a process of obtaining the depth information of the target object when the target type of the target object is in the preset category set; when the target type of the target object is not in the preset category set, the process of acquiring the depth information of the target object is exited.
Because the embodiment of the application obtains the depth information of the target object based on the data preprocessing model and the preset depth model, before obtaining the object information of the target object, the data preprocessing model and the preset depth model need to be obtained, and the specific obtaining process is as follows:
obtaining test object information corresponding to m test objects respectively, wherein m is a positive integer, and the test object information comprises: determining the maximum value from the height information, the width information and the depth information of all the tested objects, and the category feature vectors corresponding to the tested objects respectively, and carrying out normalization processing on the height information and the width information of the tested objects, wherein the normalization processing comprises the following steps:
dividing the height information of each test object by the maximum value, and dividing the width information of each test object by the maximum value to obtain two-dimensional feature vectors of each test object, respectively, wherein the two-dimensional feature vectors comprise: and splicing the two-dimensional feature vector with the category feature vector to obtain multi-dimensional feature vectors corresponding to the test objects respectively, thereby obtaining a flow of processing data by the data preprocessing model.
In order to make depth information obtained based on a preset depth model accurate, training needs to be performed based on respective corresponding depth information of each test object and respective corresponding multidimensional feature vectors, and the multidimensional feature vectors are input into a full-connection module, where the full-connection module in the embodiment of the present application may include: the full-connection (fully connected layers, FC) layer, batch normalization (Batch Normalization, BN) layer and linear rectification function (Rectified Linear Unit, reLU) layer, wherein the FC layer is used for integrating the feature vector into a value, reducing the influence of the feature position on the classification result, the BN layer is used for preventing the occurrence of over fitting in the test process, the ReLU layer is used for increasing the nonlinear relation among the layers of the neural network, and the multidimensional feature vector of each test object is input into the full-connection module for multiple training to obtain the test model corresponding to each test object.
Determining the total training times of each test object, determining the loss value of a training model corresponding to each test object when each test object is trained, wherein the loss value represents the difference between the predicted depth value of the model and the depth value of a training sample, and when the total training times reach the preset training times, the training model obtained by the last training is represented to accord with the preset condition; or when the loss value is smaller than the preset loss value, the training model corresponding to the loss value accords with the preset condition, and a specific formula for determining the loss value is as follows:
in the above formula, L represents a loss value, N represents the training number, L i Representing the actual depth value of the test object i,
indicating the predicted depth value of the test object i, it should be noted that l i Is the value obtained by normalizing the depth of the test object.
And when the training model meets the conditions described above, taking the determined training model as a preset depth model.
After the data preprocessing model and the preset depth model are determined, a three-dimensional detection frame of the target object is obtained, and the target type of the target object is obtained based on a preset classification algorithm, wherein the preset classification algorithm can be a PointNet algorithm, and after the target type of the target object is determined based on the preset classification algorithm, whether the target type of the target object is in a preset category set or not is required to be judged, and the specific judgment process is as follows:
the method comprises the steps that a plurality of target characteristics of a target object are extracted by a server, the plurality of target characteristics are matched with preset category characteristic sets, the preset category characteristic sets comprise characteristic sets corresponding to each preset object, similarity values of the plurality of target characteristics and the characteristic sets in the preset category characteristic sets are determined, the maximum similarity value is determined from the obtained plurality of similarity values, the preset category of the preset object corresponding to the maximum similarity value is obtained, and the preset category is used as the target type of the target object.
And when the target type of the target object is determined to be in the preset category based on the description, determining the width information and the height information of the target object and the object information based on the three-dimensional detection frame, and taking the obtained width information, height information and the target type as the object information of the target object.
Based on the above description, the object information of the target object is obtained, and since the data preprocessing model and the preset depth model are determined before the object information is obtained, the input of the data preprocessing model and the preset depth model can be obtained based on the object information, which is beneficial to determining the depth information of the target object.
Step S2: and converting the object information into a multi-dimensional target feature vector based on a data preprocessing model.
Since the process of obtaining the data preprocessing model and the object information of the target object have been described above, the height information, the width information and the target type of the target object can be extracted from the object information, the height information, the width information and the target type are input into the data preprocessing model to obtain the target two-dimensional feature vector and the target class vector corresponding to the target object, and the target two-dimensional feature vector and the target class vector are spliced to obtain the multi-dimensional target feature vector corresponding to the target object.
In fig. 2, after the object information is input into the data preprocessing model, normalization processing is performed on the height information and the width information of the object in the data preprocessing model to obtain one-dimensional feature vectors corresponding to the height information and the width information, respectively, n-dimensional feature vectors are determined by an embedding method according to a plurality of target features of the object, n is a positive integer, and finally, the one-dimensional feature vectors corresponding to the height information and the width information are spliced with the n-dimensional feature vectors to obtain n+2-dimensional feature vectors, and the n+2-dimensional feature vectors after the splicing are used as output of the data preprocessing model.
Based on the method, the multidimensional target feature vector corresponding to the target object is obtained based on the data preprocessing model, so that the multidimensional target feature vector can represent the object information of the target object, and the depth information of the target object can be obtained.
Step S3: and inputting the multi-dimensional target feature vector into a preset depth model to obtain depth information corresponding to the target object.
In order to obtain the depth information of the target object, the multi-dimensional target feature vector is required to be input into the preset depth model, the depth information of the target object is obtained based on the preset depth model, as shown in fig. 3, the multi-dimensional target feature vector is input into the preset depth model, the depth information of the target object is predicted through the full connection model in the preset depth model, and finally, the preset depth information is output, so that the depth information corresponding to the target object is obtained.
Based on the method, the height information and the width information of the target object are determined through the laser radar, and then the depth information of the target object is predicted through the trained data preprocessing model and the preset depth model, so that the problem that the depth information of the target object obtained based on the laser radar is inaccurate is avoided.
Based on the same inventive concept, the embodiment of the present application further provides an electronic device, where the electronic device may implement the function of the foregoing apparatus for determining a depth of a target object, and referring to fig. 4, the electronic device includes:
an obtaining module 401, configured to obtain object information corresponding to a target object, where the object information includes: the height information, the width information and the target type of the target object;
a conversion module 402, configured to convert the object information into a multidimensional target feature vector based on a data preprocessing model;
and the depth module 403 is configured to input the multi-dimensional target feature vector into a preset depth model, and obtain depth information corresponding to the target object.
In one possible design, the obtaining module 401 is specifically configured to obtain test object information corresponding to each of m test objects, perform training based on the m test objects, obtain training models corresponding to the m test objects, and determine a preset depth model corresponding to the m test objects in response to the training models meeting preset conditions.
In one possible design, the obtaining module 401 is further configured to determine a maximum value of all height information, width information and depth information corresponding to the m test objects, and class feature vectors corresponding to the m test objects, normalize the height information and the width information corresponding to each test object based on the maximum value, obtain two-dimensional feature vectors corresponding to each test object, splice the two-dimensional feature vectors corresponding to each test object and the class feature vectors corresponding to each test object, obtain multidimensional feature vectors corresponding to each test object, and train based on the depth information corresponding to each test object and the multidimensional feature vectors, so as to obtain training models corresponding to the m test objects.
In one possible design, the obtaining module 401 is further configured to obtain a total training number corresponding to the m test objects, determine a loss value of a training model corresponding to each training of the m test objects, respond to the training model meeting a preset condition when the total training number reaches a preset training number, and respond to the training model meeting a preset condition when the loss value is less than a preset loss threshold.
In one possible design, the obtaining module 401 is further configured to determine a three-dimensional detection frame of the target object, obtain a target type of the target object based on a preset classification algorithm, read height information and width information of the target object based on the three-dimensional detection frame in response to the target type being in a preset classification set, and use the target type, the height information and the width information as object information corresponding to the target object.
In one possible design, the obtaining module 401 is further configured to extract a plurality of target features corresponding to the target object, match the plurality of target features with a preset category feature set, determine a plurality of similarity values corresponding to the plurality of target feature sets, determine a preset category of the preset object corresponding to the maximum similarity from the plurality of similarity values, and use the preset category as the target type of the target object.
In one possible design, the transformation module 402 is specifically configured to input the object information corresponding to the target object into the data preprocessing model, obtain a target two-dimensional feature vector and a target class vector of the target object, and combine the target two-dimensional feature vector and the target class vector to obtain a multi-dimensional target feature vector corresponding to the target object.
Based on the same inventive concept, the embodiment of the present application further provides an electronic device, where the electronic device may implement the function of the foregoing apparatus for determining a depth of a target object, and referring to fig. 5, the electronic device includes:
the embodiment of the present application does not limit the specific connection medium between the processor 501 and the memory 502, but the connection between the processor 501 and the memory 502 through the bus 500 is exemplified in fig. 5. The connection between the other components of bus 500 is shown in bold lines in fig. 5, and is merely illustrative and not limiting. Bus 500 may be divided into an address bus, a data bus, a control bus, etc., and is represented by only one thick line in fig. 5 for ease of illustration, but does not represent only one bus or one type of bus. Alternatively, the processor 501 may be referred to as a controller, and the names are not limited.
In the embodiment of the present application, the memory 502 stores instructions executable by the at least one processor 501, and the at least one processor 501 may perform a method for determining the depth of a target object as discussed above by executing the instructions stored in the memory 502. The processor 501 may implement the functions of the various modules in the apparatus shown in fig. 4.
The processor 501 is a control center of the device, and various interfaces and lines can be used to connect various parts of the entire control device, and by executing or executing instructions stored in the memory 502 and invoking data stored in the memory 502, various functions of the device and processing data can be performed to monitor the device as a whole.
In one possible design, processor 501 may include one or more processing units, and processor 501 may integrate an application processor and a modem processor, where the application processor primarily processes operating systems, user interfaces, application programs, and the like, and the modem processor primarily processes wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 501. In some embodiments, processor 501 and memory 502 may be implemented on the same chip, or they may be implemented separately on separate chips in some embodiments.
The processor 501 may be a general purpose processor such as a Central Processing Unit (CPU), digital signal processor, application specific integrated circuit, field programmable gate array or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, and may implement or perform the methods, steps and logic blocks disclosed in embodiments of the present application. The general purpose processor may be a microprocessor or any conventional processor or the like. The steps of a method for determining the depth of a target object disclosed in connection with the embodiments of the present application may be directly embodied as a hardware processor executing the method, or may be executed by a combination of hardware and software modules in the processor.
The memory 502, as a non-volatile computer readable storage medium, may be used to store non-volatile software programs, non-volatile computer executable programs, and modules. The Memory 502 may include at least one type of storage medium, and may include, for example, flash Memory, hard disk, multimedia card, card Memory, random access Memory (Random Access Memory, RAM), static random access Memory (Static Random Access Memory, SRAM), programmable Read-Only Memory (Programmable Read Only Memory, PROM), read-Only Memory (ROM), charged erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory), magnetic Memory, magnetic disk, optical disk, and the like. Memory 502 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory 502 in the present embodiment may also be circuitry or any other device capable of implementing a memory function for storing program instructions and/or data.
By programming the processor 501, code corresponding to a method for determining the depth of a target object described in the foregoing embodiments may be cured into the chip, thereby enabling the chip to perform a step of determining the depth of a target object in the embodiment shown in fig. 1 at run-time. How to design and program the processor 501 is a technique well known to those skilled in the art, and will not be described in detail herein.
Based on the same inventive concept, embodiments of the present application also provide a storage medium storing computer instructions that, when executed on a computer, cause the computer to perform a method of determining a depth of a target object as previously discussed.
In some possible embodiments, aspects of a method of determining a depth of a target object may also be implemented in the form of a program product comprising program code for causing a control apparatus to carry out the steps of a method of determining a depth of a target object according to various exemplary embodiments of the application as described herein above when the program product is run on a device.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (10)
1. A method of determining a depth of a target object, comprising:
obtaining object information corresponding to a target object, wherein the object information comprises: the height information, the width information and the target type of the target object;
converting the object information into a multi-dimensional target feature vector based on a data preprocessing model;
and inputting the multi-dimensional target feature vector into a preset depth model to obtain depth information corresponding to the target object.
2. The method of claim 1, comprising, prior to obtaining object information corresponding to the target object:
obtaining test object information corresponding to m test objects, wherein the test object information is the height information, the width information and the depth information of the test objects and the type information of the test objects, and m is a positive integer;
training based on the m test objects to obtain training models corresponding to the m test objects;
and determining a preset depth model corresponding to the m test objects in response to the training model meeting preset conditions.
3. The method of claim 2, wherein training based on the m test objects to obtain training models corresponding to the m test objects comprises:
determining the maximum value of all height information, width information and depth information corresponding to the m test objects and category feature vectors corresponding to the m test objects respectively;
normalizing the height information and the width information corresponding to each test object based on the maximum value to obtain two-dimensional feature vectors corresponding to each test object;
splicing the two-dimensional feature vectors of each test object and the corresponding class feature vectors to obtain the multidimensional feature vectors of each test object;
training is carried out based on the depth information corresponding to each test object and the multidimensional feature vectors, and training models corresponding to the m test objects are obtained.
4. The method of claim 2, wherein responding to the training model meeting a preset condition comprises:
obtaining total training times corresponding to the m test objects, and determining a loss value of a training model corresponding to each training of the m test objects, wherein the loss value represents the difference between a model prediction depth value and an actual training sample depth value;
when the total training times reach preset training times, responding to the training model to accord with preset conditions; and
and when the loss value is smaller than a preset loss threshold value, responding to the training model to meet preset conditions.
5. The method of claim 1, wherein obtaining object information corresponding to the target object comprises:
determining a three-dimensional detection frame of the target object, and obtaining a target type of the target object based on a preset classification algorithm;
responding to the target type in a preset category set, and reading out the height information and the width information of the target object based on the three-dimensional detection frame, wherein the preset category set comprises a plurality of categories corresponding to preset objects;
and taking the target type, the height information and the width information as object information corresponding to the target object.
6. The method of claim 5, wherein obtaining the target type of the target object based on a preset classification algorithm comprises:
extracting a plurality of target characteristics corresponding to the target object;
matching the plurality of target features with a preset category feature set to determine a plurality of similarity values corresponding to the plurality of target feature sets, wherein the preset category feature set comprises feature sets corresponding to each preset object;
and determining a preset category of the preset object corresponding to the maximum similarity from the plurality of similarity values, and taking the preset category as the target type of the target object.
7. The method of claim 1, wherein converting the object information into a multi-dimensional target feature vector based on a data preprocessing model comprises:
inputting the object information corresponding to the target object into the data preprocessing model to obtain a target two-dimensional feature vector and a target category vector of the target object;
and combining the target two-dimensional feature vector and the target category vector to obtain a multi-dimensional target feature vector corresponding to the target object.
8. An apparatus for determining the depth of a target object, comprising:
the device comprises an obtaining module, a processing module and a processing module, wherein the obtaining module is used for obtaining object information corresponding to a target object, and the object information comprises: the height information, the width information and the target type of the target object;
the conversion module is used for converting the object information into a multidimensional target feature vector based on a data preprocessing model;
and the depth module is used for inputting the multi-dimensional target feature vector into a preset depth model to obtain depth information corresponding to the target object.
9. An electronic device, comprising:
a memory for storing a computer program;
a processor for carrying out the method steps of any one of claims 1-7 when executing a computer program stored on said memory.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored therein a computer program which, when executed by a processor, implements the method steps of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310164928.2A CN116148806A (en) | 2023-02-14 | 2023-02-14 | Method and device for determining depth of target object and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310164928.2A CN116148806A (en) | 2023-02-14 | 2023-02-14 | Method and device for determining depth of target object and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116148806A true CN116148806A (en) | 2023-05-23 |
Family
ID=86361699
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310164928.2A Pending CN116148806A (en) | 2023-02-14 | 2023-02-14 | Method and device for determining depth of target object and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116148806A (en) |
-
2023
- 2023-02-14 CN CN202310164928.2A patent/CN116148806A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110909651B (en) | Method, device and equipment for identifying video main body characters and readable storage medium | |
| CN112336342B (en) | Hand key point detection method and device and terminal equipment | |
| CN110287936B (en) | Image detection method, device, equipment and storage medium | |
| CN108573471B (en) | Image processing apparatus, image processing method, and recording medium | |
| US20240013573A1 (en) | Image processing method, image processing apparatus, electronic device, and computer-readable storage medium | |
| CN111160169A (en) | Face detection method, device, equipment and computer readable storage medium | |
| CN117078927A (en) | Combined target labeling method, device, equipment and storage medium | |
| CN110866428A (en) | Target tracking method and device, electronic equipment and storage medium | |
| CN111680680A (en) | Object code positioning method and device, electronic equipment and storage medium | |
| CN111914841B (en) | CT image processing method and device | |
| CN114419343A (en) | Multi-target identification tracking method and identification tracking system | |
| CN116740145A (en) | Multi-target tracking method, device, vehicle and storage medium | |
| CN116362782A (en) | User interest point identification method and system based on big data analysis | |
| CN114549429B (en) | Depth data quality evaluation method and device based on hypergraph structure | |
| CN116148806A (en) | Method and device for determining depth of target object and electronic equipment | |
| CN116363583A (en) | Human body identification method, device, equipment and medium for top view angle | |
| CN115115530B (en) | Image deblurring method, device, terminal equipment and medium | |
| CN115734072A (en) | Internet of things centralized monitoring method and device for industrial automation equipment | |
| CN115713750A (en) | Lane line detection method and device, electronic equipment and storage medium | |
| CN113033578B (en) | Image calibration method, system, terminal and medium based on multi-scale feature matching | |
| CN114743048A (en) | Method and device for detecting abnormal straw picture | |
| CN115050069A (en) | Face and attribute recognition method and system based on deep learning and computer equipment | |
| CN113569934A (en) | LOGO classification model construction method and system, electronic device and storage medium | |
| CN112308836A (en) | Corner detection method and device, electronic equipment and readable storage medium | |
| CN111883226A (en) | Information processing and model training method, device, 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 |