CN116934850A - Feature point determining method and device, electronic equipment and readable storage medium - Google Patents
Feature point determining method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN116934850A CN116934850A CN202210354969.3A CN202210354969A CN116934850A CN 116934850 A CN116934850 A CN 116934850A CN 202210354969 A CN202210354969 A CN 202210354969A CN 116934850 A CN116934850 A CN 116934850A
- Authority
- CN
- China
- Prior art keywords
- feature
- target
- feature point
- points
- feature points
- 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 42
- 238000012545 processing Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 6
- 230000002776 aggregation Effects 0.000 description 3
- 238000004220 aggregation Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/579—Depth or shape recovery from multiple images from motion
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The application provides a feature point determining method, a device, electronic equipment and a readable storage medium, wherein the method comprises the following steps: extracting features of the target image to obtain a plurality of feature points of the target image, and position information and feature scores of each feature point; sequentially adding target feature points in the feature points into a target feature point set based on the feature score, wherein the distance between the feature points in the target feature point set is larger than a preset threshold value, and the distance between the feature points is determined based on the position information and is the distance between the feature points on the target image; and outputting the feature points in the target feature point set. The application can improve the uniformity of the distribution of the characteristic points.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a method and apparatus for determining a feature point, an electronic device, and a readable storage medium.
Background
In the instant positioning and map building (Simultaneous Localization and Mapping, SLAM) technology, feature points can be extracted based on images acquired by cameras, and functions such as positioning and map building can be completed. The feature points extracted by the features in the image generally have a certain aggregation effect, and the feature points in the weak texture region in the image are sparse, and the feature points in the strong texture region are dense. In order to improve the real-time performance and the calculation accuracy of the camera pose, the equalization processing needs to be performed on the feature points extracted from the image, and the conventional equalization processing generally uses fixed grid size equalization or quadtree grid segmentation equalization, so that the uniformity of the distribution of the feature points is poor after the equalization processing due to the boundary effect.
Disclosure of Invention
The application provides a method and a device for determining characteristic points and electronic equipment, and aims to solve the problem of poor uniformity of characteristic point distribution.
In a first aspect, an embodiment of the present application provides a feature point determining method, including
Extracting features of the target image to obtain a plurality of feature points of the target image, and position information and feature scores of each feature point;
sequentially adding target feature points in the feature points into a target feature point set based on the feature score, wherein the distance between the feature points in the target feature point set is larger than a preset threshold value, and the distance between the feature points is determined based on the position information and is the distance between the feature points on the target image;
and outputting the feature points in the target feature point set.
In a second aspect, an embodiment of the present application further provides a feature point determining apparatus, including:
the extraction module is used for extracting the characteristics of the target image to obtain a plurality of characteristic points of the target image, and the position information and the characteristic score of each characteristic point;
the determining module is used for adding target feature points in the feature points into a target feature point set in sequence based on the feature scores, wherein the distance between the feature points in the target feature point set is larger than a preset threshold value, the distance between the feature points is determined based on the position information, and the distance is the distance between the feature points on the target image;
and the output module is used for outputting the characteristic points in the target characteristic point set.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a transceiver, a memory, a processor, and a program stored on the memory and executable on the processor; the processor is configured to read a program in the memory to implement the steps in the method according to the first aspect of the embodiment of the present application.
In a fourth aspect, embodiments of the present application further provide a readable storage medium, where a program is stored, the program, when executed by a processor, implementing the steps in the method according to the first aspect of the embodiments of the present application.
In the embodiment of the application, based on the feature score, the target feature points in the plurality of feature points are sequentially added into the target feature point set, the distance between the feature points in the target feature point set is larger than a preset threshold value, the distance between the feature points is determined based on the position information, the distance is the distance between the feature points on the target image, and the feature points in the target feature point set are output, so that the target feature points in the plurality of feature points can be sequentially extracted into the target feature point set according to the feature score, namely, the screening of the plurality of feature points can be realized by outputting the feature points in the target feature point set, and the distance between the output feature points is larger than the preset threshold value, thereby improving the uniformity of the distribution of the output feature points.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a schematic flow chart of a feature point determining method according to an embodiment of the present application;
fig. 2 is a schematic flow chart of an image feature point balancing method according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a feature point determining apparatus according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terms "first," "second," and the like in embodiments of the present application are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Furthermore, the use of "and/or" in the present application means at least one of the connected objects, such as a and/or B and/or C, means 7 cases including a alone a, B alone, C alone, and both a and B, both B and C, both a and C, and both A, B and C.
Referring to fig. 1, fig. 1 is a flowchart of a feature point determining method according to an embodiment of the present application, as shown in fig. 1, including the following steps:
and 101, extracting features of the target image to obtain a plurality of feature points of the target image, and position information and feature scores of each feature point.
The target image may be any image to be detected, and the feature extraction is performed on the target image, for example: feature point detection may be implemented using a scale-invariant feature transform (Scale Invariant Feature Transform, SIFT) algorithm, an accelerated robust feature (SURF) algorithm, or the like, resulting in a plurality of feature points in the target image, as well as location information and feature scores for each feature point.
It will be appreciated that the position information of each feature point may represent the position of each feature point in the target image, for example: and establishing a coordinate system, wherein the coordinate system represents the coordinate of each feature point, and the coordinate of each feature point is the position information of the feature point. The feature score may be used to characterize the significance level of each feature point, and it may be understood that when the positioning function is implemented in the SLAM system, the greater the significance of the feature point used in the calculation (i.e., the greater the feature score), the higher the accuracy.
And 102, adding target feature points in the feature points into a target feature point set in turn based on the feature scores, wherein the distance between the feature points in the target feature point set is larger than a preset threshold value, the distance between the feature points is determined based on the position information, and the distance is the distance between the feature points on the target image.
Specifically, the feature score may be used to sort the plurality of feature points, so that a target feature point of the plurality of feature points may be added to the target feature point set in sequence, and if the feature point set has a feature point with a larger feature score, feature points close to the periphery of the feature point with a larger feature score may be removed, thereby avoiding excessive aggregation of feature points and ensuring a feature point equalization effect. The distance between the feature points in the target feature point set is greater than a preset threshold, that is, the distance between the feature points existing in the target feature point set is greater than the preset threshold before the target feature point is added to the target feature point set, and the distance between the target feature point and the feature points in the target feature point set is greater than the preset threshold, so that the distance between the feature points in the target feature point set is still greater than the preset threshold after the target feature point is added to the target feature point set.
It should be noted that, the distance between any two feature points is determined based on the position information thereof, for example: as for the distance between the feature point a and the feature point B, a straight-line distance between the feature point a and the feature point B may be calculated based on the position information of the feature point a and the feature point B as the distance between the feature point a and the feature point B on the target image.
The preset threshold value can be determined according to an empirical value or an actual requirement, and the target feature points in the feature points are sequentially added into a target feature point set, and the distance between the feature points in the target feature point set is larger than the preset threshold value, so that the feature points in the target feature point set are scattered, uneven distribution of the feature points in the target image is avoided, and the feature point equalization effect is improved.
And step 103, outputting the characteristic points in the target characteristic point set.
After all the target feature points of the plurality of feature points are added into the target feature point set, the feature points in the target feature point set are feature points obtained by screening the plurality of feature points of the target image, so that the equalization processing of the feature points is realized, and the uneven distribution among the feature points caused by the boundary effect can be avoided by enabling the distance among the feature points in the target feature point set to be larger than a preset threshold value.
In the embodiment of the application, based on the feature score, the target feature points in the plurality of feature points are sequentially added into the target feature point set, the distance between the feature points in the target feature point set is larger than a preset threshold value, the distance between the feature points is determined based on the position information, the distance is the distance between the feature points on the target image, and the feature points in the target feature point set are output, so that the target feature points in the plurality of feature points can be sequentially extracted into the target feature point set according to the feature score, namely, the screening of the plurality of feature points can be realized by outputting the feature points in the target feature point set, and the distance between the output feature points is larger than the preset threshold value, thereby improving the uniformity of the distribution of the output feature points.
Optionally, the plurality of feature points includes feature points of different scales;
in step 102, based on the feature scores, adding the target feature points in the plurality of feature points to the target feature point set sequentially, including:
initializing the target feature point set as an empty set;
and based on the feature scores, sequentially adding target feature points in the feature points of each scale into the target feature point set.
When the characteristic points of the target image are detected, the characteristic points with different scales are identified to simulate the effect that the human eyes look at the same point from far to near. It should be noted that, in the different scales, each scale may include only one feature point, or may include a plurality of feature points.
In the process of sequentially adding the target feature points to the target feature point set, the steps may be sequentially performed according to different scales, for example: under the condition that feature points of multiple scales are detected in the target image, judging all feature points of one scale, adding the target feature points of the scale into the feature point set according to the sequence of feature scores, and judging the feature points of the next scale. The order of the plurality of scales may be arbitrary.
The feature points with the largest feature score are the first feature points by initializing the target feature point set as the empty set, the feature points with the second largest feature score are the second feature points, and the second feature points can be added into the target feature point set as the target feature points when the distance between the second feature points and the first feature points is larger than the preset threshold value, and the like, all the feature points in the target image can be judged and the target feature points which can meet the conditions are added into the target feature point set.
In this embodiment, the target feature point set is initialized to be an empty set, and the target feature points in the feature points of each scale are sequentially added to the target feature point set based on the feature scores, so that all the target feature points in the plurality of feature points are added to the target feature point set, equalization of the feature points in the target image is achieved, and uniformity of feature point distribution in the equalized target feature point set can be improved.
Optionally, the adding, in step 102, the target feature point of the plurality of feature points to the target feature point set sequentially based on the feature score includes:
and based on the feature scores, sequentially calculating the distance between each feature point and the feature points in the target feature point set, adding the target feature point into the target feature point set, and enabling the distance between the target feature point and the feature points in the target feature point set to be larger than the preset threshold value.
Specifically, for the feature points in each scale, the feature points may be ranked from large to small according to the feature score of each feature point, distances between the feature points and the feature points in the target feature point set are sequentially calculated, and feature points with distances between the feature points in the target feature point set being greater than the preset threshold are determined as the target feature points and added to the target feature point set.
It can be understood that before adding the target feature point to the target feature point set, the feature point needs to be determined to determine whether the feature point is the target feature point, where the determining manner is as follows: and calculating the distance between the target feature point set and the feature point in the target feature point set, judging whether the distance is larger than the preset threshold value, and determining the feature point with the distance larger than the preset threshold value as the target feature point, wherein the feature point can be added into the target feature point set.
When judging whether the distance between each feature point and the feature point in the target feature point set is larger than the preset threshold value, calculating the distance between the feature point and each feature point in the target feature point set, respectively judging whether each distance is larger than the preset threshold value, and determining the feature point, of which the distance between each feature point and each feature point in the target feature point set is larger than the preset threshold value, as a target feature point; the minimum distance between the feature point and each feature point in the target feature point set may be determined after the distance between the feature point and each feature point is calculated, and the feature point corresponding to the minimum distance being greater than the preset threshold may be determined as the target feature point.
In this embodiment, based on the feature score, distances between each feature point and feature points in the target feature point set are sequentially calculated, and a target feature point is added to the target feature point set, where the distance between the target feature point and the feature points in the target feature point set is greater than the preset threshold, so as to implement equalization processing on the feature points in the target image.
Optionally, the distance between each feature point and a feature point in the target feature point set is a manhattan distance or a euclidean distance.
Under the condition that the Manhattan distance is used as the distance between each feature point and the feature points in the target feature point set, the sum of absolute wheelbase of the two feature points on a coordinate system can be used as the distance between the two feature points, namely, the sum of coordinate difference values of the two feature points on each coordinate axis is directly calculated, so that the distance between the two feature points can be obtained, the calculated amount is reduced, and the balance efficiency of the feature points is improved.
In the case of using the euclidean distance as the distance between each feature point and the feature points in the target feature point set, it is possible to directly determine whether the feature points are close or not using the straight line distance between the two feature points, thereby avoiding excessive aggregation of the feature points and improving the accuracy of the feature point equalization process.
Optionally, the target image is an image acquired by an image acquisition device;
after the outputting the feature points in the target feature point set in step 103, the method further includes:
acquiring a reference image acquired by the image acquisition equipment and characteristic points of the reference image;
matching the characteristic points in the target characteristic point set with the characteristic points of the reference image to obtain a characteristic point matching result;
and calculating the pose of the image acquisition equipment based on the result of the feature point matching.
It can be understood that the image acquisition device may be a camera, a video camera, etc., the target image and the reference image are images acquired by the image acquisition device at different times, and pose solving of the image acquisition device is realized by matching the feature points of the target image and the feature points of the reference image.
The feature points of the reference image may be equalized according to the feature point determination method to achieve the same effect. In this way, the feature points in the target feature point set and the feature points of the reference image are subjected to feature point matching, so that the matching efficiency and accuracy can be improved.
In addition, by the feature point determining method, feature points in the target feature point set can be used as feature points of the target image, so that the number of feature points to be processed is reduced when pose solving is carried out, and the instantaneity of the method is improved.
Before calculating the pose of the image acquisition device based on the result of the feature point matching, the feature points of the target image and the reference image are subjected to equalization processing through the feature point determining method, so that the distribution uniformity of the feature points of the image is improved, the pose solving accuracy of the acquisition device can be improved, and the problem of solving singularities is reduced.
The various optional embodiments described in the embodiments of the present application may be implemented in combination with each other without collision, or may be implemented separately, which is not limited to the embodiments of the present application.
For ease of understanding, specific examples are as follows:
as shown in fig. 2, an embodiment of the present application provides an image feature point equalization method, which specifically includes the following steps:
step 21, detecting characteristic points of the image, wherein the detection result comprises characteristic point coordinates, characteristic point scales and characteristic point scores;
step 22, obtaining original feature point sets with different scales in the image according to the feature point scales;
specifically, an original feature point set under the current scale in the image is acquired and processed: firstly, sorting feature point sets under the current scale according to feature point scores, and initializing an equalization feature point set as an empty set;
step 23, according to the sequence obtained by the feature score sequencing, judging whether an equalization feature point set exists near the current feature point in sequence: and sequentially calculating the Manhattan distance between each point coordinate in the ordered characteristic point set and the point coordinate in the balanced characteristic point set. If the minimum Manhattan distance is smaller than the set threshold T, considering that an equalization feature point set exists around the current point to be processed, and discarding the current feature point without further processing; if the minimum Manhattan distance is greater than the set threshold T, considering that the current to-be-processed point is not provided with the equalization feature point set, and adding the current feature point into the equalization feature point set;
step 24, repeating the step 23 until all the characteristic points under the current scale are traversed;
step 25, repeating the steps 22, 23 and 24 until all feature points under all scales are traversed;
and step 26, outputting the feature point set after equalization under each scale.
In the embodiment of the application, the feature point sets with different scales are respectively subjected to equalization treatment to obtain the equalized feature point sets, so that uneven distribution of the feature points caused by boundary effects can be avoided, and the uniformity of the distribution of the feature points is improved. And in each scale, according to the feature point score, the coordinate difference of the current feature point and the equalization point set is compared by using the Manhattan distance, so that whether the feature point is added into the equalization point set is judged, and the equalization processing of the image feature point is realized.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a feature point determining apparatus according to an embodiment of the present application. As shown in fig. 3, the feature point determining apparatus 300 includes:
the extracting module 301 is configured to perform feature extraction on the target image to obtain a plurality of feature points of the target image, and location information and feature scores of each feature point;
a determining module 302, configured to sequentially add, based on the feature score, a target feature point of the plurality of feature points to a target feature point set, where a distance between feature points in the target feature point set is greater than a preset threshold, where a distance between feature points is determined based on the location information, where the distance is a distance between feature points on the target image;
and an output module 303, configured to output feature points in the target feature point set.
Optionally, the plurality of feature points includes feature points of different scales;
the determining module 302 includes:
the processing unit is used for initializing the target feature point set into an empty set;
and the determining unit is used for respectively adding the target characteristic points in the characteristic points of each scale into the target characteristic point set in sequence based on the characteristic scores.
Optionally, the determining module 302 includes:
the computing unit is used for sequentially computing the distance between each feature point and the feature point in the target feature point set based on the feature score, adding the target feature point into the target feature point set, and enabling the distance between the target feature point and the feature point in the target feature point set to be larger than the preset threshold value.
Optionally, the distance between each feature point and a feature point in the target feature point set is a manhattan distance or a euclidean distance.
Optionally, the target image is an image acquired by an image acquisition device;
the feature point determining apparatus 300 further includes:
the acquisition module is used for acquiring the reference image acquired by the image acquisition equipment and the characteristic points of the reference image;
the matching module is used for matching the characteristic points in the target characteristic point set with the characteristic points of the reference image to obtain a characteristic point matching result;
and the calculating module is used for calculating the pose of the image acquisition equipment based on the result of the characteristic point matching.
The feature point determining apparatus 300 can implement the processes of the method embodiment of fig. 1 in the embodiment of the present application, and achieve the same beneficial effects, and for avoiding repetition, a detailed description is omitted herein.
The embodiment of the application also provides electronic equipment. Because the principle of solving the problem of the electronic device is similar to that of the feature point determining method shown in fig. 1 in the embodiment of the present application, the implementation of the electronic device may refer to the implementation of the method, and the repetition is not repeated. As shown in fig. 4, the electronic device according to the embodiment of the present application includes a memory 420, a transceiver 410, and a processor 400;
a memory 420 for storing a computer program; a transceiver 410 for transceiving data under the control of the processor 400; a processor 400 for reading the computer program in the memory 420 and performing the following operations:
extracting features of the target image to obtain a plurality of feature points of the target image, and position information and feature scores of each feature point;
sequentially adding target feature points in the feature points into a target feature point set based on the feature score, wherein the distance between the feature points in the target feature point set is larger than a preset threshold value, and the distance between the feature points is determined based on the position information and is the distance between the feature points on the target image;
and outputting the feature points in the target feature point set.
Wherein in fig. 4, a bus architecture may comprise any number of interconnected buses and bridges, and in particular one or more processors represented by processor 400 and various circuits of memory represented by memory 420, linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., which are well known in the art and, therefore, will not be described further herein. The bus interface provides an interface. Transceiver 410 may be a number of elements, including a transmitter and a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 400 is responsible for managing the bus architecture and general processing, and the memory 420 may store data used by the processor 400 in performing operations.
The processor 400 may be a central processing unit (Central Processing Unit, CPU), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a Field programmable gate array (Field-Programmable Gate Array, FPGA), or a complex programmable logic device (Complex Programmable Logic Device, CPLD), or may employ a multi-core architecture.
Optionally, the plurality of feature points includes feature points of different scales;
the step of adding the target feature points in the feature points to the target feature point set in turn based on the feature scores comprises the following steps:
initializing the target feature point set as an empty set;
and based on the feature scores, sequentially adding target feature points in the feature points of each scale into the target feature point set.
Optionally, the adding the target feature points of the feature points to the target feature point set sequentially based on the feature scores includes:
and based on the feature scores, sequentially calculating the distance between each feature point and the feature points in the target feature point set, adding the target feature point into the target feature point set, and enabling the distance between the target feature point and the feature points in the target feature point set to be larger than the preset threshold value.
Optionally, the distance between each feature point and a feature point in the target feature point set is a manhattan distance or a euclidean distance.
Optionally, the target image is an image acquired by an image acquisition device;
processor 400 is further configured to read the computer program in memory 420 and perform the following operations:
acquiring a reference image acquired by the image acquisition equipment and characteristic points of the reference image;
matching the characteristic points in the target characteristic point set with the characteristic points of the reference image to obtain a characteristic point matching result;
and calculating the pose of the image acquisition equipment based on the result of the feature point matching.
The electronic device provided in the embodiment of the present application may execute the method embodiment shown in fig. 1, and its implementation principle and technical effects are similar, and this embodiment will not be described herein.
The present application further provides a readable storage medium, where a program is stored, where the program when executed by a processor implements the processes of the method embodiment shown in fig. 1, and the same technical effects can be achieved, and for avoiding repetition, a detailed description is omitted here.
In the several embodiments provided in the present application, it should be understood that the disclosed methods and apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may be physically included separately, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in hardware plus software functional units.
The integrated units implemented in the form of software functional units described above may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform part of the steps of the transceiving method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
While the foregoing is directed to the preferred embodiments of the present application, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present application, and such modifications and adaptations are intended to be comprehended within the scope of the present application.
Claims (10)
1. A feature point determining method is characterized by comprising the following steps of
Extracting features of the target image to obtain a plurality of feature points of the target image, and position information and feature scores of each feature point;
sequentially adding target feature points in the feature points into a target feature point set based on the feature score, wherein the distance between the feature points in the target feature point set is larger than a preset threshold value, and the distance between the feature points is determined based on the position information and is the distance between the feature points on the target image;
and outputting the feature points in the target feature point set.
2. The method of claim 1, wherein the plurality of feature points comprise feature points of different scales;
the step of adding the target feature points in the feature points to the target feature point set in turn based on the feature scores comprises the following steps:
initializing the target feature point set as an empty set;
and based on the feature scores, sequentially adding target feature points in the feature points of each scale into the target feature point set.
3. The method of claim 1, wherein sequentially adding the target feature points of the plurality of feature points to the target feature point set based on the feature scores comprises:
and based on the feature scores, sequentially calculating the distance between each feature point and the feature points in the target feature point set, adding the target feature point into the target feature point set, and enabling the distance between the target feature point and the feature points in the target feature point set to be larger than the preset threshold value.
4. The method of claim 3, wherein the distance between each feature point and a feature point in the set of target feature points is a manhattan distance or a euclidean distance.
5. The method of any one of claims 1 to 4, wherein the target image is an image acquired by an image acquisition device;
after the outputting the feature points in the target feature point set, the method further includes:
acquiring a reference image acquired by the image acquisition equipment and characteristic points of the reference image;
matching the characteristic points in the target characteristic point set with the characteristic points of the reference image to obtain a characteristic point matching result;
and calculating the pose of the image acquisition equipment based on the result of the feature point matching.
6. A feature point determination apparatus, characterized by comprising:
the extraction module is used for extracting the characteristics of the target image to obtain a plurality of characteristic points of the target image, and the position information and the characteristic score of each characteristic point;
the determining module is used for adding target feature points in the feature points into a target feature point set in sequence based on the feature scores, wherein the distance between the feature points in the target feature point set is larger than a preset threshold value, the distance between the feature points is determined based on the position information, and the distance is the distance between the feature points on the target image;
and the output module is used for outputting the characteristic points in the target characteristic point set.
7. The apparatus of claim 6, wherein the plurality of feature points comprise feature points of different scales;
the determining module includes:
the processing unit is used for initializing the target feature point set into an empty set;
and the determining unit is used for respectively adding the target characteristic points in the characteristic points of each scale into the target characteristic point set in sequence based on the characteristic scores.
8. The apparatus of claim 6, wherein the determination module comprises:
the computing unit is used for sequentially computing the distance between each feature point and the feature point in the target feature point set based on the feature score, adding the target feature point into the target feature point set, and enabling the distance between the target feature point and the feature point in the target feature point set to be larger than the preset threshold value.
9. An electronic device, comprising: a transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor; it is characterized in that the method comprises the steps of,
the processor being configured to read a program in a memory to implement the steps in the method according to any one of claims 1 to 5.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210354969.3A CN116934850A (en) | 2022-04-06 | 2022-04-06 | Feature point determining method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210354969.3A CN116934850A (en) | 2022-04-06 | 2022-04-06 | Feature point determining method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116934850A true CN116934850A (en) | 2023-10-24 |
Family
ID=88383197
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210354969.3A Pending CN116934850A (en) | 2022-04-06 | 2022-04-06 | Feature point determining method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116934850A (en) |
-
2022
- 2022-04-06 CN CN202210354969.3A patent/CN116934850A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110020592B (en) | Object detection model training method, device, computer equipment and storage medium | |
| CN111178250B (en) | Object identification positioning method and device and terminal equipment | |
| WO2018120038A1 (en) | Method and device for target detection | |
| CN109829448B (en) | Face recognition method, face recognition device and storage medium | |
| CN109272016B (en) | Target detection method, device, terminal equipment and computer readable storage medium | |
| CN111079785A (en) | Image identification method and device and terminal equipment | |
| CN111738351A (en) | Model training method and device, storage medium and electronic equipment | |
| CN114092963B (en) | Method, device, equipment and storage medium for key point detection and model training | |
| CN113095333B (en) | Unsupervised feature point detection method and unsupervised feature point detection device | |
| CN111488810A (en) | Face recognition method and device, terminal equipment and computer readable medium | |
| CN107272899B (en) | VR (virtual reality) interaction method and device based on dynamic gestures and electronic equipment | |
| CN111223128A (en) | Target tracking method, device, equipment and storage medium | |
| CN111126296A (en) | Fruit positioning method and device | |
| CN112418089A (en) | Gesture recognition method and device and terminal | |
| CN108629219B (en) | Method and device for identifying one-dimensional code | |
| CN116934850A (en) | Feature point determining method and device, electronic equipment and readable storage medium | |
| CN112950652B (en) | Robot and hand image segmentation method and device thereof | |
| CN111931794B (en) | Sketch-based image matching method | |
| CN116295466A (en) | Map generation method, map generation device, electronic device, storage medium and vehicle | |
| CN114663478A (en) | Method for estimating anchor point position according to multi-reference point prediction information | |
| CN113139579B (en) | Image classification method and system based on image feature self-adaptive convolution network | |
| CN112465007B (en) | Training method of target recognition model, target recognition method and terminal equipment | |
| CN112686936B (en) | Image depth completion method, apparatus, computer device, medium, and program product | |
| CN115512194A (en) | Image target detection method and device and terminal equipment | |
| CN110400313B (en) | Soft tissue separation method and separation system for nuclear magnetic resonance image |
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 |