CN115035407A - Method, device and equipment for identifying object in image - Google Patents
Method, device and equipment for identifying object in image Download PDFInfo
- Publication number
- CN115035407A CN115035407A CN202210671835.4A CN202210671835A CN115035407A CN 115035407 A CN115035407 A CN 115035407A CN 202210671835 A CN202210671835 A CN 202210671835A CN 115035407 A CN115035407 A CN 115035407A
- Authority
- CN
- China
- Prior art keywords
- category
- information
- confidence
- image
- determining
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
Abstract
The invention provides a method, a device and equipment for identifying an object in an image, wherein the method for identifying the object in the image comprises the following steps: respectively detecting a first image and a second image to obtain position information of a first object in the first image, a plurality of corresponding categories and confidence degrees of each category, and position information of a second object in the second image, a plurality of corresponding categories and confidence degrees of each category; and determining whether the categories of the first object and the second object are the same or not according to the position information of the first object, the corresponding categories and the confidence degrees of each category, and the position information of the second object, the corresponding categories and the confidence degrees of each category.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, and a device for identifying an object in an image.
Background
In practical application scenarios, in order to determine the change of an object in a monitoring area within a time interval, it is necessary to identify the object in images acquired at different time points. Taking an unattended visual container as an example, images in the container before and after a user opens a door need to be collected, and whether two objects belong to the same category can be determined by identifying the objects in the two images.
At present, visual algorithms are generally used to identify objects in two images, and whether two objects belong to the same category is determined according to the category and the confidence level of the identified objects.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, and a device for identifying an object in an image, which can improve accuracy of an identification result.
In a first aspect, an embodiment of the present invention provides a method for identifying an object in an image, including:
respectively detecting a first image and a second image to obtain position information of a first object in the first image, a plurality of corresponding categories and confidence degrees of each category, and position information of a second object in the second image, a plurality of corresponding categories and confidence degrees of each category;
and determining whether the categories of the first object and the second object are the same or not according to the position information of the first object, the corresponding categories and the confidence degrees of each category, and the position information of the second object, the corresponding categories and the confidence degrees of each category.
In a second aspect, an embodiment of the present invention provides an apparatus for identifying an object in an image, including:
the detection unit is configured to detect a first image and a second image respectively to obtain position information of a first object in the first image, a plurality of corresponding categories and confidence degrees of each category, and position information of a second object in the second image, a plurality of corresponding categories and confidence degrees of each category;
a determining unit configured to determine whether the categories of the first object and the second object are the same according to the position information of the first object, the corresponding categories and the confidence of each of the categories, and the position information of the second object, the corresponding categories and the confidence of each of the categories.
In a third aspect, an embodiment of the present invention provides an apparatus for identifying an object in an image, including: a processor and a memory;
the memory is used for storing execution instructions, and the processor is used for executing the execution instructions stored by the memory to realize the method of any one of the above embodiments
The embodiment of the invention adopts at least one technical scheme to achieve the following beneficial effects: the method combines the position information of the object with the category corresponding to the object and the confidence thereof, and compared with the traditional method for identifying based on the confidence, the method can consider the influence of factors such as the position of the object in the image and the like, and improve the identification accuracy.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a method for identifying an object in an image according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for identifying an object in an image according to another embodiment of the present invention;
fig. 3 is a schematic structural diagram of an apparatus for recognizing an object in an image according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts belong to the scope of the present invention.
Conventional recognition methods determine whether two objects are of the same class based on confidence alone. For example, it is determined by the conventional recognition method that the confidence that the first object in the first image is the item a is 90%, the confidence that the item B is 80%, and the confidence that the item C is 70%, the confidence that the second object in the second image is the item a is 5%, the confidence that the item B is 3%, and the confidence that the item C is 2%. Because the category corresponding to the maximum confidence corresponding to the first object is the commodity a and is the same as the category corresponding to the maximum confidence corresponding to the second object, based on the conventional identification method, the obtained identification result is: the first object and the second object are of the same category.
However, in an actual application scenario, the obtained confidence may be low, and if it is determined whether the categories of the two objects are the same based on the confidence alone, the accuracy of the recognition result is low.
For example, the goods a are placed in the first row and the first column of the container, the goods B are placed in the first row and the second column of the container, and assuming that the goods in the container are not changed, the first image and the second image are acquired under different environments, wherein the first image has poor quality due to the influence of illumination. When the first object in the first row and the first column in the first image and the second object in the first row and the first column in the second image are identified, the confidence that the first object is the commodity a is 9%, the confidence that the first object is the commodity B is 10%, the confidence that the second object is the commodity a is 90%, and the confidence that the second object is the commodity B is 80% are obtained. Therefore, based on the conventional recognition method, it is determined that the first object and the second object are different in category, and the recognition result is obviously inconsistent with the actual situation.
In view of this, an embodiment of the present invention provides a method for identifying an object in an image, as shown in fig. 1, the method may include the following steps:
step 101: and respectively detecting the first image and the second image to obtain the position information of the first object in the first image, the corresponding multiple categories and the confidence coefficient of each category, and the position information of the second object in the second image, the corresponding multiple categories and the confidence coefficient of each category.
In an actual application scenario, a visual algorithm may be used to detect position information of each object in the first image, several categories corresponding to each object, and a confidence level of each category. However, the embodiment of the present invention only takes the identification process of the first object and the second object as an example for description, and the identification process of other objects in the first image and the second image may refer to the identification process of the first object and the identification process of the second object, which is not described herein again.
Step 102: and determining whether the categories of the first object and the second object are the same according to the position information of the first object, the corresponding categories and the confidence degrees of each category, and the position information of the second object, the corresponding categories and the confidence degrees of each category.
The method combines the position information of the object with the category corresponding to the object and the confidence thereof, and compared with the traditional method for identifying based on the confidence, the method can consider the influence of factors such as the position of the object in the image and the like, and improve the identification accuracy.
In one embodiment of the present invention, the image features may also be combined with confidence level and location information to determine whether the first object and the second object are of the same category, taking into account the effects of lighting, the number of objects in the image, and the like.
At this time, step 102 includes: and determining whether the categories of the first object and the second object are the same according to the position information, the image characteristics, the corresponding categories and the confidence degrees of each category of the first object and the position information, the image characteristics, the corresponding categories and the confidence degrees of each category of the second object.
In an embodiment of the present invention, step 102 specifically includes:
a1: and determining the overlapping degree of the first object and the second object according to the position information of the first object and the position information of the second object.
A2: it is determined whether the degree of overlap is greater than a first threshold and, if so, step a3 is performed.
A3: and B, determining whether the category corresponding to the confidence degrees arranged at the first set orders and corresponding to the first object is completely different from the category corresponding to the confidence degrees arranged at the first set orders and corresponding to the second object, and if not, executing the step A4.
For example, the confidences are arranged in descending order, the first set order is 1, 2, and 3, if the categories corresponding to the confidences ranked in 1 to 3 corresponding to the first object are a, b, and c, respectively, and the categories corresponding to the confidences ranked in 1 to 3 corresponding to the second object are c, d, and e, respectively, since c exists in the categories corresponding to the first object and the second object, step a4 is executed.
A4: and determining that the first object and the second object have the same category, wherein the corresponding confidences of the first object and the second object are ordered according to the same ordering logic.
The method provided by the embodiment is suitable for identifying two objects with no or only slight position change in the first image and the second image.
The first threshold may be a predetermined value, for example, 0.8. The sorting logic may be from large to small, or from small to large, etc. The first set bit may be one or more. In one application scenario, the first set order is 1, and the sorting logic is from large to small, and in another application scenario, the first set order is 1-3, and the sorting logic is from large to small. The second setting bit and the fourth setting bit are similar to the first setting bit and are not described in detail below.
In a practical application scenario, A3 is not limited to the foregoing implementation, for example, A3 specifically includes: and B, determining whether the categories corresponding to the confidence degrees arranged at a plurality of first set orders and corresponding to the first object are the same as the categories corresponding to the confidence degrees arranged at corresponding orders and corresponding to the second object, and if so, executing the step A4.
At this time, the class corresponding to the 1 st confidence corresponding to the first object is compared with the class corresponding to the 1 st confidence corresponding to the second object, the class corresponding to the 2 nd confidence corresponding to the first object is compared with the class corresponding to the 2 nd confidence corresponding to the second object, and the class corresponding to the 3 rd confidence corresponding to the first object is compared with the class corresponding to the 3 rd confidence corresponding to the second object.
In an embodiment of the present invention, a1 specifically includes: determining the area of the intersection and the area of the union of the external outlines of the first object and the second object according to the position of the external outline of the first object and the position of the external outline of the second object; and determining the overlapping degree according to the area of the intersection and the area of the union.
Wherein, the overlapping degree is the ratio of the intersection area and the union area.
In the embodiment of the present invention, the position information is the position of the outer contour, and in other application scenarios, the position information may also be the position of the minimum bounding rectangle, and the like.
When the position information is the position of the minimum bounding rectangle, a1 specifically includes: determining the area of the intersection and the area of the union of the minimum circumscribed rectangles of the first object and the second object according to the position of the minimum circumscribed rectangle of the first object and the position of the minimum circumscribed rectangle of the second object; and determining the overlapping degree according to the area of the intersection and the area of the union.
In one embodiment of the invention, the method further comprises:
b1: if the degree of overlap is not greater than the first threshold, or if the categories corresponding to the confidences arranged at the first set levels corresponding to the first object are completely different from the categories corresponding to the confidences arranged at the first set levels corresponding to the second object, determining whether the first object and the second object satisfy the position corresponding condition according to the position information of the first object and the position information of the second object, and if so, executing B2.
B2: and B3 is executed if the category corresponding to the confidence degree arranged at the second set orders and corresponding to the first object is completely different from the category corresponding to the confidence degree arranged at the second set orders and corresponding to the second object.
B2 is similar to A2 and will not be described here.
B3: determining that the first object and the second object are of the same category.
The method provided by the embodiment is suitable for identifying two objects with certain positions changed in the first image and the second image, and compared with the above-mentioned "small change", the change range of the positions is larger in the embodiment.
In one embodiment of the present invention, the location correspondence condition includes: the ratio of the area of the intersection of the outer contours of the first object and the second object to the target area is greater than a second threshold; wherein the target area is a smaller area of the areas of the outer contours of the first object and the second object.
Wherein, the second threshold value is a preset value.
Of course, in other application scenarios, the position correspondence condition may also be in other forms. For example, the target area in the above-described position correspondence condition is a larger area of the areas of the outer contours of the first object and the second object.
It should be noted that, if the position information is the position of the minimum bounding rectangle, the position corresponding condition includes: the ratio of the area of the intersection of the minimum bounding rectangles of the first object and the second object to the target area is larger than a second threshold value; wherein the target area is the smaller area of the minimum bounding rectangles of the first object and the second object
In one embodiment of the invention, the method further comprises:
c1: if the category corresponding to the confidence degree ranked at a plurality of second setting orders corresponding to the first object is completely different from the category corresponding to the confidence degree ranked at a plurality of second setting orders corresponding to the second object, determining whether the category corresponding to the confidence degree ranked at a third setting order corresponding to the first object is the same as one of the categories corresponding to the confidence degree ranked at a plurality of fourth setting orders corresponding to the second object, and if so, executing step C2.
C2: and determining the similarity of the first object and the second object according to the image characteristics of the first object and the image characteristics of the second object, and if the similarity is greater than a third threshold value, executing the step C3.
C3: determining that the first object and the second object are of the same category.
The method provided by the embodiment of the invention is suitable for identifying the first object and the second object when the first image or the second image is influenced by illumination and human factors. Taking the identification process of two commodities in the application scene of the unattended visual container as an example, in the second image, the user replaces the commodity M with the commodity N, and then the method provided by the embodiment of the invention can identify the commodity M in the first image and the commodity N in the second image.
Image features include, but are not limited to: color features, texture features, shape features, and spatial relationship features.
As shown in FIG. 2, the embodiment of the present invention takes the identification of two commodities in a container as an example, and describes the identification method of an object in an image in detail, and the method comprises the following steps:
step 201: and respectively detecting the first image and the second image to obtain the position information of the commodity 1 in the first image, a plurality of corresponding categories and the confidence coefficient of each category, and the position information of the commodity 2 in the second image, a plurality of corresponding categories and the confidence coefficient of each category.
Step 202: and determining the intersection area and the union area of the external outlines of the commodity 1 and the commodity 2 according to the position of the external outline of the commodity 1 and the position of the external outline of the commodity 2, and determining the overlapping degree according to the intersection area and the union area.
Step 203: it is determined whether the overlap is greater than 0.9 and if so, step 204 is performed, otherwise, step 206 is performed.
Step 204: and determining whether the category corresponding to the confidence coefficient arranged at the 1-2 bit corresponding to the commodity 1 is completely different from the category corresponding to the confidence coefficient arranged at the 1-2 bit corresponding to the commodity 2, if so, executing a step 206, otherwise, executing a step 205.
The confidence degrees corresponding to the commodities 1 and 2 are sorted according to the same sorting logic.
Step 205: the categories of the article 1 and the article 2 are determined to be the same.
Step 206: and determining whether the commodity 1 and the commodity 2 meet the position corresponding condition according to the position information of the commodity 1 and the position information of the commodity 2, if so, executing step 207, and otherwise, executing step 211.
The position corresponding condition is that the ratio of the area of the intersection of the outer contours of the commodity 1 and the commodity 2 to the target area is greater than 0.5; the target area is the smaller area of the areas of the outer contours of the products 1 and 2.
Step 207: and determining whether the category corresponding to the confidence coefficient arranged at the 3 rd position and corresponding to the commodity 1 is the same as the category corresponding to the confidence coefficient arranged at the 3 rd position and corresponding to the commodity 2, if so, executing the step 205, otherwise, executing the step 208.
Step 208: and determining whether the category corresponding to the confidence degree arranged at the 1 st position and corresponding to the commodity 1 is the same as the category corresponding to the confidence degree arranged at the 3 rd position or the 4 th position and corresponding to the commodity 2, if so, executing the step 209, otherwise, executing the step 211.
Step 209: and determining the similarity between the commodity 1 and the commodity 2 according to the image characteristics of the commodity 1 and the image characteristics of the commodity 2.
Step 210: it is determined whether the similarity is greater than 90%, if so, step 205 is performed, otherwise, step 211 is performed.
Step 211: it is determined that the categories of the article 1 and the article 2 are different.
It should be noted that, the embodiment of the present invention only takes an application scenario of a container as an example, but the method is not limited to determining whether the categories of the commodities are the same. For example, the method may also be used to identify whether a first object in the first image and a second object in the second image are the same person. In this scenario, the confidence of the first/second object as the individual may be determined by a visual algorithm.
The above embodiment describes a method for recognizing an object in an image, taking recognition of only two objects as an example. In an actual application scenario, any object in the first image and any object in the second image can be recognized by using the method provided in the above embodiment.
As shown in fig. 3, an embodiment of the present invention provides an apparatus for identifying an object in an image, including:
a detection unit 301 configured to detect a first image and a second image respectively, and obtain position information of a first object in the first image, a plurality of corresponding categories and a confidence level of each category, and position information of a second object in the second image, a plurality of corresponding categories and a confidence level of each category;
a determining unit 302 configured to determine whether the categories of the first object and the second object are the same according to the position information of the first object, the corresponding categories and the confidence of each category, and the position information of the second object, the corresponding categories and the confidence of each category.
In an embodiment of the present invention, the determining unit 302 is configured to determine an overlapping degree of the first object and the second object according to the position information of the first object and the position information of the second object; determining whether the overlapping degree is larger than a first threshold value, if so, determining whether the category corresponding to the confidence degree arranged at a plurality of first set orders and corresponding to the first object is completely different from the category corresponding to the confidence degree arranged at a plurality of first set orders and corresponding to the second object, and if not, determining that the categories of the first object and the second object are the same; and the confidence degrees corresponding to the first object and the second object are sorted according to the same sorting logic.
In an embodiment of the invention, the determining unit 302 is configured to determine an area of an intersection and an area of a union of the outer contours of the first object and the second object according to a position of the outer contour of the first object and a position of the outer contour of the second object; and determining the overlapping degree according to the area of the intersection and the area of the union.
In an embodiment of the present invention, the determining unit 302 is further configured to, if the degree of overlap is not greater than a first threshold, or if a category corresponding to the first object and corresponding to the confidence degrees arranged at a plurality of first set levels is completely different from a category corresponding to the second object and corresponding to the confidence degrees arranged at a plurality of first set levels, determine whether the first object and the second object satisfy a position corresponding condition according to the position information of the first object and the position information of the second object, if so, determine whether a category corresponding to the first object and corresponding to the confidence degrees arranged at a plurality of second set levels is completely different from a category corresponding to the second object and corresponding to the confidence degrees arranged at a plurality of second set levels, and if not, determine that the categories of the first object and the second object are the same.
In one embodiment of the present invention, the location correspondence condition includes: the ratio of the area of the intersection of the outer contours of the first object and the second object to the target area is greater than a second threshold; wherein the target area is a smaller area of the areas of the outer contours of the first object and the second object.
In an embodiment of the present invention, the determining unit 302 is further configured to determine whether a category corresponding to the confidence degree ranked at several second setting orders corresponding to the first object is identical to one of categories corresponding to the confidence degree ranked at several fourth setting orders corresponding to the second object if the category corresponding to the confidence degree ranked at several second setting orders corresponding to the first object is completely different from the category corresponding to the confidence degree ranked at several second setting orders corresponding to the second object, determine a similarity between the first object and the second object according to the image feature of the first object and the image feature of the second object if the category is identical to the category of the first object and the second object if the similarity is greater than the third threshold.
The embodiment of the invention provides a device for identifying an object in an image, which comprises: a processor and a memory;
the memory is used for storing execution instructions, and the processor is used for executing the execution instructions stored by the memory to realize the method of any one of the above embodiments.
Embodiments of the present invention provide a computer-readable storage medium, on which computer-readable instructions are stored, where the computer-readable instructions can be executed by a processor to implement the method of any one of the above embodiments.
In the 90's of the 20 th century, improvements to a technology could clearly distinguish between improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements to process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain a corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical blocks. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry for implementing the logical method flows can be readily obtained by a mere need to program the method flows with some of the hardware description languages described above and into an integrated circuit.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method of identifying an object in an image, comprising:
detecting a first image to obtain a plurality of first category information corresponding to a first object in the first image and confidence information corresponding to each first category information in the plurality of first category information;
detecting a second image to obtain a plurality of second category information corresponding to a second object in the second image and confidence information corresponding to each second category in the plurality of second category information;
determining overlapping degree information of the first object and the second object;
and judging whether the categories of the first object and the second object are the same or not according to the plurality of first category information, the confidence coefficient information corresponding to each first category information, the plurality of second category information, the confidence coefficient information corresponding to each second category information and the overlapping degree information.
2. The method of claim 1, determining overlap information of the first object and the second object based on the position information of the first object and the position information of the second object.
3. The method of claim 2, wherein the first step is carried out in a single step,
the determining, according to the plurality of first category information, the confidence level information corresponding to each first category information, the plurality of second category information, the confidence level information corresponding to each second category information, and the overlapping degree information, whether the categories of the first object and the second object are the same specifically includes:
determining whether the degree of overlap is greater than a first threshold;
when the overlapping degree is larger than the first threshold, determining whether the category corresponding to the confidence degrees arranged at a plurality of first set orders and corresponding to the first object is completely different from the category corresponding to the confidence degrees arranged at the plurality of first set orders and corresponding to the second object;
if not, determining that the first object and the second object are the same in category;
and the corresponding confidence degrees of the first object and the second object are ordered according to the same ordering logic.
4. The method of claim 2, wherein the first and second light sources are selected from the group consisting of a red light source, a green light source, and a blue light source,
determining the overlapping degree of the first object and the second object according to the position information of the first object and the position information of the second object, wherein the determining comprises the following steps:
determining the area of the intersection and the area of the union of the external outlines of the first object and the second object according to the position of the external outline of the first object and the position of the external outline of the second object;
and determining the overlapping degree according to the area of the intersection and the area of the union.
5. The method of claim 3, further comprising:
if the overlapping degree is not larger than a first threshold, or the categories corresponding to the confidence degrees arranged at a plurality of first set orders and corresponding to the first object are completely different from the categories corresponding to the confidence degrees arranged at a plurality of first set orders and corresponding to the second object, determining whether the first object and the second object meet position corresponding conditions according to the position information of the first object and the position information of the second object;
when the first object and the second object meet the position corresponding condition, determining whether the category corresponding to the confidence degrees arranged at a plurality of second set levels and corresponding to the first object is completely different from the category corresponding to the confidence degrees arranged at the plurality of second set levels and corresponding to the second object;
and if not, determining that the first object and the second object are the same in category.
6. The method of claim 5, wherein the first and second light sources are selected from the group consisting of a red light source, a green light source, and a blue light source,
the position correspondence condition includes: the ratio of the area of the intersection of the outer contours of the first object and the second object to the target area is greater than a second threshold; wherein the target area is a smaller area of areas of the outer contours of the first object and the second object.
7. The method of claim 5 or 6, further comprising:
if the category corresponding to the confidence degree arranged at a plurality of second set orders and corresponding to the first object is completely different from the category corresponding to the confidence degree arranged at the plurality of second set orders and corresponding to the second object, determining whether the category corresponding to the confidence degree arranged at a third set order and corresponding to the first object is the same as one of the categories corresponding to the second object and corresponding to the confidence degree arranged at a plurality of fourth set orders;
when the category corresponding to the confidence degree arranged at the third set level corresponding to the first object is the same as one of the categories corresponding to the confidence degrees arranged at a plurality of fourth set levels corresponding to the second object, determining the similarity between the first object and the second object according to the image characteristics of the first object and the image characteristics of the second object, and if the similarity is greater than a third threshold value, determining that the categories of the first object and the second object are the same.
8. An apparatus for recognizing an object in an image, comprising:
the detection unit is used for detecting a first image to obtain a plurality of pieces of first category information corresponding to a first object in the first image and confidence information corresponding to each piece of first category information in the plurality of pieces of first category information; detecting a second image to obtain a plurality of second category information corresponding to a second object in the second image and confidence information corresponding to each second category in the plurality of second category information;
an overlapping degree information determining unit configured to determine overlapping degree information of the first object and the second object;
a category determining unit, configured to determine whether the categories of the first object and the second object are the same according to the multiple pieces of first category information, the confidence level information corresponding to each piece of first category information, the multiple pieces of second category information, the confidence level information corresponding to each piece of second category information, and the overlapping degree information.
9. The apparatus according to claim 8, wherein the overlapping degree information determining unit is specifically configured to determine the overlapping degree information of the first object and the second object according to the position information of the first object and the position information of the second object.
10. An apparatus for identifying an object in an image, comprising: a processor and a memory;
the memory is configured to store execution instructions, and the processor is configured to execute the execution instructions stored by the memory to implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210671835.4A CN115035407A (en) | 2019-11-06 | 2019-11-06 | Method, device and equipment for identifying object in image |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210671835.4A CN115035407A (en) | 2019-11-06 | 2019-11-06 | Method, device and equipment for identifying object in image |
| CN201911078767.5A CN110866478B (en) | 2019-11-06 | 2019-11-06 | Method, device and equipment for identifying object in image |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911078767.5A Division CN110866478B (en) | 2019-11-06 | 2019-11-06 | Method, device and equipment for identifying object in image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115035407A true CN115035407A (en) | 2022-09-09 |
Family
ID=69654469
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911078767.5A Active CN110866478B (en) | 2019-11-06 | 2019-11-06 | Method, device and equipment for identifying object in image |
| CN202210671835.4A Pending CN115035407A (en) | 2019-11-06 | 2019-11-06 | Method, device and equipment for identifying object in image |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911078767.5A Active CN110866478B (en) | 2019-11-06 | 2019-11-06 | Method, device and equipment for identifying object in image |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN110866478B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113627512A (en) * | 2021-08-05 | 2021-11-09 | 上海购吖科技有限公司 | Picture identification method and device |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9355312B2 (en) * | 2013-03-13 | 2016-05-31 | Kofax, Inc. | Systems and methods for classifying objects in digital images captured using mobile devices |
| US10121515B2 (en) * | 2016-06-06 | 2018-11-06 | Avigilon Corporation | Method, system and computer program product for interactively identifying same individuals or objects present in video recordings |
| US10019654B1 (en) * | 2017-06-28 | 2018-07-10 | Accenture Global Solutions Limited | Image object recognition |
| CN108802840B (en) * | 2018-05-31 | 2020-01-24 | 北京迈格斯智能科技有限公司 | Method and device for automatically identifying object based on artificial intelligence deep learning |
| CN109800794B (en) * | 2018-12-27 | 2021-10-22 | 上海交通大学 | Cross-camera re-identification fusion method and system for appearance similar targets |
| CN109886208B (en) * | 2019-02-25 | 2020-12-18 | 北京达佳互联信息技术有限公司 | Object detection method and device, computer equipment and storage medium |
-
2019
- 2019-11-06 CN CN201911078767.5A patent/CN110866478B/en active Active
- 2019-11-06 CN CN202210671835.4A patent/CN115035407A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| CN110866478A (en) | 2020-03-06 |
| CN110866478B (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107274442B (en) | Image identification method and device | |
| CN108320296B (en) | Method, device and equipment for detecting and tracking target object in video | |
| CN109034183B (en) | Target detection method, device and equipment | |
| US11093792B2 (en) | Image processing methods and devices | |
| CN112287927B (en) | Method and device for detecting inclination angle of text image | |
| US20200118189A1 (en) | Method and apparatus for improving vehicle loss assessment image identification result, and server | |
| CN111291797A (en) | Anti-counterfeiting identification method and device and electronic equipment | |
| TWI713019B (en) | Data label generation, model training, event recognition method and device | |
| CN110490225B (en) | Scene-based image classification method, device, system and storage medium | |
| CN110866478B (en) | Method, device and equipment for identifying object in image | |
| CN111652286A (en) | Object identification method, device and medium based on graph embedding | |
| CN111353417A (en) | Target detection method and device | |
| CN108804563B (en) | Data labeling method, device and equipment | |
| CN112966577B (en) | Method and device for model training and information providing | |
| CN111368902A (en) | Data labeling method and device | |
| CN112183181A (en) | Information display method | |
| CN111488776A (en) | Object detection method, object detection device and electronic equipment | |
| CN111539962A (en) | Target image classification method, device and medium | |
| CN113988162A (en) | Model training and image recognition method and device, storage medium and electronic equipment | |
| CN114863206A (en) | Model training method, target detection method and device | |
| CN109903165B (en) | Model merging method and device | |
| CN111539961A (en) | Target segmentation method, device and equipment | |
| CN111899264A (en) | Target image segmentation method, device and medium | |
| CN110503109B (en) | Image feature extraction method and device, and image processing method and device | |
| CN111753661B (en) | Target identification method, device and medium based on neural network |
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 |