CN114241343A

CN114241343A - Object attribute identification method and device, storage medium and electronic equipment

Info

Publication number: CN114241343A
Application number: CN202111555575.6A
Authority: CN
Inventors: 张凯程; 刘振华; 白亮
Original assignee: China Telecom Corp Ltd
Current assignee: China Telecom Corp Ltd
Priority date: 2021-12-17
Filing date: 2021-12-17
Publication date: 2022-03-25

Abstract

The method comprises the steps of obtaining an image to be processed, preprocessing the image to be processed to form information to be recognized, inputting the information to be recognized into a first object attribute recognition model, and finally obtaining a first object attribute label, wherein the information to be recognized comprises a target object image, a plurality of object images around the target object and actual distances between the target object and the plurality of objects around the target object. The technical scheme of the embodiment of the invention ensures that the first object attribute identification model can consider the influence between the target object and a plurality of objects around the target object in a combined manner, so that the acquired first object attribute label is more accurate and stable.

Description

Object attribute identification method and device, storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of computer vision technologies, and in particular, to an object attribute identification method and apparatus, a storage medium, and an electronic device.

Background

Object recognition is a basic research in the field of computer vision, and the recognition of object attributes is the basis and precondition of object recognition, and is also an important direction in the field of object recognition.

In the related art, the object attribute recognition method is more specifically to recognize the object attribute by using a human motion sequence and a tag of a target object. However, the target object does not exist in isolation, and the object also have a million-thread relationship and have obvious mutual influence and action. Ignoring the interactions and effects between objects can result in less accurate and stable identification of object properties.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

The present disclosure is directed to a method and an apparatus for identifying object attributes, a storage medium, and an electronic device, which overcome, at least to some extent, the problem that object attributes are not accurately and stably identified due to neglecting the interaction between a target object and objects around the target object within the limits of the related art.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.

According to an aspect of the present disclosure, there is provided an identification method of an object attribute, including:

acquiring an image to be processed;

preprocessing the image to be processed to form information to be identified, wherein the information to be identified comprises a target object image, a plurality of object images around the target object and actual distances between the target object and the plurality of objects around the target object;

and inputting the information to be identified into a first object attribute identification model to obtain a first object attribute label.

In one embodiment of the present disclosure, the identification method further includes:

preprocessing the image to be processed to form a sample to be trained, wherein the sample to be trained comprises a target object image, a plurality of object images around the target object and actual distances between the target object and the plurality of objects around the target object;

inputting the sample to be trained into a first preset model to obtain a first initial object attribute label;

and correcting the first preset model parameter according to the comparison between the target object standard attribute label and the first initial object attribute label until the training condition of the first preset model meets the preset condition, and obtaining the trained first object attribute identification model.

In one embodiment of the present disclosure, the first object property identification model includes:

the relation graph is generated through actual distances between the target object and a plurality of objects around the target object, the target object image and the plurality of object images around the target object, each object is regarded as a node on the relation graph, part of the nodes are marked with object attribute labels, and links between the target object node and the plurality of object nodes around the target object are marked with weights;

the graph label propagation calculation module is used for receiving the weight and the object attribute label input marked by the partial nodes and outputting a preliminary attribute feature vector through an icon label propagation algorithm;

and the graph attention machine system processing module is used for receiving the input of the preliminary attribute feature vector, outputting a final attribute feature vector through a graph attention machine system algorithm and generating a first object attribute label.

In one embodiment of the present disclosure, the first object property tag includes: a hardness property label, a volume property label, and a shape property label of the object.

preprocessing the image to be processed to form information to be identified, wherein the information to be identified comprises a target object image and a plurality of object images around the target object;

and inputting the information to be identified into a second object attribute identification model to obtain a second object attribute label.

In one embodiment of the present disclosure, the second object property identification model includes:

the gray level co-occurrence matrix calculation module is used for receiving the input of the target object image and a plurality of object images around the target object and outputting ten characteristics of a gray level co-occurrence matrix of each object through a gray level co-occurrence matrix algorithm;

and the support vector machine processing module is used for receiving the ten characteristic inputs, outputting a final object characteristic vector through the support vector machine algorithm and generating a second object attribute label.

In one embodiment of the present disclosure, the second object property label includes: a smooth property label and a rough property label for an object.

According to another aspect of the present disclosure, there is provided an apparatus for identifying an attribute of an object, including:

the image acquisition module is used for acquiring an image to be processed;

the image processing module is used for preprocessing the image to be processed to form information to be identified, wherein the information to be identified comprises a target object image, a plurality of object images around the target object and actual distances between the target object and the plurality of objects around the target object;

and the attribute identification module is used for inputting the information to be identified into a first object attribute identification model to obtain a first object attribute label.

According to still another aspect of the present disclosure, there is provided an electronic apparatus, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the above-described object property identification method via execution of the executable instructions.

According to yet another aspect of the present disclosure, there is provided a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the above-mentioned object property identification method.

The method and the device for identifying the object attribute, the storage medium and the electronic device provided by the embodiment of the disclosure comprise the steps of preprocessing an image to be processed to form information to be identified by acquiring the image to be processed, inputting the information to be identified into a first object attribute identification model, and finally acquiring a first object attribute label, wherein the information to be identified comprises a target object image, a plurality of object images around the target object and actual distances between the target object and a plurality of objects around the target object. The technical scheme of the embodiment of the invention ensures that the first object attribute identification model can consider the influence between the target object and a plurality of objects around the target object in a combined manner, so that the acquired first object attribute label is more accurate and stable.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.

FIG. 1 is a flow chart illustrating a method for identifying an attribute of an object according to an embodiment of the disclosure;

FIG. 2 is a flowchart of a method for obtaining a trained first object property recognition model of FIG. 1;

FIG. 3 is a flow chart of the first object property identification model of FIG. 1 identifying an object property;

FIG. 4 is a block diagram of the structure of the first object property identification model of FIG. 1;

FIG. 5 is a flow chart illustrating another method for identifying object attributes in an embodiment of the present disclosure;

FIG. 6 is a flowchart of the method for obtaining the trained second object attribute identification model in FIG. 5;

FIG. 7 is a flow chart of the second object property identification model of FIG. 5 identifying the property of the object;

FIG. 8 is a block diagram of the structure of the second object attribute identification model of FIG. 5;

FIG. 9 is a flow chart illustrating another method for identifying object attributes in an embodiment of the present disclosure;

fig. 10 schematically illustrates an electronic device for implementing the above-described object property identification method according to an exemplary embodiment of the present invention

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

The following detailed description of exemplary embodiments of the disclosure refers to the accompanying drawings.

Fig. 1 schematically shows a flow chart of an object property identification method of the present disclosure.

Referring to fig. 1, the identification method applied to an object property may include:

step S101, acquiring an image to be processed;

step S102, preprocessing the image to be processed to form information to be recognized, wherein the information to be recognized comprises a target object image, a plurality of object images around the target object and actual distances between the target object and a plurality of objects around the target object;

step S103, inputting the information to be identified into the first object attribute identification model 400, and acquiring a first object attribute tag.

The method and the device for identifying the object attribute, the storage medium and the electronic device provided by the embodiment of the disclosure comprise the steps of preprocessing an image to be processed to form information to be identified by acquiring the image to be processed, inputting the information to be identified into a first object attribute identification model 400, and finally acquiring a first object attribute label, wherein the information to be identified comprises a target object image, a plurality of object images around the target object and actual distances between the target object and a plurality of objects around the target object. The technical scheme of the embodiment of the invention ensures that the first object attribute identification model 400 can consider the influence between the target object and a plurality of objects around the target object in a combined manner, so that the acquired first object attribute label is more accurate and stable.

First, the objects of the exemplary embodiments of the present invention are explained and explained.

The current object attribute identification method mainly focuses on a target object, and the basic idea is to firstly obtain a picture of the target object, process the picture of the target object and then perform feature extraction. And then training a judgment model by using a traditional machine learning method or an emerging deep learning method according to the extracted texture features, shape features and the like. And finally, testing and judging the label-free unknown data by using the trained judgment model so as to identify the type of the object attribute.

However, the target object does not exist in isolation, and only the attributes of the target object are further refined and researched, but the target object and the surrounding objects have a million-thread relationship, and significant mutual influence and effect exist, so that the object attribute identification is not accurate and stable enough.

In addition, in the exemplary embodiment of the present invention, from the perspective of the object attribute identification model, the preset model is trained by using information about a target object and a plurality of objects around the target object, and a parameter adjustment process for optimizing parameters is performed, so that the object attribute labels obtained in the object attribute identification model generated subsequently can be more accurate and stable in object identification.

Next, the method of identifying the object attribute according to the exemplary embodiment of the present invention will be explained and explained.

Fig. 2 schematically shows a flow chart of a method of obtaining a trained first object property recognition model 400 in fig. 1.

Specifically, referring to fig. 2, the method for identifying object attributes further includes a method for obtaining a trained first object attribute identification model 400, which includes the following steps:

step S201, acquiring an image to be processed;

specifically, the image information of the target object and a plurality of objects around the target object may be acquired by using a camera or the like.

Step S202, preprocessing the image to be processed to form a sample to be trained, wherein the sample to be trained comprises a target object image, a plurality of object images around the target object and actual distances between the target object and the plurality of objects around the target object;

specifically, the image to be processed is preprocessed, each object in the image information of the target object and the plurality of objects around the target object may be segmented by using an image segmentation technology, and the actual distance between each object is calculated. Among them, the image segmentation (image segmentation) technology is an important research direction in the field of computer vision, and is an important part of image semantic understanding. From the mathematical point of view, image segmentation is a process of dividing an image into mutually disjoint areas, and the related technologies of scene object segmentation, human body front background segmentation, human face human body matching, three-dimensional reconstruction and the like have been widely applied to the industries of unmanned driving, augmented reality, security monitoring and the like.

Step S203, inputting the sample to be trained into a first preset model to obtain a first initial object attribute label;

specifically, first, a relationship graph 401 is generated by mapping the preprocessed target object image, the plurality of object images around the target object, and the actual distances between the target object and the plurality of objects around the target object onto a static graph, and regarding each object as a node on the graph. Whether a link exists between two nodes is determined according to the distance between two corresponding objects, if the actual distance is larger than a certain set value, the node corresponding to the two objects is considered to have no link, and if not, the link exists. The smaller the distance, the greater the weight of the link, and the weight of the link corresponding to the two objects that are completely attached is regarded as the maximum. And calculating link weights between the target object node and a plurality of object nodes around the target object, wherein the larger the link weight is, the larger the similarity of the two nodes is, and labeling labels of part of object attributes.

Secondly, the object attribute labels marked by the weight and part of the nodes are input into an icon label propagation calculation module 402, and a preliminary attribute characteristic vector is calculated by performing semi-supervised learning through an icon label propagation algorithm in the module. The Label Propagation Algorithm (LPA) is a graph-based semi-supervised learning method, and the basic idea is to use label information of labeled nodes to predict label information of unlabeled nodes. And establishing a relation complete graph model by utilizing the relation between the samples, wherein in the complete graph, the nodes comprise marked data and unmarked data, namely the link weight is the similarity of the two nodes, and the labels of the nodes are transmitted to other nodes according to the similarity. The label data is just like a source, label-free data can be labeled, and the greater the similarity of the nodes, the easier the label is to propagate.

Finally, the preliminary attribute feature vector is input into the graph attention machine processing module 403, and after training by the graph attention machine algorithm, the final attribute feature vector is output to generate a first preliminary object attribute mark. The Attention Mechanism (Attention Mechanism) is a data processing method in machine learning, and is widely applied to various different types of machine learning tasks such as Natural Language Processing (NLP), image processing (CV), speech recognition, and the like. The attention mechanism is divided into three types, namely a space domain, a channel domain and a mixed domain according to different application modes and different application positions of the attention mechanism in the domains. The method can realize the weighted aggregation of the neighbors, is more robust to noise neighbors, and gives a certain interpretability to the model through an attention mechanism. A multi-head graph attention machine algorithm can be used for mining a low-order relation and a high-order connection mode in the learning relation graph 401, different weights are given to neighbor nodes of the same order to achieve differential treatment, and therefore a relation with finer granularity is learned.

Step S204, according to the comparison between the standard attribute label of the target object and the attribute label of the first initial object, modifying the first preset model parameter until the training condition of the first preset model meets a preset condition, and obtaining the trained first object attribute identification model 400.

In the embodiment of the disclosure, when the first preset model is trained, the information of the target object and a plurality of objects around the target object is added into the training sample, so that the condition that only the attributes of the target object are researched and the factors influencing each other between the object and the object are ignored is avoided. Comparing the first initial object attribute label output after the first preset model training with the actual target object standard attribute label, and correcting the first preset model parameter according to the comparison result analysis until the first preset model training condition meets the preset condition, so as to obtain the trained first object attribute recognition model 400. After training, parameter correction is performed on the first preset model, so that the trained first object attribute recognition model 400 can recognize object attributes more accurately and stably.

FIG. 3 schematically illustrates a flow diagram for identifying object properties by the first object property identification model 400 of FIG. 1.

Specifically, referring to fig. 3, the method S103 for identifying the object attribute by the first object attribute identification model 400 includes the following steps:

step S301, inputting a target object image, a plurality of object images around the target object, and actual distances between the target object and a plurality of objects around the target object into a relational graph 401, and acquiring object attribute labels marked with weights and partial nodes by links between a target object node and a plurality of object nodes around the target object;

step S302, inputting the object attribute labels marked by the weight and part of the nodes into an icon label propagation calculation module 402, and outputting a preliminary attribute feature vector through an icon label propagation algorithm;

step S303, inputting the preliminary attribute feature vector into the processing module 403 of the graph attention machine, outputting the final attribute feature vector through the algorithm of the graph attention machine, and generating the first object attribute label.

Specifically, the final attribute feature vector includes a plurality of dimensions, among which: the hardness attribute feature vector, the volume attribute feature vector and the shape attribute feature vector respectively correspond to the first object attribute label generated by the method: a hardness property label, a volume property label, and a shape property label of the target object. For example: the shape attribute labels may be rectangles, circles, polygons, and the like.

In the embodiment of the disclosure, through the relationship diagram 401 in the first object identification model, the semi-supervised learning of the icon label propagation algorithm of the icon label propagation calculation module 402 and the algorithm of the attention mechanism processing module 403, after the preliminary learning of the graph label propagation algorithm, the attention mechanism is added for further processing, so that the attribute hardness, shape and volume of the object are more accurately identified.

Fig. 4 schematically shows a block diagram of the first object property identification model 400 in fig. 1.

Specifically, referring to fig. 4, the first object attribute identification model 400 includes a relationship graph 401, an icon sign propagation calculation module 402, and a graph attention mechanism processing module 403.

A relation graph 401, wherein the relation graph 401 is generated by actual distances between a target object and a plurality of objects around the target object, and the target object image and the plurality of object images around the target object, each object is regarded as a node on the relation graph 401, part of the nodes are marked with object attribute labels, and links between the target object node and the plurality of object nodes around the target object are marked with weights;

a graph label propagation calculation module 402, configured to receive an input of the object attribute labels marked by the weight and part of the nodes, and output a preliminary attribute feature vector through an icon label propagation algorithm;

and a graph attention mechanism processing module 403, configured to receive the preliminary attribute feature vector input, output a final attribute feature vector through a graph attention mechanism algorithm, and generate a first object attribute tag.

Fig. 5 schematically illustrates a flowchart of another object attribute identification method in an embodiment of the present disclosure.

Specifically, referring to fig. 5, the method applied to identify the object attribute may further include:

step S501, acquiring an image to be processed;

step S502, preprocessing the image to be processed to form information to be identified, wherein the information to be identified comprises a target object image and a plurality of object images around the target object;

step S503, inputting the information to be identified into the second object attribute identification model 800, and obtaining a second object attribute label.

In the embodiment of the present disclosure, the image to be processed is obtained and is preprocessed to form information to be recognized, where the information to be recognized includes a target object image and a plurality of object images around the target object, the information to be recognized is input into the second object attribute recognition model 800, and finally the second object attribute tag is obtained. The technical scheme of the embodiment of the invention ensures that the second object attribute identification model 800 can consider the influence between the target object and a plurality of objects around the target object in a combined manner, so that the acquired first object attribute label is more accurate and stable.

FIG. 6 is a flowchart of the method of FIG. 5 for obtaining a trained second object attribute identification model 800.

Specifically, referring to fig. 6, the method for identifying object attributes further includes a method for obtaining a trained second object attribute identification model 800, which includes the following steps:

step S601, acquiring an image to be processed;

step S602, preprocessing the image to be processed to form a sample to be trained, wherein the sample to be trained comprises a target object image and a plurality of object images around the target object;

specifically, the image to be processed is preprocessed, and as described in detail above, please refer to the description of step S202, which is not described herein again.

Step S603, inputting the sample to be trained into a second preset model to obtain a second initial object attribute label;

specifically, the target object image and a plurality of object images around the target object are input into the gray level co-occurrence matrix calculation module 802, and ten features of the gray level co-occurrence matrix of each object are output through the gray level co-occurrence matrix algorithm. The ten characteristics include: mean and standard deviation of energy, mean and standard deviation of entropy, mean and standard deviation of contrast, mean and standard deviation of moment of inverse difference, mean and standard deviation of correlation. Among them, a Gray-level co-occurrence matrix (GLCM) refers to a common method for describing texture by studying spatial correlation characteristics of Gray levels. Since the texture is formed by the repeated appearance of the gray scale distribution at the spatial position, a certain gray scale relationship, i.e., a spatial correlation characteristic of the gray scale in the image, exists between two pixels spaced apart from each other in the image space. The gray level co-occurrence matrix method can obtain a co-occurrence matrix of the gray level image by calculating the gray level image, and then obtain partial characteristic values of the matrix by calculating the co-occurrence matrix to respectively represent certain texture characteristics of the image.

Step S604, according to the comparison between the standard attribute label of the target object and the attribute label of the second initial object, correcting the second preset model parameter until the training condition of the second preset model meets a preset condition, and obtaining the trained second object attribute identification model 800.

In the embodiment of the present disclosure, according to the second preset model training result, the second preset model training result is compared with the target object standard attribute label, and then the second preset model parameter is corrected until the preset condition is met to obtain the second object attribute identification model 800, so that the stability of object attribute identification can be increased.

FIG. 7 schematically illustrates a flow chart of the second object property identification model 800 of FIG. 5 identifying an object property.

Specifically, referring to fig. 7, the second object attribute identification model 800 identifies the object attribute method S503, which includes the following steps:

step S701, inputting the target object image and the plurality of images around the target object into the gray level co-occurrence matrix calculation module 802, and outputting ten features of the gray level co-occurrence matrix of each object through the gray level co-occurrence matrix algorithm.

Step S702, inputting the ten features into the support vector machine processing module 803, and outputting the final object attribute feature vector through the support vector machine algorithm to generate a second object attribute label.

Specifically, the final object attribute feature vector includes a plurality of dimensions, among which: the smooth attribute feature vector and the rough attribute feature vector respectively correspond to the generated second object attribute label: a smooth property label and a rough property label of the target object.

In the embodiment of the present disclosure, according to the target object image and the plurality of object images around the target object, ten features of the gray level co-occurrence matrix of each object are obtained through the gray level co-occurrence matrix calculation module 802, and the plurality of objects around the target object are also considered, so that the recognition result is more reliable, and unstable recognition caused by neglecting the influence between the objects is avoided.

Fig. 8 is a block diagram schematically illustrating the structure of the second object attribute identification model 800 in fig. 5.

Specifically, referring to fig. 8, the second object attribute identification model 800 includes a gray level co-occurrence matrix calculation module 802 and a support vector machine processing module 803.

A gray level co-occurrence matrix calculation module 802, configured to receive an input of a target object image and a plurality of object images around the target object, and output ten features of a gray level co-occurrence matrix of each object through a gray level co-occurrence matrix algorithm;

and the support vector machine processing module 803 is configured to receive ten feature inputs, output a final object feature vector through a support vector machine algorithm, and generate a second object attribute label.

FIG. 9 is a flow chart illustrating another method for identifying object attributes in an embodiment of the disclosure.

Specifically, referring to fig. 9, the method for identifying an object attribute further includes:

step 901, acquiring an image to be processed;

step S902, preprocessing the image to be processed to form information to be recognized, wherein the information to be recognized comprises a target object image, a plurality of object images around the target object, and actual distances between the target object and a plurality of objects around the target object;

step S903, inputting the target object image, the plurality of object images around the target object, and the actual distances between the target object and the plurality of objects around the target object into the first object attribute identification model 400, and acquiring a first object attribute label; inputting the target object image and a plurality of object images around the target object into a second object attribute identification model 800 to obtain a second object attribute label;

step S904, integrating the first object attribute label and the second object attribute label to output an object attribute label.

Specifically, the object property labels include a hardness property label, a volume property label, a shape property label, a smoothness property label, and a roughness property label of the target object.

In the embodiment of the present disclosure, the object attribute identification model includes the first object attribute identification model 400 and the second object attribute identification model 800, and more object attribute identification results can be identified by inputting the information to be identified into the object attribute identification model and then integrating the first object attribute tag and the second object attribute tag to output the object attribute tags.

An object attribute identification system comprises an image acquisition module, an image processing module and an attribute identification module.

The image acquisition module is used for acquiring an image to be processed;

and the attribute identification module is used for inputting the information to be identified into the first object attribute identification model 400 to obtain a first object attribute label.

Since each function of the identification system applied to the object attribute has been described in detail in the corresponding method embodiment, the disclosure is not repeated herein.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

An electronic device 1000 according to this embodiment of the invention is described below with reference to fig. 10. The electronic device 1000 shown in fig. 10 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 10, the electronic device 1000 is embodied in the form of a general purpose computing device. The components of the electronic device 1000 may include, but are not limited to: the at least one processing unit 1010, the at least one memory unit 1020, and a bus 1030 that couples various system components including the memory unit 1020 and the processing unit 1010.

Wherein the storage unit stores program code that is executable by the processing unit 1010 to cause the processing unit 1010 to perform steps according to various exemplary embodiments of the present invention as described in the "exemplary methods" section above in this specification. For example, the processing unit 1010 may execute step S101 shown in fig. 1, acquiring an image to be processed; step S102, preprocessing the image to be processed to form information to be recognized, wherein the information to be recognized comprises a target object image, a plurality of object images around the target object and actual distances between the target object and a plurality of objects around the target object; step S103, inputting the information to be identified into a first object attribute identification model, and acquiring a first object attribute label.

The memory unit 1020 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)1021 and/or a cache memory unit 1022, and may further include a read-only memory unit (ROM) 1023.

Storage unit 1020 may also include a program/utility 1024 having a set (at least one) of program modules 1025, such program modules 1025 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 1030 may be any one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, and a local bus using any of a variety of bus architectures.

The electronic device 1000 may also communicate with one or more external devices 1100 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 1000, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 1000 to communicate with one or more other computing devices. Such communication may occur through input/output (I/O) interfaces 1050. Also, the electronic device 1000 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the internet) via the network adapter 1060. As shown, the network adapter 1060 communicates with the other modules of the electronic device 1000 over the bus 1030. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, aspects of the invention may also be implemented in the form of a program product comprising program code means for causing a terminal device to carry out the steps according to various exemplary embodiments of the invention described in the above section "exemplary methods" of the present description, when said program product is run on the terminal device.

A program product for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

Moreover, although the steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that the steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A method for identifying an attribute of an object, comprising:

acquiring an image to be processed;

2. The method of identifying object attributes of claim 1 further comprising:

3. The method for identifying object properties according to claim 1, wherein the first object property identification model comprises:

4. The method of identifying an object property of claim 3, wherein the first object property tag comprises: a hardness property label, a volume property label, and a shape property label of the object.

5. The method of identifying object attributes of claim 1 further comprising:

6. The method for identifying object properties according to claim 5, wherein the second object property identification model comprises:

7. The method of identifying an object property of claim 6, wherein the second object property tag comprises: a smooth property label and a rough property label for an object.

8. An apparatus for identifying an attribute of an object, comprising:

the image acquisition module is used for acquiring an image to be processed;

9. An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to execute the method for identifying an object property according to any one of claims 1 to 7 via execution of the executable instructions.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for identifying a property of an object according to any one of claims 1 to 7.