Object recognition, resource transfer method, device, storage medium, equipment and product

Abstract

The application discloses an object recognition, resource transfer method, device, storage medium, equipment and product, relates to the artificial intelligence technical field, and can be applied to the technical field such as block chain, map car networking, etc.The object recognition method comprises the following steps: acquiring an infrared image and a depth image corresponding to a target object; detecting the region position of predetermined image content from the infrared image, and acquiring an infrared region image corresponding to the region position; segmenting the depth image according to the region position to obtain a content mask corresponding to the predetermined image content; extracting a target infrared region image from the infrared region image according to the content mask; and performing detection processing on the target infrared region image to obtain a detection result, which is used to indicate whether the infrared image is used for object recognition.Some embodiments of the application can improve the detection accuracy of the infrared image, improve the object recognition success rate, and some embodiments of the application can improve the resource transfer efficiency and success rate.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, specifically to an object recognition and resource transfer method, apparatus, storage medium, device, and product. Background Technology

[0002] Object recognition is the process of identifying target objects. Object recognition is usually based on infrared images of objects. For example, it is common to identify whether an object is a moving object based on its infrared image.

[0003] Currently, because image acquisition devices are easily affected by various factors such as lighting environment, the acquired infrared images are prone to defects. Since infrared images cannot be effectively and accurately detected at present, it is easy to use defective infrared images for object recognition, resulting in object recognition failure.

[0004] Therefore, the current infrared images used for object recognition have low detection accuracy and low object recognition success rate. Summary of the Invention

[0005] This application provides object recognition, resource transfer methods, apparatus, storage media, devices and products. Some embodiments of this application can improve the detection accuracy of infrared images and increase the success rate of object recognition. Some embodiments of this application can improve the efficiency and success rate of resource transfer.

[0006] To address the aforementioned technical problems, the embodiments of this application provide the following technical solutions:

[0007] According to one embodiment of this application, an object recognition method is provided, comprising: acquiring an infrared image and a depth image corresponding to a target object; detecting a region location corresponding to predetermined image content from the infrared image and acquiring an infrared region image corresponding to the region location; segmenting the depth image according to the region location to obtain a content mask corresponding to the predetermined image content; extracting a target infrared region image from the infrared region image according to the content mask; and performing detection processing on the target infrared region image to obtain a detection result, wherein the detection result is used to indicate whether the infrared image is used for object recognition.

[0008] According to one embodiment of this application, an object recognition device includes: an image acquisition module for acquiring an infrared image and a depth image corresponding to a target object; a region acquisition module for detecting a region location corresponding to predetermined image content from the infrared image and acquiring an infrared region image corresponding to the region location; a segmentation module for segmenting the depth image according to the region location to obtain a content mask corresponding to the predetermined image content; an extraction module for extracting a target infrared region image from the infrared region image according to the content mask; and a detection module for performing detection processing based on the target infrared region image to obtain a detection result, wherein the detection result is used to indicate whether the infrared image is used for object recognition.

[0009] In some embodiments of this application, the region acquisition module includes: an alignment unit for aligning the infrared image with the depth image to obtain an aligned target infrared image; and a position detection unit for detecting the region position corresponding to the predetermined image content in the target infrared image.

[0010] In some embodiments of this application, the segmentation module includes: a target region determination unit, configured to determine a target depth region corresponding to the location of the region in the depth image; and a content mask generation unit, configured to segment the region image corresponding to the target depth region from the depth image to obtain the content mask.

[0011] In some embodiments of this application, the position detection unit is configured to: acquire a color image corresponding to the target object, and align the color image with the target infrared image to obtain a target color image; detect the position of a color region corresponding to predetermined image content in the target color image; and detect the position of the region corresponding to the predetermined image content in the target infrared image based on the position of the color region.

[0012] In some embodiments of this application, the extraction module is used to: perform superposition operations on the content mask and the infrared region image to generate the target infrared region image.

[0013] In some embodiments of this application, the detection module includes: a target image information detection unit, used to perform detection processing on the target infrared region image to obtain target image information; and a detection result analysis unit, used to generate the detection result based on the target image information, wherein the detection result includes a first detection result or a second detection result, wherein the first detection result is used to indicate that the infrared image is used for object recognition, and the second detection result is used to indicate that the infrared image is not used for object recognition.

[0014] In some embodiments of this application, the target image information includes infrared brightness; the target image information detection unit is configured to: perform infrared brightness detection processing on the target infrared region image to obtain the infrared brightness; the detection result analysis unit is configured to: generate the first detection result if the infrared brightness is within a predetermined brightness range; and generate the second detection result if the infrared brightness is outside the predetermined brightness range.

[0015] In some embodiments of this application, the predetermined image content is a face, the content mask is a face mask, and the target infrared region image is a target face infrared region image; the target image information detection unit is used to: perform infrared brightness detection processing on the target face infrared region image to obtain the infrared brightness.

[0016] In some embodiments of this application, the detection result is generated based on target image information, and the object recognition device further includes an adjustment module for: if the detection result indicates that the infrared image is not used for object recognition, then obtaining preset parameters of the infrared image acquisition device; determining target parameters of the acquisition device based on the target image information and the preset parameters; and adjusting the acquisition device based on the target parameters.

[0017] In some embodiments of this application, the object recognition device further includes a recognition module, configured to: if the detection result indicates that the infrared image is used for object recognition, acquire a target depth image and a target color image corresponding to the target object; and perform object recognition on the target object based on the infrared image, the target depth image, and the target color image.

[0018] According to one embodiment of this application, a resource transfer method includes: responding to a resource transfer instruction, performing a resource transfer operation, the resource transfer operation being performed based on an object recognition result, wherein the object recognition result is obtained by object recognition based on an infrared image of a target object, the infrared image is determined based on a detection result corresponding to a target infrared region image, the target infrared region image is extracted from an infrared region image corresponding to a region location based on a content mask, the region location is obtained by detecting predetermined image content in the infrared image, and the content mask is obtained by segmenting from a depth image corresponding to the target object based on the region location; and playing resource transfer result information, the resource transfer result information being used to indicate the resource transfer result corresponding to the resource transfer operation.

[0019] According to one embodiment of this application, an object recognition device includes: a transfer module, configured to execute a resource transfer operation in response to a resource transfer instruction, the resource transfer operation being performed based on an object recognition result, wherein the object recognition result is obtained by object recognition based on an infrared image of a target object, the infrared image is determined based on a detection result corresponding to a target infrared region image, the target infrared region image is extracted from an infrared region image corresponding to a region location based on a content mask, the region location is obtained by detecting predetermined image content in the infrared image, and the content mask is obtained by segmenting from a depth image corresponding to the target object based on the region location; and a prompting module, configured to play resource transfer result information, the resource transfer result information being used to prompt the resource transfer result corresponding to the resource transfer operation.

[0020] In some embodiments of this application, the transfer module includes: a collection unit, configured to collect an object image corresponding to the target object in response to a resource transfer instruction, the object image including the infrared image, the target color image, and the target depth image; a recognition unit, configured to play an object recognition result, the object recognition result being obtained by object recognition based on the infrared image, the target color image, and the target depth image; and an execution unit, configured to execute a resource transfer operation, the resource transfer operation being executed based on the object recognition result.

[0021] According to another embodiment of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a computer's processor, causes the computer to perform the methods described in the embodiments of this application.

[0022] According to another embodiment of this application, an electronic device includes: a memory storing a computer program; and a processor reading the computer program stored in the memory to execute the methods described in the embodiments of this application.

[0023] According to another embodiment of this application, a computer program product or computer program includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described in the embodiments of this application.

[0024] In this embodiment, an infrared image and a depth image corresponding to the target object are obtained; the region location of a predetermined image content is detected from the infrared image, and an infrared region image corresponding to the region location is obtained; the depth image is segmented according to the region location to obtain a content mask corresponding to the predetermined image content; the target infrared region image is extracted from the infrared region image according to the content mask; the target infrared region image is detected to obtain a detection result, which is used to indicate whether the infrared image is used for object recognition.

[0025] In this way, for an infrared image intended for object recognition, a content mask is obtained from depth image segmentation using the location of a predetermined image content detected in the infrared image. Based on the content mask, the target infrared region image is extracted from the infrared region image corresponding to the detected region location. This method can accurately extract the target infrared region image that locally meets the object recognition requirements. Detecting the target infrared region image to determine whether to use the infrared image for object recognition effectively improves the detection accuracy of infrared images compared to the low accuracy of global image detection or fixed-position region image detection, thereby increasing the object recognition success rate. Furthermore, when using infrared images for object recognition for resource transfer, it can improve resource transfer efficiency and success rate. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 A schematic diagram of a system to which embodiments of this application can be applied is shown.

[0028] Figure 2 A flowchart of an object recognition method according to an embodiment of this application is shown.

[0029] Figure 3 A flowchart of a resource transfer method according to an embodiment of this application is shown.

[0030] Figure 4 A flowchart illustrating object recognition in a given scenario is shown.

[0031] Figure 5 This diagram illustrates the extraction of an infrared region image of a target in a given scenario.

[0032] Figure 6A block diagram of an object recognition device according to an embodiment of this application is shown.

[0033] Figure 7 A block diagram of a resource transfer apparatus according to another embodiment of this application is shown.

[0034] Figure 8 A block diagram of an electronic device according to an embodiment of this application is shown. Detailed Implementation

[0035] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0036] It is understood that in the specific implementation of this application, data related to content information and interactive behavior information are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0037] Figure 1 A schematic diagram of a system 100 to which embodiments of this application can be applied is shown. For example... Figure 1 As shown, system 100 may include server 101 and terminal 102.

[0038] Server 101 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0039] Terminal 102 can be any device, including but not limited to mobile phones, computers, smart voice interaction devices, smart home appliances, in-vehicle terminals, VR / AR devices, smartwatches, and computers, etc. In some embodiments, terminal 102 and server 101 can be nodes in a blockchain network. In some embodiments, the target object can be a user in a map-based vehicle networking platform.

[0040] In one embodiment of this example, server 101 or terminal 102 may: acquire an infrared image and a depth image corresponding to a target object; detect the region location corresponding to predetermined image content from the infrared image and acquire an infrared region image corresponding to the region location; perform segmentation processing on the depth image according to the region location to obtain a content mask corresponding to the predetermined image content; extract a target infrared region image from the infrared region image according to the content mask; perform detection processing on the target infrared region image to obtain a detection result, the detection result being used to indicate whether to use the infrared image for object recognition.

[0041] In one embodiment of this example, terminal 102 may: respond to a resource transfer instruction and execute a resource transfer operation, the resource transfer operation being performed based on an object recognition result, wherein the object recognition result is obtained by object recognition based on an infrared image of a target object, the infrared image is determined based on a detection result corresponding to a target infrared region image, the target infrared region image is extracted from an infrared region image corresponding to a region location based on a content mask, the region location is obtained by detecting predetermined image content in the infrared image, and the content mask is obtained by segmenting from a depth image corresponding to the target object based on the region location; and play resource transfer result information, the resource transfer result information being used to indicate the resource transfer result corresponding to the resource transfer operation.

[0042] Figure 2 A flowchart illustrating an embodiment of an object recognition method according to this application is shown schematically. The entity executing this object recognition method can be any device, such as... Figure 1 The server 101 or terminal 102 shown.

[0043] like Figure 2 As shown, the object recognition method may include steps S210 to S250.

[0044] Step S210: Obtain the infrared image and depth image corresponding to the target object; Step S220: Detect the region location corresponding to the predetermined image content from the infrared image and obtain the infrared region image corresponding to the region location; Step S220: Segment the depth image according to the region location to obtain the content mask corresponding to the predetermined image content; Step S240: Extract the target infrared region image from the infrared region image according to the content mask; Step S250: Perform detection processing on the target infrared region image to obtain the detection result, which is used to indicate whether to use the infrared image for object recognition.

[0045] The target object is the object to be identified, such as a person, animal, or object. An infrared image is an image captured using pan-infrared light. A depth image is an image whose pixel values ​​reflect the distance from the target object in the scene to the acquisition device (e.g., a camera). Both infrared and depth images are images captured specifically for the target object.

[0046] Acquiring infrared and depth images corresponding to the target object can be achieved by acquiring infrared and depth images in real time from an image acquisition device (such as a camera), or by acquiring infrared and depth images uploaded by a device from a predetermined location, or by other acquisition methods that can be configured according to the actual situation.

[0047] Region detection from infrared images allows for the detection of regions corresponding to predetermined image content, and the acquisition of a portion of the infrared image corresponding to that region. This portion of the image is known as the infrared region image. The predetermined image content can be specified according to object recognition requirements, such as a face or other content of interest.

[0048] The depth image is segmented based on its location to obtain a content mask corresponding to the predetermined image content. Based on this content mask, a target infrared region image is further extracted from the infrared region image. The target infrared region image is the local infrared image within the infrared image that accurately corresponds to the predetermined image content. The predetermined image content can be specified according to object recognition requirements, thus ensuring that the target infrared region image accurately matches these requirements. Detecting the target infrared region image accurately determines whether to use infrared imagery for object recognition.

[0049] In related technologies, when performing global image detection on the entire infrared image, if the proportion of the part that meets the object recognition requirements is low, it is easy to cause detection distortion, i.e., low accuracy. When detecting fixed positions in an infrared image, the fixed positions may not match the recognition requirements due to object movement, which can also easily lead to low detection accuracy and thus low object recognition success rate.

[0050] In this way, based on steps S210 to S250, for the infrared image to be used for object recognition, a content mask is obtained from depth image segmentation using the region location of the predetermined image content detected in the infrared image. The target infrared region image is then extracted from the infrared region image corresponding to the detected region location based on the content mask. This accurately extracts the target infrared region image that locally meets the object recognition requirements. Detecting the target infrared region image to determine whether to use the infrared image for object recognition effectively improves the detection accuracy of infrared images compared to the low accuracy issues of global image detection or fixed-position region image detection, thereby increasing the object recognition success rate. Furthermore, when using infrared images for object recognition for resource transfer, avoiding the transmission of useless infrared images to resource transfer programs (such as payment programs) can improve resource transfer efficiency and success rate.

[0051] The following is a further description Figure 2 Specific embodiments of the steps performed in the object recognition implementation.

[0052] In step S210, the infrared image and depth image corresponding to the target object are acquired.

[0053] In one example, obtaining the infrared and depth images corresponding to the target object can be achieved by acquiring the infrared and depth images captured in real time by an image acquisition device (e.g., a camera in the device). For instance, when the target object is used for resource transfer based on object recognition (e.g., payment based on facial recognition), triggering the acquisition device (e.g., a camera in the device) to acquire the object image can result in the acquisition device capturing the infrared and depth images in real time.

[0054] In one example, obtaining the infrared and depth images corresponding to the target object can be achieved by acquiring the infrared and depth images uploaded by the device from a predetermined location. For example, after the acquisition device (e.g., a camera in the device) acquires the image of the object, it uploads it to a database in the server, and the server can retrieve the uploaded infrared and depth images from the database.

[0055] It is understood that in other examples, other acquisition methods can be configured to acquire infrared and depth images according to the actual situation.

[0056] In step S220, the region location corresponding to the predetermined image content is detected from the infrared image, and the infrared region image corresponding to the region location is obtained.

[0057] Content detection models can be used to detect the location of regions corresponding to predetermined image content in infrared images. For example, face detection models can be used to detect the location of regions corresponding to faces in infrared images, or interest content detection models can be used to detect the location of regions corresponding to interest content in infrared images.

[0058] Based on the detected region location, a local image located at that region can be segmented from the infrared image. This local image is the infrared region image corresponding to that region location. The infrared region image includes predetermined image content in the form of an infrared image; for example, the infrared region image may include a face or content of interest in the form of an infrared image.

[0059] An infrared region image is obtained by segmenting the region corresponding to the location in an infrared image. This infrared region image contains predetermined image content in infrared form.

[0060] In one embodiment, step S220, detecting the region location of predetermined image content from the infrared image, includes: aligning the infrared image with a depth image to obtain an aligned target infrared image; and detecting the region location corresponding to the predetermined image content in the target infrared image.

[0061] If infrared and depth images are acquired by two cameras, they can be aligned to the same spatial coordinate system by aligning them, thus obtaining the aligned target infrared and depth images.

[0062] In one approach, the infrared image and the depth image are aligned. This aligns the infrared image to the spatial coordinate system of the depth image. Specifically, based on the transformation relationship between the two spatial coordinate systems (i.e., the camera extrinsic parameters of the two cameras corresponding to the infrared and depth images, which can be transformation matrices describing the camera coordinate systems of the two cameras (including rotation and translation matrices); the camera coordinate system can be a spatial coordinate system with the camera optical center as the origin, the optical axis as the Z-axis, and the x and y axes parallel to the camera imaging pixel plane), the infrared image is transformed according to the transformation relationship (e.g., multiplying the pixel matrix of the infrared image with the transformation matrix) to obtain the target infrared image aligned to the spatial coordinate system of the depth image. In this approach, the target depth image is the initial depth image.

[0063] Alternatively, in other methods, the infrared image and the depth image are aligned. The depth image can be aligned to the spatial coordinate system of the infrared image according to the transformation relationship in the above method. In this case, the target infrared image is the initial infrared image, and the target depth image is the depth image aligned to the infrared image.

[0064] It is understandable that in other methods, based on the transformation relationship between the camera coordinate system of the corresponding camera and the third-party spatial coordinate system, the infrared image and the depth image are aligned to the same third-party spatial coordinate system. In this case, the target infrared image is an infrared image aligned to the third-party spatial coordinate system, and the target depth image is a depth image aligned to the third-party spatial coordinate system.

[0065] After aligning the infrared image and the depth image, the location of the region corresponding to the predetermined image content in the aligned target infrared image is detected. This region location is also the location of the region corresponding to the predetermined image content in the aligned target depth image. Based on this region location, when the depth image and the infrared image correspond to two cameras, a content mask can be accurately generated.

[0066] In one embodiment, detecting the location of a region corresponding to predetermined image content in a target infrared image includes: directly detecting the location of the region corresponding to the predetermined image content from the target infrared image. For example, the target infrared image is input into a content detection model to detect the location corresponding to the predetermined image content, and the detected location is directly determined as the location of the region corresponding to the predetermined image content.

[0067] In one embodiment, detecting the location of a region corresponding to predetermined image content in a target infrared image includes: acquiring a color image corresponding to the target object, and aligning the color image with the target infrared image to obtain a target color image; detecting the location of a color region corresponding to predetermined image content in the target color image; and detecting the location of the region corresponding to the predetermined image content in the target infrared image based on the location of the color region.

[0068] A color image is an image based on visible light imaging, and the color image corresponding to the target object is a color image captured of the target object. After acquiring the color image, it is aligned to the spatial coordinate system of the target infrared image to obtain the target color image. Since the target color image is a color image, the location of the region corresponding to the predetermined image content (i.e., the color region location) can be accurately detected from the target color image.

[0069] Based on the location of the colored region, the target infrared image is input into a content detection model to detect the location corresponding to the predetermined image content. This detected location is then compared with the colored region location. If the difference between the two is less than a predetermined difference, the detected location is determined as the location corresponding to the predetermined image content. This further improves the detection accuracy of this region location.

[0070] In step S220, the depth image is segmented according to the region location to obtain the content mask corresponding to the predetermined image content.

[0071] The location of a predetermined image content is detected from the infrared image. Based on this location, the depth image is segmented to obtain a content mask, which is a depth image of the region corresponding to the predetermined image content segmented from the location. In this content mask, the pixels of the predetermined image content portion are different from the pixels of the non-predetermined image content portion; for example, the pixels of the predetermined image content portion are 0, and the pixels of the non-predetermined image content portion are 1. Segmenting the content mask based on the detected region location in the infrared image allows for accurate extraction of the target infrared region image in subsequent steps.

[0072] In one embodiment, step S220, which involves segmenting the depth image based on the region location to obtain a content mask corresponding to a predetermined image content, includes: determining the target depth region corresponding to the region location in the depth image; and segmenting the region image corresponding to the target depth region from the depth image to obtain the content mask.

[0073] When infrared images and depth images are in the same spatial coordinate system, the region whose location is the same as that in the depth image can be identified as the target depth region, and the corresponding region image can be segmented to form a content mask.

[0074] When the infrared image and the depth image are not in the same spatial coordinate system: In one approach, if the infrared image is aligned to the depth image to obtain the target infrared image, and the location of this region is detected in the target infrared image, the region whose location is in the same area in the depth image can be determined as the target depth region; In another approach, if the depth image is aligned to the infrared image, the target infrared image is the initial infrared image, and the target depth image is the depth image aligned to the infrared image, then the region whose location is in the same area in the target depth image can be determined as the target depth region, and the corresponding region image of the target depth region can be segmented from the target depth image to form a content mask; In yet another approach, if the infrared image and the depth image are aligned to the same third spatial coordinate system, then the target infrared image and the target depth image are obtained, and the location of this region is detected in the target infrared image, then the region whose location is in the same area in the target depth image can be determined as the target depth region, and the corresponding region image of the target depth region can be segmented from the target depth image to form a content mask.

[0075] In step S240, the target infrared region image is extracted from the infrared region image based on the content mask.

[0076] The pixels of the predetermined image content portion in the content mask are different from the pixels of the non-predetermined image content portion. For example, the pixels of the predetermined image content portion are 0, and the pixels of the non-predetermined image content portion are 1. Based on the content mask, a target infrared region image containing only the predetermined image content portion in the content mask can be extracted from the infrared region image, thus obtaining a target infrared region image containing only the predetermined image content.

[0077] In one embodiment, step S240, extracting the target infrared region image from the infrared region image based on the content mask, includes: performing superposition operations on the content mask and the infrared region image to generate the target infrared region image.

[0078] The content mask and the infrared region image are superimposed, which means that the pixel values ​​of the content mask and the pixels in the infrared region image are superimposed. For example, the superposition operation is achieved by "AND" the pixel values ​​of the content mask and the pixels in the infrared region image. Then, through the superposition operation, the corresponding part of the image in the infrared region image of the predetermined image content in the content mask can be extracted from the infrared region image, so as to obtain the target infrared region image containing only the predetermined image content.

[0079] In one embodiment, step S240, extracting a target infrared region image from an infrared region image based on a content mask, includes: determining the outline of a predetermined image content portion in the content mask, and further segmenting the infrared region image based on the outline to obtain a target infrared region image containing only the predetermined image content.

[0080] In step S250, the target infrared region image is processed to obtain a detection result, which is used to indicate whether to use the infrared image for object recognition.

[0081] In one embodiment, step S250, which involves detecting and processing the target infrared region image to obtain a detection result, includes: detecting and processing the target infrared region image to obtain target image information; generating a detection result based on the target image information, wherein the detection result includes a first detection result or a second detection result, wherein the first detection result is used to indicate that the infrared image is used for object recognition, and the second detection result is used to indicate that the infrared image is not used for object recognition.

[0082] Target image information refers to the target information within the image information. This information may include at least one of the following: brightness information, contrast information, and pupil brightness information. Different detection methods can be used to detect and process the target infrared region image, thereby detecting the corresponding image information.

[0083] Image information can accurately reflect the identifiability of the target infrared region image, and thus a detection result can be generated based on the image information. If the detection result is the first detection result, it indicates that the infrared image can be used for object recognition; if the detection result is the second detection result, it indicates that the infrared image cannot be used for object recognition.

[0084] In one embodiment, the target image information includes infrared brightness; the detection processing of the target infrared region image to obtain the target image information includes: performing infrared brightness detection processing on the target infrared region image to obtain infrared brightness; generating a detection result based on the target image information includes: if the infrared brightness is within a predetermined brightness range, generating a first detection result; if the infrared brightness is outside the predetermined brightness range, generating a second detection result.

[0085] By performing infrared brightness detection processing on the target infrared region image, the average infrared brightness or the sum of the red brightness of all pixels in the target infrared region image can be statistically determined as the detected infrared brightness.

[0086] If the infrared brightness is within the predetermined brightness range, the target infrared region image is neither too dark nor too exposed, and the target infrared region image has good identifiability, thus enabling the accurate generation of the first detection result.

[0087] If the infrared brightness is outside the predetermined brightness range, the target infrared region image will be too dark or overexposed, resulting in poor recognizable target infrared region image, thus hindering the accurate generation of the second detection result.

[0088] In one embodiment, the target image information includes contrast; the detection processing of the target infrared region image to obtain the target image information includes: performing contrast detection processing on the target infrared region image to obtain the contrast; generating a detection result based on the target image information includes: if the contrast is within a predetermined contrast range, generating a first detection result; if the contrast is outside the predetermined contrast range, generating a second detection result.

[0089] In one embodiment, the predetermined image content is a face, the content mask is a face mask, and the target infrared region image is a target face infrared region image; infrared brightness detection processing is performed on the target infrared region image to obtain infrared brightness, including: performing infrared brightness detection processing on the target face infrared region image to obtain infrared brightness.

[0090] In this embodiment, the predetermined image content is a face, the content mask is a face mask, and then the extracted target infrared region image is the target face infrared region image. The infrared brightness is obtained by performing infrared brightness detection processing on the target face infrared region image. The infrared brightness can effectively reflect the identifiability of the infrared image in object recognition.

[0091] In one embodiment, the detection result is generated based on the target image information; after the detection result is obtained by performing detection processing based on the target infrared region image, the method further includes: if the detection result indicates that the infrared image is not used for object recognition, then obtaining the preset parameters of the infrared image acquisition device; determining the target parameters of the acquisition device based on the target image information and the preset parameters; and adjusting the acquisition device according to the target parameters.

[0092] Infrared image acquisition devices include infrared cameras, and preset parameters for the acquisition devices include camera focal length or angle.

[0093] In one example, determining the target parameters of the acquisition device based on the target image information and preset parameters may include: inputting the target image information and preset parameters into a pre-trained analysis model based on machine learning or deep learning to obtain the target parameters output by the analysis model.

[0094] In one example, determining the target parameters of the acquisition device based on the target image information and preset parameters may include: querying the target parameters that match the target image information and preset parameters from a preset parameter table.

[0095] After obtaining the target parameters, the acquisition device is adjusted according to the target parameters, and the adjusted acquisition device can then acquire infrared images that meet the recognition requirements.

[0096] In one embodiment, after performing detection processing based on the target infrared region image in step S250 and obtaining the detection result, the method further includes: if the detection result indicates that the infrared image is used for object recognition, then obtaining the target depth image and the target color image corresponding to the target object; and performing object recognition on the target object based on the infrared image, the target depth image, and the target color image.

[0097] If the detection result indicates that an infrared image is used for object recognition, then the infrared image is selected as the preferred infrared image, and the target depth image and target color image can be selected from depth images and color images taken for the target object.

[0098] Object recognition is performed based on infrared images, target depth images, and target color images. Specifically, infrared images and target depth images can be used to identify whether the target object is a moving object, and the target color image can be used to extract features to identify the object's identity.

[0099] In one approach, the infrared image, the target depth image, and the target color image can be a terminal (e.g., Figure 1 The terminal 102 shown can select the infrared image, target depth image, and target color image, and then upload them to the server (e.g., ...). Figure 1The server 101 shown performs object identification.

[0100] In one approach, the infrared image, the target depth image, and the target color image can be a terminal (e.g., Figure 1 The terminal 102 shown can perform object recognition based on the selected infrared image, target depth image and target color image.

[0101] In one approach, the terminal uploads the captured object image to the server (e.g., ...). Figure 1 The server 101 shown selects an infrared image, a target depth image, and a target color image from the object image, and then performs object recognition based on the selected infrared image, target depth image, and target color image.

[0102] According to one embodiment of this application, see [link to relevant documentation]. Figure 3 A resource transfer method includes steps S310 to S320.

[0103] Step S310: In response to the resource transfer instruction, a resource transfer operation is performed. The resource transfer operation is performed based on the object recognition result. The object recognition result is obtained by object recognition based on the infrared image of the target object. The infrared image is determined based on the detection result corresponding to the infrared region image of the target object. The infrared region image of the target object is extracted from the infrared region image corresponding to the region position based on the content mask. The region position is obtained by detecting predetermined image content in the infrared image. The content mask is obtained by segmenting from the depth image corresponding to the target object based on the region position.

[0104] Step S320: Play the resource transfer result information. The resource transfer result information is used to indicate the resource transfer result corresponding to the resource transfer operation.

[0105] A resource transfer instruction can be triggered by the target object sending voice to the terminal or by a control on the terminal interface. The terminal responds to the resource transfer instruction by executing a resource transfer operation, such as a payment operation.

[0106] Before performing a resource transfer operation in the terminal, the terminal can, according to Figure 2 In the embodiments described above, a detection result corresponding to an infrared image of a target object is obtained, and then an infrared image indicating that object recognition can be used is obtained, and an object recognition result is obtained based on the infrared image.

[0107] If the object recognition result is successful, the resource transfer operation will succeed; if the object recognition result is unsuccessful, the resource transfer operation will fail.

[0108] After the resource transfer operation is completed, the terminal can display the resource transfer result information on the screen or play the resource transfer result information by voice to prompt the resource transfer result corresponding to the resource transfer operation, such as payment success or payment recognition.

[0109] Furthermore, during resource transfer, object recognition results can be obtained efficiently and successfully, thereby completing the resource transfer efficiently and successfully.

[0110] In one embodiment, in response to a resource transfer instruction, a resource transfer operation is performed, including: in response to the resource transfer instruction, acquiring an object image corresponding to a target object, the object image including an infrared image, a target color image, and a target depth image; playing an object recognition result, the object recognition result being obtained by object recognition based on the target infrared image, target color image, and target depth image; and performing a resource transfer operation, the resource transfer operation being performed based on the object recognition result.

[0111] In response to a resource transfer command, the terminal can activate an image acquisition device (e.g., a camera) to acquire an image of the target object. From the acquired object image, the terminal can select an infrared image that indicates the detection result and can use it for object recognition. The terminal can also select a target color image and a target depth image.

[0112] After selecting the infrared image, target color image, and target depth image, in one approach, the infrared image, target depth image, and target color image can be a terminal (e.g., Figure 1 The terminal 102 shown can select the infrared image, target depth image, and target color image, and then upload them to the server (e.g., ...). Figure 1 The server 101 shown performs object recognition. In one approach, the infrared image, target depth image, and target color image can be a terminal (e.g., Figure 1 The terminal 102 shown is selected from the selected infrared image, target depth image, and target color image. In one embodiment, the terminal uploads the acquired object image to a server (e.g., ...). Figure 1 The server 101 shown selects an infrared image, a target depth image, and a target color image from the object image, and then performs object recognition based on the selected infrared image, target depth image, and target color image.

[0113] Furthermore, the terminal can accurately perform resource transfer operations based on the object recognition results.

[0114] The above embodiments are further described below with reference to the object recognition process in an application scenario. See also... Figure 4 and Figure 5 , Figure 4 The flowchart for object recognition in this scenario is shown. Figure 5 This diagram illustrates the extraction of the target infrared region image in this scenario. The scenario uses facial recognition-based payment in a terminal as an example. In this scenario, the resource transfer instruction is a payment instruction, the predetermined image content is a face, the content mask is a face mask, and the target infrared region image is the target face infrared region image.

[0115] See Figure 4 In this scenario, the payment process based on facial recognition at the terminal may include:

[0116] In response to the payment instruction, an object image corresponding to the target object is acquired; after the first frame of the object image is acquired, steps S410 to S470 can be executed, and the infrared image with the detection result being the first detection result is selected. In addition, after step S470, a target color image and a target depth image can be selected from the acquired object images.

[0117] In step S410, the terminal can "obtain the infrared image and depth image corresponding to the target object" from the collected object image.

[0118] Steps S420 to S430 involve detecting the location of the face region from the infrared image.

[0119] Step S420: Align the infrared image with the depth image to obtain the aligned target infrared image. The target infrared image is as follows: Figure 5 As shown in the infrared image, the depth image is as follows Figure 5 The depth image is shown in the image.

[0120] Step S430: Detect the region location corresponding to the face in the target infrared image. Specifically, the region location corresponding to the face is detected directly from the target infrared image. For example, the target infrared image is input into a content detection model to detect the location corresponding to the face, and the detected location is directly determined as the region location corresponding to the face. The region location is as follows: Figure 5 The area highlighted in the mid-infrared image.

[0121] Step S440: Segment the depth image based on the region location to obtain a face mask corresponding to the face. Specifically, determine the target depth region corresponding to the region location in the depth image; segment the region image corresponding to the target depth region from the depth image to obtain the face mask. The face mask is as follows: Figure 5 The face mask is shown in the image.

[0122] Step S450: Obtain the infrared region image corresponding to the region location, and extract the target face infrared region image from the infrared region image based on the face mask. Specifically, the face mask and the infrared region image are superimposed to generate the target face infrared region image. The target face infrared region image is as follows: Figure 5 The infrared image of the target face is shown.

[0123] Steps S460 to S470 involve detecting the infrared region image of the target face to obtain a detection result. The detection result is used to indicate whether to use the infrared image for object recognition.

[0124] Step S460: Perform infrared brightness detection on the infrared region image of the target face.

[0125] Specifically, the infrared region image of the target is detected and processed to obtain target image information. The target image information includes infrared brightness. Step S460, detecting and processing the infrared region image of the target to obtain target image information, includes: performing infrared brightness detection processing on the infrared region image of the target to obtain infrared brightness. Performing infrared brightness detection processing on the infrared region image of the target to obtain infrared brightness includes: performing infrared brightness detection processing on the infrared region image of the target face to obtain infrared brightness.

[0126] Step S470: Generate detection results based on infrared brightness.

[0127] Specifically, a detection result is generated based on the target image information. The detection result includes a first detection result or a second detection result, wherein the first detection result indicates that infrared imagery is used for object recognition, and the second detection result indicates that infrared imagery is not used for object recognition. Generating the detection result based on the target image information includes: generating a first detection result if the infrared brightness is within a predetermined brightness range; and generating a second detection result if the infrared brightness is outside the predetermined brightness range.

[0128] The acquired infrared images can be detected according to the acquisition sequence based on steps S410 to S470. After step S470, if the detection result indicates that the infrared image is used for object recognition (i.e., the detection result is the first detection result), the target depth image and target color image corresponding to the target object can be obtained from the acquired object image; the target object is recognized based on the infrared image, target depth image and target color image.

[0129] If the detection result indicates that infrared images should be used for object recognition, then the infrared image is selected as the preferred infrared image. The target depth image and target color image can be selected from depth images and color images taken of the target object. Object recognition is performed based on the infrared image, target depth image, and target color image. Specifically, the infrared image and target depth image can be used to identify whether the target object is a moving object, and features can be extracted from the target color image to identify the object's identity.

[0130] In one approach, the infrared image, the target depth image, and the target color image can be a terminal (e.g., Figure 1 The terminal 102 shown can select the infrared image, target depth image, and target color image, and then upload them to the server (e.g., ...). Figure 1 The server 101 shown performs object recognition. In one approach, the infrared image, target depth image, and target color image can be a terminal (e.g., Figure 1 The terminal 102 shown is selected from the selected infrared image, target depth image, and target color image. In one embodiment, the terminal uploads the acquired object image to a server (e.g., ...). Figure 1 The server 101 shown selects an infrared image, a target depth image, and a target color image from the object image, and then performs object recognition based on the selected infrared image, target depth image, and target color image.

[0131] Object recognition is performed based on infrared images, target depth images, and target color images. Specifically, infrared images and target depth images can be used to identify whether the target object is a moving object, and the target color image can be used to extract features to identify the object's identity.

[0132] Afterwards, the terminal can display the object recognition results, which are obtained by identifying the object based on the target's infrared image, color image, and depth image. The payment operation is then executed based on the object recognition results. Specifically, if the object recognition result is successful, the payment operation succeeds; if the object recognition result is unsuccessful, the payment operation fails.

[0133] In this way, by applying the embodiments of this application in this scenario, at least the following beneficial effects can be achieved: the detection accuracy of infrared images can be effectively improved, the success rate of object recognition can be increased, the payment efficiency and success rate can be improved when making payments based on facial recognition, and the user experience can be effectively improved.

[0134] To facilitate better implementation of the object recognition method provided in this application, this application also provides an object recognition device based on the above-described object recognition method. The meanings of the terms used are the same as in the object recognition method described above, and specific implementation details can be found in the descriptions within the method embodiments. Figure 6 A block diagram of an object recognition device according to an embodiment of this application is shown. Figure 7 A block diagram of a resource transfer apparatus according to another embodiment of this application is shown.

[0135] like Figure 6 As shown, the object recognition device 500 may include an image acquisition module 510, a region acquisition module 520, a segmentation module 530, an extraction module 540, and a detection module 550.

[0136] Image acquisition module 510 can be used to acquire infrared image and depth image corresponding to target object; region acquisition module 520 can be used to detect the region position corresponding to predetermined image content from the infrared image and acquire infrared region image corresponding to the region position; segmentation module 530 can be used to segment the depth image according to the region position to obtain content mask corresponding to the predetermined image content; extraction module 540 can be used to extract target infrared region image from infrared region image according to content mask; detection module 550 can be used to perform detection processing based on target infrared region image to obtain detection result, the detection result being used to indicate whether to use infrared image for object recognition.

[0137] In some embodiments of this application, the region acquisition module includes: an alignment unit for aligning the infrared image with the depth image to obtain an aligned target infrared image; and a position detection unit for detecting the region position corresponding to the predetermined image content in the target infrared image.

[0138] In some embodiments of this application, the segmentation module includes: a target region determination unit, configured to determine a target depth region corresponding to the location of the region in the depth image; and a content mask generation unit, configured to segment the region image corresponding to the target depth region from the depth image to obtain the content mask.

[0139] In some embodiments of this application, the position detection unit is configured to: acquire a color image corresponding to the target object, and align the color image with the target infrared image to obtain a target color image; detect the position of a color region corresponding to predetermined image content in the target color image; and detect the position of the region corresponding to the predetermined image content in the target infrared image based on the position of the color region.

[0140] In some embodiments of this application, the extraction module is used to: perform superposition operations on the content mask and the infrared region image to generate the target infrared region image.

[0141] In some embodiments of this application, the detection module includes: a target image information detection unit, used to perform detection processing on the target infrared region image to obtain target image information; and a detection result analysis unit, used to generate the detection result based on the target image information, wherein the detection result includes a first detection result or a second detection result, wherein the first detection result is used to indicate that the infrared image is used for object recognition, and the second detection result is used to indicate that the infrared image is not used for object recognition.

[0142] In some embodiments of this application, the target image information includes infrared brightness; the target image information detection unit is configured to: perform infrared brightness detection processing on the target infrared region image to obtain the infrared brightness; the detection result analysis unit is configured to: generate the first detection result if the infrared brightness is within a predetermined brightness range; and generate the second detection result if the infrared brightness is outside the predetermined brightness range.

[0143] In some embodiments of this application, the predetermined image content is a face, the content mask is a face mask, and the target infrared region image is a target face infrared region image; the target image information detection unit is used to: perform infrared brightness detection processing on the target face infrared region image to obtain the infrared brightness.

[0144] In some embodiments of this application, the detection result is generated based on target image information, and the object recognition device further includes an adjustment module for: if the detection result indicates that the infrared image is not used for object recognition, then obtaining preset parameters of the infrared image acquisition device; determining target parameters of the acquisition device based on the target image information and the preset parameters; and adjusting the acquisition device based on the target parameters.

[0145] In some embodiments of this application, the object recognition device further includes a recognition module, configured to: if the detection result indicates that the infrared image is used for object recognition, acquire a target depth image and a target color image corresponding to the target object; and perform object recognition on the target object based on the infrared image, the target depth image, and the target color image.

[0146] like Figure 7 As shown, the resource transfer device 600 may include a transfer module 610 and a notification module 620.

[0147] The transfer module 610 can be used to execute a resource transfer operation in response to a resource transfer instruction. The resource transfer operation is performed based on the object recognition result, which is obtained by object recognition based on the infrared image of the target object. The infrared image is determined based on the detection result corresponding to the target infrared region image. The target infrared region image is extracted from the infrared region image corresponding to the region position based on the content mask. The region position is obtained by detecting predetermined image content in the infrared image. The content mask is obtained by segmenting from the depth image corresponding to the target object based on the region position. The prompting module 620 can be used to play resource transfer result information, which is used to prompt the resource transfer result corresponding to the resource transfer operation.

[0148] In some embodiments of this application, the transfer module 610 includes: a collection unit, configured to collect an object image corresponding to the target object in response to a resource transfer instruction, the object image including the infrared image, the target color image, and the target depth image; a recognition unit, configured to play an object recognition result, the object recognition result being obtained by object recognition based on the infrared image, the target color image, and the target depth image; and an execution unit, configured to execute a resource transfer operation, the resource transfer operation being executed based on the object recognition result.

[0149] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0150] Furthermore, embodiments of this application also provide an electronic device, which can be a terminal or a server, such as... Figure 8 As shown, it illustrates a schematic diagram of the structure of an electronic device involved in an embodiment of this application. Specifically:

[0151] The electronic device may include components such as a processor 701 with one or more processing cores, a memory 702 with one or more computer-readable storage media, a power supply 703, and an input unit 704. Those skilled in the art will understand that... Figure 8 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0152] The processor 701 is the control center of the electronic device. It connects to various parts of the computer device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 702, and by calling data stored in the memory 702, it performs various functions of the computer device and processes data, thereby detecting the electronic device. Optionally, the processor 701 may include one or more processing cores; preferably, the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user page, and application programs, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 701.

[0153] The memory 702 can be used to store software programs and modules. The processor 701 executes various functional applications and data processing by running the software programs and modules stored in the memory 702. The memory 702 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 702 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 702 may also include a memory controller to provide the processor 701 with access to the memory 702.

[0154] The electronic device also includes a power supply 703 that supplies power to the various components. Preferably, the power supply 703 can be logically connected to the processor 701 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 703 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0155] The electronic device may also include an input unit 704, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0156] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 701 in the electronic device loads the executable files corresponding to the processes of one or more computer programs into the memory 702 according to the following instructions, and the processor 701 runs the computer programs stored in the memory 702, thereby realizing the various functions of the foregoing embodiments of this application.

[0157] In one embodiment, the processor 701 may perform the following actions: acquiring an infrared image and a depth image corresponding to a target object; detecting the region location corresponding to predetermined image content from the infrared image and acquiring an infrared region image corresponding to the region location; segmenting the depth image according to the region location to obtain a content mask corresponding to the predetermined image content; extracting a target infrared region image from the infrared region image according to the content mask; performing detection processing on the target infrared region image to obtain a detection result, wherein the detection result is used to indicate whether the infrared image is used for object recognition.

[0158] In another embodiment, for example, the processor 701 may execute: in response to a resource transfer instruction, perform a resource transfer operation, the resource transfer operation being performed based on an object recognition result, the object recognition result being obtained by object recognition based on an infrared image of a target object, the infrared image being determined based on a detection result corresponding to a target infrared region image, the target infrared region image being extracted from an infrared region image corresponding to a region location based on a content mask, the region location being obtained by detecting predetermined image content in the infrared image, and the content mask being segmented from a depth image corresponding to the target object based on the region location; and play resource transfer result information, the resource transfer result information being used to indicate the resource transfer result corresponding to the resource transfer operation.

[0159] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by a computer program, or by a computer program controlling related hardware. The computer program can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0160] Therefore, embodiments of this application also provide a computer-readable storage medium storing a computer program that can be loaded by a processor to perform the steps in any of the methods provided in embodiments of this application.

[0161] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0162] Since the computer program stored in the computer-readable storage medium can execute the steps in any of the methods provided in the embodiments of this application, the beneficial effects that the methods provided in the embodiments of this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0163] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations of the above embodiments of this application.

[0164] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0165] It should be understood that this application is not limited to the embodiments described above and shown in the accompanying drawings, but various modifications and changes can be made without departing from its scope.

Claims

1. An object recognition method, characterized in that, include: Acquire the infrared and depth images corresponding to the target object; Detect the location of a predetermined image content region from the infrared image, and obtain the infrared region image corresponding to the region location; The region image corresponding to the target depth region is segmented from the depth image to obtain the content mask corresponding to the predetermined image content. The target depth region is the region in the depth image corresponding to the location of the region. Extract the target infrared region image from the infrared region image based on the content mask; The infrared image of the target region is processed to obtain a detection result, which is used to indicate whether the infrared image is used for object recognition.

2. The method according to claim 1, characterized in that, The detection of the region location of predetermined image content from the infrared image includes: The infrared image and the depth image are aligned to obtain the aligned target infrared image; Detect the location of the region corresponding to the predetermined image content in the target infrared image.

3. The method according to claim 2, characterized in that, The detection of the region location corresponding to the predetermined image content in the target infrared image includes: A color image corresponding to the target object is obtained, and the color image is aligned with the target infrared image to obtain a target color image; Detect the position of the color region corresponding to the predetermined image content in the target color image; The location of the region corresponding to the predetermined image content in the target infrared image is detected based on the location of the colored region.

4. The method according to claim 1, characterized in that, Extracting the target infrared region image from the infrared region image based on the content mask includes: The content mask is superimposed on the infrared region image to generate the target infrared region image.

5. The method according to claim 1, characterized in that, The detection processing of the target infrared region image to obtain the detection result includes: The target infrared region image is processed to obtain target image information; The detection result is generated based on the target image information. The detection result includes a first detection result or a second detection result, wherein the first detection result is used to indicate that the infrared image is used for object recognition, and the second detection result is used to indicate that the infrared image is not used for object recognition.

6. The method according to claim 5, characterized in that, The target image information includes infrared brightness; the detection and processing of the target infrared region image to obtain the target image information includes: The infrared brightness is obtained by performing infrared brightness detection processing on the target infrared region image; The step of generating the detection result based on the target image information includes: If the infrared brightness is within a predetermined brightness range, then the first detection result is generated; If the infrared brightness is outside the predetermined brightness range, then the second detection result is generated.

7. The method according to claim 6, characterized in that, The predetermined image content is a face, the content mask is a face mask, and the target infrared region image is a target face infrared region image; The infrared brightness detection processing of the target infrared region image to obtain the infrared brightness includes: The infrared brightness is obtained by performing infrared brightness detection processing on the infrared region image of the target face.

8. The method according to any one of claims 1 to 7, characterized in that, The detection result is generated based on the target image information; after processing the target infrared region image to obtain the detection result, the method further includes: If the detection result indicates that the infrared image is not used for object recognition, then the preset parameters of the infrared image acquisition device are obtained; The target parameters of the acquisition device are determined based on the target image information and the preset parameters. Adjust the acquisition device according to the target parameters.

9. The method according to any one of claims 1 to 7, characterized in that, After processing the target infrared region image to obtain the detection result, the method further includes: If the detection result indicates that the infrared image is used for object recognition, then the target depth image and target color image corresponding to the target object are obtained; The target object is identified based on the infrared image, the target depth image, and the target color image.

10. A resource transfer method, characterized in that, include: In response to a resource transfer command, a resource transfer operation is executed. The resource transfer operation is performed based on an object recognition result, which is obtained by object recognition based on an infrared image of a target object. The infrared image is determined based on the detection result corresponding to the target infrared region image. The target infrared region image is extracted from the infrared region image corresponding to the region location based on a content mask. The region location is obtained by detecting predetermined image content in the infrared image. The content mask is obtained by segmenting from the depth image corresponding to the target object based on the region location. Play the resource transfer result information, which is used to indicate the resource transfer result corresponding to the resource transfer operation.

11. The method according to claim 10, characterized in that, The step of performing a resource transfer operation in response to a resource transfer instruction includes: In response to a resource transfer command, an object image corresponding to the target object is acquired, the object image including the infrared image, the target color image, and the target depth image; Play the object recognition result, which is obtained by object recognition based on the infrared image, the target color image, and the target depth image; Perform a resource transfer operation, which is performed based on the object identification result.

12. An object recognition device, characterized in that, include: The image acquisition module is used to acquire the infrared image and depth image corresponding to the target object; The region acquisition module is used to detect the region location corresponding to the predetermined image content in the infrared image, and acquire the infrared region image corresponding to the region location; The segmentation module is used to segment the region image corresponding to the target depth region from the depth image to obtain the content mask corresponding to the predetermined image content, wherein the target depth region is the region in the depth image corresponding to the region location; The extraction module is used to extract the target infrared region image from the infrared region image based on the content mask; The detection module is used to perform detection processing based on the target infrared region image to obtain a detection result, which is used to indicate whether the infrared image is used for object recognition.

13. The apparatus according to claim 12, characterized in that, The region acquisition module includes: An alignment unit is used to align the infrared image with the depth image to obtain an aligned target infrared image. A position detection unit is used to detect the location of the region corresponding to the predetermined image content in the target infrared image.

14. The apparatus according to claim 13, characterized in that, The position detection unit is configured to: acquire a color image corresponding to the target object, and align the color image with the target infrared image to obtain a target color image; detect the position of a color region corresponding to predetermined image content in the target color image; and detect the position of the region corresponding to the predetermined image content in the target infrared image based on the position of the color region.

15. The apparatus according to claim 12, characterized in that, The extraction module is used to: perform superposition operations on the content mask and the infrared region image to generate the target infrared region image.

16. The apparatus according to claim 12, characterized in that, The detection module includes: The target image information detection unit is used to detect and process the infrared region image of the target to obtain target image information; The detection result analysis unit is used to generate the detection result based on the target image information. The detection result includes a first detection result or a second detection result, wherein the first detection result is used to indicate that the infrared image is used for object recognition, and the second detection result is used to indicate that the infrared image is not used for object recognition.

17. The apparatus according to claim 16, characterized in that, The target image information includes infrared brightness; The target image information detection unit is used to: perform infrared brightness detection processing on the target infrared region image to obtain the infrared brightness; The detection result analysis unit is configured to: generate the first detection result if the infrared brightness is within a predetermined brightness range; and generate the second detection result if the infrared brightness is outside the predetermined brightness range.

18. The apparatus according to claim 17, characterized in that, The predetermined image content is a face, the content mask is a face mask, and the target infrared region image is a target face infrared region image; The target image information detection unit is used to: perform infrared brightness detection processing on the infrared region image of the target face to obtain the infrared brightness.

19. The apparatus according to any one of claims 12 to 18, characterized in that, The detection result is generated based on the target image information. The object recognition device further includes: The adjustment module is configured to: if the detection result indicates that the infrared image is not used for object recognition, obtain the preset parameters of the infrared image acquisition device; determine the target parameters of the acquisition device based on the target image information and the preset parameters; and adjust the acquisition device based on the target parameters.

20. The apparatus according to any one of claims 12 to 18, characterized in that, The object recognition device further includes: The recognition module is configured to: if the detection result indicates that the infrared image is used for object recognition, acquire the target depth image and the target color image corresponding to the target object; and perform object recognition on the target object based on the infrared image, the target depth image and the target color image.

21. An object recognition device, characterized in that, The device includes: A transfer module is used to execute a resource transfer operation in response to a resource transfer command. The resource transfer operation is performed based on the object recognition result, which is obtained by object recognition based on the infrared image of the target object. The infrared image is determined based on the detection result corresponding to the target infrared region image. The target infrared region image is extracted from the infrared region image corresponding to the region position based on the content mask. The region position is obtained by detecting predetermined image content in the infrared image. The content mask is obtained by segmenting from the depth image corresponding to the target object based on the region position. A prompting module is used to play resource transfer result information, which is used to prompt the resource transfer result corresponding to the resource transfer operation.

22. The apparatus according to claim 21, characterized in that, The transfer module includes: The acquisition unit is used to acquire an object image corresponding to the target object in response to a resource transfer command. The object image includes the infrared image, the target color image, and the target depth image. The recognition unit is used to play the object recognition result, which is obtained by recognizing the object based on the infrared image, the target color image, and the target depth image. An execution unit is used to perform a resource transfer operation, which is performed based on the object identification result.

23. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by the computer's processor, causes the computer to perform the method described in any one of claims 1 to 11.

24. An electronic device, characterized in that, include: Memory, which stores computer programs; A processor reads a computer program stored in memory to perform the method described in any one of claims 1 to 11.

25. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 11.

Images