Object determination method and device, storage medium and electronic equipment

Abstract

The invention discloses an object determination method and device, a storage medium and electronic equipment. The method relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring a target luminous remote sensing image of a target area; processing the target noctilucent remote sensing image through a target algorithm to obtain a plurality of target remote sensing sub-images; determining the total number of the lamplight fishing boats in the target luminous remote sensing image according to the target indexes corresponding to the plurality of target remote sensing sub-images; and if the total number of the lamplight fishing boats is greater than a second preset threshold value and the acquisition time corresponding to the target luminous remote sensing image is in the no-fishing period, determining that the target object is an object with risk in repayment. Through the method and the device, the problem of relatively low accuracy of determining the risk user caused by determining whether the loan user of the fishing industry is the risk user or not by adopting a universal method in the related technology is solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method and device for determining an object, a storage medium, and an electronic device. Background Art

[0002] With the development of economy and the growth of population, fishery has become one of the important resource industries. However, due to problems such as overfishing and environmental pollution, many fishery enterprises are facing difficulties. Therefore, it is very important to conduct risk assessment on the lending of fishery enterprises. By conducting risk assessment on the lending of fishery enterprises, the risk of financial institutions can be effectively reduced and the investment efficiency can be improved. And after issuing loans to fishing industry loan users, financial institutions also need to conduct risk detection on fishing industry loan users to reduce financial risks. However, the prior art often adopts a general method to determine whether a fishing industry loan user is a risky user. For example, the capital flow of the fishing industry loan user is used to detect whether the user is a risky user, but this method is inaccurate for fishing industry loan users.

[0003] With regard to the problem that the common method used in the related art to determine whether a fishing industry loan user is a risky user leads to a relatively low accuracy in determining risky users, no effective solution has been proposed so far. Summary of the invention

[0004] The main purpose of the present application is to provide a method and device for determining an object, a storage medium and an electronic device, so as to solve the problem that a common method is used in the related art to determine whether a fishing industry loan user is a risky user, resulting in a relatively low accuracy in determining risky users.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for determining an object is provided. The method comprises: obtaining a target night light remote sensing image of a target area, wherein the target area is an operating area of ​​a light fishing boat, wherein the light fishing boat is a fishing boat owned by a target object, and the target object is an object that obtains a loan based on the light fishing boat in a target financial institution; processing the target night light remote sensing image through a target algorithm to obtain a plurality of target remote sensing sub-images, wherein the probability that an image corresponding to the light fishing boat exists in the plurality of target remote sensing sub-images is greater than a first preset threshold; determining the total number of the light fishing boats in the target night light remote sensing image based on a target index corresponding to the plurality of target remote sensing sub-images, wherein the target index is determined by the light brightness values ​​in the plurality of target remote sensing sub-images; if the total number of the light fishing boats is greater than a second preset threshold, and the acquisition time corresponding to the target night light remote sensing image is in the fishing ban period, then determining the target object as an object with repayment risk.

[0006] Furthermore, the target night light remote sensing image is processed by a target algorithm to obtain a plurality of target remote sensing sub-images, including: identifying the target night light remote sensing image by the target algorithm to obtain a first label corresponding to each pixel in the target night light remote sensing image, wherein the first label is used to characterize whether the pixel is a pixel of the image corresponding to the lighted fishing boat; segmenting the target night light remote sensing image according to the first label corresponding to each pixel in the target night light remote sensing image to obtain the plurality of target remote sensing sub-images.

[0007] Furthermore, the target night light remote sensing image is identified by the target algorithm to obtain a first label corresponding to each pixel in the target night light remote sensing image, including: performing brightness feature extraction on the target night light remote sensing image by the first feature extraction layer in the target algorithm to obtain a brightness feature vector; performing shape feature extraction on the target night light remote sensing image by the first feature extraction layer in the target algorithm to obtain a shape feature vector; processing the brightness feature vector and the shape feature vector by the fully connected layer in the target algorithm to obtain a first label corresponding to each pixel.

[0008] Furthermore, determining the total number of the lighted fishing boats in the target night light remote sensing image based on the target indices corresponding to the multiple target remote sensing sub-images includes: for each target remote sensing sub-image, performing median filtering on the target remote sensing sub-image to obtain a processed target remote sensing sub-image; calculating based on the light intensity value of the processed target remote sensing sub-image and the light intensity values ​​of the multiple target remote sensing sub-images to obtain a target index corresponding to a pixel point in each target remote sensing sub-image; determining the number of lighted fishing boats in the target remote sensing sub-image based on the target index; and determining the total number of lighted fishing boats based on the number of lighted fishing boats in the target remote sensing sub-image.

[0009] Furthermore, determining the number of fishing boats with lights in the target remote sensing sub-image based on the target index includes: for each pixel point in the target remote sensing sub-image, calculating the target index within the target range centered on the pixel point to obtain a relative deviation value corresponding to each pixel point; segmenting the target remote sensing sub-image based on the relative deviation value corresponding to each pixel point to obtain a segmented target remote sensing sub-image; and determining the number of fishing boats with lights in the target remote sensing sub-image based on the light intensity value of the segmented target remote sensing sub-image.

[0010] Furthermore, determining the number of fishing boats with lights in the target remote sensing sub-image based on the light intensity values ​​of the segmented target remote sensing sub-image includes: performing mean filtering on the segmented target remote sensing sub-image to obtain a filtered target remote sensing sub-image; performing calculations based on the light intensity values ​​of the segmented target remote sensing sub-image and the light intensity values ​​of the filtered target remote sensing sub-image to obtain target light intensity values ​​corresponding to pixel points in the segmented target remote sensing sub-image; and determining the number of fishing boats with lights in the target remote sensing sub-image based on the target light intensity values.

[0011] Furthermore, determining the number of fishing boats with lights in the target remote sensing sub-image based on the target light intensity value includes: determining a second label corresponding to a pixel point in the target remote sensing sub-image based on the target light intensity value and a preset intensity threshold; and determining the number of fishing boats with lights in the target remote sensing sub-image based on the second label.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a device for determining an object is provided. The device comprises: an acquisition unit, used to acquire a target night light remote sensing image of a target area, wherein the target area is an operating area of ​​light fishing boats, wherein the light fishing boats are fishing boats owned by the target object, and the target object is an object that obtains a loan based on the light fishing boats in a target financial institution; a processing unit, used to process the target night light remote sensing image through a target algorithm to obtain a plurality of target remote sensing sub-images, wherein the probability that the image corresponding to the light fishing boat exists in the plurality of target remote sensing sub-images is greater than a first preset threshold; a first determination unit, used to determine the total number of the light fishing boats in the target night light remote sensing image according to the target index corresponding to the plurality of target remote sensing sub-images, wherein the target index is determined by the light brightness values ​​in the plurality of target remote sensing sub-images; a second determination unit, used to determine that the target object is an object with repayment risk if the total number of the light fishing boats is greater than a second preset threshold and the acquisition time corresponding to the target night light remote sensing image is in the fishing ban period.

[0013] Furthermore, the processing unit includes: an identification subunit, used to identify the target night light remote sensing image through the target algorithm, and obtain a first label corresponding to each pixel point in the target night light remote sensing image, wherein the first label is used to characterize whether the pixel point is a pixel point of the image corresponding to the light fishing boat; a segmentation subunit, used to segment the target night light remote sensing image according to the first label corresponding to each pixel point in the target night light remote sensing image, and obtain the multiple target remote sensing sub-images.

[0014] Furthermore, the identification subunit includes: a first extraction module, used to perform brightness feature extraction on the target night light remote sensing image through the first feature extraction layer in the target algorithm to obtain a brightness feature vector; a second extraction module, used to perform shape feature extraction on the target night light remote sensing image through the first feature extraction layer in the target algorithm to obtain a shape feature vector; a processing module, used to process the brightness feature vector and the shape feature vector through the fully connected layer in the target algorithm to obtain a first label corresponding to each pixel point.

[0015] Furthermore, the first determination unit includes: a processing subunit, used to perform median filtering on each target remote sensing sub-image to obtain a processed target remote sensing sub-image; a calculation subunit, used to perform calculations based on the light intensity value of the processed target remote sensing sub-image and the light intensity values ​​of the multiple target remote sensing sub-images to obtain a target index corresponding to a pixel point in each target remote sensing sub-image; a first determination subunit, used to determine the number of light fishing boats in the target remote sensing sub-image based on the target index; and a second determination subunit, used to determine the total number of light fishing boats based on the number of light fishing boats in the target remote sensing sub-image.

[0016] Furthermore, the first determination subunit includes: a calculation module, which is used to calculate, for each pixel point in the target remote sensing sub-image, a target index within a target range centered on the pixel point, to obtain a relative deviation value corresponding to each pixel point; a segmentation module, which is used to segment the target remote sensing sub-image according to the relative deviation value corresponding to each pixel point, to obtain a segmented target remote sensing sub-image; and a determination module, which is used to determine the number of light fishing boats in the target remote sensing sub-image according to the light intensity value of the segmented target remote sensing sub-image.

[0017] Furthermore, the determination module includes: a processing submodule, used to perform mean filtering on the segmented target remote sensing subimage to obtain a filtered target remote sensing subimage; a calculation submodule, used to perform calculations based on the light intensity values ​​of the segmented target remote sensing subimage and the light intensity values ​​of the filtered target remote sensing subimage to obtain target light intensity values ​​corresponding to pixel points in the segmented target remote sensing subimage; and a determination submodule, used to determine the number of lighted fishing boats in the target remote sensing subimage based on the target light intensity values.

[0018] Furthermore, the determination submodule includes: a first determination submodule, used to determine the second label corresponding to the pixel point in the target remote sensing subimage based on the target light intensity value and a preset intensity threshold; a second determination submodule, used to determine the number of lighted fishing boats in the target remote sensing subimage based on the second label.

[0019] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein when the program is run, any one of the above-mentioned methods for determining an object is executed.

[0020] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, the storage medium storing a program, wherein when the program is running, the device where the storage medium is located is controlled to execute any one of the above object determination methods.

[0021] Through the present application, the following steps are adopted: obtaining a target night light remote sensing image of a target area, wherein the target area is an operating area of ​​light fishing boats, wherein the light fishing boats are fishing boats owned by a target object, and the target object is an object that obtains a loan based on the light fishing boats at a target financial institution; processing the target night light remote sensing image through a target algorithm to obtain a plurality of target remote sensing sub-images, wherein the probability that an image corresponding to the light fishing boat exists in the plurality of target remote sensing sub-images is greater than a first preset threshold; determining the total number of light fishing boats in the target night light remote sensing image based on a target index corresponding to the plurality of target remote sensing sub-images, wherein the target index is determined by the light brightness values ​​in the plurality of target remote sensing sub-images; if the total number of light fishing boats is greater than a second preset threshold, and the acquisition time corresponding to the target night light remote sensing image is in a fishing ban period, then determining the target object as an object with repayment risk, solves the problem of low accuracy in determining risk users caused by a general method used in the related art to determine whether a fishing industry loan user is a risky user.

[0022] In this scheme, target night light remote sensing images are collected in the operating area of ​​light fishing boats, and multiple target remote sensing sub-images where light fishing boats may exist are cropped out through a target algorithm. Then, the total number of light fishing boats is determined based on the light brightness values ​​in the multiple target remote sensing sub-images. Finally, based on the total number of light fishing boats and the acquisition time corresponding to the target night light remote sensing images, it is determined whether the target object is an object with repayment risk. The total number of light fishing boats and the acquisition time can be used to determine whether the target object has engaged in illegal fishing, thereby accurately judging whether the target object is a risky user, thereby achieving the effect of improving the accuracy of identifying risky users. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1 The process of the method for determining an object provided in the embodiment of the present application is as follows Figure 1 ;

[0025] Figure 2 The process of the method for determining an object provided in the embodiment of the present application is as follows Figure 2 ;

[0026] Figure 3 is a schematic diagram of a device for determining an object provided in an embodiment of the present application;

[0027] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0029] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0032] The present invention is described below in conjunction with preferred implementation steps. Figure 1 The process of the method for determining an object provided in the embodiment of the present application is as follows Figure 1 ,like Figure 1 As shown, the method comprises the following steps:

[0033] Step S101, obtaining a target night light remote sensing image of a target area, wherein the target area is an operating area of ​​a light fishing boat, wherein the light fishing boat is a fishing boat owned by a target object, and the target object is an object that obtains a loan based on the light fishing boat in a target financial institution;

[0034] Optionally, the user (i.e., the target object mentioned above) can apply for a loan from a financial institution based on the light fishing boat. After the financial institution issues the loan to the user, in order to avoid the risk of repayment caused by the user's illegal fishing, the behavior of the light fishing boat needs to be tracked. Therefore, the target night light remote sensing image of the operating area of ​​the light fishing boat is collected. The night light remote sensing image is used to detect whether the light fishing boat is working in the operating area.

[0035] Step S102, processing the target night light remote sensing image by a target algorithm to obtain a plurality of target remote sensing sub-images, wherein the probability that an image corresponding to a lighted fishing boat exists in the plurality of target remote sensing sub-images is greater than a first preset threshold;

[0036] Optionally, after obtaining the target night light remote sensing image of the operation area, a target algorithm can be used to identify whether there is a lighted fishing boat in the target night light remote sensing image, and then the night light remote sensing image corresponding to the image that may contain the lighted fishing boat is cropped to obtain the above-mentioned multiple target remote sensing sub-images. It should be noted that the above-mentioned target algorithm can be an image segmentation algorithm.

[0037] Step S103, determining the total number of lighted fishing boats in the target night light remote sensing image according to the target indexes corresponding to the multiple target remote sensing sub-images, wherein the target index is determined by the light brightness values ​​in the multiple target remote sensing sub-images;

[0038] Optionally, after segmenting the target remote sensing sub-image where lighted fishing boats may exist, the total number of lighted fishing boats in the target night light remote sensing image is determined by the target index corresponding to the target remote sensing sub-image. It should be noted that the target index is determined by the light brightness value in the target remote sensing sub-image. The light brightness in the remote sensing image can accurately identify whether there are lighted fishing boats in the remote sensing image.

[0039] Step S104: if the total number of light fishing boats is greater than a second preset threshold, and the acquisition time corresponding to the target night light remote sensing image is in a closed fishing period, the target object is determined to be an object with repayment risks.

[0040] Optionally, after obtaining the total number of light fishing boats, it is determined whether the total number of light fishing boats is greater than a second preset threshold value (e.g., 1). If the total number of light fishing boats is greater than the second preset threshold value, and the acquisition time corresponding to the target night light remote sensing image is in the fishing ban period, it means that the user (i.e., the above-mentioned target object) has a problem of illegal fishing, and therefore, the target object can be determined to be an object with repayment risk.

[0041] To summarize, target night light remote sensing images are collected in the operating area of ​​light fishing boats, and multiple target remote sensing sub-images where light fishing boats may exist are cropped out through the target algorithm. Then, the total number of light fishing boats is determined based on the light brightness values ​​in the multiple target remote sensing sub-images. Finally, based on the total number of light fishing boats and the acquisition time corresponding to the target night light remote sensing images, it is determined whether the target object is an object with repayment risk. The total number of light fishing boats and the acquisition time can be used to determine whether the target object has engaged in illegal fishing, thereby accurately judging whether the target object is a risky user, thereby achieving the effect of improving the accuracy of identifying risky users.

[0042] Optionally, in the object determination method provided in the embodiment of the present application, the target night light remote sensing image is processed by a target algorithm to obtain multiple target remote sensing sub-images, including: identifying the target night light remote sensing image by a target algorithm to obtain a first label corresponding to each pixel in the target night light remote sensing image, wherein the first label is used to characterize whether the pixel is a pixel of the image corresponding to a lighted fishing boat; segmenting the target night light remote sensing image according to the first label corresponding to each pixel in the target night light remote sensing image to obtain multiple target remote sensing sub-images.

[0043] In an optional embodiment, the target algorithm identifies each pixel in the target night light remote sensing image to determine whether it is an image corresponding to a light fishing boat, that is, the first label corresponding to each pixel in the target night light remote sensing image is determined, and the first label is used to identify whether the pixel is a pixel of the image corresponding to the light fishing boat, for example, 0 indicates that it is not a pixel of the image corresponding to the light fishing boat, and 1 indicates that it is a pixel of the image corresponding to the light fishing boat. Finally, the target night light remote sensing image is segmented according to the first label corresponding to each pixel to obtain multiple target remote sensing sub-images.

[0044] The target algorithm can be used to accurately identify the target night light remote sensing image, which helps to improve the accuracy of subsequent determination of the number of light fishing vessels.

[0045] Optionally, in the object determination method provided in the embodiment of the present application, the target night light remote sensing image is identified through the target algorithm to obtain the first label corresponding to each pixel in the target night light remote sensing image, including: performing brightness feature extraction on the target night light remote sensing image through the first feature extraction layer in the target algorithm to obtain a brightness feature vector; performing shape feature extraction on the target night light remote sensing image through the first feature extraction layer in the target algorithm to obtain a shape feature vector; processing the brightness feature vector and the shape feature vector through the fully connected layer in the target algorithm to obtain the first label corresponding to each pixel.

[0046] In an optional embodiment, the first label corresponding to each pixel point is determined by the following steps: the first feature extraction layer in the target algorithm performs brightness feature extraction on the target night light remote sensing image to obtain a brightness feature vector, and the second feature extraction layer in the target algorithm performs shape feature extraction on the target night light remote sensing image to obtain a shape feature vector; finally, the fully connected layer in the target algorithm processes the brightness feature vector and the shape feature vector to obtain the above-mentioned first label.

[0047] It should be noted that the brightness feature vector and the shape feature vector may be firstly fused, and then the fused feature vector may be calculated through a fully connected layer to obtain the first label corresponding to each pixel.

[0048] The shape features and brightness features can be used to accurately characterize the characteristics of light fishing vessels and improve the accuracy of light fishing vessels recognition.

[0049] Optionally, in the object determination method provided in the embodiment of the present application, determining the total number of lighted fishing boats in the target night light remote sensing image based on the target indices corresponding to multiple target remote sensing sub-images includes: for each target remote sensing sub-image, performing median filtering on the target remote sensing sub-image to obtain a processed target remote sensing sub-image; calculating based on the light intensity value of the processed target remote sensing sub-image and the light intensity values ​​of multiple target remote sensing sub-images to obtain a target index corresponding to a pixel point in each target remote sensing sub-image; determining the number of lighted fishing boats in the target remote sensing sub-image based on the target index; and determining the total number of lighted fishing boats based on the number of lighted fishing boats in the target remote sensing sub-image.

[0050] In an optional embodiment, in order to improve the accuracy of determining the total number of lighted fishing boats, for each target remote sensing sub-image, a median filter is first performed to obtain a processed target remote sensing sub-image. Median filtering is a commonly used image denoising method, which can remove isolated noise points in an image and retain the edge information of the image.

[0051] The target index corresponding to the pixel point in each target remote sensing sub-image is calculated by calculating the light intensity value of the processed target remote sensing sub-image and the light intensity values ​​of multiple target remote sensing sub-images. In an optional embodiment, the difference between the light intensity value of the processed target remote sensing sub-image and the light intensity values ​​of multiple target remote sensing sub-images can be calculated first, and then the ratio between the difference and the light intensity value of the processed target remote sensing sub-image is calculated, and finally the ratio is determined as the target index corresponding to the pixel point. By calculating the target index, the radiation value of the light fishing boat can be amplified to a higher level, while the radiation value of the background pixel is maintained at a lower level, thereby enhancing the contrast between the light fishing boat and the background.

[0052] The number of fishing boats with lights in the target remote sensing sub-image is determined according to the target index. For example, by setting an appropriate index threshold, the target and non-target can be distinguished, thereby improving the accuracy and efficiency of target detection and recognition. Finally, the total number of fishing boats with lights in the target remote sensing sub-image is obtained by summing the number of fishing boats with lights in the target remote sensing sub-image.

[0053] The light intensity value can be used to amplify the radiation value of the light fishing vessel to a higher level, while the radiation value of the background pixel is kept at a lower level, thereby improving the accuracy of identifying the light fishing vessel.

[0054] Optionally, in the object determination method provided in the embodiment of the present application, determining the number of lighted fishing boats in the target remote sensing sub-image based on the target index includes: for each pixel point in the target remote sensing sub-image, calculating according to the target index within the target range centered on the pixel point, to obtain a relative deviation value corresponding to each pixel point; segmenting the target remote sensing sub-image according to the relative deviation value corresponding to each pixel point to obtain a segmented target remote sensing sub-image; and determining the number of lighted fishing boats in the target remote sensing sub-image based on the light intensity value of the segmented target remote sensing sub-image.

[0055] In an optional embodiment, the following steps are used to determine the number of lighted fishing boats in the target remote sensing sub-image: for each pixel in the target remote sensing sub-image, obtain the target index within the target range centered on the pixel, and then calculate based on these indexes to obtain the relative deviation value corresponding to each pixel. For example, in a 3×3 window, determine the maximum and minimum values ​​in the target index in this window, and obtain the above relative deviation value by calculating the sum of the maximum and minimum values ​​and the difference between the maximum and minimum values. The relative deviation value indicates the sharpness of the pixel. Generally speaking, the pixel of the lighted fishing boat has a higher sharpness, while the background pixel has a lower sharpness.

[0056] The target remote sensing sub-image is segmented by the relative deviation value corresponding to each pixel. For example, a threshold value (such as 0.4) can be set to consider pixels with relative deviation values ​​greater than the threshold as possible fishing boats with lights, while pixels with relative deviation values ​​less than the threshold are considered as background. The above segmented target remote sensing sub-image is obtained by segmenting the target remote sensing sub-image. Finally, the number of fishing boats with lights in the target remote sensing sub-image is determined based on the light intensity value of the segmented target remote sensing sub-image.

[0057] The relative deviation value can be used to accurately distinguish the pixels of lighted fishing vessels from the background pixels, thereby improving the accuracy of lighted fishing vessel recognition.

[0058] Optionally, in the object determination method provided in the embodiment of the present application, determining the number of fishing boats with lights in the target remote sensing sub-image based on the light intensity value of the segmented target remote sensing sub-image includes: performing mean filtering on the segmented target remote sensing sub-image to obtain a filtered target remote sensing sub-image; performing calculations based on the light intensity value of the segmented target remote sensing sub-image and the light intensity value of the filtered target remote sensing sub-image to obtain target light intensity values ​​corresponding to pixel points in the segmented target remote sensing sub-image; and determining the number of fishing boats with lights in the target remote sensing sub-image based on the target light intensity value.

[0059] In an optional embodiment, in order to further improve the accuracy of identifying lighted fishing vessels, the following steps are used to determine the number of lighted fishing vessels in the target remote sensing sub-image: first, the segmented target remote sensing sub-image is subjected to mean filtering. Mean filtering is a commonly used image smoothing method that can remove detailed information in the image and retain the overall characteristics of the image.

[0060] Then, the light intensity values ​​of the segmented target remote sensing sub-image and the light intensity values ​​of the filtered target remote sensing sub-image are calculated again to obtain the target light intensity values ​​corresponding to the pixel points in the segmented target remote sensing sub-image. For example, the difference between the light intensity values ​​of the segmented target remote sensing sub-image and the light intensity values ​​of the filtered target remote sensing sub-image is first calculated, and then the ratio between the difference and the light intensity value of the filtered target remote sensing sub-image is calculated to obtain the above-mentioned target light intensity value. Finally, the number of lighted fishing boats in the target remote sensing sub-image is determined based on the target light intensity value.

[0061] By calculating the target light intensity value, we can get a value that reflects the radiation level of the pixel relative to the surrounding environment. Generally speaking, the pixels of fishing boats with lights have higher target light intensity values, while non-fishing boats such as clouds and city lights have lower or negative target light intensity values. Therefore, the target light intensity value can effectively improve the accuracy of identifying fishing boats with lights.

[0062] Optionally, in the object determination method provided in the embodiment of the present application, determining the number of lighted fishing boats in the target remote sensing sub-image based on the target light intensity value includes: determining a second label corresponding to a pixel point in the target remote sensing sub-image based on the target light intensity value and a preset intensity threshold; determining the number of lighted fishing boats in the target remote sensing sub-image based on the second label.

[0063] In an optional embodiment, the following steps are used to determine the number of fishing boats with lights: based on the calculated target light intensity value and a preset intensity threshold, a second label corresponding to a pixel point in the target remote sensing sub-image is determined; and finally, based on the second label, the number of fishing boats with lights in the target remote sensing sub-image is determined.

[0064] For example, a preset intensity threshold (such as 0.75) is set, and pixels with target light intensity values ​​greater than the threshold are considered to be lighted fishing boats, while pixels with target light intensity values ​​less than the threshold are excluded. The number of pixels with target light intensity values ​​greater than the threshold is calculated, and the identified fishing boat location information is counted at a spatial resolution of 0.5×0.5 to obtain the number of fishing boats.

[0065] By further screening the pixel points in the target remote sensing sub-image through the above steps, some high-sharp pixel points that may be caused by non-fishing boats such as clouds and city lights can be effectively excluded, thereby improving the accuracy of determining the number of fishing boats.

[0066] In an optional embodiment, the following may be used: Figure 2 The process shown realizes accurate identification of light fishing boats: obtain night light image data, realize identification of light fishing boats according to the radiation characteristics of light fishing boats on night light remote sensing images, use target index to distinguish light fishing boats from background, use sharpness index (i.e. the relative deviation value mentioned above) for segmentation, and regard pixels with relative deviation values ​​greater than the threshold as possible light fishing boats, and regard pixels with relative deviation values ​​less than the threshold as background. Set the threshold corresponding to the target light intensity value, regard pixels with target light intensity values ​​greater than the threshold as light fishing boats, and exclude pixels with target light intensity values ​​less than the threshold. Count the identified fishing boat location information at a spatial resolution of 0.5×0.5 to obtain the number of operating fishing boats in each grid unit.

[0067] The object determination method provided in the embodiment of the present application is through obtaining a target night light remote sensing image of a target area, wherein the target area is the operating area of ​​light fishing boats, wherein the light fishing boat is a fishing boat owned by the target object, and the target object is an object that obtains a loan based on the light fishing boat at a target financial institution; the target night light remote sensing image is processed by a target algorithm to obtain multiple target remote sensing sub-images, wherein the probability that an image corresponding to the light fishing boat exists in the multiple target remote sensing sub-images is greater than a first preset threshold; based on the target index corresponding to the multiple target remote sensing sub-images, the total number of light fishing boats in the target night light remote sensing image is determined, wherein the target index is determined by the light brightness values ​​in the multiple target remote sensing sub-images; if the total number of light fishing boats is greater than a second preset threshold, and the acquisition time corresponding to the target night light remote sensing image is in a fishing ban period, then the target object is determined to be an object with repayment risks, which solves the problem of low accuracy in determining risk users due to a general method used in the related art to determine whether a fishing industry loan user is a risky user.

[0068] In this scheme, target night light remote sensing images are collected in the operating area of ​​light fishing boats, and multiple target remote sensing sub-images where light fishing boats may exist are cropped out through a target algorithm. Then, the total number of light fishing boats is determined based on the light brightness values ​​in the multiple target remote sensing sub-images. Finally, based on the total number of light fishing boats and the acquisition time corresponding to the target night light remote sensing images, it is determined whether the target object is an object with repayment risk. The total number of light fishing boats and the acquisition time can be used to determine whether the target object has engaged in illegal fishing, thereby accurately judging whether the target object is a risky user, thereby achieving the effect of improving the accuracy of identifying risky users.

[0069] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0070] The present application also provides an object determination device. It should be noted that the object determination device of the present application can be used to execute the object determination method provided by the present application. The object determination device provided by the present application is introduced below.

[0071] Figure 3 is a schematic diagram of an object determination device according to an embodiment of the present application. Figure 3 As shown, the device includes: an acquisition unit 301, a processing unit 302, a first determination unit 303 and a second determination unit 304.

[0072] The acquisition unit 301 is used to acquire a target night light remote sensing image of a target area, wherein the target area is an operation area of ​​a light fishing boat, wherein the light fishing boat is a fishing boat owned by a target object, and the target object is an object that obtains a loan based on the light fishing boat in a target financial institution;

[0073] The processing unit 302 is used to process the target night light remote sensing image by using a target algorithm to obtain a plurality of target remote sensing sub-images, wherein the probability that an image corresponding to a lighted fishing boat exists in the plurality of target remote sensing sub-images is greater than a first preset threshold;

[0074] A first determining unit 303 is used to determine the total number of lighted fishing boats in the target night light remote sensing image according to target indices corresponding to the multiple target remote sensing sub-images, wherein the target index is determined by the light brightness values ​​in the multiple target remote sensing sub-images;

[0075] The second determination unit 304 is used to determine that the target object is an object with repayment risk if the total number of light fishing boats is greater than a second preset threshold and the acquisition time corresponding to the target night light remote sensing image is in a closed fishing period.

[0076] The object determination device provided in the embodiment of the present application obtains a target night light remote sensing image of a target area through an acquisition unit 301, wherein the target area is an operating area of ​​light fishing boats, wherein the light fishing boats are fishing boats owned by the target object, and the target object is an object that obtains a loan based on the light fishing boats in the target financial institution; the processing unit 302 processes the target night light remote sensing image through a target algorithm to obtain multiple target remote sensing sub-images, wherein the probability that there are images corresponding to light fishing boats in the multiple target remote sensing sub-images is greater than a first preset threshold; the first determination unit 303 determines the total number of light fishing boats in the target night light remote sensing image based on the target index corresponding to the multiple target remote sensing sub-images, wherein the target index is determined by the light brightness values ​​in the multiple target remote sensing sub-images; the second determination unit 304 determines that the target object is an object with repayment risks if the total number of light fishing boats is greater than the second preset threshold and the acquisition time corresponding to the target night light remote sensing image is in a fishing ban period, thereby solving the problem that the accuracy of determining risk users is relatively low using a general method in the related art to determine whether a fishing industry loan user is a risky user.

[0077] In this scheme, target night light remote sensing images are collected in the operating area of ​​light fishing boats, and multiple target remote sensing sub-images where light fishing boats may exist are cropped out through a target algorithm. Then, the total number of light fishing boats is determined based on the light brightness values ​​in the multiple target remote sensing sub-images. Finally, based on the total number of light fishing boats and the acquisition time corresponding to the target night light remote sensing images, it is determined whether the target object is an object with repayment risk. The total number of light fishing boats and the acquisition time can be used to determine whether the target object has engaged in illegal fishing, thereby accurately judging whether the target object is a risky user, thereby achieving the effect of improving the accuracy of identifying risky users.

[0078] Optionally, in the object determination device provided in the embodiment of the present application, the processing unit includes: an identification subunit, used to identify the target night light remote sensing image through a target algorithm, and obtain a first label corresponding to each pixel point in the target night light remote sensing image, wherein the first label is used to characterize whether the pixel point is a pixel point of the image corresponding to the light fishing boat; a segmentation subunit, used to segment the target night light remote sensing image according to the first label corresponding to each pixel point in the target night light remote sensing image, and obtain multiple target remote sensing sub-images.

[0079] Optionally, in the object determination device provided in the embodiment of the present application, the identification subunit includes: a first extraction module, used to perform brightness feature extraction on the target night light remote sensing image through the first feature extraction layer in the target algorithm to obtain a brightness feature vector; a second extraction module, used to perform shape feature extraction on the target night light remote sensing image through the first feature extraction layer in the target algorithm to obtain a shape feature vector; a processing module, used to process the brightness feature vector and the shape feature vector through the fully connected layer in the target algorithm to obtain a first label corresponding to each pixel point.

[0080] Optionally, in the object determination device provided in the embodiment of the present application, the first determination unit includes: a processing subunit, used to perform median filtering on each target remote sensing sub-image to obtain a processed target remote sensing sub-image; a calculation subunit, used to perform calculations based on the light intensity value of the processed target remote sensing sub-image and the light intensity values ​​of multiple target remote sensing sub-images to obtain a target index corresponding to a pixel point in each target remote sensing sub-image; a first determination subunit, used to determine the number of light fishing boats in the target remote sensing sub-image based on the target index; and a second determination subunit, used to determine the total number of light fishing boats based on the number of light fishing boats in the target remote sensing sub-image.

[0081] Optionally, in the object determination device provided in the embodiment of the present application, the first determination subunit includes: a calculation module, which is used to calculate, for each pixel point in the target remote sensing sub-image, a target index within a target range centered on the pixel point, to obtain a relative deviation value corresponding to each pixel point; a segmentation module, which is used to segment the target remote sensing sub-image according to the relative deviation value corresponding to each pixel point, to obtain a segmented target remote sensing sub-image; and a determination module, which is used to determine the number of light fishing boats in the target remote sensing sub-image based on the light intensity value of the segmented target remote sensing sub-image.

[0082] Optionally, in the object determination device provided in the embodiment of the present application, the determination module includes: a processing submodule, used to perform mean filtering on the segmented target remote sensing subimage to obtain a filtered target remote sensing subimage; a calculation submodule, used to perform calculations based on the light intensity values ​​of the segmented target remote sensing subimage and the light intensity values ​​of the filtered target remote sensing subimage to obtain the target light intensity values ​​corresponding to the pixel points in the segmented target remote sensing subimage; and a determination submodule, used to determine the number of lighted fishing boats in the target remote sensing subimage based on the target light intensity values.

[0083] Optionally, in the object determination device provided in the embodiment of the present application, the determination submodule includes: a first determination submodule, used to determine the second label corresponding to the pixel point in the target remote sensing subimage based on the target light intensity value and a preset intensity threshold; a second determination submodule, used to determine the number of lighted fishing boats in the target remote sensing subimage based on the second label.

[0084] The object determination device includes a processor and a memory. The above-mentioned acquisition unit 301, processing unit 302, first determination unit 303 and second determination unit 304 are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to implement corresponding functions.

[0085] The processor contains a kernel, which calls the corresponding program unit from the memory. The kernel can be set to one or more, and the kernel parameters can be adjusted to accurately judge the risky users.

[0086] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0087] An embodiment of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, a method for determining an object is implemented.

[0088] An embodiment of the present invention provides a processor, which is used to run a program, wherein a method for determining an execution object is performed when the program is run.

[0089] like Figure 4 As shown, an embodiment of the present invention provides an electronic device, the device includes a processor, a memory and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: obtaining a target night light remote sensing image of a target area, wherein the target area is an operating area of ​​light fishing boats, wherein the light fishing boats are fishing boats owned by a target object, and the target object is an object that obtains a loan based on the light fishing boats at a target financial institution; processing the target night light remote sensing image through a target algorithm to obtain a plurality of target remote sensing sub-images, wherein the probability that an image corresponding to the light fishing boat exists in the plurality of target remote sensing sub-images is greater than a first preset threshold; determining the total number of light fishing boats in the target night light remote sensing image based on a target index corresponding to the plurality of target remote sensing sub-images, wherein the target index is determined by the light brightness values ​​in the plurality of target remote sensing sub-images; if the total number of light fishing boats is greater than a second preset threshold, and the acquisition time corresponding to the target night light remote sensing image is in a fishing ban period, determining the target object is an object with repayment risk.

[0090] Optionally, the target night light remote sensing image is processed by a target algorithm to obtain multiple target remote sensing sub-images, including: identifying the target night light remote sensing image by a target algorithm to obtain a first label corresponding to each pixel in the target night light remote sensing image, wherein the first label is used to characterize whether the pixel is a pixel of an image corresponding to a lighted fishing boat; segmenting the target night light remote sensing image according to the first label corresponding to each pixel in the target night light remote sensing image to obtain multiple target remote sensing sub-images.

[0091] Optionally, the target night light remote sensing image is identified through the target algorithm to obtain a first label corresponding to each pixel in the target night light remote sensing image, including: performing brightness feature extraction on the target night light remote sensing image through the first feature extraction layer in the target algorithm to obtain a brightness feature vector; performing shape feature extraction on the target night light remote sensing image through the first feature extraction layer in the target algorithm to obtain a shape feature vector; processing the brightness feature vector and the shape feature vector through the fully connected layer in the target algorithm to obtain the first label corresponding to each pixel.

[0092] Optionally, determining the total number of lighted fishing boats in the target night light remote sensing image based on the target indices corresponding to multiple target remote sensing sub-images includes: for each target remote sensing sub-image, performing median filtering on the target remote sensing sub-image to obtain a processed target remote sensing sub-image; calculating based on the light intensity value of the processed target remote sensing sub-image and the light intensity values ​​of multiple target remote sensing sub-images to obtain a target index corresponding to a pixel point in each target remote sensing sub-image; determining the number of lighted fishing boats in the target remote sensing sub-image based on the target index; and determining the total number of lighted fishing boats based on the number of lighted fishing boats in the target remote sensing sub-image.

[0093] Optionally, determining the number of fishing boats with lights in the target remote sensing sub-image based on the target index includes: for each pixel point in the target remote sensing sub-image, calculating the target index within the target range centered on the pixel point to obtain a relative deviation value corresponding to each pixel point; segmenting the target remote sensing sub-image based on the relative deviation value corresponding to each pixel point to obtain a segmented target remote sensing sub-image; and determining the number of fishing boats with lights in the target remote sensing sub-image based on the light intensity value of the segmented target remote sensing sub-image.

[0094] Optionally, determining the number of fishing boats with lights in the target remote sensing sub-image based on the light intensity values ​​of the segmented target remote sensing sub-image includes: performing mean filtering on the segmented target remote sensing sub-image to obtain a filtered target remote sensing sub-image; performing calculations based on the light intensity values ​​of the segmented target remote sensing sub-image and the light intensity values ​​of the filtered target remote sensing sub-image to obtain target light intensity values ​​corresponding to pixel points in the segmented target remote sensing sub-image; and determining the number of fishing boats with lights in the target remote sensing sub-image based on the target light intensity values.

[0095] Optionally, determining the number of fishing boats with lights in the target remote sensing sub-image based on the target light intensity value includes: determining a second label corresponding to a pixel point in the target remote sensing sub-image based on the target light intensity value and a preset intensity threshold; and determining the number of fishing boats with lights in the target remote sensing sub-image based on the second label.

[0096] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0097] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with the following method steps: obtaining a target night light remote sensing image of a target area, wherein the target area is an operating area of ​​light fishing boats, wherein the light fishing boats are fishing boats owned by a target object, and the target object is an object that obtains a loan from a target financial institution based on the light fishing boats; processing the target night light remote sensing image through a target algorithm to obtain a plurality of target remote sensing sub-images, wherein the probability that an image corresponding to a light fishing boat exists in the plurality of target remote sensing sub-images is greater than a first preset threshold; determining the total number of light fishing boats in the target night light remote sensing image based on a target index corresponding to the plurality of target remote sensing sub-images, wherein the target index is determined by the light brightness values ​​in the plurality of target remote sensing sub-images; if the total number of light fishing boats is greater than a second preset threshold, and the acquisition time corresponding to the target night light remote sensing image is in a fishing ban period, then determining the target object as an object with repayment risk.

[0098] Optionally, the target night light remote sensing image is processed by a target algorithm to obtain multiple target remote sensing sub-images, including: identifying the target night light remote sensing image by a target algorithm to obtain a first label corresponding to each pixel in the target night light remote sensing image, wherein the first label is used to characterize whether the pixel is a pixel of an image corresponding to a lighted fishing boat; segmenting the target night light remote sensing image according to the first label corresponding to each pixel in the target night light remote sensing image to obtain multiple target remote sensing sub-images.

[0099] Optionally, the target night light remote sensing image is identified through the target algorithm to obtain a first label corresponding to each pixel in the target night light remote sensing image, including: performing brightness feature extraction on the target night light remote sensing image through the first feature extraction layer in the target algorithm to obtain a brightness feature vector; performing shape feature extraction on the target night light remote sensing image through the first feature extraction layer in the target algorithm to obtain a shape feature vector; processing the brightness feature vector and the shape feature vector through the fully connected layer in the target algorithm to obtain the first label corresponding to each pixel.

[0100] Optionally, determining the total number of lighted fishing boats in the target night light remote sensing image based on the target indices corresponding to multiple target remote sensing sub-images includes: for each target remote sensing sub-image, performing median filtering on the target remote sensing sub-image to obtain a processed target remote sensing sub-image; calculating based on the light intensity value of the processed target remote sensing sub-image and the light intensity values ​​of multiple target remote sensing sub-images to obtain a target index corresponding to a pixel point in each target remote sensing sub-image; determining the number of lighted fishing boats in the target remote sensing sub-image based on the target index; and determining the total number of lighted fishing boats based on the number of lighted fishing boats in the target remote sensing sub-image.

[0101] Optionally, determining the number of fishing boats with lights in the target remote sensing sub-image based on the target index includes: for each pixel point in the target remote sensing sub-image, calculating the target index within the target range centered on the pixel point to obtain a relative deviation value corresponding to each pixel point; segmenting the target remote sensing sub-image based on the relative deviation value corresponding to each pixel point to obtain a segmented target remote sensing sub-image; and determining the number of fishing boats with lights in the target remote sensing sub-image based on the light intensity value of the segmented target remote sensing sub-image.

[0102] Optionally, determining the number of fishing boats with lights in the target remote sensing sub-image based on the light intensity values ​​of the segmented target remote sensing sub-image includes: performing mean filtering on the segmented target remote sensing sub-image to obtain a filtered target remote sensing sub-image; performing calculations based on the light intensity values ​​of the segmented target remote sensing sub-image and the light intensity values ​​of the filtered target remote sensing sub-image to obtain target light intensity values ​​corresponding to pixel points in the segmented target remote sensing sub-image; and determining the number of fishing boats with lights in the target remote sensing sub-image based on the target light intensity values.

[0103] Optionally, determining the number of fishing boats with lights in the target remote sensing sub-image based on the target light intensity value includes: determining a second label corresponding to a pixel point in the target remote sensing sub-image based on the target light intensity value and a preset intensity threshold; and determining the number of fishing boats with lights in the target remote sensing sub-image based on the second label.

[0104] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0105] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0106] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0108] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0109] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0110] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0111] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0112] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0113] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining an object, characterized in that: include: Acquire a target night light remote sensing image of a target area, wherein the target area is an operating area of ​​a light fishing boat, wherein the light fishing boat is a fishing boat owned by a target object, and the target object is an object that obtains a loan based on the light fishing boat at a target financial institution; Processing the target night light remote sensing image by a target algorithm to obtain a plurality of target remote sensing sub-images, wherein the probability that an image corresponding to the lighted fishing boat exists in the plurality of target remote sensing sub-images is greater than a first preset threshold; Determine the total number of the lighted fishing boats in the target night light remote sensing image according to the target indexes corresponding to the multiple target remote sensing sub-images, wherein the target index is determined by the light brightness values ​​in the multiple target remote sensing sub-images; If the total number of the lighted fishing boats is greater than a second preset threshold, and the acquisition time corresponding to the target night light remote sensing image is during a fishing ban period, the target object is determined to be an object with repayment risks.

2. The method according to claim 1, characterized in that The target night light remote sensing image is processed by a target algorithm to obtain a plurality of target remote sensing sub-images including: The target night light remote sensing image is identified by the target algorithm to obtain a first label corresponding to each pixel in the target night light remote sensing image, wherein the first label is used to indicate whether the pixel is a pixel of the image corresponding to the light fishing boat; The target night light remote sensing image is segmented according to the first label corresponding to each pixel in the target night light remote sensing image to obtain the multiple target remote sensing sub-images.

3. The method according to claim 2, characterized in that The target night light remote sensing image is identified by the target algorithm, and the first label corresponding to each pixel in the target night light remote sensing image is obtained, which includes: Performing brightness feature extraction on the target night light remote sensing image through the first feature extraction layer in the target algorithm to obtain a brightness feature vector; Performing shape feature extraction on the target night light remote sensing image through the first feature extraction layer in the target algorithm to obtain a shape feature vector; The brightness feature vector and the shape feature vector are processed by a fully connected layer in the target algorithm to obtain a first label corresponding to each pixel.

4. The method according to claim 1, characterized in that: Determining the total number of the lighted fishing boats in the target night light remote sensing image according to the target indexes corresponding to the multiple target remote sensing sub-images includes: For each target remote sensing sub-image, performing median filtering on the target remote sensing sub-image to obtain a processed target remote sensing sub-image; Calculating according to the light intensity value of the processed target remote sensing sub-image and the light intensity values ​​of the multiple target remote sensing sub-images to obtain a target index corresponding to a pixel point in each target remote sensing sub-image; Determining the number of lighted fishing vessels in the target remote sensing sub-image according to the target index; The total number of the lighted fishing boats is determined based on the number of lighted fishing boats in the target remote sensing sub-image.

5. The method according to claim 4, characterized in that Determining the number of lighted fishing boats in the target remote sensing sub-image according to the target index includes: For each pixel point in the target remote sensing sub-image, a relative deviation value corresponding to each pixel point is obtained by calculating according to a target index within a target range centered on the pixel point; Segmenting the target remote sensing sub-image according to the relative deviation value corresponding to each pixel point to obtain a segmented target remote sensing sub-image; The number of fishing boats with lights in the target remote sensing sub-image is determined according to the light intensity value of the segmented target remote sensing sub-image.

6. The method according to claim 5, characterized in that Determining the number of lighted fishing boats in the target remote sensing sub-image according to the light intensity value of the segmented target remote sensing sub-image includes: Performing mean filtering on the segmented target remote sensing sub-image to obtain a filtered target remote sensing sub-image; Calculating according to the light intensity value of the segmented target remote sensing sub-image and the light intensity value of the filtered target remote sensing sub-image, to obtain the target light intensity value corresponding to the pixel point in the segmented target remote sensing sub-image; The number of lighted fishing boats in the target remote sensing sub-image is determined according to the target light intensity value.

7. The method according to claim 6, characterized in that Determining the number of lighted fishing boats in the target remote sensing sub-image according to the target light intensity value includes: Determine a second label corresponding to a pixel point in the target remote sensing sub-image according to the target light intensity value and a preset intensity threshold; The number of lighted fishing boats in the target remote sensing sub-image is determined based on the second label.

8. A device for determining an object, characterized in that: include: an acquisition unit, used for acquiring a target night light remote sensing image of a target area, wherein the target area is an operation area of ​​a light fishing boat, wherein the light fishing boat is a fishing boat owned by a target object, and the target object is an object that obtains a loan based on the light fishing boat in a target financial institution; a processing unit, configured to process the target night light remote sensing image by a target algorithm to obtain a plurality of target remote sensing sub-images, wherein a probability that an image corresponding to the lighted fishing boat exists in the plurality of target remote sensing sub-images is greater than a first preset threshold; A first determining unit is used to determine the total number of the lighted fishing boats in the target night light remote sensing image according to the target indexes corresponding to the multiple target remote sensing sub-images, wherein the target index is determined by the light brightness values ​​in the multiple target remote sensing sub-images; The second determination unit is used to determine that the target object is an object with repayment risk if the total number of the light fishing boats is greater than a second preset threshold and the acquisition time corresponding to the target night light remote sensing image is in a fishing ban period.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the storage medium is located is controlled to execute the method for determining the object of any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the object determination method described in any one of claims 1 to 7.

Images