CN113808134A

CN113808134A - Oil tank layout information generation method, oil tank layout information generation device, electronic apparatus, and medium

Info

Publication number: CN113808134A
Application number: CN202111373228.1A
Authority: CN
Inventors: 区东
Original assignee: Zhongke Xingrui Technology Beijing Co ltd
Current assignee: Zhongke Xingrui Technology Beijing Co ltd
Priority date: 2021-11-19
Filing date: 2021-11-19
Publication date: 2021-12-17
Anticipated expiration: 2041-11-19
Also published as: CN113808134B

Abstract

The embodiment of the disclosure discloses a method and a device for generating oil tank layout information, electronic equipment and a medium. One embodiment of the method comprises: carrying out image segmentation on the first target remote sensing image to obtain a sub-image set; acquiring a second target remote sensing image set; generating position information of each first oil tank information in a first oil tank information set corresponding to the first target remote sensing image and radius information of each first oil tank information in the first oil tank information set; for each second target remote sensing image in the second target remote sensing image set, generating position information of each second oil tank information in a second oil tank information set corresponding to the second target remote sensing image and radius information of each second oil tank information in the second oil tank information set according to the second target remote sensing image and the oil tank identification model set; tank layout information for the target area is generated. This embodiment can accurately and efficiently generate tank layout information for a target area.

Description

Oil tank layout information generation method, oil tank layout information generation device, electronic apparatus, and medium

Technical Field

The embodiment of the disclosure relates to the technical field of computers, in particular to a method and a device for generating oil tank layout information, electronic equipment and a medium.

Background

At present, in daily life, an oil tank is often a large container for storing oil and having a prescribed regular shape (for example, a cylindrical shape). The target detection and parameter extraction of the oil tank have important significance in the application fields of oil tank monitoring, oil storage analysis and the like. For the detection of objects in the tank, the following methods are generally adopted: convolutional Neural Networks (CNN) are used for target detection for tanks.

However, when the oil tank is detected in the above manner, the following technical problems often occur:

firstly, a convolutional neural network is used for oil tank detection of a target area, and if the resolution of an area image corresponding to the target area is high, the size of data bytes occupied by the area image is large, so that the calculation amount for training the convolutional neural network and detecting the subsequent target area is large. In addition, the memory space needed for the area image is relatively large. If the resolution of the area image corresponding to the target area is small, the problem of low oil tank detection accuracy often exists.

Second, the use of convolutional neural networks for tank detection in a target area is often problematic in terms of low accuracy. For example, convolutional neural networks often do not take into account some of the main characteristic information in the tank images (e.g., structural categories, shaded areas, etc.), resulting in low detection accuracy of the tanks.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose a tank layout information generation method, apparatus, electronic device, and computer readable medium to solve one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide a method for generating tank layout information, including: carrying out image segmentation on a first target remote sensing image acquired in advance to obtain a sub-image set, wherein the first target remote sensing image is an image which is shot by a first target remote sensing image sensor aiming at a target area and has a resolution which meets a first preset condition; acquiring a second target remote sensing image set which is shot by a second target remote sensing image sensor aiming at each area corresponding to the area information in the area information set and has the resolution which meets a second preset condition, wherein the resolution of a second target remote sensing image in the second target remote sensing image set is greater than that of a first target remote sensing image, and the area information set and the sub-image set have a corresponding relation; generating position information of each first oil tank information in a first oil tank information set corresponding to the first target remote sensing image and radius information of each first oil tank information in the first oil tank information set according to the first target remote sensing image and a pre-trained oil tank identification model set; generating, for each second target remote sensing image in the second target remote sensing image set, position information of each second tank information in the second tank information set corresponding to the second target remote sensing image and radius information of each second tank information in the second tank information set, based on the second target remote sensing image and the tank identification model set; and generating the tank layout information of the target area based on the position information of each of the first tank information, the radius information of each of the first tank information, the position information of each of the obtained second tank information, and the radius information of each of the obtained second tank information.

In a second aspect, some embodiments of the present disclosure provide a tank layout information generating apparatus, including: the image segmentation method comprises the steps that a segmentation unit is configured to carry out image segmentation on a first target remote sensing image acquired in advance to obtain a sub-image set, wherein the first target remote sensing image is an image which is shot by a first target remote sensing image sensor aiming at a target area and has a resolution size meeting a first preset condition; an acquisition unit configured to acquire a second target remote sensing image set which is shot by a second target remote sensing image sensor for each area corresponding to the area information in the area information set and has a resolution satisfying a second predetermined condition, wherein the resolution of the second target remote sensing image in the second target remote sensing image set is greater than that of the first target remote sensing image, and the area information set and the subimage set have a corresponding relationship; a first generation unit configured to generate, based on the first target remote sensing image and a previously trained tank recognition model set, position information of each first tank information in a first tank information set corresponding to the first target remote sensing image and radius information of each first tank information in the first tank information set; a second generation unit configured to generate, for each second target remote sensing image in the second target remote sensing image set, position information of each second tank information in a second tank information set corresponding to the second target remote sensing image and radius information of each second tank information in the second tank information set, based on the second target remote sensing image and the tank identification model set; and a third generating unit configured to generate the tank layout information of the target area based on the position information of each of the first tank information, the radius information of each of the first tank information, the position information of each of the obtained second tank information, and the radius information of each of the obtained second tank information.

In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method as described in any of the implementations of the first aspect.

In a fourth aspect, some embodiments of the disclosure provide a computer readable medium having a computer program stored thereon, where the program when executed by a processor implements a method as described in any of the implementations of the first aspect.

The above embodiments of the present disclosure have the following beneficial effects: the oil tank layout information generation method of some embodiments of the present disclosure can accurately and efficiently generate oil tank layout information for a target area. Specifically, the reason why the tank layout information for the target area cannot be accurately and efficiently generated is that: the convolutional neural network is used for oil tank detection of a target area, and if the resolution of an area image corresponding to the target area is high, the size of data bytes occupied by the area image is large, so that the calculation amount for training the convolutional neural network and detecting the subsequent target area is large. In addition, the memory space needed for the area image is relatively large. If the resolution of the region image corresponding to the target region is small, the oil tank detection accuracy is often low, so that the oil tank layout information for the target region cannot be generated efficiently subsequently. Specifically, since the image pixel distribution may not be uniform, although the height of the segmented image becomes small, the size of the image may have a large difference. When the size of the segmented image is large, the image loading speed is still influenced, and the purpose of shortening the image loading time is difficult to achieve. Based on this, the tank layout information generation method according to some embodiments of the present disclosure may first perform image segmentation on a first target remote sensing image acquired in advance to obtain a sub-image set, where the first target remote sensing image is an image that is captured by a first target remote sensing image sensor for a target area and has a resolution that meets a first predetermined condition. Here, the purpose of image segmentation of the first remote sensing target image is to subsequently acquire more detailed feature information for the target region, that is, feature information of the second remote sensing target image set corresponding to each sub-image. Then, a second target remote sensing image set which is shot by a second target remote sensing image sensor aiming at the corresponding area of each area information in the area information set and has the resolution size meeting a second preset condition is obtained. And the resolution ratio of the second target remote sensing image in the second target remote sensing image set is greater than that of the first target remote sensing image, and the area information set and the sub-image set have a corresponding relation. Namely, by acquiring the second target remote sensing image set, more characteristic information of each geographic position in the target area can be acquired, so that the subsequent oil tank layout information can be generated more accurately. Furthermore, the position information of each first tank information in the first tank information set corresponding to the first target remote sensing image and the radius information of each first tank information in the first tank information set can be efficiently and accurately generated from the first target remote sensing image and the previously trained tank recognition model set. Similarly, for each second target remote sensing image in the second target remote sensing image set, the position information of each second tank information in the second tank information set corresponding to the second target remote sensing image and the radius information of each second tank information in the second tank information set can be efficiently and accurately generated based on the second target remote sensing image and the tank identification model set. Finally, the tank layout information of the target area can be accurately and efficiently generated based on the position information of each of the first tank information, the radius information of each of the first tank information, the position information of each of the second tank information, and the radius information of each of the second tank information. Here, the tank layout information can be generated more accurately by considering the image feature information of the image with the lower resolution corresponding to the target area and the image feature information of the image with the higher resolution corresponding to the target area, based on the position information of each of the first tank information, the radius information of each of the first tank information, the position information of each of the obtained second tank information, and the radius information of each of the obtained second tank information.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.

Fig. 1 is a schematic diagram of one application scenario of a tank layout information generation method according to some embodiments of the present disclosure;

fig. 2 is a flow diagram of some embodiments of a tank layout information generation method according to the present disclosure;

FIG. 3 is a flow diagram of further embodiments of a tank layout information generation method according to the present disclosure;

fig. 4 is a schematic structural diagram of some embodiments of a tank layout information generating device according to the present disclosure;

FIG. 5 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 is a schematic diagram of one application scenario of a tank layout information generation method according to some embodiments of the present disclosure.

In the application scenario of fig. 1, the electronic device 101 may first perform image segmentation on the first remote sensing image of interest 102 to obtain a sub-image set 103. The first remote sensing target image 102 is an image captured by the first remote sensing target image sensor for a target area and having a resolution that satisfies a first predetermined condition. In the present application scenario, the sub-image set 103 includes: sub-image 1031, sub-image 1032, and sub-image 1033. Next, the electronic device 101 may acquire a second set 105 of remote sensing images of interest having a resolution size satisfying a second predetermined condition, which are captured by a second remote sensing image sensor for each area corresponding to the area information in the set 104 of area information. The resolution of the second remote sensing image in the second remote sensing image set 105 is greater than the resolution of the first remote sensing image 102. In the present application scenario, the region information set 104 includes: region information 1041 corresponding to sub-image 1031, region information 1042 corresponding to sub-image 1032, and region information 1043 corresponding to sub-image 1033. The region information set 104 corresponds to the sub-image set 103. The second set 105 of target remote sensing images may include: a second target remote sensing image 1051, a second target remote sensing image 1052, and a second target remote sensing image 1053. Furthermore, the electronic device 101 may generate position information 107 of each first tank information in the first tank information set corresponding to the first target remote sensing image 102 and radius information 108 of each first tank information in the first tank information set, based on the first target remote sensing image 102 and a previously trained tank recognition model set 106. In the present application scenario, the tank identification model set 106 includes: an oil tank identification model 1061, an oil tank identification model 1062, and an oil tank identification model 1063. Furthermore, the electronic device 101 may generate, for each second remote sensing image of the second remote sensing image set 105, position information 109 of each second tank information of the second tank information set corresponding to the second remote sensing image and radius information 110 of each second tank information of the second tank information set, based on the second remote sensing image and the tank recognition model set 106. Finally, the electronic device 101 may generate the tank layout information 111 of the target area based on the position information 107 of each of the first tank information, the radius information 110 of each of the first tank information, the position information 109 of each of the obtained second tank information, and the radius information 110 of each of the obtained second tank information.

The electronic device 101 may be hardware or software. When the electronic device is hardware, the electronic device may be implemented as a distributed cluster formed by a plurality of servers or terminal devices, or may be implemented as a single server or a single terminal device. When the electronic device is embodied as software, it may be installed in the above-listed hardware devices. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.

It should be understood that the number of electronic devices in fig. 1 is merely illustrative. There may be any number of electronic devices, as desired for implementation.

With continued reference to fig. 2, a flow 200 of some embodiments of a tank layout information generation method according to the present disclosure is shown. The oil tank layout information generation method comprises the following steps:

step 201, performing image segmentation on a first target remote sensing image acquired in advance to obtain a sub-image set.

In some embodiments, the executing subject may perform image segmentation on the first remote sensing target image acquired in advance to obtain a sub-image set. The first target remote sensing image is an image which is shot by the first target remote sensing image sensor aiming at the target area and has the resolution size meeting a first preset condition. The target area is an area where tank information is to be determined. The first target remote sensing image sensor may be a sensor for taking a remote sensing image of a certain resolution. The first preset condition may be that the resolution size of the image is within a first interval. For example, the resolution size of the first target remote sensing image sensor may be 500 pixels × 1000 pixels. The first interval corresponding to the first preset condition may be [400, 800] pixel × [400, 2000] pixel. The first target remote sensing image may be an optical image, or an image in another format, and is not limited again.

As an example, the execution subject may obtain a preset pixel number size corresponding to each sub-image in the sub-image set. The number of pixels corresponding to each sub-image in the sub-image set may be the same. And then, according to the preset pixel number, carrying out image segmentation on the first target remote sensing image to obtain a sub-image set.

In some optional implementation manners of some embodiments, the image segmentation on the first remote sensing target image to obtain a sub-image set may include the following steps:

the method comprises the first step of determining segmentation proportion information for segmenting the first target remote sensing image according to the resolution of the first target remote sensing image.

As an example, the executing body may query a table representing a relationship between a resolution size and division ratio information, which is established in advance, to determine the division ratio information for dividing the first target remote sensing image according to the resolution size of the first target remote sensing image.

As yet another example, the resolution size of the first target remote sensing image is 240 pixels × 320 pixels. By looking up the table representing the relationship between the resolution and the division ratio information, the division ratio information can be obtained as 1: 4.

And secondly, carrying out image segmentation on the first target remote sensing image according to the segmentation proportion information to obtain the sub-image set.

As an example, the executing body may perform image uniform segmentation on the first target remote sensing image according to the segmentation scale information to obtain the sub-image set. That is, the size of the number of pixels of each sub-image in the resulting set of sub-images is the same.

As yet another example, the resolution size of the first target remote sensing image is 240 pixels × 320 pixels. The division ratio information is 1: 4. The executing body uniformly divides the first target remote sensing image, and the resolution of each sub-image in the sub-image set is 60 pixels × 80 pixels.

Step 202, a second target remote sensing image set which is shot by a second target remote sensing image sensor aiming at the corresponding area of each area information in the obtained area information set and has the resolution size meeting a second preset condition is obtained.

In some embodiments, the executing subject may acquire, in a wired manner or in a wireless manner, a second target remote sensing image set which is captured by a second target remote sensing image sensor for each area corresponding to the area information in the obtained area information set and has a resolution satisfying a second predetermined condition. And the resolution ratio of the second target remote sensing image in the second target remote sensing image set is greater than that of the first target remote sensing image. The second target remote sensing image sensor may be a sensor for taking a remote sensing image of a certain resolution. The resolution of the remote sensing image taken by the second target remote sensing image sensor may be greater than the resolution of the remote sensing image taken by the first target remote sensing image sensor. The second predetermined condition may be that the resolution size is within a second interval. For example, the second section corresponding to the first preset condition may be [800, 2000] pixel × [2000, 3000] pixel. The area information may represent geographical location information of an area. The area information corresponding to the sub-image may be geographical location information corresponding to the sub-image. I.e. the geographical location information of the sub-image corresponding content. For example, the area information may include respective coordinates to characterize geographic location information of the corresponding area.

And 203, generating position information of each first oil tank information in a first oil tank information set corresponding to the first target remote sensing image and radius information of each first oil tank information in the first oil tank information set according to the first target remote sensing image and a pre-trained oil tank identification model set.

In some embodiments, the execution main body may generate, based on the first target remote sensing image and a previously trained tank recognition model set, position information of each first tank information in a first tank information set corresponding to the first target remote sensing image and radius information of each first tank information in the first tank information set. The position information of the first tank information may be coordinate information of the tank on the first remote sensing target image.

Wherein the tank identification model may be, but is not limited to, at least one of: SSD (Single Shot MultiBox Detector) algorithm, R-CNN (Region-conditional Neural Networks) algorithm, Fast R-CNN (Fast Region-conditional Neural Networks) algorithm, SPP-NET (spatial Neural Networks) algorithm, YOLO (Young Look one) algorithm, FPN (feed Neural Networks) algorithm, DCN (DeformaConvNet) algorithm, Retina target detection algorithm.

As an example, the execution main body may generate, based on the first target remote sensing image and a previously trained tank recognition model set, position information of each first tank information in a first tank information set corresponding to the first target remote sensing image and radius information of each first tank information in the first tank information set by performing the following steps:

in the first step, the execution body may input the first target remote sensing image into each tank recognition model in a tank recognition model set trained in advance, to output position information of each third tank information in a third tank information set corresponding to the first target remote sensing image and radius information of each third tank information in the third tank information set, and to obtain position information of each third tank information in a third tank information set group and radius information of each third tank information in the third tank information set group.

In the second step, the execution main body may perform position information deduplication processing to remove duplicate position information in the position information of each third tank information in the third tank information set group, and obtain position information of each first tank information in the first tank information set corresponding to the first target remote sensing image and radius information of each first tank information in the first tank information set.

And 204, for each second target remote sensing image in the second target remote sensing image set, generating position information of each second oil tank information in a second oil tank information set corresponding to the second target remote sensing image and radius information of each second oil tank information in the second oil tank information set according to the second target remote sensing image and the oil tank identification model set.

In some embodiments, the execution body may generate, for each second target remote sensing image in the second target remote sensing image set, position information of each second tank information in the second tank information set corresponding to the second target remote sensing image and radius information of each second tank information in the second tank information set, based on the second target remote sensing image and the tank identification model set. Wherein the position information of the second tank information may be coordinate information of the tank on the second remote sensing target image.

As an example, the execution main body may generate, based on the second target remote sensing image and the tank identification model set, position information of each of the second tank information in the second tank information set corresponding to the second target remote sensing image and radius information of each of the second tank information in the second tank information set by performing the following steps:

in the first step, the execution body may input the second target remote sensing image into each tank recognition model in a tank recognition model set trained in advance, and output position information of each fifth tank information in a fifth tank information set corresponding to the second target remote sensing image and radius information of each fifth tank information in the fifth tank information set, to obtain position information of each fifth tank information in a fifth tank information set group and radius information of each fifth tank information in the fifth tank information set group.

In the second step, the execution main body may perform position information deduplication processing to remove duplicate position information from the position information of each fifth tank information in a fifth tank information set group, and obtain position information of each second tank information in a second tank information set corresponding to the second target remote sensing image and radius information of each second tank information in the second tank information set.

In some optional implementations of some embodiments, the generating, from the second target remote sensing image and the tank identification model set, position information of each second tank information in a second tank information set corresponding to the second target remote sensing image and radius information of each second tank information in the second tank information set may include:

In the second step, the execution main body may re-divide the fifth tank information set group according to the position information of each of the fifth tank information sets to obtain a sixth tank information set group. The sixth tank information in the sixth tank information set includes the same position information.

And a third step, the execution main body may determine the number of the oil tanks corresponding to each sixth oil tank information set in the sixth oil tank information set group, to obtain a second oil tank number set.

The execution main body may generate, based on the second tank number set, position information of each piece of second tank information in a second tank information set corresponding to the second target remote sensing image and radius information of each piece of second tank information in the second tank information set.

As an example, the execution main body may first filter out the second number of oil tanks, the number of which is greater than a preset threshold value, from the second number of oil tanks set, as a target second number of oil tanks, and obtain at least one second number of oil tanks. And the preset threshold value is smaller than the number of the oil tank identification models in the oil tank identification model set. Then, the execution main body may determine a sixth tank information set corresponding to each of the at least one second tank number, and obtain at least one sixth tank information set. And finally, generating the position information of each second oil tank information in the second oil tank information set corresponding to the second target remote sensing image and the radius information of each second oil tank information in the second oil tank information set by determining the oil tank position information and the radius information corresponding to each sixth oil tank information set in at least one sixth oil tank information set.

in the first step, the execution body may input the second target remote sensing image into each tank recognition model in a tank recognition model set trained in advance, and output position information of each seventh tank information in a seventh tank information set corresponding to the second target remote sensing image, radius information of each seventh tank information in the seventh tank information set, and confidence information of each seventh tank information in the seventh tank information set, to obtain position information of each seventh tank information in a seventh tank information set group, radius information of each seventh tank information in the seventh tank information set group, and confidence information of each seventh tank information in the seventh tank information set group.

In the second step, the execution main body may re-divide the seventh tank information set group according to the position information of each of the seventh tank information to obtain an eighth tank information set group. Wherein the same position information exists for each of the eighth tank information in the eighth tank information set.

In the third step, the execution body may determine the number of tanks corresponding to each of the eighth tank information sets in the eighth tank information set group.

In the fourth step, the execution main body may remove an eighth tank information set having a number of tanks smaller than a first predetermined threshold from the eighth tank information set group to obtain at least one eighth tank information set. Wherein, the first predetermined threshold may be preset.

In the fifth step, the execution main body may obtain a priority of each tank identification model in the tank identification model set. The priority of each tank model may be preset.

The execution agent may generate weight information corresponding to each of the tank identification models based on the priority of each of the tank identification models. The weight information corresponding to each of the tank identification models may be preset.

The execution main body may generate position information of each of the second tank information in the second tank information set corresponding to the second target remote sensing image and radius information of each of the second tank information in the second tank information set, based on the weight information corresponding to each of the tank identification models, the confidence information of each of the eighth tank information in the at least one eighth tank information set, and the number of tanks corresponding to each of the eighth tank information sets in the at least one eighth tank information set.

As an inventive point of the embodiments of the present disclosure, the technical problem mentioned in the background art is solved, that "there is often a problem of low accuracy in performing oil tank detection for a target area by using a convolutional neural network alone". Factors that lead to a relatively low tank detection accuracy are as follows: the convolutional neural network often does not consider some main characteristic information (such as structural types, shadow areas and the like) in the oil tank image, so that the detection accuracy of the oil tank is low. In order to achieve the effect, the oil tank detection is carried out by adopting a plurality of oil tank identification models, and the comprehensive detection of the oil tank identification models can greatly improve the accuracy of the oil tank detection aiming at the target area. In addition, a corresponding priority is set for each of the plurality of tank identification models. The purpose of setting the priority is to: each oil tank identification model has its own model identification characteristics. For each characteristic of the oil tank, a model with particularly high accuracy for identifying the oil tank often exists in the plurality of oil tank identification models (that is, the model is sensitive to each characteristic of the oil tank and is easy to identify). Thus, the detection of each tank in the target area can be more accurate by setting the priority to each tank identification model.

And a step 205 of generating tank layout information of the target area based on the position information of each of the first tank information, the radius information of each of the first tank information, the position information of each of the obtained second tank information, and the radius information of each of the obtained second tank information.

In some embodiments, the execution main body may generate the tank layout information of the target area based on the position information of each of the first tank information, the radius information of each of the first tank information, the position information of each of the obtained second tank information, and the radius information of each of the obtained second tank information. The tank layout information may be position information and radius information corresponding to each of the tanks in the target area. The tank layout information may be various forms of information. For example, the information may be in the form of a table.

As an example, the execution main body may perform data summarization and data deduplication on the position information of each of the first tank information, the radius information of each of the first tank information, the obtained position information of each of the second tank information, and the obtained radius information of each of the second tank information according to a predetermined data format to obtain the tank layout information of the target area.

In some optional implementations of some embodiments, the generating the tank layout information of the target area based on the position information of each of the first tank information, the radius information of each of the first tank information, the obtained position information of each of the second tank information, and the obtained radius information of each of the second tank information may include:

a first step of generating the tank layout information for each of the first tank information by performing a generation step of:

in the first substep, the execution body may determine position information of the first tank information.

In the second sub-step, the execution subject may determine region information corresponding to the location information.

In a third substep, the executing entity may determine a second set of tank information corresponding to the region information.

A fourth substep, the executing body may compare whether second tank information having the same geographical position as the first tank information exists in a second tank information set.

A fifth substep, said executing agent being capable of generating layout information indicative of the presence of said first tank information at said geographical location in said target area in response to determining presence.

And a second step of generating tank layout information of the target area based on the obtained layout information.

As an example, the execution body may first acquire format information of the tank layout information. Then, the execution body may correspondingly convert each of the obtained layout information into the tank layout information of the target area according to the format information.

In some optional implementations of some embodiments, the foregoing step further includes:

in the first step, the execution main body can acquire each standard specification information of the oil tank.

The standard specification information of the oil tank may be standard radius information of the oil tank.

As an example, the execution body may acquire each standard specification information of the oil tank by means of various queries.

And secondly, checking whether each oil tank related in the oil tank layout information meets the standard or not according to each standard specification information.

As an example, the execution body may verify whether or not each of the tanks involved in the tank layout information conforms to each of the standard radius information.

And thirdly, responding to the determined coincidence, and sending the oil tank layout information to an oil tank display terminal to display the oil tank layout information.

With further reference to fig. 3, a flow 300 of further embodiments of a tank layout information generation method according to the present disclosure is shown. The oil tank layout information generation method comprises the following steps:

step 301, performing image segmentation on a first target remote sensing image acquired in advance to obtain a sub-image set.

Step 302, a second target remote sensing image set which is shot by a second target remote sensing image sensor aiming at the corresponding area of each area information in the area information set and has the resolution which meets a second preset condition is obtained.

Step 303 is to input the first target remote sensing image into each tank recognition model in a previously trained tank recognition model set, and output position information of each third tank information in a third tank information set corresponding to the first target remote sensing image and radius information of each third tank information in the third tank information set, thereby obtaining position information of each third tank information in a third tank information set group and radius information of each third tank information in the third tank information set group.

In some embodiments, the execution main body (for example, the electronic device shown in fig. 1) may input the first target remote sensing image into each tank recognition model in a previously trained tank recognition model set, and output position information of each third tank information in a third tank information set corresponding to the first target remote sensing image and radius information of each third tank information in the third tank information set, to obtain position information of each third tank information in a third tank information set group and radius information of each third tank information in the third tank information set group.

And 304, re-dividing the third oil tank information set group according to the position information of each third oil tank information in the third oil tank information set group to obtain a fourth oil tank information set group.

In some embodiments, the execution main body may re-divide the third tank information set group according to the position information of each of the third tank information sets to obtain a fourth tank information set group. Wherein the same position information exists for each of the fourth tank information sets.

Step 305, determining the number of oil tanks corresponding to each fourth oil tank information set in the fourth oil tank information set group to obtain a first oil tank number set.

In some embodiments, the execution main body may determine the number of oil tanks corresponding to each fourth oil tank information set in the fourth oil tank information set group, to obtain the first oil tank number set.

Step 306 is to generate position information of each first tank information in the first tank information set corresponding to the first target remote sensing image and radius information of each first tank information in the first tank information set, based on the first tank number set.

In some embodiments, the execution main body may generate, based on the first tank number set, position information of each first tank information in a first tank information set corresponding to the first target remote sensing image and radius information of each first tank information in the first tank information set.

Step 307 is to generate, for each second target remote sensing image in the second target remote sensing image set, position information of each second tank information in the second tank information set corresponding to the second target remote sensing image and radius information of each second tank information in the second tank information set, based on the second target remote sensing image and the tank identification model set.

And a step 308 of generating tank layout information of the target area based on the position information of each of the first tank information, the radius information of each of the first tank information, the position information of each of the obtained second tank information, and the radius information of each of the obtained second tank information.

In some embodiments, the specific implementation of the

steps

301, 307, and 308 and the technical effect thereof can refer to the

steps

201, 204, and 205 in the embodiment corresponding to fig. 2, which are not described herein again.

As can be seen from fig. 3, compared with the description of some embodiments corresponding to fig. 2, the specific steps of generating the position information of each first tank information in the first tank information set corresponding to the first target remote sensing image and the radius information of each first tank information in the first tank information set are more highlighted in the flow 300 of the tank layout information generating method in some embodiments corresponding to fig. 3. Therefore, the solutions described in the embodiments may generate, with higher accuracy and higher efficiency, the position information of each first tank information in the first tank information set corresponding to the first target remote sensing image and the radius information of each first tank information in the first tank information set by using the tank identification model set.

With further reference to fig. 4, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a tank layout information generation apparatus, which correspond to those of the method embodiments shown in fig. 2, and which may be applied in various electronic devices in particular.

As shown in fig. 4, a tank layout information generating device 400 includes: a dividing unit 401, an acquisition unit 402, a first generation unit 403, a second generation unit 404, and a third generation unit 405. The segmentation unit 401 is configured to perform image segmentation on a first target remote sensing image acquired in advance to obtain a sub-image set, where the first target remote sensing image is an image which is shot by a first target remote sensing image sensor for a target area and has a resolution that meets a first predetermined condition; an obtaining unit 402, configured to obtain a second target remote sensing image set, which is shot by a second target remote sensing image sensor for each corresponding area of area information in an area information set and has a resolution that meets a second predetermined condition, wherein the resolution of the second target remote sensing image in the second target remote sensing image set is greater than the resolution of the first target remote sensing image, and the area information set and the sub-image set have a corresponding relationship; a first generation unit 403 configured to generate, based on the first target remote sensing image and a previously trained tank recognition model set, position information of each first tank information in a first tank information set corresponding to the first target remote sensing image and radius information of each first tank information in the first tank information set; a second generating unit 404 configured to generate, for each second target remote sensing image in the second target remote sensing image set, position information of each second tank information in a second tank information set corresponding to the second target remote sensing image and radius information of each second tank information in the second tank information set, based on the second target remote sensing image and the tank identification model set; the third generating unit 405 is configured to generate the tank layout information of the target area based on the position information of each of the first tank information, the radius information of each of the first tank information, the position information of each of the obtained second tank information, and the radius information of each of the obtained second tank information.

It will be understood that the elements described in the apparatus 400 correspond to various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 400 and the units included therein, and will not be described herein again.

Referring now to fig. 5, a schematic diagram of an electronic device (e.g., the electronic device of fig. 1) 500 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 5, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 5 may represent one device or may represent multiple devices as desired.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program, when executed by the processing device 501, performs the above-described functions defined in the methods of some embodiments of the present disclosure.

It should be noted that the computer readable medium described above in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: carrying out image segmentation on a first target remote sensing image acquired in advance to obtain a sub-image set, wherein the first target remote sensing image is an image which is shot by a first target remote sensing image sensor aiming at a target area and has a resolution which meets a first preset condition; acquiring a second target remote sensing image set which is shot by a second target remote sensing image sensor aiming at each area corresponding to the area information in the area information set and has the resolution which meets a second preset condition, wherein the resolution of a second target remote sensing image in the second target remote sensing image set is greater than that of a first target remote sensing image, and the area information set and the sub-image set have a corresponding relation; generating position information of each first oil tank information in a first oil tank information set corresponding to the first target remote sensing image and radius information of each first oil tank information in the first oil tank information set according to the first target remote sensing image and a pre-trained oil tank identification model set; generating, for each second target remote sensing image in the second target remote sensing image set, position information of each second tank information in the second tank information set corresponding to the second target remote sensing image and radius information of each second tank information in the second tank information set, based on the second target remote sensing image and the tank identification model set; and generating tank layout information of the target area based on the position information of each of the first tank information, the radius information of each of the first tank information, the position information of each of the second tank information, and the radius information of each of the second tank information.

Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, and may be described as: a processor includes a dividing unit, an obtaining unit, a first generating unit, a second generating unit, and a third generating unit. The names of the units do not limit the units themselves in some cases, and for example, the segmentation unit may also be described as a unit for performing image segmentation on a first pre-acquired target remote sensing image to obtain a sub-image set.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims

1. A method for generating oil tank layout information comprises the following steps:

carrying out image segmentation on a first target remote sensing image obtained in advance to obtain a sub-image set, wherein the first target remote sensing image is an image which is shot by a first target remote sensing image sensor aiming at a target area and has a resolution which meets a first preset condition;

acquiring a second target remote sensing image set which is shot by a second target remote sensing image sensor aiming at each area corresponding to the area information in the area information set and has the resolution which meets a second preset condition, wherein the resolution of a second target remote sensing image in the second target remote sensing image set is greater than that of a first target remote sensing image, and the area information set and the sub-image set have a corresponding relation;

generating position information of each first oil tank information in a first oil tank information set corresponding to the first target remote sensing image and radius information of each first oil tank information in the first oil tank information set according to the first target remote sensing image and a pre-trained oil tank identification model set;

for each second target remote sensing image in the second target remote sensing image set, generating position information of each second oil tank information in a second oil tank information set corresponding to the second target remote sensing image and radius information of each second oil tank information in the second oil tank information set according to the second target remote sensing image and the oil tank identification model set;

and generating the tank layout information of the target area based on the position information of each of the first tank information, the radius information of each of the first tank information, the position information of each of the obtained second tank information, and the radius information of each of the obtained second tank information.

2. The method of claim 1, wherein the method further comprises:

acquiring information of each standard specification of the oil tank;

according to the standard specification information, checking whether the oil tanks related in the oil tank layout information meet the checking conditions or not;

and responding to the determined conformity, and sending the oil tank layout information to an oil tank display terminal to display the oil tank layout information.

3. The method of claim 1, wherein the image segmentation of the pre-acquired first target remote sensing image to obtain a sub-image set comprises:

determining segmentation proportion information for segmenting the first target remote sensing image according to the resolution of the first target remote sensing image;

and carrying out image segmentation on the first target remote sensing image according to the segmentation proportion information to obtain the sub-image set.

4. The method according to claim 1, wherein the generating, from the first target remote sensing image and a pre-trained tank recognition model set, position information of each first tank information in a first tank information set corresponding to the first target remote sensing image and radius information of each first tank information in the first tank information set comprises:

inputting the first target remote sensing image into each oil tank identification model in a pre-trained oil tank identification model set, and outputting position information of each third oil tank information in a third oil tank information set corresponding to the first target remote sensing image and radius information of each third oil tank information in the third oil tank information set to obtain the position information of each third oil tank information in a third oil tank information set group and the radius information of each third oil tank information in the third oil tank information set group;

the third oil tank information set group is divided again according to the position information of each piece of third oil tank information in the third oil tank information set group to obtain a fourth oil tank information set group, wherein the same position information exists in each piece of fourth oil tank information in the fourth oil tank information set;

determining the number of oil tanks corresponding to each fourth oil tank information set in the fourth oil tank information set group to obtain a first oil tank number set;

and generating position information of each first oil tank information in a first oil tank information set corresponding to the first target remote sensing image and radius information of each first oil tank information in the first oil tank information set according to the first oil tank number set.

5. The method according to claim 1, wherein the generating, from the second target remote sensing image and the tank identification model set, position information of each second tank information in a second tank information set corresponding to the second target remote sensing image and radius information of each second tank information in the second tank information set comprises:

inputting the second target remote sensing image into each oil tank identification model in a pre-trained oil tank identification model set, and outputting position information of each fifth oil tank information in a fifth oil tank information set corresponding to the second target remote sensing image and radius information of each fifth oil tank information in the fifth oil tank information set to obtain the position information of each fifth oil tank information in a fifth oil tank information set group and the radius information of each fifth oil tank information in the fifth oil tank information set group;

the fifth oil tank information set group is divided again according to the position information of each piece of fifth oil tank information in the fifth oil tank information set group to obtain a sixth oil tank information set group, wherein the same position information exists in each piece of sixth oil tank information in the sixth oil tank information set;

determining the number of oil tanks corresponding to each sixth oil tank information set in the sixth oil tank information set group to obtain a second oil tank number set;

and generating position information of each second oil tank information in a second oil tank information set corresponding to the second target remote sensing image and radius information of each second oil tank information in the second oil tank information set according to the second oil tank number set.

6. The method according to claim 1, wherein the generating, from the second target remote sensing image and the tank identification model set, position information of each second tank information in a second tank information set corresponding to the second target remote sensing image and radius information of each second tank information in the second tank information set comprises:

inputting the second target remote sensing image into each oil tank identification model in a pre-trained oil tank identification model set, and outputting position information of each piece of seventh oil tank information in a seventh oil tank information set corresponding to the second target remote sensing image, radius information of each piece of seventh oil tank information in the seventh oil tank information set and confidence information of each piece of seventh oil tank information in the seventh oil tank information set to obtain position information of each piece of seventh oil tank information in a seventh oil tank information set group, radius information of each piece of seventh oil tank information in the seventh oil tank information set group and confidence information of each piece of seventh oil tank information in the seventh oil tank information set group;

the seventh oil tank information set group is divided again according to the position information of each piece of seventh oil tank information in the seventh oil tank information set group to obtain an eighth oil tank information set group, wherein the same position information exists in each piece of eighth oil tank information in the eighth oil tank information set;

determining the number of oil tanks corresponding to each eighth oil tank information set in the eighth oil tank information set group;

removing eighth oil tank information sets of which the number of oil tanks is smaller than a first preset threshold value from the eighth oil tank information set group to obtain at least one eighth oil tank information set;

acquiring the priority of each oil tank identification model in the oil tank identification model set;

generating weight information corresponding to each oil tank identification model according to the priority of each oil tank identification model;

and generating position information of each piece of second oil tank information in the second oil tank information set corresponding to the second target remote sensing image and radius information of each piece of second oil tank information in the second oil tank information set according to the weight information corresponding to each oil tank identification model, the confidence information of each piece of eighth oil tank information in the at least one piece of eighth oil tank information set and the number of oil tanks corresponding to each piece of eighth oil tank information set in the at least one piece of eighth oil tank information set.

7. The method according to claim 1, wherein the generating tank layout information for the target area based on the position information of the respective first tank information, the radius information of the respective first tank information, the obtained position information of the respective second tank information, and the obtained radius information of the respective second tank information, comprises:

for each of the respective first tank information, performing the following generating steps to generate layout information of the first tank information:

determining position information of the first tank information;

determining area information corresponding to the position information;

determining a second set of tank information corresponding to the regional information;

comparing whether second oil tank information with the same geographical position as the first oil tank information exists in a second oil tank information set or not;

in response to determining presence, generating layout information characterizing the presence of the first tank information at the geographic location in the target area;

and generating the oil tank layout information of the target area according to the obtained layout information.

8. An oil tank layout information generation device comprising:

the image segmentation unit is configured to perform image segmentation on a first target remote sensing image acquired in advance to obtain a sub-image set, wherein the first target remote sensing image is an image which is shot by a first target remote sensing image sensor aiming at a target area and has a resolution size meeting a first preset condition;

an acquisition unit configured to acquire a second target remote sensing image set which is shot by a second target remote sensing image sensor for each area corresponding to area information in an area information set and has a resolution size satisfying a second predetermined condition, wherein the resolution of a second target remote sensing image in the second target remote sensing image set is greater than that of a first target remote sensing image, and the area information set and the subimage set have a corresponding relationship;

a first generation unit configured to generate, according to the first target remote sensing image and a pre-trained tank recognition model set, position information of each first tank information in a first tank information set corresponding to the first target remote sensing image and radius information of each first tank information in the first tank information set;

a second generation unit configured to generate, for each second target remote sensing image in the second target remote sensing image set, position information of each second tank information in a second tank information set corresponding to the second target remote sensing image and radius information of each second tank information in the second tank information set, based on the second target remote sensing image and the tank identification model set;

and a third generating unit configured to generate the tank layout information of the target area based on the position information of each of the first tank information, the radius information of each of the first tank information, the position information of each of the obtained second tank information, and the radius information of each of the obtained second tank information.

9. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.

10. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-7.