Fire spread area prediction method based on image recognition

Abstract

The present application relates to the field of image recognition technology, and discloses a method for predicting the fire spread area based on image recognition, including: obtaining a first image to be recognized corresponding to a target area; the first image to be recognized is obtained by photographing a forest or mountain area at a preset position; determining whether a fire has occurred according to the first image to be recognized, and in the case of a fire, determining a first fire area according to the first image to be recognized; obtaining a second image to be recognized corresponding to the target area after a preset time period, and determining a second fire area according to the second image to be recognized; predicting the fire spread area according to the first fire area and the second fire area. In this way, it is convenient to improve the prevention and control ability of forest fires and is beneficial to effectively carry out rescue when a forest fire occurs.

Description

Technical Field

[0001] This application relates to the field of image recognition technology, for example, to a method for predicting the spread area of a fire based on image recognition. Background Art

[0002] Forest fires are one of the most difficult natural disasters to prevent globally and cause the most serious harm, easily leading to serious losses of forest resources and causing serious casualties.

[0003] Predicting the spread range of a forest fire is of great significance for determining the impact range of the forest fire and related rescue measures, helping to improve the prevention and control ability of forest fires and facilitating effective rescue when a forest fire occurs. Summary of the Invention

[0004] To provide a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a comprehensive review nor is it intended to identify key / important elements or delineate the scope of protection of these embodiments, but rather serves as a preamble to the following detailed description.

[0005] Embodiments of the present disclosure provide a method for predicting the spread area of a fire based on image recognition to facilitate predicting the spread range of a forest fire.

[0006] In some embodiments, the method includes: obtaining a first image to be recognized corresponding to a target area; the first image to be recognized is obtained by photographing a forest or mountain at a preset position; determining whether a fire has occurred based on the first image to be recognized, and in the case of a fire, determining a first ignition area based on the first image to be recognized; obtaining a second image to be recognized corresponding to the target area after a preset time period, and determining a second ignition area based on the second image to be recognized; predicting the fire spread area based on the first ignition area and the second ignition area.

[0007] The method for predicting the spread area of a fire based on image recognition provided by the embodiments of the present disclosure can achieve the following technical effects: obtaining a first image to be recognized corresponding to a target area by photographing a forest at a preset position, determining whether a fire has occurred based on the first image to be recognized, and in the case of a fire, determining a first ignition area based on the first image to be recognized and obtaining a second image to be recognized corresponding to the target area after a preset time period, determining a second ignition area based on the second image to be recognized, and then predicting the fire spread area based on the first ignition area and the second ignition area, which is convenient for improving the prevention and control ability of forest fires and is beneficial to effective rescue when a forest fire occurs.

[0008] The above general description and the following description are only exemplary and explanatory and are not used to limit this application. Brief Description of the Drawings

[0009] One or more embodiments are exemplarily illustrated by corresponding drawings. These exemplary illustrations and the drawings do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation, and wherein:

[0010] Figure 1 It is a schematic diagram of a method for predicting the fire spread area based on image recognition provided by an embodiment of the present disclosure. Detailed implementation manners

[0011] In order to be able to understand the features and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure will be described in detail below with reference to the drawings. The attached drawings are for reference and illustration only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the sake of explanation, numerous details are provided to give a thorough understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other instances, well-known structures and devices may be shown in a simplified manner to simplify the drawings.

[0012] The terms "first", "second", etc. in the specification, claims and above-mentioned drawings of the embodiments of the present disclosure are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such data may be interchanged under appropriate circumstances so as to implement the embodiments of the present disclosure described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion.

[0013] Unless otherwise stated, the term "plurality" means two or more.

[0014] In the embodiments of the present disclosure, the character " / " indicates that the front and rear objects are in an "or" relationship. For example, A / B means: A or B.

[0015] The term "and / or" is a description of the associated relationship of an object, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B these three relationships.

[0016] The term "corresponding" may refer to an associated relationship or a binding relationship. A corresponding to B means that there is an associated relationship or a binding relationship between A and B.

[0017] Combined with Figure 1 As shown, the embodiments of the present disclosure provide a method for predicting the fire spread area based on image recognition, including:

[0018] Step S101, obtaining a first image to be recognized corresponding to a target area; the first image to be recognized is obtained by photographing a forest or mountain at a preset position;

[0019] Step S102: Determine whether a fire has occurred based on the first image to be recognized. In the case of a fire, determine the first ignition area based on the first image to be recognized.

[0020] Step S103: After a preset time period, obtain a second image to be recognized corresponding to the target area, and determine the second ignition area based on the second image to be recognized.

[0021] Step S104: Predict the fire spread area based on the first ignition area and the second ignition area.

[0022] Using the method for predicting the fire spread area based on image recognition provided by the embodiments of the present disclosure, a first image to be recognized corresponding to the target area is obtained by photographing a forest at a preset position. Determine whether a fire has occurred based on the first image to be recognized. In the case of a fire, determine the first ignition area based on the first image to be recognized and obtain a second image to be recognized corresponding to the target area after a preset time period. Determine the second ignition area based on the second image to be recognized, and then predict the fire spread area based on the first ignition area and the second ignition area, which is convenient for improving the prevention and control ability of forest fires and is beneficial to effective rescue when a forest fire occurs.

[0023] Optionally, the first image to be recognized is a remote sensing image. Optionally, the first image to be recognized is an image taken at a preset position.

[0024] Optionally, the second image to be recognized is a remote sensing image. Optionally, the second image to be recognized is an image taken at a preset position.

[0025] Optionally, determining whether a fire has occurred based on the first image to be recognized includes: determining the pixels with a preset first RGB value in the first image to be recognized as the first alternative pixels; in the case where the number of the first alternative pixels reaches a preset threshold, determining that a fire has occurred; in the case where the number of the first alternative pixels does not reach the preset threshold, determining that no fire has occurred.

[0026] Optionally, determining the first ignition area based on the first image to be recognized includes: determining all the first alternative pixels in the first image to be recognized as the first ignition area.

[0027] Optionally, determining the second ignition area based on the second image to be recognized includes: determining the pixels with a preset first RGB value in the second image to be recognized as the second alternative pixels; determining all the second alternative pixels in the second image to be recognized as the second ignition area.

[0028] Optionally, predicting the fire spread area based on the first fire area and the second fire area includes: determining a second alternative pixel point different from the position of the first alternative pixel point as a fire spread pixel point; determining all fire spread pixel points in the second image to be recognized as an alternative fire spread area; obtaining wind direction prediction information for a plurality of different time periods; inputting the first image to be recognized into a preset plant recognition model to obtain a first plant area; inputting the first plant area and the wind direction prediction information into a preset fire spread time prediction model to obtain a plurality of second plant areas and the corresponding fire spread time periods for each second plant area; the second plant area is an area in the first plant area; inputting the second image to be recognized, the alternative fire spread area, each second plant area, and each fire spread time period into a preset fire spread area prediction model to obtain the fire spread area corresponding to each fire spread time period in the second image to be recognized.

[0029] Optionally, obtaining wind direction prediction information for a plurality of different time periods includes: obtaining wind direction prediction information for a plurality of different time periods from a cloud server.

[0030] Optionally, the plant recognition model is obtained by: inputting a sample image with a plant area label into a preset neural network model for training to obtain the plant recognition model.

[0031] Optionally, the first plant area is used to represent the position information of the plants in the first image to be recognized. The first plant area is the pixel coordinates representing the plants in the first image to be recognized.

[0032] Optionally, the fire spread time prediction model is obtained by: inputting first sample information with a plant area label and a fire spread time period label into a preset neural network model for training to obtain the fire spread time prediction model; the first sample information includes a wind direction prediction information sample and a plant area sample.

[0033] Optionally, the fire spread time period is the different time periods corresponding to the wind direction prediction information.

[0034] Optionally, the fire spread area prediction model is obtained by: inputting second sample information with a fire spread area label and a fire spread time period label into a preset neural network model for training to obtain the fire spread area prediction model; the second sample information includes a sample image, an alternative fire spread area sample, a fire spread time period sample, and a plant area sample.

[0035] Since the alternative fire spread area is all the fire spread pixel points in the second image to be recognized, which is the actual area where the fire has occurred and is equivalent to the starting ignition point, while the second plant area and its corresponding fire spread time period are estimated based on the wind direction prediction information and the position information of the plants in the first image to be recognized, which is obtained equivalent to the prediction basis or prediction experience. In this way, combining the alternative fire spread area and the fire spread time period to predict the fire spread area in a future time period is more in line with the actual situation and the estimation is more accurate.

[0036] By using the fire spread area prediction method provided by the embodiments of the present disclosure to predict the fire spread range of a forest fire, the influence range of the forest fire can be determined more accurately, which is convenient for carrying out relevant rescue measures, helps to improve the prevention and control ability of forest fires, and is more convenient for effective rescue when a forest fire occurs.

[0037] In some embodiments, after predicting the fire spread area based on the first ignition area and the second ignition area, it further includes: generating a rescue route according to the fire spread area.

[0038] Optionally, generating a rescue route according to the fire spread area includes: obtaining the to-be-rescued position selection information sent by the user through the user terminal, where the to-be-rescued position selection information is the to-be-rescued position pixel points in the second image to be recognized; obtaining the time point for generating the route input by the user; determining the fire spread area corresponding to the time point for generating the route as the target fire spread area; determining the pixel points outside the target fire spread area in the second image to be recognized as the target pixel points; splicing the second image to be recognized with a preset map to obtain a target image; the map is preset with safe area pixel points; the safe area pixel points are used to represent buildings; selecting a target pixel point with the smallest distance to the safe area pixel points in the target image as the safe pixel point; connecting the to-be-rescued position pixel points and the safe pixel points with straight line segments in the target image, and connecting the safe pixel points and the safe area pixel points with straight line segments to form a rescue route in the target image.

[0039] Optionally, the to-be-rescued position pixel point is a pixel point selected by the user in the second image to be recognized. The to-be-rescued position pixel point is used to represent the to-be-rescued position.

[0040] Since the safe pixel point is the target pixel point with the smallest distance to the safe area pixel points in the target image, connecting the to-be-rescued position pixel points and the safe area pixel points with straight line segments through the safe pixel points to form a rescue route, through which the to-be-rescued position in the forest can be reached more quickly and it is convenient for rescue.

[0041] When the pixel point at the position to be rescued is not in the target fire spread area or not in the fire spread area, the straight line segment between the safe pixel point and the pixel point at the position to be rescued does not pass through the target fire spread area, and the straight line segment between the safe pixel point and the pixel point in the safe area does not pass through the target fire spread area; in this way, the entire rescue route is made safer and it is convenient to quickly carry out rescue work. Even when the pixel point at the position to be rescued is in the target fire spread area or in the fire spread area, rescue work can still be carried out more quickly through the rescue route. By carrying out rescue work through the rescue route formed by the embodiments of the present disclosure, it can not only play an indicative role of the rescue route during rescue, but also play an indicative role of the retreat route during retreat.

[0042] Optionally, the user terminal refers to an electronic device with wireless connection function. In some embodiments, the user terminal is, for example, a mobile device, a computer, or an in-vehicle device built in a hovering vehicle, etc., or any combination thereof. The mobile device may include, for example, a mobile phone, a smart home device, a wearable device, a smart mobile device, a virtual reality device, etc., or any combination thereof, where the wearable device includes, for example: a smart watch, a smart bracelet, a pedometer, etc.

[0043] Optionally, after generating the rescue route according to the fire spread area, it further includes: sending the target image with the rescue route to the user terminal to trigger the user terminal to display the target image with the rescue route.

[0044] The technical solution of the embodiments of the present disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present disclosure. The foregoing storage medium may be a non-transitory storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc, etc., which are various media that can store program codes, or it may also be a transient storage medium.

[0045] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure, enabling those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. The embodiments only represent possible variations. Unless explicitly required, the individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terms used in this application are only for describing the embodiments and do not limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to also include the plural forms. Similarly, as used in this application, the term "and / or" refers to any and all possible combinations including one or more of the associated listed items. Additionally, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" etc. mean the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups of these. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, or apparatus including the element. In this article, what each embodiment focuses on can be the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method parts disclosed in the embodiments, the relevant parts can refer to the description of the method parts.

[0046] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner can depend on the specific application and design constraints of the technical solution. The technical personnel can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the embodiments of the present disclosure. The technical personnel can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0047] The flowcharts in the accompanying drawings illustrate the possible architectures, functions, and operations of methods and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart may represent a segment or portion of a program, and the segment or portion of the program may include one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the descriptions, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. Each block in the flowchart, as well as combinations of blocks in the flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for predicting the fire spread area based on image recognition, characterized in that, Including: Obtaining a first image to be recognized corresponding to a target area; The first image to be recognized is obtained by photographing a forest or mountain area at a preset position; Determining whether a fire has occurred according to the first image to be recognized, and in the case of a fire, determining a first fire area according to the first image to be recognized; Obtaining a second image to be recognized corresponding to the target area after a preset time period, and determining a second fire area according to the second image to be recognized; Predicting a fire spread area according to the first fire area and the second fire area; Wherein, pixel points with a preset first RGB value in the first image to be recognized are determined as first alternative pixel points, and the first alternative pixel points are used to determine the first fire area; pixel points with the preset first RGB value in the second image to be recognized are determined as second alternative pixel points, and the second alternative pixel points are used to determine the second fire area; Wherein, predicting the fire spread area according to the first fire area and the second fire area includes: determining second alternative pixel points with different positions from the first alternative pixel points as fire spread pixel points; determining all the fire spread pixel points in the second image to be recognized as an alternative fire spread area; obtaining wind direction prediction information for several different time periods; inputting the first image to be recognized into a preset plant recognition model to obtain a first plant area; inputting the first plant area and the wind direction prediction information into a preset fire spread time prediction model to obtain several second plant areas and corresponding fire spread time periods for each of the second plant areas, where the fire spread time periods are different time periods corresponding to the wind direction prediction information; the second plant areas are areas in the first plant area; inputting the second image to be recognized, the alternative fire spread area, each of the second plant areas, and each of the fire spread time periods into a preset fire spread area prediction model to obtain the fire spread area corresponding to each of the fire spread time periods in the second image to be recognized; wherein, the first plant area is the pixel point coordinates representing plants in the first image to be recognized; After predicting the fire spread area according to the first fire area and the second fire area, it further includes: obtaining the rescue position selection information sent by the user through the user terminal, where the rescue position selection information is the pixel points of the rescue position in the second image to be recognized; obtaining the route generation time point input by the user; determining the fire spread area corresponding to the route generation time point as the target fire spread area; determining the pixel points outside the target fire spread area in the second image to be recognized as target pixel points; splicing the second image to be recognized with a preset map to obtain a target image; the map is preset with safe area pixel points; the safe area pixel points are used to represent buildings; selecting a target pixel point with the smallest distance to the safe area pixel points in the target image as the safe pixel point; connecting the rescue position pixel points and the safe pixel points with a straight line segment in the target image to form a rescue route in the target image.

2. The method according to claim 1, wherein Determining whether a fire has occurred according to the first image to be recognized includes: When the number of the first alternative pixel points reaches a preset threshold, it is determined that a fire has occurred; when the number of the first alternative pixel points does not reach the preset threshold, it is determined that no fire has occurred.

3. The method according to claim 2, wherein Determining a first fire area according to the first image to be recognized includes: Determining all the first alternative pixel points in the first image to be recognized as the first fire area.

4. The method according to claim 3, characterized in that, Determining a second fire area according to the second image to be recognized includes: Determining all the second alternative pixel points in the second image to be recognized as the second fire area.

Images