CN110866900A

CN110866900A - Water body color identification method and device

Info

Publication number: CN110866900A
Application number: CN201911069177.6A
Authority: CN
Inventors: 邹煜; 周威; 田丁; 聂一亮; 林作永; 陈鹏飞; 舒伟; 陈琳
Original assignee: Jiang He Tong (beijing) Technology Co Ltd
Current assignee: Jiang He Tong (beijing) Technology Co Ltd
Priority date: 2019-11-05
Filing date: 2019-11-05
Publication date: 2020-03-06

Abstract

The application provides a water color identification method and a water color identification device, wherein the method comprises the following steps: collecting water body color picture information of a target water area; inputting the water color picture information of the target water area into a preset water pollution level judgment model; and outputting and displaying an output result of the preset water pollution level judgment model so as to determine the pollution degree of the target water area. The method and the device can improve the accuracy and the real-time performance of water color identification, and further improve the accuracy of water pollution detection.

Description

Water body color identification method and device

Technical Field

The application relates to the technical field of image recognition, in particular to a water body color recognition method and device.

Background

With the development of industrial technology and urbanization, a great deal of water pollution is generated, the water pollution not only causes environmental damage but also influences the life safety of human beings, and the most obvious characteristic of the water pollution is that the color of a water body is changed.

In order to identify the color of a water body, the prior art generally adopts a method comprising: a water body color detection method and an SVM image processing method based on an MODIS image; the water color detection method based on the MODIS image comprises the steps of converting an RGB value of each pixel into a tristimulus value in colorimetry, calculating a chromaticity coordinate of each pixel in a chromaticity diagram coordinate system based on the tristimulus value of each pixel, and determining the water color level and the water color through multiple processing based on the chromaticity coordinate; the SVM image processing method comprises the steps of extracting saturation brightness ratio color features (S/V) of water body areas in samples, combining four texture features of a gray level co-occurrence matrix to form a five-dimensional feature vector, and then constructing an SVM classifier model through sample training, wherein the area of positive samples in the classifier is a water body, and the negative samples are the earth surface.

The water color detection method based on the MODIS image can carry out macroscopic, large-scale and long-time remote sensing detection on the water color, but is not suitable for small-scale water color identification, and in addition, RGB imaging of the image cannot well express the actual water color, so that the identification result is inaccurate. The SVM image processing method can effectively weaken the negative influence of illumination change on the water body detection based on the color characteristics, but the overall accuracy is difficult to guarantee.

Disclosure of Invention

Aiming at the problems in the prior art, the application provides a water body color identification method and device, which can improve the accuracy and real-time of water body color identification and further improve the accuracy of water body pollution detection.

In order to solve the technical problem, the present application provides the following technical solutions:

in a first aspect, the present application provides a water color identification method, including:

collecting water body color picture information of a target water area;

inputting the water color picture information of the target water area into a preset water pollution level judgment model;

and outputting and displaying an output result of the preset water pollution level judgment model so as to determine the pollution degree of the target water area.

Further, before the acquiring the water color picture information of the target water area, the method further comprises:

and inputting the pre-acquired water color labeling picture information into a U-Net model for training to acquire the water pollution level judgment model.

Further, before inputting the pre-acquired water color labeling picture information into the U-Net model for training, the method further includes: collecting water body color image information of different areas; and setting a corresponding semantic label for the water color picture information according to a semantic segmentation technology and a preset water pollution level so as to generate the water color labeling picture information.

Further, after the inputting the water color picture information of the target water area into a preset water pollution level judgment model, the method further includes: and if the output result of the preset water pollution level judgment model exceeds a preset early warning level, outputting early warning information.

In a second aspect, the present application provides a water color identification device, comprising:

the first acquisition module is used for acquiring water body color picture information of a target water area;

the processing module is used for inputting the water color picture information of the target water area into a preset water pollution level judgment model;

and the output module is used for outputting and displaying an output result of the preset water pollution level judgment model so as to determine the pollution degree of the target water area.

Further, the water color recognition device further includes: and the training module is used for inputting the pre-acquired water color labeling picture information into a U-Net model for training so as to acquire the water pollution level judgment model.

Further, the water color recognition device further includes: the second acquisition module is used for acquiring water body color image information of different areas; and the semantic label setting module is used for setting a corresponding semantic label for the water color picture information according to a semantic segmentation technology and a preset water pollution level so as to generate the water color labeling picture information.

Further, the water color recognition device further includes: and the early warning module is used for outputting early warning information if the output result of the preset water pollution level judgment model exceeds a preset early warning level.

In a third aspect, the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the water color identification method when executing the program.

In a fourth aspect, the present application provides a computer readable storage medium having stored thereon computer instructions which, when executed, implement the steps of the water color identification method.

According to the technical scheme, the embodiment of the application provides a water color identification method and a device, wherein the water color identification method comprises the following steps: collecting water body color picture information of a target water area; inputting the water color picture information of the target water area into a preset water pollution level judgment model; the output result of the preset water pollution level judgment model is output and displayed to determine the pollution degree of the target water area, so that the accuracy and the real-time performance of water color identification can be improved, the accuracy and the high efficiency of water pollution early warning are improved, the application range is wider, and the method is not only suitable for large-scale water areas but also suitable for small-scale water areas.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flow chart of a water color identification method in an embodiment of the present application;

fig. 2 is a schematic flow chart of

steps

011, 012 and 010 of a water color identification method in an embodiment of the present application;

fig. 3 is a schematic structural diagram of a water color identification device according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of a second acquisition module, a semantic label setting module and a training module of the water color recognition device in the embodiment of the present application;

fig. 5 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present application.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

In order to facilitate understanding of the technical solutions provided by the present application, the following briefly describes the related knowledge and research background in the technical field of the present application.

Image Recognition (Image Recognition), which is a technology for processing, analyzing and understanding images by using a computer to recognize various different patterns of objects and objects, is a practical application for applying a deep learning algorithm. The traditional image identification process is divided into four steps: image acquisition → image preprocessing → feature extraction → image recognition. In addition, the technology refers to the technology for classifying remote sensing images in geography.

Convolutional Neural Networks (CNN) are a class of feed forward Neural Networks (fed forward Neural Networks) that contain convolution computations and have a deep structure, and are one of the representative algorithms for deep learning (deep). Convolutional neural Networks have a feature learning (rendering) capability, and can perform Shift-Invariant classification (Shift-Invariant classification) on input information according to a hierarchical structure thereof, and are also called "Shift-Invariant artificial neural Networks (SIANN)".

Semantic Segmentation (Semantic Segmentation) is a typical computer vision problem that involves taking some raw data (e.g., flat images) as input and converting them into masks with highlighted regions of interest. Many people use the term full-pixel semantic segmentation (full-pixel semantic segmentation), in which each pixel in an image is assigned a category ID according to the object of interest to which it belongs. Early computer vision problems only found elements like edges (lines and curves) or gradients, but they never provided pixel-level image understanding in a fully human-perceptible manner. Semantic segmentation solves this problem by grouping together image parts belonging to the same object, thus expanding its application area. To understand the features of image segmentation, the following three general classes of image classification techniques will be introduced: 1. and image classification, which is mainly used for identifying images. For example, a categorical digital script such as "handwriting a number, which number is one of 0-9". Amazon recognition, originally issued from Amazon, also belongs to this image classification and needs to distinguish "cups, smartphones and bottles" and so on, but now Amazon recognition has labeled cups and coffee cups as the whole image, and after doing so, it cannot be used to classify scenes with multiple objects in the image. In this case, an "image detection" technique should be used. 2. Image detection, mainly to identify "what is" and "where it is" in an image. 3. And image segmentation, mainly identifying image areas. Instead of detecting the entire image or a portion of the image, image segmentation, known as semantic segmentation, marks the meaning indicated by the pixel of each pixel.

U-Net network encoder-decoder (encoder-decoder) architecture. Wherein the encoder progressively reduces the spatial dimension of the input data using the pooling layer, while the decoder progressively restores the details and corresponding spatial dimension of the target through a network layer such as an deconvolution layer. From encoder to decoder, there is usually a direct information connection to help the decoder to better recover the target details. The U-Net network has a good recognition effect in the application of semantic segmentation.

In the prior art, a method for detecting water color includes: a water body color detection method and an SVM image processing method based on an MODIS image are disclosed. The method for detecting the water color based on the MODIS image comprises the steps of obtaining the MODIS image which reflects the water color and has RGB wave band combination; converting the RGB value of each pixel of the MODIS image into tristimulus values; calculating the chromaticity coordinate of each pixel in a chromaticity diagram coordinate system based on the tristimulus values of the pixels; calculating new coordinates of the chromaticity coordinates of each pixel in a predetermined coordinate system; calculating the included angle of the new coordinate of each pixel relative to the X axis of a preset coordinate system; determining the color dominant wavelength of each included angle according to the corresponding relation between the preset included angle and the color dominant wavelength, and determining the water color grade of each included angle according to the corresponding relation between the preset included angle and the water color grade; and determining the water color according to the determined color dominant wavelength and the water color level. The method realizes the application of the remote sensing method to the macroscopic, large-range and long-time remote sensing detection of the water body color. Specifically, new coordinates of the chromaticity coordinates of each pixel in a predetermined coordinate system are calculated through coordinate conversion, the X axis of the predetermined coordinate system is parallel to the Y axis of the chromaticity diagram coordinate system, and the forward direction of the chromaticity diagram coordinate system is consistent, and the Y axis of the predetermined coordinate system is parallel to the X axis of the chromaticity diagram coordinate system, and the forward direction of the chromaticity diagram coordinate system is consistent; calculating the included angle of the new coordinate of each pixel relative to the X axis of a preset coordinate system; determining the color dominant wavelength of each included angle according to the corresponding relation between the preset included angle and the color dominant wavelength, and determining the water color grade of each included angle according to the corresponding relation between the preset included angle and the water color grade; and determining the water color reflected by the MODIS image according to the determined color dominant wavelength and the water color level.

However, the MODIS image belongs to an aerial image and is not suitable for small-scale water color recognition. The method is that RGB value of each pixel is converted into tristimulus value in colorimetry, and chromaticity coordinate of each pixel in chromaticity coordinate system is calculated based on the tristimulus value of each pixel. The color of the water body is greatly influenced by various factors such as illumination, shadow, wind speed and the like. The RGB imaging of images does not represent the actual water color well. This technique results in a large color conversion error from RGB to chromaticity coordinates, resulting in inaccurate recognition results.

The SVM image processing method mainly comprises the steps of extracting color and texture features, constructing a classifier model and detecting a water body area entity. According to the texture characteristics of high brightness, low saturation and smoothness of a water barrier in a field environment, extracting saturation brightness ratio color characteristics (S/V) of a water region in a sample, combining four texture characteristics of a gray level co-occurrence matrix to form a five-dimensional feature vector, and constructing an SVM classifier model through sample training, wherein a positive sample region in the classifier is a water body, and a negative sample is a ground surface. Simulation and test results show that the water body obstacle detection method is effective and can effectively weaken the negative influence of illumination change on the detection of the water body purely based on the color characteristics.

Because the traditional SVM image processing algorithm is adopted at the server end, the algorithm is theoretically inaccurate for the environment which is greatly influenced by external illumination, wind speed and shadow and is used for water body color identification. The SVM is developed from an optimal classification surface under the condition of linear separability, and the basic idea is that the optimal classification line is popularized to a high-dimensional space, the classification which can not be classified in the low-dimensional space is changed into high-dimensional separability, and then the optimal classification line is changed into the optimal classification surface, so that the separability of data features is guaranteed. However, the dichotomy method of the SVM image processing method needs to divide the multidimensional feature into two parts, and the feature accuracy is reduced each time the feature is classified. For the nonlinear problem, the nonlinear problem can be converted into a linear problem in a certain high-dimensional space through nonlinear transformation, and an optimal classification surface is obtained in a transformation space. The nonlinear SVM raises the dimension of the sample point, namely, the sample point is mapped to a high-dimension space or even an infinite-dimension space, and then a linear problem processing method is adopted in the high-dimension space. According to the principle of cross multiplication in probability, the overall precision is difficult to guarantee.

Based on the above, in order to improve the accuracy and real-time performance of water color identification and further improve the accuracy of water pollution early warning, the application considers starting with changing the existing water color identification method and applies a U-Net network encoder-decoder (encoder-decoder) and a semantic segmentation technology, and the application provides a water color identification method and a water color identification device, and intercepts images reflecting water colors; setting water pollution levels aiming at different water body colors, carrying out semantic labeling on different polluted water body colors, namely setting semantic labels of a data set according to the water body pollution levels, and generating a deep learning model after training by utilizing a large number of labeled training set pictures printed with the semantic labels, thereby carrying out accurate water body color identification and identifying the water body pollution degree.

In order to improve accuracy and real-time of water color identification and further improve accuracy of water pollution early warning, the embodiment of the application provides a water color identification device, the device can be a server or a client device, and the client device can include a smart phone, a tablet electronic device, a network set top box, a portable computer, a desktop computer, a Personal Digital Assistant (PDA), a vehicle-mounted device, an intelligent wearable device and the like. Wherein, intelligence wearing equipment can include intelligent glasses, intelligent wrist-watch and intelligent bracelet etc..

In practical applications, the part for performing the water body color recognition may be performed on the server side as described in the above, or all operations may be performed in the client device. The selection may be specifically performed according to the processing capability of the client device, the limitation of the user usage scenario, and the like. This is not a limitation of the present application. The client device may further include a processor if all operations are performed in the client device.

The client device may have a communication module (i.e., a communication unit), and may be communicatively connected to a remote server to implement data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, the server may also include a server on an intermediate platform, for example, a server on a third-party server platform that is communicatively linked to the task scheduling center server. The server may include a single computer device, or may include a server cluster formed by a plurality of servers, or a server structure of a distributed apparatus.

The server and the client device may communicate using any suitable network protocol, including network protocols not yet developed at the filing date of this application. The network protocol may include, for example, a TCP/IP protocol, a UDP/IP protocol, an HTTP protocol, an HTTPS protocol, or the like. Of course, the network Protocol may also include, for example, an RPC Protocol (Remote Procedure Call Protocol), a REST Protocol (Representational State Transfer Protocol), and the like used above the above Protocol.

The following examples are intended to illustrate the details.

In order to improve the accuracy and the real-time of water color identification and further improve the accuracy of water pollution early warning, the application provides an embodiment of a water color identification method with an execution main body being a water color identification device, and referring to fig. 1, the method specifically comprises:

step 100: collecting water color picture information of a target water area.

Specifically, the water color picture information of the target water area is picture information of the target water area to be detected, and the picture information includes the water color information of the target water area.

Step 200: and inputting the water color picture information of the target water area into a preset water pollution level judgment model.

Step 300: and outputting and displaying an output result of the preset water pollution level judgment model so as to determine the pollution degree of the target water area.

Specifically, the output result includes a water pollution level of the target water area, and the pollution degree of the target water area can be determined according to the water pollution level. The target water area can be set according to actual conditions, and the application is not limited to this.

In an embodiment of the present application, in order to obtain a water pollution level determination model and further improve accuracy and real-time performance of water color identification, referring to fig. 2, before step 100, the method further includes:

step 010: and inputting the pre-acquired water color labeling picture information into a U-Net model for training to acquire the water pollution level judgment model.

Specifically, the U-Net model comprises a U-Net network encoder-decoder (encoder-decoder) structure. Wherein the encoder progressively reduces the spatial dimension of the input data using the pooling layer, while the decoder progressively restores the details and corresponding spatial dimension of the target through a network layer such as an deconvolution layer. From encoder to decoder, there is usually a direct information connection to help the decoder to better recover the target details. The U-Net network has a good recognition effect in the application of semantic segmentation.

In an embodiment of the present application, in order to further improve the reliability and accuracy of the training data, referring to fig. 2, before step 010, the method further includes:

step 011: collecting water body color image information of different areas.

Step 012: and setting a corresponding semantic label for the water color picture information according to a semantic segmentation technology and a preset water pollution level so as to generate the water color labeling picture information.

Specifically, in order to improve the reliability of the training data, the water color image information may be a large number of water color pictures acquired from a plurality of different regions. Semantic labels can be set on the water color picture information of the target water area and used for training the water pollution level judgment model so as to improve the accuracy of the water pollution level judgment model. The preset water pollution level can be set according to actual conditions to distinguish the water pollution conditions, and the method is not limited in this application.

Early computer vision fields found only elements like edges (lines and curves) or gradations, but they never provided pixel-level image understanding in a fully human-perceptible manner. The Semantic Segmentation (Semantic Segmentation) technique solves this problem by clustering together image parts belonging to the same object, thus expanding its application field. Some raw data (e.g., a flat image) is taken as input and converted into a mask with a highlighted region of interest. In the present application, the semantic segmentation technique applied may be a process in which standard semantic segmentation (also called full-pixel semantic segmentation) classifies each pixel as belonging to an object class; instance aware semantic segmentation (instance aware segmentation) is a subtype of standard semantic segmentation or full-pixel semantic segmentation, classifying each pixel as belonging to an object class and an entity ID of that class; the term full-pixel semantic segmentation (full-pixel semantic segmentation), in which each pixel in an image is assigned a category ID according to the object of interest to which it belongs.

In order to further improve the real-time performance of water pollution identification and timely treat water pollution, the method further includes, after step 200:

step 201: and if the output result of the preset water pollution level judgment model exceeds a preset early warning level, outputting early warning information.

Specifically, if the output result exceeds the pre-warning level in the preset water pollution level, real-time warning is performed. The preset early warning level can be set according to actual conditions, and the preset early warning level is not limited in this application.

On the aspect of software, in order to improve accuracy and real-time of water color identification and further improve accuracy of water pollution early warning, the present application provides an embodiment of a water color identification device with all or part of contents in a water color identification method, where the water color identification device, as shown in fig. 3, specifically includes the following contents:

the first acquisition module 10 is used for acquiring water body color picture information of a target water area;

the processing module 20 is configured to input the water color picture information of the target water area into a preset water pollution level judgment model;

and the output module 30 is used for outputting and displaying an output result of the preset water pollution level judgment model so as to determine the pollution degree of the target water area.

In an embodiment of the present application, referring to fig. 4, the water color identification apparatus further includes:

and the training module 40 is used for inputting the pre-acquired water color labeling picture information into a U-Net model for training so as to acquire the water pollution level judgment model.

and the second acquisition module 50 is used for acquiring water body color image information of different areas.

And a semantic tag setting module 60, configured to set a corresponding semantic tag for the water color image information according to a semantic segmentation technology and a preset water pollution level, so as to generate the water color labeling image information.

In an embodiment of the present application, the water color identification device further includes:

and the early warning module 70 is configured to output early warning information if the output result of the preset water pollution level judgment model exceeds a preset early warning level.

In order to further improve the accuracy and the real-time performance of water color identification and further improve the accuracy of water pollution early warning, the application further provides a specific application example of the water color identification method, and the specific contents are as follows:

step S1: and receiving an image intercepting instruction, and intercepting an image reflecting the water body color.

Step S2: and setting the water pollution level according to different water colors.

Step S3: and setting a semantic label of a data set (namely the intercepted image reflecting the water body color) by utilizing a semantic segmentation algorithm and the water body pollution level so as to generate an annotated image.

Step S4: and training the U-Net model by using the labeled image.

Step S5: and (5) carrying out water body color identification by using the trained U-Net model.

As can be seen from the above description, the water color identification method and apparatus provided in the present application include acquiring water color image information of a target water area; inputting the water color picture information of the target water area into a preset water pollution level judgment model; outputting and displaying an output result of the preset water pollution level judgment model to determine the pollution degree of the target water area; the accuracy and the real-time performance of water color identification and the application universality can be improved, and the accuracy of water pollution early warning is further improved. And the accuracy and the real-time performance of water color identification are improved by utilizing a U-Net network semantic segmentation algorithm. The water color identification is more accurate, and the water color presented by the water bodies with different pollution degrees is more accurate by combining the semantic label classification. The early warning and identification strength of water body pollution in the water area is greatly improved, and abnormity is found more timely and accurately. By applying the water color identification method and the water color identification device, the water identification capacity is greatly improved, the target identification requirement of a large number of application scenes for water pollution can be met, the influence of customers in the industry is greatly improved, the user experience is improved, and the method and the device become a leader of new technology application in the industry.

In terms of hardware, in order to improve accuracy and real-time of water color identification and further improve accuracy of water pollution early warning, the present application provides an embodiment of an electronic device for implementing all or part of contents in the water color identification method, where the electronic device specifically includes the following contents:

a processor (processor), a memory (memory), a communication Interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the communication interface is used for realizing information transmission among the water body color recognition device, the user terminal and other related equipment; the electronic device may be a desktop computer, a tablet computer, a mobile terminal, and the like, but the embodiment is not limited thereto. In this embodiment, the electronic device may be implemented with reference to the embodiment for implementing the water color identification method and the embodiment for implementing the water color identification apparatus in the embodiments, and the contents thereof are incorporated herein, and repeated descriptions are omitted.

Fig. 5 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present application. As shown in fig. 5, the electronic device 9600 can include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. Notably, this FIG. 5 is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.

In one or more embodiments of the present application, the water color identification function can be integrated into the central processor 9100. The central processor 9100 may be configured to control as follows:

step 100: collecting water color picture information of a target water area.

According to the above description, the electronic device provided by the embodiment of the application can improve the accuracy and the real-time performance of water body color identification, and further improve the accuracy of water body pollution early warning.

In another embodiment, the water color recognition device may be configured separately from the central processor 9100, for example, the water color recognition device may be configured as a chip connected to the central processor 9100, and the water color recognition function is realized by the control of the central processor.

As shown in fig. 5, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 also does not necessarily include all of the components shown in fig. 5; further, the electronic device 9600 may further include components not shown in fig. 5, which may be referred to in the art.

As shown in fig. 5, a central processor 9100, sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device, which central processor 9100 receives input and controls the operation of the various components of the electronic device 9600.

The memory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 9100 can execute the program stored in the memory 9140 to realize information storage or processing, or the like.

The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. Power supply 9170 is used to provide power to electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, an LCD display, but is not limited thereto.

The memory 9140 can be a solid state memory, e.g., Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 9140 could also be some other type of device. Memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 being used for storing application programs and function programs or for executing a flow of operations of the electronic device 9600 by the central processor 9100.

The memory 9140 can also include a data store 9143, the data store 9143 being used to store data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers for the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, contact book applications, etc.).

The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.

Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing ordinary telecommunications functions. The audio processor 9130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100, thereby enabling recording locally through the microphone 9132 and enabling locally stored sounds to be played through the speaker 9131.

According to the above description, the electronic device provided by the embodiment of the application can improve the accuracy and the real-time performance of water color identification, and further improve the accuracy of water pollution early warning.

Embodiments of the present application further provide a computer-readable storage medium capable of implementing all steps in the water color identification method in the foregoing embodiments, where the computer-readable storage medium stores thereon a computer program, and when the computer program is executed by a processor, the computer program implements all steps of the water color identification method in the foregoing embodiments, for example, when the processor executes the computer program, the processor implements the following steps:

step 100: collecting water color picture information of a target water area.

From the above description, the computer-readable storage medium provided in the embodiment of the present application can improve accuracy and real-time performance of water color identification, and further improve accuracy of water pollution early warning.

In the present application, each embodiment of the method is described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. Reference is made to the description of the method embodiments.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The principle and the implementation mode of the present application are explained by applying specific embodiments in the present application, and the description of the above embodiments is only used to help understanding the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A water body color identification method is characterized by comprising the following steps:

collecting water body color picture information of a target water area;

2. The method for identifying water color according to claim 1, further comprising, before the acquiring the water color picture information of the target water area:

3. The method for recognizing water body color according to claim 2, wherein before inputting the pre-acquired water body color labeling picture information into a U-Net model for training, the method further comprises:

collecting water body color image information of different areas;

and setting a corresponding semantic label for the water color picture information according to a semantic segmentation technology and a preset water pollution level so as to generate the water color labeling picture information.

4. The method for identifying water color according to claim 1, wherein after the inputting the water color picture information of the target water into a preset water pollution level judgment model, the method further comprises:

and if the output result of the preset water pollution level judgment model exceeds a preset early warning level, outputting early warning information.

5. A water color identification device, comprising:

6. The water color identification device of claim 5, further comprising:

and the training module is used for inputting the pre-acquired water color labeling picture information into a U-Net model for training so as to acquire the water pollution level judgment model.

7. The water color identification device of claim 6, further comprising:

the second acquisition module is used for acquiring water body color image information of different areas;

and the semantic label setting module is used for setting a corresponding semantic label for the water color picture information according to a semantic segmentation technology and a preset water pollution level so as to generate the water color labeling picture information.

8. The water color identification device of claim 5, further comprising:

and the early warning module is used for outputting early warning information if the output result of the preset water pollution level judgment model exceeds a preset early warning level.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the water color identification method of any one of claims 1 to 4.

10. A computer readable storage medium having stored thereon computer instructions, wherein the instructions, when executed, implement the steps of the water color identification method of any one of claims 1 to 4.