CN111783732A - Group mist identification method and device, electronic equipment and storage medium - Google Patents
Group mist identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111783732A CN111783732A CN202010699922.1A CN202010699922A CN111783732A CN 111783732 A CN111783732 A CN 111783732A CN 202010699922 A CN202010699922 A CN 202010699922A CN 111783732 A CN111783732 A CN 111783732A
- Authority
- CN
- China
- Prior art keywords
- image
- cloud
- group
- fog
- scene image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 239000003595 mist Substances 0.000 title claims abstract description 26
- 230000000875 corresponding effect Effects 0.000 claims description 66
- 238000012545 processing Methods 0.000 claims description 35
- 238000000605 extraction Methods 0.000 claims description 21
- 230000015654 memory Effects 0.000 claims description 21
- 238000005070 sampling Methods 0.000 claims description 17
- 238000011176 pooling Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000002596 correlated effect Effects 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 17
- 238000013528 artificial neural network Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/32—Normalisation of the pattern dimensions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/048—Detecting movement of traffic to be counted or controlled with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Image Analysis (AREA)
Abstract
The disclosure provides a method and a device for identifying group mist, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a scene image of a target scene; extracting the features of the scene image to obtain global feature information; and classifying the global characteristic information to determine the group fog in the scene image and the group fog level corresponding to the group fog.
Description
Technical Field
The present disclosure relates to the field of computer vision technologies, and in particular, to a method and an apparatus for identifying a cloud, an electronic device, and a storage medium.
Background
The fog is affected by the microclimate environment of local areas, and in the local range of tens to hundreds of meters in the big fog, the fog with lower visibility appears. The clustered fog has the characteristics of strong regionality and high prediction difficulty, and can cause the sudden change of visibility on an expressway, thereby being extremely harmful to the traffic safety of the expressway and easily causing major traffic accidents.
Conventionally, the mist can be recognized by using dedicated hardware such as a photoelectric sensor or a camera. Compared with a scheme which is high in cost and difficult to popularize on a large scale and utilizes special hardware, the camera is utilized to acquire image information, so that the group fog is identified, and the feasibility is higher.
However, in the scheme of using the camera to realize the group fog recognition, methods such as dark channel prior or manual feature selection are mostly adopted, the shallow feature of the image is obtained from the image collected by the camera, and the method is easily influenced by factors such as the angle of the light camera, so that the recognition effect is poor.
Disclosure of Invention
The embodiment of the disclosure is expected to provide a group fog identification method and device, electronic equipment and storage medium.
The technical scheme of the embodiment of the disclosure is realized as follows:
the embodiment of the disclosure provides a method for identifying cluster fog, which comprises the following steps:
acquiring a scene image of a target scene;
extracting the features of the scene image to obtain global feature information;
and classifying the global characteristic information to determine the group fog in the scene image and the group fog level corresponding to the group fog.
In the above method for identifying a cloud, before the extracting features of the scene image to obtain global feature information, the method further includes:
carrying out image preprocessing on the scene image to obtain a processed image;
correspondingly, the performing feature extraction on the scene image to obtain global feature information includes:
and extracting the features of the processed image to obtain the global feature information.
In the above method for identifying the cloud, the image preprocessing the scene image to obtain a processed image includes:
carrying out pixel sampling on the scene image to obtain a sampling image with a target size;
and carrying out normalization processing on the sampling image to obtain the processed image.
In the method for identifying group fog, the classifying the global feature information to determine the group fog in the scene image and the group fog level corresponding to the group fog includes:
performing average pooling on the global characteristic information to obtain global average characteristic information;
and classifying the global average characteristic information to determine the cluster fog and the cluster fog level.
In the method for identifying mist cloud, after determining mist cloud in the scene image and a mist cloud level corresponding to the mist cloud, the method further includes:
acquiring a first visibility range corresponding to a group fog level according to a corresponding relation between a preset group fog level and the visibility range;
under the condition that the first visibility range is lower than a preset visibility range, first early warning information corresponding to the group fog level is obtained;
and outputting the first early warning information.
In the above method for identifying mist cloud, the scene image includes a plurality of images at a plurality of times, the mist cloud level includes a plurality of levels corresponding to the plurality of images, and after determining the mist cloud in the scene image and the mist cloud level corresponding to the mist cloud, the method further includes:
under the condition that the multiple levels are positively correlated with the multiple moments, second early warning information is obtained;
acquiring early warning reminding equipment in the target scene;
and transmitting the second early warning information to the early warning reminding equipment.
In the above method for identifying mist cloud, the scene image includes a plurality of images at a plurality of times, the mist cloud level includes a plurality of levels corresponding to the plurality of images, and after determining the mist cloud in the scene image and the mist cloud level corresponding to the mist cloud, the method further includes:
counting the multiple levels to obtain a statistical result;
and determining the frequency of the cluster fog of the target scene according to the statistical result.
The embodiment of the present disclosure provides a group fog recognition device, which includes:
the image acquisition module is used for acquiring a scene image of a target scene;
the feature extraction module is used for extracting features of the scene image to obtain global feature information;
and the classification processing module is used for classifying the global characteristic information and determining the group fog in the scene image and the group fog level corresponding to the group fog.
The group fog recognition device further comprises the image processing module,
the image processing module is used for carrying out image preprocessing on the scene image to obtain a processed image;
correspondingly, the feature extraction module is specifically configured to perform feature extraction on the processed image to obtain the global feature information.
In the above cloud identification apparatus, the image processing module is specifically configured to perform pixel sampling on the scene image to obtain a sampled image of a target size; and carrying out normalization processing on the sampling image to obtain the processed image.
In the above device for identifying mist, the classification processing module is specifically configured to perform average pooling on the global feature information to obtain global average feature information; and classifying the global average characteristic information to determine the cluster fog and the cluster fog level.
The group fog recognition device also comprises an information output module,
the information output module is used for acquiring a first visibility range corresponding to the group fog level according to the corresponding relation between the preset group fog level and the visibility range; under the condition that the first visibility range is lower than a preset visibility range, first early warning information corresponding to the group fog level is obtained; and outputting the first early warning information.
In the above-described cloud identification device, the device further includes an information output module, the scene image includes a plurality of images at a plurality of times, the cloud level includes a plurality of levels corresponding to the plurality of images,
the information output module is used for acquiring second early warning information under the condition that the multiple levels are positively correlated with the multiple moments; acquiring early warning reminding equipment in the target scene; and transmitting the second early warning information to the early warning reminding equipment.
In the above cloud identification device, the device further comprises a statistical processing module, the scene image comprises a plurality of images at a plurality of times, the cloud level comprises a plurality of levels corresponding to the plurality of images,
the statistical processing module is used for carrying out statistics on the multiple levels to obtain a statistical result; and determining the frequency of the cluster fog of the target scene according to the statistical result.
The embodiment of the present disclosure provides an electronic device, which includes: a processor, a memory, and a communication bus; wherein the content of the first and second substances,
the communication bus is used for realizing connection communication between the processor and the memory;
the processor is used for executing the group fog identification program stored in the memory so as to realize the group fog identification method.
Embodiments of the present disclosure provide a computer-readable storage medium storing one or more programs, which may be executed by one or more processors, to implement the above-described cloud identification method.
The embodiment of the disclosure provides a method and a device for identifying group fog, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a scene image of a target scene, and performing feature extraction on the scene image to obtain global feature information; and classifying the global characteristic information to determine the group fog in the scene image and the group fog level corresponding to the group fog. According to the technical scheme provided by the embodiment of the disclosure, global deep-level features of the image are extracted, the effectiveness of the group fog information representation is improved, and the interference of information irrelevant to group fog identification in the image is reduced, so that the accuracy of the group fog identification is improved.
Drawings
Fig. 1 is a schematic flow chart of a method for identifying mist according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of an exemplary image processing process provided by an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a group fog recognition device according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a group fog recognition device according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure.
The disclosed embodiments provide a group fog recognition method, the execution subject of which may be a group fog recognition apparatus, for example, the group fog recognition method may be executed by a terminal device or a server or other electronic devices, wherein the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, or the like. In some possible implementations, the cloud identification method may be implemented by a processor calling computer readable instructions stored in a memory.
The embodiment of the disclosure provides a group fog recognition method. Fig. 1 is a schematic flow chart of a method for identifying group mist according to an embodiment of the present disclosure. As shown in fig. 1, the method for identifying the mist mainly comprises the following steps:
s101, obtaining a scene image of a target scene.
In an embodiment of the present disclosure, the cloud recognition device may acquire a scene image of the target scene.
In the embodiment of the present disclosure, the scene image is a scene that needs to be identified as the cloud, that is, an image corresponding to the target scene. Under the condition that the group fog recognition method is applied to the expressway monitoring scene, the scene image is actually the expressway monitoring image, the subsequent group fog recognition is not limited by special hardware, and the large-scale application is facilitated. Specific target scenes and scene images of target scenes embodiments of the present disclosure are not limited.
It should be noted that, in the embodiment of the present disclosure, the scene image may be acquired by the group fog recognition device, or may also be an image acquired by an independent camera, a server, or a cloud device, and transmitted to the group fog recognition device. Specific sources of scene images embodiments of the present disclosure are not limited.
And S102, extracting the features of the scene image to obtain global feature information.
In the embodiment of the disclosure, after the group fog recognition device obtains the scene image, the feature extraction may be performed on the scene image, so as to obtain global feature information in the scene image.
It should be noted that, in the embodiment of the present disclosure, before performing feature extraction on a scene image to obtain global feature information, the group fog recognition apparatus may further perform the following steps: carrying out image preprocessing on the scene image to obtain a processed image; correspondingly, the group fog recognition device performs feature extraction on the scene image to obtain global feature information, and the method comprises the following steps: and performing feature extraction on the processed image to obtain global feature information.
Specifically, in an embodiment of the present disclosure, the image preprocessing performed on the scene image by the cloud recognition device to obtain a processed image includes: carrying out pixel sampling on a scene image to obtain a sampling image with a target size; and carrying out normalization processing on the sampling image to obtain a processed image.
It should be noted that, in the embodiment of the present disclosure, the cloud identification device performs pixel sampling on the scene image, which is essentially to reshape the size of the scene image to a specific size, i.e., a target size, so as to determine the obtained image as the sampled image. The group fog recognition device may sample pixels of the scene image by using a bilinear interpolation algorithm, and may also sample pixels by using other sampling algorithms to obtain a sampled image. The specific target size and the pixel sampling mode may be selected according to actual requirements, and the embodiment of the disclosure is not limited.
It should be noted that, in the embodiment of the present disclosure, the cloud identification apparatus performs normalization processing on the sampled image, and it is essential that the pixel value of each pixel point in the sampled image is converted into a value between 0 and 1, so that the pixel values of different pixel points are mapped into the same fixed range.
It can be understood that, in the embodiment of the present disclosure, the cloud identification apparatus performs pixel sampling and normalization processing on the scene image, and the obtained processed image can meet a certain standard in terms of both the size and the representation manner of the pixels, so that subsequent feature extraction can be facilitated, and the efficiency of feature extraction can be improved.
It should be noted that, in the embodiment of the present disclosure, the cloud identification apparatus stores therein a preset deep neural network. The preset deep neural network can be used for extracting global deep features in the image, the specific preset deep neural network can be obtained by utilizing a large number of sample images to perform feature extraction training, and the embodiment of the application is not limited.
It should be noted that, in the embodiment of the present disclosure, the preset deep neural network may include: according to the characteristic extraction depth, multiple groups of convolution layers are connected in sequence from shallow to deep, the group fog recognition device can utilize the multiple groups of convolution layers to carry out multiple times of iterative convolution processing on the processed image to obtain a characteristic image, and then the characteristic image is determined as global characteristic information.
Fig. 2 is a schematic diagram of an exemplary image processing process provided in an embodiment of the present disclosure. As shown in fig. 2, the predetermined deep neural network includes 5 sets of convolutional layers, which are the first set, the second set, the third set, the fourth set, and the fifth set, respectively. Wherein, the first group of convolutional layers adopts a filter with the size of 7 multiplied by 7, and can convolve the input processed images of 2 channels to obtain images of 64 channels, and simultaneously, the image size is down-sampled to 1/2; and the convolution layers of the second group to the fifth group, each group comprises 1-3 convolution layers, the size of the convolution kernel is 3 multiplied by 3, the number of convolution output channels is 64, 128, 256 and 512 in sequence, the convolution result output by each group of convolution layers, namely the output image can be changed into 1/4, 1/8, 1/16 and 1/32 of the processed image, after the processed image is processed by 5 groups of convolution layers, the image size is gradually reduced, the image is gradually deepened, and the characteristic hierarchy is increased and advanced.
It should be noted that, in the embodiment of the present disclosure, each convolutional layer of the plurality of convolutional layers may perform maximum pooling, i.e., downsampling, before outputting the image obtained by the convolution processing to the next convolutional layer connected thereto, specifically, every four pixels in the image are grouped, and only the pixel value in the image is reserved with the maximum value, so that the length and width of the downsampled image are actually 1/2 of the input image.
It should be noted that, in the embodiment of the present disclosure, the number of groups of convolutional layers included in the deep neural network and related parameters in each group of convolutional layers, for example, the size of a convolutional core, may be set according to actual requirements, and the embodiment of the present disclosure is not limited.
It can be understood that, in the embodiment of the disclosure, global feature extraction of a processed image can be realized by using a preset deep neural network, and compared with a traditional scheme for extracting local features of an image, the method can more effectively represent the group fog information in the image, thereby improving the accuracy of group fog identification.
S103, carrying out classification processing on the global characteristic information, and determining the group fog in the scene image and the group fog level corresponding to the group fog.
In the embodiment of the disclosure, the group fog recognition device may classify the global feature information after the global feature information of the scene image, and determine the group fog in the scene image and the group fog level corresponding to the group fog.
Specifically, in the embodiment of the present disclosure, the classifying the global feature information by the group fog recognition device to determine the group fog in the scene image and the group fog level corresponding to the group fog includes: carrying out average pooling on the global characteristic information to obtain global average characteristic information; and classifying the global average characteristic information to determine the cluster fog and the cluster fog level.
It should be noted that, in the embodiment of the present disclosure, as shown in fig. 2, a global pooling layer and a preset classifier may be stored in the group fog recognition apparatus, and the group fog recognition apparatus may implement average pooling of global feature information by using the global pooling layer. The global pooling layer may be set in a preset classifier, and may actually be set in a preset deep neural network, and the implemented functions thereof are not changed.
It should be noted that, in the embodiment of the present disclosure, as shown in fig. 2, the preset classifier may include a first fully-connected layer, a second fully-connected layer, and a normalization layer, and is used for implementing classification of the global average feature information. The number of the fully-connected layers may be two, or of course, may be one or more than two. The number of the specific full connection layers can be set according to actual requirements, and the embodiment of the disclosure is not limited.
It can be understood that, in the embodiment of the present disclosure, since the global feature information is actually a feature image obtained by convolution processing, the group fog recognition apparatus performs global average pooling on the global feature information by using a global pooling layer, that is, averages each channel in the feature image, thereby avoiding an influence of a local area interference factor in the image on group fog recognition due to poor local light during imaging, and being capable of improving accuracy of group fog recognition.
It should be noted that, in the embodiment of the present disclosure, the cloud identification apparatus may classify the global average feature information, so as to determine the cloud in the scene image and the level of the cloud corresponding to the cloud. The global average feature information represents the average feature of the scene image, and the cluster fog level actually represents the cluster fog condition of the scene image.
It should be noted that, in the embodiment of the present disclosure, the cloud identification device actually identifies the cloud of the global average feature information and classifies the cloud of the global average feature information into the cloud levels, so as to obtain the ratios of different cloud levels, as shown in fig. 2, the global average feature information has the most information matched with the third level in the cloud levels, and therefore, the finally determined cloud level is the third level. In addition, the output level of the cluster fog corresponds to the visibility, and compared with the current cluster fog recognition scheme, the output results of whether the cluster fog exists or not or the concentration of the cluster fog are all output, so that the degree of the cluster fog can be reflected more obviously and flexibly.
Exemplarily, in the embodiment of the present disclosure, in the corresponding relationship between the preset group fog level and the visibility range, the visibility corresponding to the group fog level is 0-50 m for the first level, the visibility corresponding to the group fog level is 50-100 m for the second level, the visibility corresponding to the group fog level is 200 m for the third level, the visibility corresponding to the group fog level is 200 m for the fourth level, the visibility corresponding to the group fog level is 500 m for the fifth level, and the visibility corresponding to the group fog level is 1000 m for the fifth level, and the visibility corresponding to the group fog level is more than 1000 m for the fog-free level.
In an embodiment of the disclosure, after determining the cloud in the scene image and the level of the cloud corresponding to the cloud, the cloud identifying device may further perform the following steps: acquiring a first visibility range corresponding to the group fog level according to the corresponding relation between the preset group fog level and the visibility range; under the condition that the first visibility range is lower than the preset visibility range, first early warning information corresponding to the group fog level is obtained; and outputting the first early warning information.
It should be noted that, in the embodiment of the present disclosure, a corresponding relationship between a preset fog level and a visibility range is stored, different fog levels correspond to different visibility ranges, and a specific corresponding relationship between a fog level and a visibility range may be preset according to an actual situation, which is not limited in the embodiment of the present disclosure.
It can be understood that, in the embodiment of the present disclosure, the fog group identification device may search a corresponding visibility range from the correspondence between the preset fog group level and the visibility range according to the obtained fog group level, and determine the searched visibility range as the first visibility range.
It should be noted that, in the embodiment of the present disclosure, a preset visibility range, for example, more than 500 meters, is stored in the group fog recognition device, and when the group fog level obtained by the group fog recognition device is between four levels and one level, the visibility represented by the group fog recognition device is lower than 500 meters, so that corresponding warning information needs to be determined. The specific warning information may be determined according to a corresponding relationship between a preset group fog level and the warning information, and the embodiment of the disclosure is not limited.
It should be noted that, in the embodiment of the present disclosure, different levels of the foggy group correspond to different visibility, and therefore, in a case that the visibility range corresponding to the level of the foggy group is lower than the preset visibility range, corresponding warning information may be determined in time, and the warning information is output to prompt, so as to provide warning and scientific basis for processing the foggy group.
In an embodiment of the present disclosure, the scene image includes a plurality of images at a plurality of times, the group fog level includes a plurality of levels corresponding to the plurality of images, and after the group fog recognition device determines the group fog in the scene image and the group fog level corresponding to the group fog, the following steps may be further performed: under the condition that a plurality of levels are positively correlated with a plurality of moments, second early warning information is obtained; acquiring early warning reminding equipment in a target scene; and transmitting the second early warning information to early warning reminding equipment.
It is understood that, in the embodiment of the present disclosure, the group fog recognition apparatus may acquire a large number of images of the target scene in a period of time, for example, a plurality of images on a highway in a day, and the obtained images are all scene images, that is, the scene images may include a plurality of images at a plurality of time instants. The group fog recognition means may perform group fog recognition separately for each image, resulting in a corresponding group fog level, i.e. a plurality of levels. If the multiple levels also exhibit a lifting condition as the time of day increases, i.e., the multiple levels are positively correlated with the multiple times of day, the cloud characterizing the target scene is aggravated. The group fog recognition device can acquire an early warning reminding device, such as a vehicle, in a target scene, so that second early warning information for prompting that group fog is aggravated is transmitted to the early warning reminding device.
In an embodiment of the present disclosure, the scene image includes a plurality of images at a plurality of times, the group fog level includes a plurality of levels corresponding to the plurality of images, and after the group fog recognition device determines the group fog in the scene image and the group fog level corresponding to the group fog, the following steps may be further performed: carrying out statistics on a plurality of levels to obtain a statistical result; and determining the occurrence frequency of the cluster fog of the target scene according to the statistical result.
It can be understood that, in the embodiment of the present disclosure, the group fog recognition device performs statistical analysis on a plurality of levels corresponding to the obtained plurality of images, and can determine the group fog occurrence frequency of the target scene according to the statistical result, and in addition, can analyze the group fog multiple-occurrence-point and multiple-occurrence time period, summarize the rule of group fog occurrence, and generate the group fog prevention diagram, so that prevention can be performed in advance at the multiple-occurrence-point and multiple-occurrence time period, and loss caused by group fog is reduced.
The embodiment of the disclosure provides a method for identifying group fog, which comprises the following steps: acquiring a scene image of a target scene; extracting the features of the scene image to obtain global feature information; and classifying the global characteristic information to determine the group fog in the scene image and the group fog level corresponding to the group fog. According to the group fog recognition method provided by the embodiment of the disclosure, the deep neural network is adopted to extract the global features of the image, so that the effectiveness of the group fog information representation is improved, and the interference of information irrelevant to the group fog recognition in the image is reduced, thereby improving the accuracy of the group fog recognition.
The embodiment of the disclosure provides a group fog recognition device, and fig. 3 is a schematic structural diagram of the group fog recognition device provided by the embodiment of the disclosure. As shown in fig. 3, the cloud identification device includes:
an image obtaining module 201, configured to obtain a scene image of a target scene;
a feature extraction module 202, configured to perform feature extraction on the scene image to obtain global feature information;
and the classification processing module 203 is configured to perform classification processing on the global feature information, and determine the cloud in the scene image and the cloud level corresponding to the cloud.
Fig. 4 is a schematic structural diagram of a group fog recognition device according to an embodiment of the present application. As shown in fig. 4, in an embodiment of the present disclosure, the cloud identification apparatus further includes: the image processing module 204 is configured to perform image processing,
the image processing module 204 is configured to perform image preprocessing on the scene image to obtain a processed image;
correspondingly, the feature extraction module 202 is specifically configured to perform feature extraction on the processed image to obtain the global feature information.
In an embodiment of the present disclosure, the image processing module 204 is specifically configured to perform pixel sampling on the scene image to obtain a sampled image of a target size; and carrying out normalization processing on the sampling image to obtain the processed image.
In an embodiment of the present disclosure, the classification processing module 203 is specifically configured to perform average pooling on the global feature information to obtain global average feature information; and classifying the global average characteristic information to determine the cluster fog and the cluster fog level.
In an embodiment of the present disclosure, as shown in fig. 4, the cloud identification device further includes: the information output module 205, configured to obtain, according to a corresponding relationship between a preset group fog level and a visibility range, a first visibility range corresponding to the group fog level; under the condition that the first visibility range is lower than a preset visibility range, first early warning information corresponding to the group fog level is obtained; and outputting the first early warning information.
In an embodiment of the present disclosure, the scene image includes a plurality of images at a plurality of time instants, the fog level includes a plurality of levels corresponding to the plurality of images,
the information output module 205 is configured to obtain second warning information when the multiple levels are positively correlated with the multiple moments; acquiring early warning reminding equipment in the target scene; and transmitting the second early warning information to the early warning reminding equipment.
In an embodiment of the present disclosure, as shown in fig. 4, the cloud identification device further includes: a statistical processing module 206, wherein the scene image comprises a plurality of images at a plurality of time instants, the fog level comprises a plurality of levels corresponding to the plurality of images,
the statistical processing module 206 is configured to perform statistics on the multiple levels to obtain a statistical result; and determining the frequency of the cluster fog of the target scene according to the statistical result.
The embodiment of the disclosure provides a group fog recognition device, which acquires a scene image of a target scene; extracting and extracting the scene image to obtain global characteristic information; and classifying the global characteristic information to determine the cluster fog in the scene image and the corresponding cluster fog level. The group fog recognition device provided by the embodiment of the disclosure adopts the deep neural network to extract the global features of the image, improves the effectiveness of group fog information representation, and reduces the interference of information irrelevant to group fog recognition in the image, thereby improving the accuracy of group fog recognition.
The embodiment of the disclosure provides an electronic device. Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 5, the electronic apparatus includes: a processor 301, a memory 302, and a communication bus 303; wherein the content of the first and second substances,
the communication bus 303 is used for realizing connection communication between the processor 301 and the memory 302;
the processor 301 is configured to execute the cloud identification program stored in the memory 302 to implement the cloud identification method.
Embodiments of the present disclosure provide a computer-readable storage medium storing one or more programs, which may be executed by one or more processors, to implement the above-described cloud identification method. The computer-readable storage medium may be a volatile Memory (volatile Memory), such as a Random-Access Memory (RAM); or a non-volatile Memory (non-volatile Memory), such as a Read-Only Memory (ROM), a flash Memory (flash Memory), a Hard disk (Hard disk Drive, HDD) or a Solid-State Drive (SSD); or may be a respective device, such as a mobile phone, computer, tablet device, personal digital assistant, etc., that includes one or any combination of the above-mentioned memories.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure 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, optical storage, and the like) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. 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 signal processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable signal 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 signal 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 signal 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 above description is only for the preferred embodiment of the present disclosure, and is not intended to limit the scope of the present disclosure.
Claims (10)
1. A method of identifying mist, the method comprising:
acquiring a scene image of a target scene;
extracting the features of the scene image to obtain global feature information;
and classifying the global characteristic information to determine the group fog in the scene image and the group fog level corresponding to the group fog.
2. The method of claim 1, wherein before the feature extraction of the scene image to obtain global feature information, the method further comprises:
carrying out image preprocessing on the scene image to obtain a processed image;
correspondingly, the performing feature extraction on the scene image to obtain global feature information includes:
and extracting the features of the processed image to obtain the global feature information.
3. The method of claim 2, wherein the image preprocessing the scene image to obtain a processed image comprises:
carrying out pixel sampling on the scene image to obtain a sampling image with a target size;
and carrying out normalization processing on the sampling image to obtain the processed image.
4. The method according to any one of claims 1 to 3, wherein the classifying the global feature information to determine the cloud in the scene image and the cloud level corresponding to the cloud comprises:
performing average pooling on the global characteristic information to obtain global average characteristic information;
and classifying the global average characteristic information to determine the cluster fog and the cluster fog level.
5. The method according to any one of claims 1 to 4, wherein after determining the cloud in the scene image and the cloud level corresponding to the cloud, the method further comprises:
acquiring a first visibility range corresponding to a group fog level according to a corresponding relation between a preset group fog level and the visibility range;
under the condition that the first visibility range is lower than a preset visibility range, first early warning information corresponding to the group fog level is obtained;
and outputting the first early warning information.
6. The method according to any one of claims 1 to 5, wherein the scene image comprises a plurality of images at a plurality of time instants, the cloud level comprises a plurality of levels corresponding to the plurality of images, and after determining the cloud in the scene image and the cloud level corresponding to the cloud, the method further comprises:
under the condition that the multiple levels are positively correlated with the multiple moments, second early warning information is obtained;
acquiring early warning reminding equipment in the target scene;
and transmitting the second early warning information to the early warning reminding equipment.
7. The method according to any one of claims 1 to 5, wherein the scene image comprises a plurality of images at a plurality of time instants, the cloud level comprises a plurality of levels corresponding to the plurality of images, and after determining the cloud in the scene image and the cloud level corresponding to the cloud, the method further comprises:
counting the multiple levels to obtain a statistical result;
and determining the frequency of the cluster fog of the target scene according to the statistical result.
8. A group mist identifying device, characterized by comprising:
the image acquisition module is used for acquiring a scene image of a target scene;
the feature extraction module is used for extracting features of the scene image to obtain global feature information;
and the classification processing module is used for classifying the global characteristic information and determining the group fog in the scene image and the group fog level corresponding to the group fog.
9. An electronic device, characterized in that the electronic device comprises: a processor, a memory, and a communication bus; wherein the content of the first and second substances,
the communication bus is used for realizing connection communication between the processor and the memory;
the processor is configured to execute the group mist identification program stored in the memory to implement the group mist identification method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores one or more programs which are executable by one or more processors to implement the group fog identification method of any one of claims 1-7.
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010699922.1A CN111783732A (en) | 2020-07-17 | 2020-07-17 | Group mist identification method and device, electronic equipment and storage medium |
| KR1020227006772A KR20220041892A (en) | 2020-07-17 | 2021-05-18 | Mist identification method, apparatus, electronic device, storage medium and computer program product |
| JP2022513667A JP2022545962A (en) | 2020-07-17 | 2021-05-18 | Fog Recognition Method and Apparatus, Electronic Device, Storage Medium and Computer Program Product |
| PCT/CN2021/094385 WO2022012149A1 (en) | 2020-07-17 | 2021-05-18 | Agglomerate fog recognition method and apparatus, electronic device, storage medium, and computer program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010699922.1A CN111783732A (en) | 2020-07-17 | 2020-07-17 | Group mist identification method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111783732A true CN111783732A (en) | 2020-10-16 |
Family
ID=72763612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010699922.1A Pending CN111783732A (en) | 2020-07-17 | 2020-07-17 | Group mist identification method and device, electronic equipment and storage medium |
Country Status (4)
| Country | Link |
|---|---|
| JP (1) | JP2022545962A (en) |
| KR (1) | KR20220041892A (en) |
| CN (1) | CN111783732A (en) |
| WO (1) | WO2022012149A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112686105A (en) * | 2020-12-18 | 2021-04-20 | 云南省交通规划设计研究院有限公司 | Fog concentration grade identification method based on video image multi-feature fusion |
| CN112816483A (en) * | 2021-03-05 | 2021-05-18 | 北京文安智能技术股份有限公司 | Group fog recognition early warning method and system based on fog value analysis and electronic equipment |
| WO2022012149A1 (en) * | 2020-07-17 | 2022-01-20 | 上海商汤智能科技有限公司 | Agglomerate fog recognition method and apparatus, electronic device, storage medium, and computer program product |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102779349B (en) * | 2012-06-30 | 2015-02-18 | 东南大学 | Foggy day detecting method based on image color spatial feature |
| JP2014164375A (en) * | 2013-02-22 | 2014-09-08 | Pioneer Electronic Corp | Information processor, information processing system and information processing method, and program for information processor |
| US9305339B2 (en) * | 2014-07-01 | 2016-04-05 | Adobe Systems Incorporated | Multi-feature image haze removal |
| CN105303844B (en) * | 2015-10-26 | 2017-09-12 | 南京本来信息技术有限公司 | Night expressway fog automatic detection device and its detection method based on laser |
| CN108846324B (en) * | 2018-05-28 | 2020-06-30 | 中用科技有限公司 | Road fog detection method based on image |
| CN109683209A (en) * | 2018-12-27 | 2019-04-26 | 吉林省气象服务中心 | The monitoring method and monitoring system of group's mist |
| CN109961070A (en) * | 2019-03-22 | 2019-07-02 | 国网河北省电力有限公司电力科学研究院 | The method of mist body concentration is distinguished in a kind of power transmission line intelligent image monitoring |
| CN110378865A (en) * | 2019-04-28 | 2019-10-25 | 湖南师范大学 | A kind of greasy weather visibility intelligence hierarchical identification method and system under complex background |
| CN110598613B (en) * | 2019-09-03 | 2022-10-25 | 长安大学 | Expressway agglomerate fog monitoring method |
| CN111783732A (en) * | 2020-07-17 | 2020-10-16 | 上海商汤智能科技有限公司 | Group mist identification method and device, electronic equipment and storage medium |
-
2020
- 2020-07-17 CN CN202010699922.1A patent/CN111783732A/en active Pending
-
2021
- 2021-05-18 JP JP2022513667A patent/JP2022545962A/en active Pending
- 2021-05-18 WO PCT/CN2021/094385 patent/WO2022012149A1/en active Application Filing
- 2021-05-18 KR KR1020227006772A patent/KR20220041892A/en active Search and Examination
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022012149A1 (en) * | 2020-07-17 | 2022-01-20 | 上海商汤智能科技有限公司 | Agglomerate fog recognition method and apparatus, electronic device, storage medium, and computer program product |
| CN112686105A (en) * | 2020-12-18 | 2021-04-20 | 云南省交通规划设计研究院有限公司 | Fog concentration grade identification method based on video image multi-feature fusion |
| CN112816483A (en) * | 2021-03-05 | 2021-05-18 | 北京文安智能技术股份有限公司 | Group fog recognition early warning method and system based on fog value analysis and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022012149A1 (en) | 2022-01-20 |
| KR20220041892A (en) | 2022-04-01 |
| JP2022545962A (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112528878B (en) | Method and device for detecting lane line, terminal equipment and readable storage medium | |
| CN110276767B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN110473185B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN111783732A (en) | Group mist identification method and device, electronic equipment and storage medium | |
| CN109711264B (en) | Method and device for detecting occupation of bus lane | |
| CN108268867B (en) | License plate positioning method and device | |
| CN110580428A (en) | image processing method, image processing device, computer-readable storage medium and electronic equipment | |
| CN110781756A (en) | Urban road extraction method and device based on remote sensing image | |
| CN111461170A (en) | Vehicle image detection method and device, computer equipment and storage medium | |
| CN112487848B (en) | Character recognition method and terminal equipment | |
| CN110176024B (en) | Method, device, equipment and storage medium for detecting target in video | |
| CN108734684B (en) | Image background subtraction for dynamic illumination scene | |
| CN107704797B (en) | Real-time detection method, system and equipment based on pedestrians and vehicles in security video | |
| CN111259783A (en) | Video behavior detection method and system, highlight video playback system and storage medium | |
| CN113160106B (en) | Infrared target detection method and device, electronic equipment and storage medium | |
| CN111340831A (en) | Point cloud edge detection method and device | |
| CN111881984A (en) | Target detection method and device based on deep learning | |
| CN110991414A (en) | High-precision traffic element segmentation method, electronic equipment and storage medium | |
| CN113014876A (en) | Video monitoring method and device, electronic equipment and readable storage medium | |
| CN110428402B (en) | Image tampering identification method and device, computer equipment and storage medium | |
| CN110688926B (en) | Subject detection method and apparatus, electronic device, and computer-readable storage medium | |
| CN111860287A (en) | Target detection method and device and storage medium | |
| CN113239738B (en) | Image blurring detection method and blurring detection device | |
| CN114581664A (en) | Road scene segmentation method and device, electronic equipment and storage medium | |
| CN113963438A (en) | Behavior recognition method and device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40039167 Country of ref document: HK |