CN110186471A - Air navigation aid, device, computer equipment and storage medium based on history video - Google Patents
Air navigation aid, device, computer equipment and storage medium based on history video Download PDFInfo
- Publication number
- CN110186471A CN110186471A CN201910371108.4A CN201910371108A CN110186471A CN 110186471 A CN110186471 A CN 110186471A CN 201910371108 A CN201910371108 A CN 201910371108A CN 110186471 A CN110186471 A CN 110186471A
- Authority
- CN
- China
- Prior art keywords
- road
- picture
- real
- road conditions
- conditions
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 21
- 238000012549 training Methods 0.000 claims description 36
- 239000011159 matrix material Substances 0.000 claims description 21
- 238000013527 convolutional neural network Methods 0.000 claims description 19
- 241001269238 Data Species 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 14
- 238000000354 decomposition reaction Methods 0.000 claims description 13
- 238000000034 method Methods 0.000 abstract description 19
- 238000010586 diagram Methods 0.000 description 12
- 238000013528 artificial neural network Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 210000002569 neuron Anatomy 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 230000001537 neural effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3492—Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses air navigation aid, device, computer equipment and storage mediums based on history video.This method is by obtaining the road weather condition recognition result with the real road road conditions real picture using the real road road conditions real picture as the input of road weather condition identification model trained in advance；If the road weather condition recognition result is greater than preset bad weather early warning value, corresponding real road road conditions real picture and the corresponding geographical position coordinates of the real road road conditions real picture are obtained；And the corresponding real road road conditions real picture of the geographical position coordinates is replaced with into the road conditions real picture under non-severe weather conditions.This method uses nerual network technique, realizes and obtains road conditions picture by the period, and updates on electronic map, is based on real-time road data, can efficient navigation when in complex road surface.
Description
Technical field
The present invention relates to nerual network technique field more particularly to it is a kind of by the air navigation aid of history video, device, based on
Calculate machine equipment and storage medium.
Background technique
Currently, navigation software is more and more widely used because city transit route is more and more intricate.It is existing
Navigation software when being navigated, usually simple two-dimensional surface map combination road scenes figure come to user carry out route
Navigation, can not carry out the assisting navigation under inclement weather conditions.
Summary of the invention
The embodiment of the invention provides a kind of air navigation aid based on history video, device, computer equipment and storages to be situated between
Matter, it is intended to which solving navigation software in the prior art, when being navigated, usually simple two-dimensional surface map combination road is real
Scape figure carrys out the problem of carrying out route guidance to user, can not carrying out the assisting navigation under inclement weather conditions.
In a first aspect, the embodiment of the invention provides a kind of air navigation aids based on history video comprising:
If the time interval at current time and previous video acquisition moment is equal to preset collection period, obtain presetly
Road corresponding to position coordinates is managed in the road conditions video data at current time；
The road conditions video data is subjected to video decomposition, is obtained corresponding more with the road conditions video data
Frame road conditions picture；
A frame picture is obtained at random in multiframe road conditions picture corresponding with the road conditions video data, to make
For real road road conditions real picture corresponding with the road conditions video data；
Using the real road road conditions real picture as the input of road weather condition identification model trained in advance, obtain
To the road weather condition recognition result with the real road road conditions real picture；
If the road weather condition recognition result is greater than preset bad weather early warning value, corresponding real road is obtained
Road conditions real picture and the corresponding geographical position coordinates of the real road road conditions real picture；And
The corresponding real road road conditions real picture of the geographical position coordinates is replaced under non-severe weather conditions
Road conditions real picture.
Second aspect, the embodiment of the invention provides a kind of navigation devices based on history video comprising:
Current video acquisition unit, if for the time interval at current time and previous video acquisition moment equal to preset
Collection period obtains road corresponding to preset geographical position coordinates in the road conditions video data at current time；
Current video decomposition unit obtains and the road for the road conditions video data to be carried out video decomposition
The corresponding multiframe road conditions picture of road road conditions video data；
Unit is randomly selected, for random in multiframe road conditions picture corresponding with the road conditions video data
A frame picture is obtained, using as real road road conditions real picture corresponding with the road conditions video data；
Weather conditions recognition unit, for using the real road road conditions real picture as road weather trained in advance
The input of situation identification model obtains the road weather condition recognition result with the real road road conditions real picture；
As a result judging unit, if being greater than preset bad weather early warning value for the road weather condition recognition result,
Obtain corresponding real road road conditions real picture and the corresponding geographical position coordinates of the real road road conditions real picture；
And
Picture replacement unit, it is non-for replacing with the corresponding real road road conditions real picture of the geographical position coordinates
Road conditions real picture under severe weather conditions.
The third aspect, the embodiment of the present invention provide a kind of computer equipment again comprising memory, processor and storage
On the memory and the computer program that can run on the processor, the processor execute the computer program
Air navigation aid based on history video described in the above-mentioned first aspect of Shi Shixian.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, wherein the computer can
It reads storage medium and is stored with computer program, it is above-mentioned that the computer program when being executed by a processor executes the processor
Air navigation aid based on history video described in first aspect.
The embodiment of the invention provides a kind of air navigation aid based on history video, device, computer equipment and storages to be situated between
Matter.If this method includes that the time interval at current time and previous video acquisition moment is equal to preset collection period, obtain pre-
If geographical position coordinates corresponding to road current time road conditions video data；By the road conditions video counts
According to video decomposition is carried out, multiframe road conditions picture corresponding with the road conditions video data is obtained；With the road
Obtain a frame picture at random in the corresponding multiframe road conditions picture of road conditions video data, using as with the road conditions video
The corresponding real road road conditions real picture of data；Using the real road road conditions real picture as road day trained in advance
The input of vaporous condition identification model obtains the road weather condition recognition result with the real road road conditions real picture；If
The road weather condition recognition result is greater than preset bad weather early warning value, obtains corresponding real road road conditions realistic picture
Piece and the corresponding geographical position coordinates of the real road road conditions real picture；And it is the geographical position coordinates are corresponding
Real road road conditions real picture replaces with the road conditions real picture under non-severe weather conditions.This method uses nerve net
Network technology realizes and obtains road conditions picture by the period, and updates on electronic map, is based on real-time road number
According to can efficient navigation when in complex road surface.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the application scenarios schematic diagram of the air navigation aid provided in an embodiment of the present invention based on history video；
Fig. 2 is the flow diagram of the air navigation aid provided in an embodiment of the present invention based on history video；
Fig. 3 is the sub-process schematic diagram of the air navigation aid provided in an embodiment of the present invention based on history video；
Fig. 4 is the schematic block diagram of the navigation device provided in an embodiment of the present invention based on history video；
Fig. 5 is the subelement schematic block diagram of the navigation device provided in an embodiment of the present invention based on history video；
Fig. 6 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Fig. 1 and Fig. 2 are please referred to, Fig. 1 is the applied field of the air navigation aid provided in an embodiment of the present invention based on history video
Scape schematic diagram, Fig. 2 are the flow diagram of the air navigation aid provided in an embodiment of the present invention based on history video, should be based on history
The air navigation aid of video is applied in server, and this method is executed by the application software being installed in server.
As shown in Fig. 2, the method comprising the steps of S110~S160.
If S110, current time and the time interval at previous video acquisition moment are equal to preset collection period, obtain pre-
If geographical position coordinates corresponding to road current time road conditions video data.
In the present embodiment, an acquisition is arranged to the front-end acquisition device (such as high-definition camera) that road cross is arranged in
Period is to periodically carry out road conditions videograph to each monitored road, and at interval of collection period, (such as setting is adopted
Collecting the period is 30 minutes) duration of road conditions video data collected is also identical (such as 5 seconds), and can be to institute
After the road conditions video data of acquisition is handled, the Navigation Picture of newest road conditions is obtained.
S120, the road conditions video data is subjected to video decomposition, obtained and the road conditions video data pair
The multiframe road conditions picture answered.
In the present embodiment, by the forming process of video it is found that video is made of multiframe picture, such as each second view
Frequency can be converted to 24-30 picture.By video disassembling tool, (such as Adobe Premiere is cut in Adobe Premiere
Collect and to need the segment of output sequence bitmap, output is at sequence bitmap in File menu) it can be by the road conditions
Video data carries out video decomposition, obtains multiframe road conditions picture corresponding with the road conditions video data.
S130, a frame figure is obtained at random in multiframe road conditions picture corresponding with the road conditions video data
Piece, using as real road road conditions real picture corresponding with the road conditions video data.
In the present embodiment, in the road conditions video data of current time acquired preset duration (5 seconds), depending on
After frequency division solution, 120-150 road conditions pictures have been obtained, can wherein randomly choose one as current time at this time
Road conditions picture collects road conditions video data at interval of collection period for every a road section in this way and only retains a figure
Piece is as road conditions real picture.
In one embodiment, after step S130 further include:
The real road road conditions real picture at current time and corresponding acquisition time are stored.
In the specific implementation, for each monitored road, at interval of collection period road collected
Road conditions video data only retains a road conditions real picture after video decomposes and selects a frame picture at random, then each quilt
The road of monitoring accumulates in multiple road conditions video acquisition periods gets off to have multiple road conditions real pictures.Such as road
The road conditions video acquisition period is set as 30 minutes, then monitored has 48 road conditions real pictures within road one day for each
It is saved.Once the state of the road changes, it can timely upload and the server of navigation Service is provided, by server
Timely update the road conditions real picture of each monitored road.
By this road conditions real picture for periodically updating road, the use using navigation Service more can be timely reminded
The real road situation of each road in family.For example, a certain moment present road enters extraordinary maintenance state, the corresponding acquisition of this moment
The road road conditions real picture in can embody the road in time and enter service mode, may cause congestion, prompt
Driver plans that other routes detour in time.
S140, using the real road road conditions real picture as the defeated of road weather condition identification model trained in advance
Enter, obtains the road weather condition recognition result with the real road road conditions real picture.
In one embodiment, before step S140 further include:
Multiple training datas are obtained, is trained, is obtained for knowing with the road weather condition identification model for treating trained
The road weather condition identification model of other road weather condition recognition result；Wherein, each training data in multiple training datas
Using the corresponding picture feature vector of road conditions picture as the input of road weather condition identification model to be trained, and with road
Output of the weather conditions recognition result in road as road weather condition identification model to be trained；Wherein, in multiple training datas
The acquisition moment of the corresponding road conditions picture of each training data and the difference at current time were less than or equal between the preset time
Every threshold value；The corresponding road weather condition recognition result of each training data is the weather conditions recognition result marked in advance.
In the present embodiment, in advance training one road weather condition identification model when, can select present road multiple
Captured road conditions real picture under weather conditions, it is such as vaporous in rainy day, snowy day, haze sky, fine day, cloudy 5 kinds of days
Road conditions real picture under condition, it is 1 that the corresponding road weather condition recognition result of fine day, which is then arranged, cloudy day corresponding road
Weather conditions recognition result in road is 2, and rainy day corresponding road weather condition recognition result is 3, snowy day corresponding road weather
Situation recognition result is 4, and the corresponding road weather condition recognition result of haze sky is 5.By under a large amount of various weather conditions
The corresponding picture feature vector of road conditions real picture as input, and the road weather condition being correspondingly arranged is identified and is tied
Fruit obtains road weather condition identification model into training as output, to deep neural network.
Used deep neural network, that is, DNN (Deep Neural Networks, abbreviation DNN), DNN can be understood as
There is the neural network of many hidden layers.Neural net layer inside DNN can be divided into three classes, input layer, hidden layer and output layer,
In general first layer is input layer, and the last layer is output layer, and the intermediate number of plies is all hidden layer.It is complete between layers
Connection, that is to say, that i-th layer any one neuron is centainly connected with any one neuron of i+1 layer.
In one embodiment, as shown in figure 3, using the real road road conditions real picture as preparatory instruction in step S140
The input of experienced road weather condition identification model, comprising:
S141, picture element matrix corresponding with the real road road conditions real picture is obtained；
S142, using the picture element matrix as the input of input layer in convolutional neural networks model, correspondence obtains multiple spies
Sign figure；
S143, the pond layer that multiple characteristic patterns are input to convolutional neural networks model, it is corresponding to obtain each characteristic pattern
One-dimensional row vector corresponding to maximum value；
S144, one-dimensional row vector corresponding to the corresponding maximum value of each characteristic pattern is input to convolutional neural networks model
Full articulamentum obtains picture feature vector corresponding with the real road road conditions real picture；
S145, using the picture feature vector as the input of road weather condition identification model trained in advance.
In the present embodiment, each frame road conditions real picture can be converted into the picture element matrix (picture of such as 256*256
Prime matrix), using picture element matrix as when the input of input layer, input layer is obtained by convolution operation in convolutional neural networks model
Several Feature Map (Feature Map can be understood as characteristic pattern), after the size for setting convolution window, pass through
Convolution window, which carries out convolution to picture element matrix, will obtain Feature Map of several columns for 1.
In the layer of pond, it can be used and propose maximum value from Feature Map one-dimensional before.By this
Pooling mode (i.e. the mode in pond) can solve the input problem of variable picture pixels size (because regardless of Feature
In Map how many value, it is only necessary to extract maximum value therein), the most output of terminal cistern layer be each Feature Map most
Big value, i.e. an one-dimensional vector.
One-dimensional row vector corresponding to the corresponding maximum value of each characteristic pattern is finally input to convolutional neural networks model
Full articulamentum obtains picture feature vector corresponding with the real road road conditions real picture, can be by the picture feature
Input of the vector as road weather condition identification model trained in advance.
If S150, the road weather condition recognition result are greater than preset bad weather early warning value, corresponding reality is obtained
Border road conditions real picture and the corresponding geographical position coordinates of the real road road conditions real picture.
In the present embodiment, the real road road conditions real picture is carried out when by road weather condition identification model
When identification, if the corresponding road weather condition recognition result of current time road conditions real picture collected is 3, have exceeded
Preset bad weather early warning value 2, then it represents that the road conditions real picture at this moment of present road is not suitable for as road
Real scene navigation picture.Needing positioning at this time, there are road weather condition recognition results to be greater than corresponding to preset bad weather early warning value
The geographical position coordinates of road need to replace with road under non-severe weather conditions with the real scene navigation picture for judging which road
Road road conditions real picture (the lower road conditions real picture of such as fine day or cloudy day) is typically chosen with current time interval recently
Road conditions real picture is replaced under non-severe weather conditions.
S160, the corresponding real road road conditions real picture of the geographical position coordinates is replaced with into non-severe weather conditions
Under road conditions real picture.
In one embodiment, before step S160 further include:
Multiple history road conditions real pictures corresponding with the geographical position coordinates are obtained, and it is real to obtain each history road conditions
The acquisition time of scape picture；
It obtains multiple corresponding acquisition times of history road conditions real picture and the time interval at current time is minimum time
Interval and corresponding road weather condition recognition result are the history road conditions real picture of non-severe weather conditions.
Wherein, non-severe weather conditions are fine day or cloudy day, the road surface or high-visible under both weather conditions,
Road conditions real picture under the Lu Fei severe weather conditions of old course replaces with road of the road under non-severe weather conditions
Road road conditions real picture, can be effectively by road conditions real picture of the road under non-severe weather conditions as navigation
Picture.
If there are many real pictures in the geographical location, preferential selection is apart from the recent acquisition of present system time
Obtained real picture is replaced；For example, before being 30 minutes apart from the recent acquisition of present system time, and
It is non-bad weather before 30 minutes, the road conditions real picture acquired before available 30 minutes at this time is as navigation
Picture；It before being 30 minutes apart from the recent acquisition of present system time, and is bad weather before 30 minutes, at this time
The road conditions real picture acquired before available 1 hour judges whether it is bad weather again, until to being pushed forward
A certain moment road conditions real picture collected corresponds to non-bad weather.
The method achieve road conditions picture is obtained by the period, and update on electronic map, based on real-time
Road condition data, can efficient navigation when in complex road surface.
The embodiment of the present invention also provides a kind of navigation device based on history video, should the navigation device based on history video
For executing any embodiment of the aforementioned air navigation aid based on history video.Specifically, referring to Fig. 4, Fig. 4 is of the invention real
The schematic block diagram of the navigation device based on history video of example offer is provided.The navigation device 100 based on history video can be with
It is configured in server.
As shown in figure 4, the navigation device 100 based on history video includes current video acquisition unit 110, current video point
Solution unit 120 randomly selects unit 130, weather conditions recognition unit 140, result judging unit 150, picture replacement unit
160。
Current video acquisition unit 110, if being equal to for the time interval at current time and previous video acquisition moment pre-
If collection period, obtain road corresponding to preset geographical position coordinates in the road conditions video data at current time.
In the present embodiment, an acquisition is arranged to the front-end acquisition device (such as high-definition camera) that road cross is arranged in
Period is to periodically carry out road conditions videograph to each monitored road, and at interval of collection period, (such as setting is adopted
Collecting the period is 30 minutes) duration of road conditions video data collected is also identical (such as 5 seconds), and can be to institute
After the road conditions video data of acquisition is handled, the Navigation Picture of newest road conditions is obtained.
Current video decomposition unit 120, for by the road conditions video data carry out video decomposition, obtain with it is described
The corresponding multiframe road conditions picture of road conditions video data.
In the present embodiment, by the forming process of video it is found that video is made of multiframe picture, such as each second view
Frequency can be converted to 24-30 picture.By video disassembling tool, (such as Adobe Premiere is cut in Adobe Premiere
Collect and to need the segment of output sequence bitmap, output is at sequence bitmap in File menu) it can be by the road conditions
Video data carries out video decomposition, obtains multiframe road conditions picture corresponding with the road conditions video data.
Unit 130 is randomly selected, in multiframe road conditions picture corresponding with the road conditions video data
It is random to obtain a frame picture, using as real road road conditions real picture corresponding with the road conditions video data.
In the present embodiment, in the road conditions video data of current time acquired preset duration (5 seconds), depending on
After frequency division solution, 120-150 road conditions pictures have been obtained, can wherein randomly choose one as current time at this time
Road conditions picture collects road conditions video data at interval of collection period for every a road section in this way and only retains a figure
Piece is as road conditions real picture.
In one embodiment, based on the navigation device 100 of history video further include:
Picture timing storage unit, for by the real road road conditions real picture and corresponding acquisition time at current time
It is stored.
In the specific implementation, for each monitored road, at interval of collection period road collected
Road conditions video data only retains a road conditions real picture after video decomposes and selects a frame picture at random, then each quilt
The road of monitoring accumulates in multiple road conditions video acquisition periods gets off to have multiple road conditions real pictures.Such as road
The road conditions video acquisition period is set as 30 minutes, then monitored has 48 road conditions real pictures within road one day for each
It is saved.Once the state of the road changes, it can timely upload and the server of navigation Service is provided, by server
Timely update the road conditions real picture of each monitored road.
By this road conditions real picture for periodically updating road, the use using navigation Service more can be timely reminded
The real road situation of each road in family.For example, a certain moment present road enters extraordinary maintenance state, the corresponding acquisition of this moment
The road road conditions real picture in can embody the road in time and enter service mode, may cause congestion, prompt
Driver plans that other routes detour in time.
Weather conditions recognition unit 140, for using the real road road conditions real picture as road trained in advance
The input of weather conditions identification model obtains the road weather condition recognition result with the real road road conditions real picture.
In one embodiment, based on the navigation device 100 of history video further include:
Model training unit, for obtaining multiple training datas, with treat trained road weather condition identification model into
Row training, obtains the road weather condition identification model of road weather condition recognition result for identification；Wherein, multiple trained numbers
Each training data is identified using the corresponding picture feature vector of road conditions picture as road weather condition to be trained in
The input of model, and using road weather condition recognition result as the output of road weather condition identification model to be trained；Its
In, in multiple training datas the acquisition moment of the corresponding road conditions picture of each training data and the difference at current time be less than or
Equal to preset time interval threshold value；The corresponding road weather condition recognition result of each training data is the weather marked in advance
Situation recognition result.
In the present embodiment, in advance training one road weather condition identification model when, can select present road multiple
Captured road conditions real picture under weather conditions, it is such as vaporous in rainy day, snowy day, haze sky, fine day, cloudy 5 kinds of days
Road conditions real picture under condition, it is 1 that the corresponding road weather condition recognition result of fine day, which is then arranged, cloudy day corresponding road
Weather conditions recognition result in road is 2, and rainy day corresponding road weather condition recognition result is 3, snowy day corresponding road weather
Situation recognition result is 4, and the corresponding road weather condition recognition result of haze sky is 5.By under a large amount of various weather conditions
The corresponding picture feature vector of road conditions real picture as input, and the road weather condition being correspondingly arranged is identified and is tied
Fruit obtains road weather condition identification model into training as output, to deep neural network.
Used deep neural network, that is, DNN (Deep Neural Networks, abbreviation DNN), DNN can be understood as
There is the neural network of many hidden layers.Neural net layer inside DNN can be divided into three classes, input layer, hidden layer and output layer,
In general first layer is input layer, and the last layer is output layer, and the intermediate number of plies is all hidden layer.It is complete between layers
Connection, that is to say, that i-th layer any one neuron is centainly connected with any one neuron of i+1 layer.
In one embodiment, as shown in figure 5, weather conditions recognition unit 140 includes:
Picture element matrix acquiring unit 141, for obtaining picture element matrix corresponding with the real road road conditions real picture；
Convolution unit 142, for corresponding to using the picture element matrix as the input of input layer in convolutional neural networks model
Obtain multiple characteristic patterns；
Pond unit 143 obtains each spy for multiple characteristic patterns to be input to the pond layer of convolutional neural networks model
Sign schemes one-dimensional row vector corresponding to corresponding maximum value；
Full connection unit 144, for one-dimensional row vector corresponding to the corresponding maximum value of each characteristic pattern to be input to convolution
The full articulamentum of neural network model obtains picture feature vector corresponding with the real road road conditions real picture；
Input vector acquiring unit 145, for using the picture feature vector as road weather condition trained in advance
The input of identification model.
In the present embodiment, each frame road conditions real picture can be converted into the picture element matrix (picture of such as 256*256
Prime matrix), using picture element matrix as when the input of input layer, input layer is obtained by convolution operation in convolutional neural networks model
Several Feature Map (Feature Map can be understood as characteristic pattern), after the size for setting convolution window, pass through
Convolution window, which carries out convolution to picture element matrix, will obtain Feature Map of several columns for 1.
In the layer of pond, it can be used and propose maximum value from Feature Map one-dimensional before.By this
Pooling mode (i.e. the mode in pond) can solve the input problem of variable picture pixels size (because regardless of Feature
In Map how many value, it is only necessary to extract maximum value therein), the most output of terminal cistern layer be each Feature Map most
Big value, i.e. an one-dimensional vector.
One-dimensional row vector corresponding to the corresponding maximum value of each characteristic pattern is finally input to convolutional neural networks model
Full articulamentum obtains picture feature vector corresponding with the real road road conditions real picture, can be by the picture feature
Input of the vector as road weather condition identification model trained in advance.
As a result judging unit 150, if being greater than preset bad weather early warning for the road weather condition recognition result
Value, obtains corresponding real road road conditions real picture and the corresponding geographical location of the real road road conditions real picture is sat
Mark.
In the present embodiment, the real road road conditions real picture is carried out when by road weather condition identification model
When identification, if the corresponding road weather condition recognition result of current time road conditions real picture collected is 3, have exceeded
Preset bad weather early warning value 2, then it represents that the road conditions real picture at this moment of present road is not suitable for as road
Real scene navigation picture.Needing positioning at this time, there are road weather condition recognition results to be greater than corresponding to preset bad weather early warning value
The geographical position coordinates of road need to replace with road under non-severe weather conditions with the real scene navigation picture for judging which road
Road road conditions real picture (the lower road conditions real picture of such as fine day or cloudy day) is typically chosen with current time interval recently
Road conditions real picture is replaced under non-severe weather conditions.
Picture replacement unit 160, for replacing the corresponding real road road conditions real picture of the geographical position coordinates
For the road conditions real picture under non-severe weather conditions.
In one embodiment, in the navigation device 100 of history video further include:
History road conditions real picture acquiring unit, for obtaining multiple history road conditions corresponding with the geographical position coordinates
Real picture, and obtain the acquisition time of each history road conditions real picture；
Picture screening unit, for obtain multiple corresponding acquisition times of history road conditions real picture and current time when
Between spacing be minimum interval and corresponding road weather condition recognition result be non-severe weather conditions history road conditions it is real
Scape picture.
Wherein, non-severe weather conditions are fine day or cloudy day, the road surface or high-visible under both weather conditions,
Road conditions real picture under the Lu Fei severe weather conditions of old course replaces with road of the road under non-severe weather conditions
Road road conditions real picture, can be effectively by road conditions real picture of the road under non-severe weather conditions as navigation
Picture.
If there are many real pictures in the geographical location, preferential selection is apart from the recent acquisition of present system time
Obtained real picture is replaced；For example, before being 30 minutes apart from the recent acquisition of present system time, and
It is non-bad weather before 30 minutes, the road conditions real picture acquired before available 30 minutes at this time is as navigation
Picture；It before being 30 minutes apart from the recent acquisition of present system time, and is bad weather before 30 minutes, at this time
The road conditions real picture acquired before available 1 hour judges whether it is bad weather again, until to being pushed forward
A certain moment road conditions real picture collected corresponds to non-bad weather.
The arrangement achieves road conditions picture is obtained by the period, and update on electronic map, based on real-time
Road condition data, can efficient navigation when in complex road surface.
The above-mentioned navigation device based on history video can be implemented as the form of computer program, which can be with
It is run in computer equipment as shown in FIG. 6.
Referring to Fig. 6, Fig. 6 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.The computer equipment
500 be server, and server can be independent server, is also possible to the server cluster of multiple server compositions.
Refering to Fig. 6, which includes processor 502, memory and the net connected by system bus 501
Network interface 505, wherein memory may include non-volatile memory medium 503 and built-in storage 504.
The non-volatile memory medium 503 can storage program area 5031 and computer program 5032.The computer program
5032 are performed, and processor 502 may make to execute the air navigation aid based on history video.
The processor 502 supports the operation of entire computer equipment 500 for providing calculating and control ability.
The built-in storage 504 provides environment for the operation of the computer program 5032 in non-volatile memory medium 503, should
When computer program 5032 is executed by processor 502, processor 502 may make to execute the air navigation aid based on history video.
The network interface 505 is for carrying out network communication, such as the transmission of offer data information.Those skilled in the art can
To understand, structure shown in Fig. 6, only the block diagram of part-structure relevant to the present invention program, is not constituted to this hair
The restriction for the computer equipment 500 that bright scheme is applied thereon, specific computer equipment 500 may include than as shown in the figure
More or fewer components perhaps combine certain components or with different component layouts.
Wherein, the processor 502 is for running computer program 5032 stored in memory, to realize following function
Can: if the time interval at current time and previous video acquisition moment is equal to preset collection period, obtain preset geographical position
Road corresponding to coordinate is set in the road conditions video data at current time；The road conditions video data is subjected to video
It decomposes, obtains multiframe road conditions picture corresponding with the road conditions video data；With the road conditions video counts
According to obtaining a frame picture at random in corresponding multiframe road conditions picture, using as corresponding with the road conditions video data
Real road road conditions real picture；Using the real road road conditions real picture as road weather condition identification trained in advance
The input of model obtains the road weather condition recognition result with the real road road conditions real picture；If the road day
Vaporous condition recognition result is greater than preset bad weather early warning value, obtains corresponding real road road conditions real picture and described
The corresponding geographical position coordinates of real road road conditions real picture；And by the corresponding real road road of the geographical position coordinates
Condition real picture replaces with the road conditions real picture under non-severe weather conditions.
In one embodiment, the road corresponding to the execution preset geographical position coordinates of acquisition of processor 502 exists
It before the step of road conditions video data at current time, also performs the following operations: obtaining multiple training datas, to treat instruction
Experienced road weather condition identification model is trained, and the road day for obtaining road weather condition recognition result for identification is vaporous
Condition identification model；Wherein, each training data is made in multiple training datas with the corresponding picture feature vector of road conditions picture
For the input of road weather condition identification model to be trained, and using road weather condition recognition result as road to be trained
The output of weather conditions identification model.
In one embodiment, processor 502 is described using the real road road conditions real picture as preparatory instruction in execution
It when the step of the input of experienced road weather condition identification model, performs the following operations: obtaining real with the real road road conditions
The corresponding picture element matrix of scape picture；Using the picture element matrix as the input of input layer in convolutional neural networks model, to deserved
To multiple characteristic patterns；Multiple characteristic patterns are input to the pond layer of convolutional neural networks model, it is corresponding to obtain each characteristic pattern
One-dimensional row vector corresponding to maximum value；One-dimensional row vector corresponding to the corresponding maximum value of each characteristic pattern is input to convolutional Neural
The full articulamentum of network model obtains picture feature vector corresponding with the real road road conditions real picture；By the figure
Input of the piece feature vector as road weather condition identification model trained in advance.
In one embodiment, processor 502 is executing the corresponding real road road conditions reality of the geographical position coordinates
It before scape picture replaces with the step of road conditions real picture under non-severe weather conditions, also performs the following operations: obtaining
Multiple history road conditions real pictures corresponding with the geographical position coordinates, and obtain the acquisition of each history road conditions real picture
Time；Multiple corresponding acquisition times of history road conditions real picture and the time interval at current time are obtained between minimum time
Every and corresponding road weather condition recognition result be non-severe weather conditions history road conditions real picture.
In one embodiment, processor 502 is described in multiframe road corresponding with the road conditions video data in execution
A frame picture is obtained in the road conditions picture of road at random, using real as corresponding with road conditions video data real road road conditions
It after the step of scape picture, also performs the following operations: by the real road road conditions real picture at current time and corresponding acquisition
Time is stored.
It will be understood by those skilled in the art that the embodiment of computer equipment shown in Fig. 6 is not constituted to computer
The restriction of equipment specific composition, in other embodiments, computer equipment may include components more more or fewer than diagram, or
Person combines certain components or different component layouts.For example, in some embodiments, computer equipment can only include depositing
Reservoir and processor, in such embodiments, the structure and function of memory and processor are consistent with embodiment illustrated in fig. 6,
Details are not described herein.
It should be appreciated that in embodiments of the present invention, processor 502 can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable GateArray, FPGA) or other programmable logic devices
Part, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
The processor is also possible to any conventional processor etc..
Computer readable storage medium is provided in another embodiment of the invention.The computer readable storage medium can be with
For non-volatile computer readable storage medium.The computer-readable recording medium storage has computer program, wherein calculating
If machine program performs the steps of current time when being executed by processor and the time interval at previous video acquisition moment is equal in advance
If collection period, obtain road corresponding to preset geographical position coordinates in the road conditions video data at current time；
The road conditions video data is subjected to video decomposition, obtains multiframe Road corresponding with the road conditions video data
Condition picture；A frame picture is obtained at random in multiframe road conditions picture corresponding with the road conditions video data, to make
For real road road conditions real picture corresponding with the road conditions video data；By the real road road conditions real picture
As the input of road weather condition identification model trained in advance, the road with the real road road conditions real picture is obtained
Weather conditions recognition result；If the road weather condition recognition result is greater than preset bad weather early warning value, obtains and correspond to
Real road road conditions real picture and the corresponding geographical position coordinates of the real road road conditions real picture；And by institute
It states the corresponding real road road conditions real picture of geographical position coordinates and replaces with road conditions outdoor scene under non-severe weather conditions
Picture.
In one embodiment, described to obtain road corresponding to preset geographical position coordinates in the Road at current time
Before condition video data, further includes: obtain multiple training datas, instructed with the road weather condition identification model for treating trained
Practice, obtains the road weather condition identification model of road weather condition recognition result for identification；Wherein, in multiple training datas
Each training data is using the corresponding picture feature vector of road conditions picture as road weather condition identification model to be trained
Input, and using road weather condition recognition result as the output of road weather condition identification model to be trained.
In one embodiment, described using the real road road conditions real picture as road weather condition trained in advance
The input of identification model, comprising: obtain picture element matrix corresponding with the real road road conditions real picture；By the pixel square
Input of the battle array as input layer in convolutional neural networks model, correspondence obtain multiple characteristic patterns；Multiple characteristic patterns are input to volume
The pond layer of product neural network model, obtains one-dimensional row vector corresponding to the corresponding maximum value of each characteristic pattern；By each feature
Scheme the full articulamentum that one-dimensional row vector corresponding to corresponding maximum value is input to convolutional neural networks model, obtains and the reality
The corresponding picture feature vector of road conditions real picture；The picture feature vector is vaporous as road day trained in advance
The input of condition identification model.
In one embodiment, it is described the corresponding real road road conditions real picture of the geographical position coordinates is replaced with it is non-
Before road conditions real picture under severe weather conditions, further includes: obtain it is corresponding with the geographical position coordinates multiple
History road conditions real picture, and obtain the acquisition time of each history road conditions real picture；Obtain multiple history road conditions realistic pictures
The corresponding acquisition time of piece is minimum interval with the time interval at current time and the identification of corresponding road weather condition is tied
Fruit is the history road conditions real picture of non-severe weather conditions.
In one embodiment, described random in multiframe road conditions picture corresponding with the road conditions video data
A frame picture is obtained, as after real road road conditions real picture corresponding with the road conditions video data, comprising:
The real road road conditions real picture at current time and corresponding acquisition time are stored.
It is apparent to those skilled in the art that for convenience of description and succinctly, foregoing description is set
The specific work process of standby, device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
Those of ordinary skill in the art may be aware that unit described in conjunction with the examples disclosed in the embodiments of the present disclosure and algorithm
Step can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and software
Interchangeability generally describes each exemplary composition and step according to function in the above description.These functions are studied carefully
Unexpectedly the specific application and design constraint depending on technical solution are implemented in hardware or software.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided by the present invention, it should be understood that disclosed unit and method, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only logical function partition, there may be another division manner in actual implementation, can also will be with the same function
Unit set is at a unit, such as multiple units or components can be combined or can be integrated into another system or some
Feature can be ignored, or not execute.In addition, shown or discussed mutual coupling, direct-coupling or communication connection can
Be through some interfaces, the indirect coupling or communication connection of device or unit, be also possible to electricity, mechanical or other shapes
Formula connection.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of unit therein can be selected to realize the embodiment of the present invention according to the actual needs
Purpose.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, is also possible to two or more units and is integrated in one unit.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in one storage medium.Based on this understanding, technical solution of the present invention is substantially in other words to existing
The all or part of part or the technical solution that technology contributes can be embodied in the form of software products, should
Computer software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
Personal computer, server or network equipment etc.) execute all or part of step of each embodiment the method for the present invention
Suddenly.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), magnetic disk or
The various media that can store program code such as person's CD.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (10)
1. a kind of air navigation aid based on history video characterized by comprising
If the time interval at current time and previous video acquisition moment is equal to preset collection period, preset geographical position is obtained
Road corresponding to coordinate is set in the road conditions video data at current time；
The road conditions video data is subjected to video decomposition, obtains multiframe road corresponding with the road conditions video data
Road road conditions picture；
Obtain a frame picture at random in multiframe road conditions picture corresponding with the road conditions video data, using as with
The corresponding real road road conditions real picture of the road conditions video data；
Using the real road road conditions real picture as the input of road weather condition identification model trained in advance, obtain with
The road weather condition recognition result of the real road road conditions real picture；
If the road weather condition recognition result is greater than preset bad weather early warning value, corresponding real road road conditions are obtained
Real picture and the corresponding geographical position coordinates of the real road road conditions real picture；And
The corresponding real road road conditions real picture of the geographical position coordinates is replaced with into the road under non-severe weather conditions
Road conditions real picture.
2. the air navigation aid according to claim 1 based on history video, which is characterized in that described to obtain preset geography
Road corresponding to position coordinates is before the road conditions video data at current time, further includes:
Multiple training datas are obtained, is trained with the road weather condition identification model for treating trained, obtains road for identification
The road weather condition identification model of road weather conditions recognition result；Wherein, in multiple training datas each training data with road
Input of the road conditions picture corresponding picture feature vector in road as road weather condition identification model to be trained, and with road day
Output of the vaporous condition recognition result as road weather condition identification model to be trained；Wherein, each in multiple training datas
The acquisition moment of the corresponding road conditions picture of training data and the difference at current time are less than or equal to preset time interval threshold
Value；The corresponding road weather condition recognition result of each training data is the weather conditions recognition result marked in advance.
3. the air navigation aid according to claim 1 based on history video, which is characterized in that described by the real road
Input of the road conditions real picture as road weather condition identification model trained in advance, comprising:
Obtain picture element matrix corresponding with the real road road conditions real picture；
Using the picture element matrix as the input of input layer in convolutional neural networks model, correspondence obtains multiple characteristic patterns；
Multiple characteristic patterns are input to the pond layer of convolutional neural networks model, it is right to obtain the corresponding maximum value institute of each characteristic pattern
Answer one-dimensional row vector；
One-dimensional row vector corresponding to the corresponding maximum value of each characteristic pattern is input to the full articulamentum of convolutional neural networks model,
Obtain picture feature vector corresponding with the real road road conditions real picture；
Using the picture feature vector as the input of road weather condition identification model trained in advance.
4. the air navigation aid according to claim 1 based on history video, which is characterized in that described by the geographical location
Before the corresponding real road road conditions real picture of coordinate replaces with the road conditions real picture under non-severe weather conditions, also
Include:
Multiple history road conditions real pictures corresponding with the geographical position coordinates are obtained, and obtain each history road conditions realistic picture
The acquisition time of piece；
Obtain multiple corresponding acquisition times of history road conditions real picture and the time interval at current time be minimum interval,
And corresponding road weather condition recognition result is the history road conditions real picture of non-severe weather conditions.
5. the air navigation aid according to claim 1 based on history video, which is characterized in that it is described with the Road
Obtain a frame picture at random in the corresponding multiframe road conditions picture of condition video data, using as with the road conditions video counts
After corresponding real road road conditions real picture, comprising:
The real road road conditions real picture at current time and corresponding acquisition time are stored.
6. a kind of navigation device based on history video characterized by comprising
Current video acquisition unit, if being equal to preset acquisition for the time interval at current time and previous video acquisition moment
Period obtains road corresponding to preset geographical position coordinates in the road conditions video data at current time；
Current video decomposition unit obtains and the Road for the road conditions video data to be carried out video decomposition
The corresponding multiframe road conditions picture of condition video data；
Unit is randomly selected, for obtaining at random in multiframe road conditions picture corresponding with the road conditions video data
One frame picture, using as real road road conditions real picture corresponding with the road conditions video data；
Weather conditions recognition unit, for using the real road road conditions real picture as road weather condition trained in advance
The input of identification model obtains the road weather condition recognition result with the real road road conditions real picture；
As a result judging unit obtains if being greater than preset bad weather early warning value for the road weather condition recognition result
Corresponding real road road conditions real picture and the corresponding geographical position coordinates of the real road road conditions real picture；And
Picture replacement unit, it is non-severe for replacing with the corresponding real road road conditions real picture of the geographical position coordinates
Road conditions real picture under weather conditions.
7. the navigation device according to claim 6 based on history video, which is characterized in that further include:
Model training unit is instructed for obtaining multiple training datas with the road weather condition identification model for treating trained
Practice, obtains the road weather condition identification model of road weather condition recognition result for identification；Wherein, in multiple training datas
Each training data is using the corresponding picture feature vector of road conditions picture as road weather condition identification model to be trained
Input, and using road weather condition recognition result as the output of road weather condition identification model to be trained；Wherein, more
The acquisition moment of the corresponding road conditions picture of each training data and the difference at current time are less than or equal in a training data
Preset time interval threshold value；The corresponding road weather condition recognition result of each training data is the weather conditions marked in advance
Recognition result.
8. the navigation device according to claim 6 based on history video, which is characterized in that the weather conditions identification is single
Member, comprising:
Picture element matrix acquiring unit, for obtaining picture element matrix corresponding with the real road road conditions real picture；
Convolution unit, for using the picture element matrix as the input of input layer in convolutional neural networks model, correspondence to obtain more
A characteristic pattern；
Pond unit obtains each characteristic pattern pair for multiple characteristic patterns to be input to the pond layer of convolutional neural networks model
One-dimensional row vector corresponding to the maximum value answered；
Full connection unit, for one-dimensional row vector corresponding to the corresponding maximum value of each characteristic pattern to be input to convolutional neural networks
The full articulamentum of model obtains picture feature vector corresponding with the real road road conditions real picture；
Input vector acquiring unit, for using the picture feature vector as road weather condition identification model trained in advance
Input.
9. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 5 when executing the computer program
Any one of described in the air navigation aid based on history video.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence, the computer program make the processor execute such as base described in any one of claim 1 to 5 when being executed by a processor
In the air navigation aid of history video.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910371108.4A CN110186471A (en) | 2019-05-06 | 2019-05-06 | Air navigation aid, device, computer equipment and storage medium based on history video |
| PCT/CN2019/103329 WO2020224117A1 (en) | 2019-05-06 | 2019-08-29 | Historical video-based navigation method and device, computer apparatus and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910371108.4A CN110186471A (en) | 2019-05-06 | 2019-05-06 | Air navigation aid, device, computer equipment and storage medium based on history video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110186471A true CN110186471A (en) | 2019-08-30 |
Family
ID=67715601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910371108.4A Pending CN110186471A (en) | 2019-05-06 | 2019-05-06 | Air navigation aid, device, computer equipment and storage medium based on history video |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110186471A (en) |
| WO (1) | WO2020224117A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110807549A (en) * | 2019-10-29 | 2020-02-18 | 国网电力科学研究院武汉南瑞有限责任公司 | Generation method, generation device, generation system and electronic equipment of meteorological prediction model |
| CN111178407A (en) * | 2019-12-19 | 2020-05-19 | 中国平安人寿保险股份有限公司 | Road condition data screening method and device, computer equipment and storage medium |
| CN113887286A (en) * | 2021-08-31 | 2022-01-04 | 际络科技(上海)有限公司 | Driver behavior monitoring method based on online video understanding network |
| CN115148040A (en) * | 2022-06-28 | 2022-10-04 | 东莞中科云计算研究院 | Unmanned vehicle control method and system for closed road environment |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008257403A (en) * | 2007-04-03 | 2008-10-23 | Denso Corp | Driving support device for vehicle |
| JP2010257253A (en) * | 2009-04-24 | 2010-11-11 | Denso Corp | Display device for vehicle |
| CN104834912A (en) * | 2015-05-14 | 2015-08-12 | 北京邮电大学 | Weather identification method and apparatus based on image information detection |
| CN105575119A (en) * | 2015-12-29 | 2016-05-11 | 大连楼兰科技股份有限公司 | Road condition climate deep learning and recognition method and apparatus |
| CN106611162A (en) * | 2016-12-20 | 2017-05-03 | 西安电子科技大学 | Method for real-time detection of road vehicle based on deep learning SSD frame |
| CN106709511A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Urban rail transit panoramic monitoring video fault detection method based on depth learning |
| CN107238874A (en) * | 2017-05-25 | 2017-10-10 | 苏州工业职业技术学院 | Based on when scape photo real-time weather detection method and system |
| EP3361412A1 (en) * | 2017-02-10 | 2018-08-15 | Fujitsu Limited | Black ice detection system, program, and method |
| CN108513674A (en) * | 2018-03-26 | 2018-09-07 | 深圳市锐明技术股份有限公司 | A kind of detection alarm method, storage medium and the server of Chinese herbaceous peony accumulated snow and icing |
| CN108701396A (en) * | 2018-03-26 | 2018-10-23 | 深圳市锐明技术股份有限公司 | A kind of detection alarm method, storage medium and the server of Chinese herbaceous peony accumulated snow and icing |
| CN108805198A (en) * | 2018-06-08 | 2018-11-13 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
| CN108875593A (en) * | 2018-05-28 | 2018-11-23 | 上海交通大学 | Visible images weather recognition methods based on convolutional neural networks |
| CN108921013A (en) * | 2018-05-16 | 2018-11-30 | 浙江零跑科技有限公司 | A kind of visual scene identifying system and method based on deep neural network |
| CN109447018A (en) * | 2018-11-08 | 2019-03-08 | 天津理工大学 | A kind of road environment visual perception method based on improvement Faster R-CNN |
| CN109525901A (en) * | 2018-11-27 | 2019-03-26 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and computer-readable medium |
| DE102017217072A1 (en) * | 2017-09-26 | 2019-03-28 | Volkswagen Aktiengesellschaft | A method for detecting a weather condition in an environment of a motor vehicle and control device and motor vehicle |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105628034B (en) * | 2016-02-04 | 2019-04-23 | 合肥杰发科技有限公司 | Navigation map update method and equipment |
| WO2018225446A1 (en) * | 2017-06-09 | 2018-12-13 | 株式会社デンソー | Map points-of-change detection device |
| JP7062892B2 (en) * | 2017-07-13 | 2022-05-09 | トヨタ自動車株式会社 | Dynamic map updater, dynamic map update method, dynamic map update program |
| CN108196285B (en) * | 2017-11-30 | 2021-12-17 | 中山大学 | Accurate positioning system based on multi-sensor fusion |
| CN108282635B (en) * | 2018-02-11 | 2020-11-10 | 中国联合网络通信集团有限公司 | Panoramic image generation method and system and Internet of vehicles big data service platform |
-
2019
- 2019-05-06 CN CN201910371108.4A patent/CN110186471A/en active Pending
- 2019-08-29 WO PCT/CN2019/103329 patent/WO2020224117A1/en active Application Filing
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008257403A (en) * | 2007-04-03 | 2008-10-23 | Denso Corp | Driving support device for vehicle |
| JP2010257253A (en) * | 2009-04-24 | 2010-11-11 | Denso Corp | Display device for vehicle |
| CN104834912A (en) * | 2015-05-14 | 2015-08-12 | 北京邮电大学 | Weather identification method and apparatus based on image information detection |
| US20160334546A1 (en) * | 2015-05-14 | 2016-11-17 | Beijing University Of Posts And Telecommunications | Weather recognition method and device based on image information detection |
| CN105575119A (en) * | 2015-12-29 | 2016-05-11 | 大连楼兰科技股份有限公司 | Road condition climate deep learning and recognition method and apparatus |
| CN106709511A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Urban rail transit panoramic monitoring video fault detection method based on depth learning |
| CN106611162A (en) * | 2016-12-20 | 2017-05-03 | 西安电子科技大学 | Method for real-time detection of road vehicle based on deep learning SSD frame |
| EP3361412A1 (en) * | 2017-02-10 | 2018-08-15 | Fujitsu Limited | Black ice detection system, program, and method |
| CN107238874A (en) * | 2017-05-25 | 2017-10-10 | 苏州工业职业技术学院 | Based on when scape photo real-time weather detection method and system |
| DE102017217072A1 (en) * | 2017-09-26 | 2019-03-28 | Volkswagen Aktiengesellschaft | A method for detecting a weather condition in an environment of a motor vehicle and control device and motor vehicle |
| CN108513674A (en) * | 2018-03-26 | 2018-09-07 | 深圳市锐明技术股份有限公司 | A kind of detection alarm method, storage medium and the server of Chinese herbaceous peony accumulated snow and icing |
| CN108701396A (en) * | 2018-03-26 | 2018-10-23 | 深圳市锐明技术股份有限公司 | A kind of detection alarm method, storage medium and the server of Chinese herbaceous peony accumulated snow and icing |
| CN108921013A (en) * | 2018-05-16 | 2018-11-30 | 浙江零跑科技有限公司 | A kind of visual scene identifying system and method based on deep neural network |
| CN108875593A (en) * | 2018-05-28 | 2018-11-23 | 上海交通大学 | Visible images weather recognition methods based on convolutional neural networks |
| CN108805198A (en) * | 2018-06-08 | 2018-11-13 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
| CN109447018A (en) * | 2018-11-08 | 2019-03-08 | 天津理工大学 | A kind of road environment visual perception method based on improvement Faster R-CNN |
| CN109525901A (en) * | 2018-11-27 | 2019-03-26 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and computer-readable medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110807549A (en) * | 2019-10-29 | 2020-02-18 | 国网电力科学研究院武汉南瑞有限责任公司 | Generation method, generation device, generation system and electronic equipment of meteorological prediction model |
| CN111178407A (en) * | 2019-12-19 | 2020-05-19 | 中国平安人寿保险股份有限公司 | Road condition data screening method and device, computer equipment and storage medium |
| CN111178407B (en) * | 2019-12-19 | 2024-09-06 | 中国平安人寿保险股份有限公司 | Road condition data screening method, device, computer equipment and storage medium |
| CN113887286A (en) * | 2021-08-31 | 2022-01-04 | 际络科技(上海)有限公司 | Driver behavior monitoring method based on online video understanding network |
| CN115148040A (en) * | 2022-06-28 | 2022-10-04 | 东莞中科云计算研究院 | Unmanned vehicle control method and system for closed road environment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020224117A1 (en) | 2020-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110186471A (en) | Air navigation aid, device, computer equipment and storage medium based on history video | |
| EP3951713A1 (en) | Method and apparatus for training image semantic segmentation network, device, and storage medium | |
| JP6935946B2 (en) | Post-processing methods and devices that detect lanes for planning the driving route of autonomous vehicles using segmentation score maps and clustering maps. | |
| CN107247718B (en) | Map data updating method and device, navigation system and server | |
| Rettie et al. | Hierarchical habitat selection by woodland caribou: its relationship to limiting factors | |
| DE102020106176A1 (en) | LOCALIZATION SYSTEMS AND PROCEDURES | |
| KR102373430B1 (en) | Method and device for providing personalized and calibrated adaptive deep learning model for the user of an autonomous vehicle | |
| CN110471058A (en) | The system and method detected automatically for trailer attribute | |
| CN112925348B (en) | Unmanned aerial vehicle control method, unmanned aerial vehicle control device, electronic equipment and medium | |
| US20060176213A1 (en) | Method and apparatus for enhancing a digital elevation model (DEM) for topographical modeling | |
| DE102016118647A1 (en) | Augmented reality communication system and augmented reality interaction device | |
| CN107703931A (en) | Method and apparatus for controlling automatic driving vehicle | |
| CN110251942A (en) | Control the method and device of virtual role in scene of game | |
| DE102021111096A1 (en) | VISUAL BEHAVIOR GUIDED OBJECT DETECTION | |
| US9524564B2 (en) | Method for viewing a multi-spectral image | |
| US11816543B2 (en) | System and method for using knowledge gathered by a vehicle | |
| CN107492144A (en) | Shadow processing method and electronic equipment | |
| CN113850828A (en) | Image processing method, image processing apparatus, electronic device, storage medium, and program product | |
| CN113095194A (en) | Image classification method and device, storage medium and electronic equipment | |
| DE102021103189A1 (en) | Systems and methods for training networks for real super resolution with unknown degradations | |
| CN113313099B (en) | Real-time acquisition method, system and storage medium based on remote sensing image map | |
| Laha et al. | Haar Wavelet-Based Attention Network for Image Dehazing | |
| CN106651776A (en) | Image repair method and image repair device | |
| DE102020115892A1 (en) | PREDICTION OF A CONTACT FOR THE NEXT CALL | |
| CN118052956B (en) | Novel distributed system scene modeling method, system, equipment and 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190830 |