CN109664820A - Driving reminding method, device, equipment and storage medium based on automobile data recorder - Google Patents
Driving reminding method, device, equipment and storage medium based on automobile data recorder Download PDFInfo
- Publication number
- CN109664820A CN109664820A CN201811117981.2A CN201811117981A CN109664820A CN 109664820 A CN109664820 A CN 109664820A CN 201811117981 A CN201811117981 A CN 201811117981A CN 109664820 A CN109664820 A CN 109664820A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- image
- pedestrian
- target
- data recorder
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
- B60Q9/008—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling for anti-collision purposes
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of driving reminding method based on automobile data recorder, comprising: the video information based on automobile data recorder acquisition vehicle surrounding enviroment extracts the target analysis region containing default subject matter from each frame video image of the video information;Using each target analysis region of default pedestrian's classifier and/or preset vehicle detection of classifier, the pedestrian image and/or vehicle image in each target analysis region are obtained;According to each pedestrian image and/or each vehicle image, the relative movement information of each target pedestrian and/or each target vehicle and current vehicle is determined;According to the relative movement information, generates and drive prompt information.The invention also discloses a kind of driving suggestion device, equipment and storage medium based on automobile data recorder.Image procossing is combined with data analysis in the present invention, determines the relative movement information of vehicle and subject matter, to realize that driving conditions are intelligent using automobile data recorder.
Description
Technical field
The present invention relates to intelligent automobile auxiliary driving technology fields more particularly to a kind of driving based on automobile data recorder to mention
Show method, apparatus, equipment and storage medium.
Background technique
Since the quantity of vehicle constantly increases, intelligent transportation is pursued by more and more people, and people more pay attention to
The level of security of traffic, to avoid traffic accident.
Existing vehicle configuration is higher, and people drive a vehicle for convenience, and car owner installs automobile data recorder in the car usually with side
Just vehicle driving etc. operates;Existing automobile data recorder is only capable of the video information of surrounding enviroment during record is driven, that is,
Existing automobile data recorder focuses on the shooting of vehicle-surroundings environment, can not play in the driving process of vehicle apparent
How effect utilizes automobile data recorder, realizes the intelligence of driving conditions, become a technical problem to be solved urgently.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The driving reminding method that the main purpose of the present invention is to provide a kind of based on automobile data recorder, device, equipment and
Storage medium, it is intended to realize that driving conditions are intelligent by automobile data recorder.
To achieve the above object, the present invention is based on the driving reminding methods of automobile data recorder, described to be based on automobile data recorder
Driving reminding method the following steps are included:
Based on the video information of automobile data recorder acquisition vehicle surrounding enviroment, from each frame video image of the video information
It is middle to extract the target analysis region containing default subject matter;
Using each target analysis region of default pedestrian's classifier and/or preset vehicle detection of classifier, each institute is obtained
State the pedestrian image and/or vehicle image in target analysis region;
According to each pedestrian image and/or each vehicle image, determine each target pedestrian and/or each target vehicle with
The relative movement information of current vehicle;
Wherein, the target pedestrian refers to the pedestrian in each pedestrian image, and the target vehicle refers to each vehicle
Vehicle in image, the current vehicle refer to the vehicle for installing the automobile data recorder;
According to the relative movement information, generates and drive prompt information.
Optionally, the video information based on automobile data recorder acquisition vehicle surrounding enviroment, from the video information
Before the step of extracting the target analysis region containing default subject matter in each frame video image, comprising:
The light intensity of external environment locating for the automobile data recorder is monitored and obtained, and by the light intensity and is preset
Light intensity is compared;
If the light intensity is less than the default light intensity, the automobile data recorder is adjusted to infrared mode,
To acquire the video information of surrounding enviroment under the infrared mode of the automobile data recorder;
If the light intensity is more than or equal to the default light intensity, the automobile data recorder is adjusted to can
Light-exposed mode, to acquire the video information of surrounding enviroment under the automobile data recorder visible mode.
Optionally, the video information based on automobile data recorder acquisition vehicle surrounding enviroment, from the video information
The step of target analysis region containing default subject matter is extracted in each frame video image, comprising:
Based on the video information of automobile data recorder acquisition vehicle surrounding enviroment, by frame video image each in the video information
It is filtered, the filtering image that obtains that treated;
By filtering image described in preset threshold algorithm process, default subject matter is obtained, will include the default subject matter
Region as target analysis region, wherein the default subject matter refers to pedestrian and/or vehicle.
Optionally, described to utilize default pedestrian's classifier and/or each target analysis area of preset vehicle detection of classifier
Domain, the step of obtaining the pedestrian image and/or vehicle image in each target analysis region, comprising:
The target analysis region is handled by default algorithm of histogram equalization, obtains pedestrian area image and/or vehicle
Area image;
By pedestrian area image described in default pedestrian's detection of classifier, obtain in default pedestrian's classifier with it is described
The corresponding pedestrian sample of pedestrian area image determines the pedestrian image in the pedestrian area image according to the pedestrian sample,
And/or;
By vehicle region image described in preset vehicle detection of classifier, obtain in the preset vehicle classifier with it is described
The corresponding vehicle sample of vehicle region image determines the vehicle image in the vehicle region image according to the vehicle sample.
Optionally, described according to each pedestrian image and/or each vehicle image, determine each target pedestrian and/or
The step of relative movement information of each target vehicle and current vehicle, comprising:
Obtain the image size data and actual size data of target pedestrian and/or each institute in each pedestrian image
State the image size data of target vehicle and actual size data in vehicle image;
The current focus for obtaining the drive recorder camera, according to preset formula: each mesh is calculated in f=h*D/H
Pedestrian and/or each target vehicle are marked at a distance from current vehicle, wherein
The f is the current focus of the drive recorder camera;
The h is the image size data of the target pedestrian and/or the target vehicle;
The H is the actual size data of the target pedestrian and/or the target vehicle;
The D is the distance of the target pedestrian and/or the target vehicle to the current vehicle;
The acquisition time of each pedestrian image and/or each vehicle image is obtained, and is arranged by the acquisition time
Each distance;
Each distance is analyzed, the relative movement information of each target pedestrian and/or each target vehicle and current vehicle is obtained.
Optionally, described according to the relative movement information, generate the step of driving prompt information, comprising:
The relative movement information is input in default route simulation model, by the default route simulation model into
Row digital simulation obtains the collision probability of the target pedestrian and/or the target vehicle and the current vehicle;
When the collision probability is higher than preset threshold, generates and drive prompt information.
Optionally, described according to the relative movement information, after generating the step of driving prompt information, comprising:
Obtain the vehicle position information and vehicle movement information in automobile data recorder, wherein the vehicle movement packet
Include vehicle speed, vehicle acceleration, vehicle angular speed and/or vehicle heading;
Based on the vehicle speed, the vehicle acceleration, the vehicle angular speed and/or the vehicle heading,
Estimate vehicle running route;
According to the vehicle position information and the vehicle running route, generates vehicle and run navigation information.
In addition, to achieve the above object, the present invention also provides a kind of driving suggestion device based on automobile data recorder is described
Driving suggestion device based on automobile data recorder includes:
Video acquisition module, for the video information based on automobile data recorder acquisition vehicle surrounding enviroment, from the video
The target analysis region containing default subject matter is extracted in each frame video image of information;
Image analysis module, for utilizing default pedestrian's classifier and/or each target of preset vehicle detection of classifier
Analyzed area obtains the pedestrian image and/or vehicle image in each target analysis region;
State determining module, for determining each target pedestrian according to each pedestrian image and/or each vehicle image
And/or the relative movement information of each target vehicle and current vehicle, wherein the target pedestrian refers in each pedestrian image
Pedestrian, the target vehicle refers to the vehicle in each vehicle image, and the current vehicle refers to that the installation driving is remembered
Record the vehicle of instrument;
Cue module is driven, for generating and driving prompt information according to the relative movement information.
In addition, to achieve the above object, the present invention also provides a kind of, and the driving based on automobile data recorder prompts equipment;
The driving prompt equipment based on automobile data recorder includes: camera, memory, processor and is stored in described
On memory and the computer program that can run on the processor, in which:
The camera, for acquiring the video information of vehicle surrounding enviroment;
Realize that the driving based on automobile data recorder as described above mentions when the computer program is executed by the processor
The step of showing method.
In addition, to achieve the above object, the present invention also provides computer storage mediums;
Computer program, the realization when computer program is executed by processor are stored in the computer storage medium
Such as the step of the above-mentioned driving reminding method based on automobile data recorder.
The embodiment of the present invention proposes driving reminding method, device, equipment and storage medium based on automobile data recorder, leads to
The video information for crossing automobile data recorder acquisition vehicle surrounding enviroment, extracts from each frame video image of the video information and contains
The target analysis region of default subject matter;Utilize default pedestrian's classifier and/or each target of preset vehicle detection of classifier
Analyzed area obtains the pedestrian image and/or vehicle image in each target analysis region;According to each pedestrian image
And/or each vehicle image, determine the relative movement information of each target pedestrian and/or each target vehicle and current vehicle;Root
According to the relative movement information, generates and drive prompt information.Middle rolling car recorder of the present invention shoots video information, to video information
And handled, to obtain the pedestrian image and/or vehicle image in each frame video image, and according to pedestrian image and/or vehicle
Image, obtains the relative movement information of target pedestrian and/or target vehicle and current vehicle, with the traveling to current vehicle into
Row prompt realizes that driving conditions are intelligent, improves the driving experience of car owner.
Detailed description of the invention
Fig. 1 is the apparatus structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to;
Fig. 2 is the flow diagram of the driving reminding method first embodiment the present invention is based on automobile data recorder;
Fig. 3 is the functional block diagram of driving one embodiment of suggestion device the present invention is based on automobile data recorder.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in Figure 1, the terminal that Fig. 1 is the hardware running environment that the embodiment of the present invention is related to (is called based on driving
The driving of recorder prompts equipment, wherein the driving prompt equipment based on automobile data recorder can be by individually based on driving
The driving suggestion device of recorder is constituted, and is also possible to be combined by other devices with the driving suggestion device based on automobile data recorder
Formed) structural schematic diagram.
The terminal of that embodiment of the invention can be also possible to mobile terminal, wherein fixed terminal such as " Internet of Things with fixed terminal
Equipment ", the intelligent air condition with network savvy, intelligent electric lamp, intelligent power etc.;Mobile terminal, such as with the intelligence of network savvy
Speaker, autonomous driving vehicle, PC (personal computer) personal computer, smart phone, tablet computer, e-book are read
Read the terminal devices having a display function such as device, portable computer.
As shown in Figure 1, the terminal may include: processor 1001, such as central processing unit Central Processing
Unit, CPU), network interface 1004, user interface 1003, memory 1005, communication bus 1002.Wherein, communication bus 1002
For realizing the connection communication between these components.User interface 1003 may include display screen (Display), input unit ratio
Such as keyboard (Keyboard), optional user interface 1003 can also include standard wireline interface and wireless interface.Network interface
1004 may include optionally that (such as Wireless Fidelity WIreless-FIdelity, WIFI connect standard wireline interface and wireless interface
Mouthful).Memory 1005 can be high speed RAM memory, be also possible to stable memory (non-volatile memory),
Such as magnetic disk storage.Memory 1005 optionally can also be the storage device independently of aforementioned processor 1001.
Optionally, terminal can also include camera, RF (Radio Frequency, radio frequency) circuit, sensor, audio
Circuit, WiFi module;Input unit, than display screen, touch screen;Network interface can in blanking wireless interface in addition to WiFi, bluetooth,
Probe, 3G/4G/5G (digital representation of front be cellular mobile communication networks algebra.Exactly indicate be which generation net
Network.English alphabet G indicates generation) internet base station equipment etc..Wherein, sensor such as optical sensor, motion-sensing
Device and other sensors.Specifically, optical sensor may include ambient light sensor and proximity sensor;Certainly, mobile terminal
It can also configure the other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, details are not described herein.
It will be understood by those skilled in the art that the restriction of the not structure paired terminal of terminal structure shown in Fig. 1, can wrap
It includes than illustrating more or fewer components, perhaps combines certain components or different component layouts.
As shown in Figure 1, the computer software product, which is stored in a storage medium, (storage medium: is called computer storage
Medium, computer media, readable medium, readable storage medium storing program for executing, computer readable storage medium are directly medium etc., such as
RAM, magnetic disk, CD) in, including some instructions are used so that a terminal device (can be mobile phone, computer, server, sky
Adjust device or the network equipment etc.) method described in each embodiment of the present invention is executed, as a kind of depositing for computer storage medium
It may include operating system, network communication module, Subscriber Interface Module SIM and computer program in reservoir 1005.
In terminal shown in Fig. 1, network interface 1004 is mainly used for connecting background server, carries out with background server
Data communication;User interface 1003 is mainly used for connecting client (user terminal), carries out data communication with client;And processor
1001 can be used for calling the computer program stored in memory 1005, and execute that following embodiment of the present invention provides based on
The step of automobile data recorder driven in reminding method.
It is described based on row in the first embodiment for driving reminding method the present invention is based on automobile data recorder referring to Fig. 2
The driving reminding method of vehicle recorder includes:
Step S10, based on the video information of automobile data recorder acquisition vehicle surrounding enviroment, from each frame of the video information
The target analysis region containing default subject matter is extracted in video image.
(the mobile detection function when automobile data recorder is in open state or automobile data recorder starting mobile detection function
Refer to automobile data recorder detect object automobile data recorder Digital Video Recorder (also known as DVR or
Hard disk video recorder) front it is mobile when, DVR can start video recording automatically, when the body stops moving, video recording is automatically stopped, into detecing
Survey standby mode), automobile data recorder can be foreground camera or panoramic camera, the camera of the video camera by video camera
It can be CCD (ChargecoupledDevice, charge coupled cell) camera or CMOS (Complementary
MetalOxideSemiconductor, complementary metal oxide semiconductor) camera, acquisition apart from vehicle camera it is default away from
From interior video information, pre-determined distance is arranged according to concrete scene, for example, the front video apart from 60 meters of vehicle camera is believed
Breath.
Further, after collecting video information, collected video information is input to the processor of automobile data recorder
Either and in the server of automobile data recorder communication connection, video is believed by the processor or server of automobile data recorder
Each video image in breath carries out proper treatment, for example, pedestrian in each frame video image of acquisition and vehicle may occur
The location information of collision estimated, pedestrian can not occurs to part and pedestrian is not at the image of danger zone and is not counted in inspection
It surveys, or the road scene on both sides of the road of removal image left-right parts pixel, to obtain the target analysis area comprising default subject matter
Domain.Wherein, default subject matter refers to the subject matter for presetting and being analyzed, for example, default subject matter can be set to
Pedestrian and/or vehicle, the detection method in the target analysis region include method for testing motion, based on shape detecting method with
And region threshold method.
For example, the method for testing motion passes through the motion information detected in each frame video image, in conjunction with optical flow analysis
Motion detection carries out the segmentation in target analysis region, that is, is based on same color pixel zonule coherent motion, each pixel
It is given the possibility probability for belonging to certain given zonule, and the movement of each zonule is by according to the general of movement
Rate model is classified to prepare the pedestrian of next stage identification, by the region for uniquely having consistency to move, so
It is voted afterwards based on interframe analysis a straight line path, a regular track is only detected in a framing, is just recognized
To find a pedestrian and/or vehicle, and target analysis region is obtained with this.Further, it can also be examined by a zero crossing
Method of determining and calculating, the space-time Gaussian convolution for the history pixel value being utilized in N frame, then by being filtered using the second order Kalman of extension
The processing of wave device is blocked, to obtain the target analysis region comprising default subject matter.
Step S20, using each target analysis region of default pedestrian's classifier and/or preset vehicle detection of classifier,
Obtain the pedestrian image and/or vehicle image in each target analysis region.
In the present embodiment, using target analysis region described in preset pedestrian's detection of classifier, the target point is detected
Analysis region preferably includes: 1) utilizing target analysis region described in pedestrian's classifier on-line checking;2) it is sieved by multiframe method of calibration
Select the testing result of pedestrian's classifier.The testing result for screening pedestrian's classifier by multiframe method of calibration is to retain and connect
The same target that occurs in continuous multiple image and pedestrian's as a result, removal continuous multiple frames figure is continuously detected as by pedestrian's classifier
The same target that occurs and the result for being continuously judged as non-pedestrian by pedestrian's classifier as in.Finally, the target point is obtained
Analyse the pedestrian image in region.Pedestrian's classifier preferably includes Adaboost iterative algorithm classifier, SVM
(SupportVectorMachine, support vector machines) classifier and/or;
The target analysis region is detected using preset vehicle classification device, the target analysis region is detected and preferably wraps
It includes: 1) utilizing target analysis region described in the vehicle classification device on-line checking;2) vehicle point is screened by multiframe method of calibration
The testing result of class device.The testing result for screening vehicle classification device by multiframe method of calibration is to retain continuous multiple frames figure
As in the same target that occurs and by vehicle classification device be continuously detected as vehicle as a result, going out in removal continuous multiple frames image
Existing same target and the result for being continuously judged as non-vehicle by vehicle classification device.Finally, the vehicle in target analysis region is obtained
Image.
The present embodiment is in vehicle travel process, then by default pedestrian's classifier and/or preset vehicle classifier to institute
It states target analysis region to be detected, obtains the pedestrian image and/or vehicle image in the target analysis region, rather than only
It can be realized in vehicle travel process, by the artificially pedestrian of determining vehicle front and/or vehicle automatically to the pedestrian on road
And/or vehicle is detected.
Step S30 determines each target pedestrian and/or each mesh according to each pedestrian image and/or each vehicle image
Mark the relative movement information of vehicle and current vehicle.
Multi-frame video image in the combination video information of automobile data recorder, according to each pedestrian in each frame video image
Image and/or each vehicle image are analyzed, and automobile data recorder determines target pedestrian and current vehicle in pedestrian image
Relative movement information and/or vehicle image in target vehicle and current vehicle relative movement information.For example, pedestrian image
In target pedestrian A gradually decreased at a distance from current vehicle, it is determined that the opposite fortune of target pedestrian A and current vehicle being in
Behavior is relatively close, and the speed of specific relative motion is determined according to concrete scene.
The present embodiment middle rolling car recorder according to pedestrian image and/or each vehicle image, determine each target pedestrian and/
Or the relative movement information of each target vehicle and current vehicle, it can realize in different ways:
Implementation one: the image size data and actual size number of target pedestrian in each pedestrian image are obtained
According to and/or each vehicle image in target vehicle image size data and actual size data;Obtain the driving note
The current focus of instrument camera is recorded, according to preset formula: each target pedestrian and/or each target vehicle is calculated in f=h*D/H
At a distance from current vehicle, wherein the f is the current focus of the drive recorder camera;The h is the target line
The image size data of people and/or the target vehicle;The H is the reality of the target pedestrian and/or the target vehicle
Dimension data;The D is the distance of the target pedestrian and/or the target vehicle to the current vehicle;It obtains each described
The acquisition time of pedestrian image and/or each vehicle image, and each distance is arranged by the acquisition time;Analyze each institute
Distance is stated, obtains the relative movement information of each target pedestrian and/or each target vehicle and current vehicle, that is, in the present embodiment
Know f, h and H, so that it may find out D, correspondence obtains target pedestrian and/or target vehicle at a distance from current vehicle, automobile data recorder
According in each time video image target pedestrian and/or target vehicle at a distance from current vehicle, obtain each target pedestrian
And/or the relative movement information of each target vehicle and current vehicle.
For example, automobile data recorder obtains 10 frame of video image that time interval in video information is 1s, 10 frame video images
In all include target pedestrian A, 30 meters of pedestrian A and current vehicle interval are calculated in first video image;Second
It opens in video image and 29 meters of pedestrian A and current vehicle interval is calculated, and so on, it is respectively as follows: 28 meters, 27 meters, 26 meters, 25
Rice, 24 meters, 23 meters, 22 meters and 21 meters, then automobile data recorder determines target pedestrian A with 60 meters of speed per minute as current vehicle
Close, as target pedestrian A and current vehicle relative movement information.
Implementation two: the infrared distance sensor that automobile data recorder utilizes launches a branch of infrared light, is being irradiated to object
The process that a reflection is formed after body is reflected into sensor and is followed by the collection of letters number, then according to the number of transmitting and received time difference
According to obtaining that pedestrian image corresponds to target pedestrian and/or each vehicle image corresponds to target vehicle at a distance from current vehicle, row
Vehicle recorder according in each time video image target pedestrian and/or target vehicle at a distance from current vehicle, obtain each
The relative movement information of target pedestrian and/or each target vehicle and current vehicle.
It should be added that may include multiple pedestrians and/or vehicle in frame video image, in the present embodiment with
Be illustrated for one pedestrian and/or vehicle, that is, automobile data recorder by the same target occurred in multiple image and
By pedestrian's classifier be continuously detected as pedestrian's as a result, determine the pedestrian at a distance from the current vehicle of case automobile data recorder.
In the present embodiment in conjunction with the motion information analysis video information in each pedestrian image correspond to target pedestrian with/
Or each vehicle image corresponds to the status information of target vehicle, realizes and carries out the judgement of position identification state based on image.
Step S40 is generated according to the relative movement information and is driven prompt information.
Automobile data recorder is according to the relative movement information, that is, relative movement information is input to default by automobile data recorder
In route simulation model, wherein default route simulation model refers to the Driving Scene simulation model that training obtains in advance, passes through institute
It states the simulation of default route simulation model and carries out digital simulation, obtain the target pedestrian and/or the target vehicle is worked as with described
The collision probability of vehicle in front;When the collision probability is higher than preset threshold, generates and drive prompt information.Wherein, the present embodiment
In driving prompt information can be speech prompt information, can also be text importing prompt.
Video information in the present embodiment based on automobile data recorder acquisition, to video information and is handled, to obtain
Pedestrian image and/or vehicle image in each video image, and according to pedestrian image and/or vehicle image, obtain target line
The relative movement information of people and/or target vehicle and current vehicle is prompted with the traveling to current vehicle, and realization was driven a vehicle
Journey is intelligent, improves the driving experience of car owner.
Further, on the basis of first embodiment of the invention, the driving the present invention is based on automobile data recorder is proposed
The present embodiment of reminding method, the present embodiment are the refinements of first embodiment step S10.The driving based on automobile data recorder
Reminding method includes:
Step S11, based on the video information of automobile data recorder acquisition vehicle surrounding enviroment, by frame each in the video information
Video image is filtered, the filtering image that obtains that treated;
Based on the video information of automobile data recorder acquisition vehicle surrounding enviroment, by frame video image each in the video information
It is filtered, the filtering image that obtains that treated;Collected video image can be filtered in the present embodiment
Processing, with to carrying out denoising in the video image.
Step S12 is obtained default subject matter, will be included described pre- by filtering image described in preset threshold algorithm process
If the region of subject matter is as target analysis region, wherein the default subject matter refers to pedestrian and/or vehicle.
The image that filtering obtains is handled by preset threshold algorithm, wherein preset threshold algorithm refers in advance
The dynamic threshold segmentation algorithm of setting obtains the background and default subject matter in video image, will include the default subject matter
Region as target analysis region, specifically, for example, establishing image grey level histogram, (L indicates that gray level, p mark occur general
Rate)And pi=ni/ N, further, according toWith
(wherein, t is expressed as preset threshold value, and A is expressed as background (gray level 0-N), PAIt is expressed as the probability of background appearance, PBIt indicates
To preset the probability that subject matter occurs) probability that background and default subject matter occur is calculated, and will include the default subject matter
Region as target analysis region.
In the present embodiment, after collecting video information, the noise of the method removal video image of filtering processing is first passed through
It is interfered with noise, then to treated, image carries out region threshold, is worth thresholded image, the region threshold method
It is preferred that are as follows: it is determined according to the statistical nature of the grey scale pixel value in pixel level each in video image field and divides threshold value,
Binary conversion treatment is carried out to input picture and obtains bianry image;The noise in bianry image is filtered out by morphological erosion operation again
Pixel, and Weak link region is filled up with morphological dilations operation, finally extract all connected regions in the bianry image
As target analysis region.
Further, on the basis of the above embodiment of the present invention, the driving the present invention is based on automobile data recorder is proposed
The present embodiment of reminding method, the present embodiment are the refinements of first embodiment step S20.The driving based on automobile data recorder
Reminding method includes:
Step S21 handles the target analysis region by default algorithm of histogram equalization, obtains pedestrian area image
And/or vehicle region image.
In the present embodiment, the side after collecting the target analysis region, preferably by presetting histogram equalization
Method enhances the contrast in the target analysis region and background area, and according to the bright of the target analysis region and background area
Difference is spent, the boundary profile in the target analysis region and background area is determined, finally, according to the side in the target analysis region
Boundary's profile obtains pedestrian area image and/or vehicle region image, it is to be understood that can also be carried out by edge detection algorithm
Edge processing or dynamic bi-threshold method carry out binary conversion treatment, enhance brightness between the target analysis region and background area
Difference determines boundary profile according to the luminance difference, and according to the boundary profile obtain the pedestrian area image and/or
Vehicle region image.
Step S22 obtains default pedestrian's classifier by pedestrian area image described in default pedestrian's detection of classifier
In pedestrian sample corresponding with the pedestrian area image, the row in the pedestrian area image is determined according to the pedestrian sample
People's image,
And/or it by vehicle region image described in preset vehicle detection of classifier, obtains in the preset vehicle classifier
Vehicle sample corresponding with the vehicle region image determines the vehicle in the vehicle region image according to the vehicle sample
Image.
In the present embodiment, pass through pedestrian area image described in preset pedestrian's detection of classifier, detection mode are as follows: by institute
The each pedestrian sample stated in pedestrian's classifier is compared with the pedestrian area image, and is detecting pedestrian's classification
When pedestrian sample in device with the pedestrian area images match, using the pedestrian sample detected as testing result, root
The pedestrian image in the pedestrian area image is determined according to the testing result.And/or institute is detected by preset vehicle classification device
State vehicle region image, the detection mode are as follows: by the vehicle classification device each vehicle sample and the vehicle region
Image is compared, and when vehicle sample in detecting the vehicle classification device with the vehicle region images match, will
The vehicle sample detected determines the vehicle in the vehicle region image as testing result, according to the testing result
Image.
It should be added that: needed the step of before in the present embodiment one pedestrian's classifier of training in advance and/
Or vehicle classification device, to train pedestrian's classifier to be illustrated in the present embodiment, that is, first obtain the pedestrian image as pedestrian
Training sample set is added in sample, the pedestrian sample that then will acquire, finally, utilizing the training sample set training row
People's classifier obtains updated pedestrian's classifier.It realizes in pedestrian's detection process, the pedestrian image obtained in real time can be added
Enter training sample set, and according to training sample set training pedestrian's classifier, such as Adaboost classifier or SVM classifier, finally,
So that the pedestrian sample that training sample is concentrated is more, the accuracy of pedestrian detection is improved.Namely in order in vehicle row
During sailing, online updating is carried out to improve the adaptation of algorithm to pedestrian's classifier by constantly extracting various pedestrian samples
Property.
Originally implementing in example using default pedestrian's classifier and/or preset vehicle classifier is to realize in video image
Pedestrian and vehicle accurately identify.
Further, on the basis of the above embodiment of the present invention, the driving the present invention is based on automobile data recorder is proposed
The present embodiment of reminding method, the present embodiment are the refinements of first embodiment step S30.The driving based on automobile data recorder
Reminding method includes:
Step S31 obtains the image size data and actual size data of target pedestrian in each pedestrian image,
And/or in each vehicle image target vehicle image size data and actual size data.
Automobile data recorder obtains the image size data and actual size data of target pedestrian in each pedestrian image,
And/or in each vehicle image target vehicle image size data and actual size data;Automobile data recorder will acquire
The image size data and actual size data of target pedestrian A, is input in preset formula, each target pedestrian is calculated
And/or each target vehicle is at a distance from current vehicle.
Step S32 obtains the current focus of the drive recorder camera, according to preset formula: f=h*D/H, calculates
Each target pedestrian and/or each target vehicle are obtained at a distance from current vehicle, wherein
The f is the current focus of the drive recorder camera;
The h is the image size data of the target pedestrian and/or the target vehicle;
The H is the actual size data of the target pedestrian and/or the target vehicle;
The D is the distance of the target pedestrian and/or the target vehicle to the current vehicle;
That is, obtaining the current focus 200 of the drive recorder camera in the present embodiment, automobile data recorder obtains video
Target person A height 0.85cm in image sets pedestrian's actual size data 1.7m in automobile data recorder, that is, automobile data recorder
Obtain the distance 8m of current vehicle described in target pedestrian A.Same method, automobile data recorder are determined at interval of 0.1s video image
Middle target pedestrian A is at a distance from the current vehicle, to determine relative movement information by distance change.
Step S33 obtains the acquisition time of each pedestrian image and/or each vehicle image, and presses the acquisition
Each distance of Time alignment;
Automobile data recorder obtains the acquisition time of each pedestrian image and/or each vehicle image, and adopts by described
Collect each distance of Time alignment, for example, 1s target pedestrian A is 16m with current vehicle distance 18m, the 2s distance;3s away from
From for 14m, 4s distance is 12m;5s distance is 14m, and 6s distance is 18m etc..
Step S34 analyzes each distance, obtains the opposite of each target pedestrian and/or each target vehicle and current vehicle
Motion information.
By obtaining target in video image pedestrian and/or each target carriage to each video image analysis in the present embodiment
Distance change with current vehicle, and further, obtain the phase of target pedestrian and/or each target vehicle and current vehicle
To motion information, realizes and distance analysis is carried out based on automobile data recorder, improve analysis precision.
Further, in the second embodiment for driving reminding method the present invention is based on automobile data recorder, with the present invention
The difference of first embodiment is that the present embodiment middle rolling car recorder is provided with different acquisition modes, described based on driving note
Record instrument driving reminding method include:
Step S50 monitors and obtains the light intensity of external environment locating for the automobile data recorder, and the light is strong
Degree is compared with default light intensity.
Light intensity monitoring device is provided in automobile data recorder, for the light to external environment locating for automobile data recorder
Intensity is monitored, and obtains the light intensity of monitoring, the light intensity that automobile data recorder will acquire and default light intensity into
Row compares, to determine the screening-mode in automobile data recorder according to the comparison result of light intensity and default light intensity,
In, default light intensity refers to pre-set intensity of illumination, can be arranged as the case may be.
Step S60 adjusts the automobile data recorder to red if the light intensity is less than the default light intensity
External schema, to acquire the video information of surrounding enviroment under the infrared mode of the automobile data recorder.
If the light intensity is less than the default light intensity, that is, external environment locating for automobile data recorder is darker, then will
The automobile data recorder is adjusted to infrared mode, to acquire the video of surrounding enviroment under the infrared mode of the automobile data recorder
Information.
Step S70, if the light intensity is more than or equal to the default light intensity, by the automobile data recorder
It adjusts to visible mode, to acquire the video information of surrounding enviroment under the automobile data recorder visible mode.
If the light intensity is more than or equal to the default light intensity, that is, external environment locating for automobile data recorder
Normally, then the automobile data recorder is adjusted to visible mode, to acquire week under the automobile data recorder visible mode
The video information of surrounding environment.
In the present embodiment according to the comparison result of light intensity and default light intensity, the bat in automobile data recorder is determined
Mode is taken the photograph, more accurate pedestrian image and/or vehicle image are got, to carry out more accurately prompt.
Further, on the basis of the above embodiment of the present invention, the driving the present invention is based on automobile data recorder is proposed
The 3rd embodiment of reminding method generates navigation information in the present embodiment, so that, tool more intelligent based on automobile data recorder information
Body includes:
Step S80 obtains vehicle position information and vehicle movement information in automobile data recorder, wherein the vehicle fortune
Dynamic information includes vehicle speed, vehicle acceleration, vehicle angular speed and/or vehicle heading;
Vehicle position information and vehicle movement information, vehicle position information in automobile data recorder acquisition automobile data recorder can
With the positioning confidence of satellite positioning, it can also be and positioned by mobile phone or other network positions, the vehicle movement packet
Include vehicle speed, vehicle acceleration, vehicle angular speed and/or vehicle heading.
Step S90 is based on the vehicle speed, the vehicle acceleration, the vehicle angular speed and/or the vehicle row
Direction is sailed, vehicle running route is estimated;
That is, automobile data recorder is based on the vehicle speed, the vehicle acceleration, the vehicle angular speed and/or described
Vehicle heading, estimates vehicle running route, and automobile data recorder estimates vehicle running route based on vehicle.
Step S100 generates vehicle and runs navigation information according to the vehicle position information and the vehicle running route.
Automobile data recorder generates vehicle operation navigation letter according to the vehicle position information and the vehicle running route
Existing remote navigation and short distance outdoor scene, i.e., be combined, so that automobile navigation is more intelligent by breath in the present embodiment.
In addition, the embodiment of the present invention also proposes the driving suggestion device based on automobile data recorder, described to be based on referring to Fig. 3
The driving suggestion device of automobile data recorder includes:
Video acquisition module 10, for the video information based on automobile data recorder acquisition vehicle surrounding enviroment, from the view
The target analysis region containing default subject matter is extracted in each frame video image of frequency information;
Image analysis module 20, for utilizing default pedestrian's classifier and/or each mesh of preset vehicle detection of classifier
Analyzed area is marked, the pedestrian image and/or vehicle image in each target analysis region are obtained;
State determining module 30, for determining each target line according to each pedestrian image and/or each vehicle image
The relative movement information of people and/or each target vehicle and current vehicle, wherein the target pedestrian refers to each pedestrian image
In pedestrian, the target vehicle refers to the vehicle in each vehicle image;
Cue module 40 is driven, for generating and driving prompt information according to the relative movement information.
Optionally, the driving suggestion device based on automobile data recorder, comprising:
Light intensity detection module, for monitoring and obtaining the light intensity of external environment locating for the automobile data recorder, and will
The light intensity is compared with default light intensity;
Infrared adjustment module, if being less than the default light intensity for the light intensity, by the driving recording
Instrument is adjusted to infrared mode, to acquire the video information of surrounding enviroment under the infrared mode of the automobile data recorder;
Visible light adjustment module, if being more than or equal to the default light intensity for the light intensity, by institute
It states automobile data recorder to adjust to visible mode, to acquire the video of surrounding enviroment under the automobile data recorder visible mode
Information.
Optionally, the video acquisition module 10, comprising:
Filter unit is acquired, for the video information based on automobile data recorder acquisition vehicle surrounding enviroment, by the video
Each frame video image is filtered in information, the filtering image that obtains that treated;
Area determination unit, for obtaining default subject matter, wrapping by filtering image described in preset threshold algorithm process
Region containing the default subject matter is as target analysis region, wherein the default subject matter refers to pedestrian and/or vehicle.
Optionally, described image analysis module 20, comprising:
Image analyzing unit is gone for handling the target analysis region by default algorithm of histogram equalization
People's area image and/or vehicle region image;
First processing units, for obtaining described default by pedestrian area image described in default pedestrian's detection of classifier
Pedestrian sample corresponding with the pedestrian area image, determines the pedestrian area according to the pedestrian sample in pedestrian's classifier
Pedestrian image in image, and/or;
The second processing unit, for obtaining described default by vehicle region image described in preset vehicle detection of classifier
Vehicle sample corresponding with the vehicle region image in vehicle classification device, determines the vehicle region according to the vehicle sample
Vehicle image in image.
Optionally, the state determining module 30, comprising:
Size acquiring unit, for obtaining the image size data of target pedestrian and practical ruler in each pedestrian image
The image size data and actual size data of target vehicle in very little data and/or each vehicle image;
Distance determining unit, for obtaining the current focus of the drive recorder camera, according to preset formula: f=
Each target pedestrian and/or each target vehicle is calculated at a distance from current vehicle in h*D/H, wherein
The f is the current focus of the drive recorder camera;
The h is the image size data of the target pedestrian and/or the target vehicle;
The H is the actual size data of the target pedestrian and/or the target vehicle;
The D is the distance of the target pedestrian and/or the target vehicle to the current vehicle;
Acquiring unit, for obtaining the acquisition time of each pedestrian image and/or each vehicle image, and by described
Acquisition time arranges each distance;
Analytical unit obtains each target pedestrian and/or each target vehicle and current vehicle for analyzing each distance
Relative movement information.
Optionally, the driving cue module 40, comprising:
Probability analysis unit, for the relative movement information to be input in default route simulation model, by described
Default route simulation model carries out digital simulation, obtains the target pedestrian and/or the target vehicle and the current vehicle
Collision probability;
Prompt unit, for generating and driving prompt information when the collision probability is higher than preset threshold.
Optionally, the driving suggestion device based on automobile data recorder, further includes:
Module is obtained, for obtaining vehicle position information and vehicle movement information in automobile data recorder, wherein the vehicle
Motion information includes vehicle speed, vehicle acceleration, vehicle angular speed and/or vehicle heading;
Route estimates module, for based on the vehicle speed, the vehicle acceleration, the vehicle angular speed and/or
The vehicle heading estimates vehicle running route;
Navigate generation module, for generating vehicle operation according to the vehicle position information and the vehicle running route
Navigation information.
Wherein, the step of each Implement of Function Module of the driving suggestion device based on automobile data recorder can refer to the present invention
Each embodiment of driving reminding method based on automobile data recorder, details are not described herein again.
In addition, the embodiment of the present invention also proposes a kind of computer storage medium.
Computer program, the realization when computer program is executed by processor are stored in the computer storage medium
Operation provided by the above embodiment that drive in reminding method based on automobile data recorder.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body/operation/object is distinguished with another entity/operation/object, without necessarily requiring or implying these entity/operations/
There are any actual relationship or orders between object;The terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or the system that include a series of elements not only include that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of system.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in process, method, article or the system for including the element.
For device embodiment, since it is substantially similar to the method embodiment, related so describing fairly simple
Place illustrates referring to the part of embodiment of the method.The apparatus embodiments described above are merely exemplary, wherein making
It may or may not be physically separated for the unit of separate part description.In can selecting according to the actual needs
Some or all of the modules realize the purpose of the present invention program.Those of ordinary skill in the art are not making the creative labor
In the case where, it can it understands and implements.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of driving reminding method based on automobile data recorder, which is characterized in that the driving based on automobile data recorder mentions
Show method the following steps are included:
Based on the video information of automobile data recorder acquisition vehicle surrounding enviroment, mentioned from each frame video image of the video information
Take the target analysis region containing default subject matter;
Using each target analysis region of default pedestrian's classifier and/or preset vehicle detection of classifier, each mesh is obtained
Mark the pedestrian image and/or vehicle image in analyzed area;
According to each pedestrian image and/or each vehicle image, each target pedestrian and/or each target vehicle and current are determined
The relative movement information of vehicle, wherein the target pedestrian refers to the pedestrian in each pedestrian image, and the target vehicle is
Refer to that the vehicle in each vehicle image, the current vehicle refer to the vehicle for installing the automobile data recorder;
According to the relative movement information, generates and drive prompt information.
2. the driving reminding method based on automobile data recorder as described in claim 1, which is characterized in that described based on driving note
The video information for recording instrument acquisition vehicle surrounding enviroment is extracted from each frame video image of the video information containing default target
Before the step of target analysis region of object, comprising:
Monitor and obtain the light intensity of external environment locating for the automobile data recorder, and by the light intensity and default light
Intensity is compared;
If the light intensity be less than the default light intensity, the automobile data recorder is adjusted to infrared mode, with
The video information of surrounding enviroment is acquired under the infrared mode of the automobile data recorder;
If the light intensity is more than or equal to the default light intensity, the automobile data recorder is adjusted to visible light
Mode, to acquire the video information of surrounding enviroment under the automobile data recorder visible mode.
3. the driving reminding method based on automobile data recorder as described in claim 1, which is characterized in that described based on driving note
The video information for recording instrument acquisition vehicle surrounding enviroment is extracted from each frame video image of the video information containing default target
The step of target analysis region of object, comprising:
Based on the video information of automobile data recorder acquisition vehicle surrounding enviroment, frame video image each in the video information is carried out
Filtering processing, the filtering image that obtains that treated;
By filtering image described in preset threshold algorithm process, default subject matter is obtained, by the area comprising the default subject matter
Domain is as target analysis region, wherein the default subject matter refers to pedestrian and/or vehicle.
4. the driving reminding method based on automobile data recorder as described in claim 1, which is characterized in that described to utilize default row
People's classifier and/or each target analysis region of preset vehicle detection of classifier, obtain in each target analysis region
The step of pedestrian image and/or vehicle image, comprising:
The target analysis region is handled by default algorithm of histogram equalization, obtains pedestrian area image and/or vehicle area
Area image;
By pedestrian area image described in default pedestrian's detection of classifier, obtain in default pedestrian's classifier with the pedestrian
The corresponding pedestrian sample of area image determines the pedestrian image in the pedestrian area image according to the pedestrian sample, and/
Or;
By vehicle region image described in preset vehicle detection of classifier, obtain in the preset vehicle classifier with the vehicle
The corresponding vehicle sample of area image determines the vehicle image in the vehicle region image according to the vehicle sample.
5. the driving reminding method based on automobile data recorder as described in claim 1, which is characterized in that described according to each described
Pedestrian image and/or each vehicle image, determine the relative motion of each target pedestrian and/or each target vehicle and current vehicle
The step of information, comprising:
Obtain the image size data and actual size data of target pedestrian and/or each vehicle in each pedestrian image
The image size data and actual size data of target vehicle in image;
The current focus for obtaining the drive recorder camera, according to preset formula: each target line is calculated in f=h*D/H
People and/or each target vehicle are at a distance from current vehicle, wherein
The f is the current focus of the drive recorder camera;
The h is the image size data of the target pedestrian and/or the target vehicle;
The H is the actual size data of the target pedestrian and/or the target vehicle;
The D is the distance of the target pedestrian and/or the target vehicle to the current vehicle;
The acquisition time of each pedestrian image and/or each vehicle image is obtained, and arranges each institute by the acquisition time
State distance;
Each distance is analyzed, the relative movement information of each target pedestrian and/or each target vehicle and current vehicle is obtained.
6. the driving reminding method based on automobile data recorder as described in claim 1, which is characterized in that described according to the phase
To motion information, the step of driving prompt information is generated, comprising:
The relative movement information is input in default route simulation model, is counted by the default route simulation model
According to simulation, the collision probability of the target pedestrian and/or the target vehicle and the current vehicle is obtained;
When the collision probability is higher than preset threshold, generates and drive prompt information.
7. the driving reminding method based on automobile data recorder as described in claim 1, which is characterized in that described according to the phase
To motion information, after generating the step of driving prompt information, comprising:
Obtain the vehicle position information and vehicle movement information in automobile data recorder, wherein the vehicle movement information includes vehicle
Speed, vehicle acceleration, vehicle angular speed and/or vehicle heading;
Based on the vehicle speed, the vehicle acceleration, the vehicle angular speed and/or the vehicle heading, estimate
Vehicle running route;
According to the vehicle position information and the vehicle running route, generates vehicle and run navigation information.
8. a kind of driving suggestion device based on automobile data recorder, which is characterized in that the driving based on automobile data recorder mentions
Showing device includes:
Video acquisition module, for the video information based on automobile data recorder acquisition vehicle surrounding enviroment, from the video information
Each frame video image in extract the target analysis region containing default subject matter;
Image analysis module, for utilizing default pedestrian's classifier and/or each target analysis of preset vehicle detection of classifier
Region obtains the pedestrian image and/or vehicle image in each target analysis region;
State determining module, for according to each pedestrian image and/or each vehicle image, determine each target pedestrian and/
Or the relative movement information of each target vehicle and current vehicle, wherein the target pedestrian refers in each pedestrian image
Pedestrian, the target vehicle refer to that the vehicle in each vehicle image, the current vehicle refer to the installation driving recording
The vehicle of instrument;
Cue module is driven, for generating and driving prompt information according to the relative movement information.
9. a kind of driving based on automobile data recorder prompts equipment, which is characterized in that the driving based on automobile data recorder mentions
Show that equipment includes: camera, memory, processor and is stored in the meter that can be run on the memory and on the processor
Calculation machine program, in which:
The camera, for acquiring the video information of vehicle surrounding enviroment;
When the computer program is executed by the processor realize as described in any one of claims 1 to 7 based on driving
The step of driving reminding method of recorder.
10. a kind of computer storage medium, which is characterized in that be stored with computer program, institute in the computer storage medium
State the driving based on automobile data recorder realized as described in any one of claims 1 to 7 when computer program is executed by processor
The step of sailing reminding method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811117981.2A CN109664820A (en) | 2018-09-25 | 2018-09-25 | Driving reminding method, device, equipment and storage medium based on automobile data recorder |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811117981.2A CN109664820A (en) | 2018-09-25 | 2018-09-25 | Driving reminding method, device, equipment and storage medium based on automobile data recorder |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109664820A true CN109664820A (en) | 2019-04-23 |
Family
ID=66141618
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811117981.2A Pending CN109664820A (en) | 2018-09-25 | 2018-09-25 | Driving reminding method, device, equipment and storage medium based on automobile data recorder |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109664820A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110312106A (en) * | 2019-07-30 | 2019-10-08 | 广汽蔚来新能源汽车科技有限公司 | Display methods, device, computer equipment and the storage medium of image |
CN110570689A (en) * | 2019-09-05 | 2019-12-13 | 成都亿盟恒信科技有限公司 | vehicle monitoring system based on driving record and anti-collision early warning |
CN110688943A (en) * | 2019-09-25 | 2020-01-14 | 武汉光庭信息技术股份有限公司 | Method and device for automatically acquiring image sample based on actual driving data |
CN111091591A (en) * | 2019-12-23 | 2020-05-01 | 百度国际科技(深圳)有限公司 | Collision detection method and device, electronic equipment and storage medium |
CN111126807A (en) * | 2019-12-12 | 2020-05-08 | 浙江大华技术股份有限公司 | Stroke segmentation method and device, storage medium and electronic device |
CN111666839A (en) * | 2020-05-25 | 2020-09-15 | 东华大学 | Road pedestrian detection system based on improved Faster RCNN |
CN112185146A (en) * | 2020-09-14 | 2021-01-05 | 智慧互通科技有限公司 | Early warning method and system for non-vehicle target |
CN113283311A (en) * | 2021-05-07 | 2021-08-20 | 恒大新能源汽车投资控股集团有限公司 | Animal driving-away method and device for vehicle |
CN113501003A (en) * | 2021-06-30 | 2021-10-15 | 深圳市路卓科技有限公司 | Driving assistance prompting method, device, equipment, storage medium and program product |
CN114290989A (en) * | 2021-12-21 | 2022-04-08 | 东软睿驰汽车技术(沈阳)有限公司 | Prompting method, vehicle and computer readable storage medium |
CN115273552A (en) * | 2022-09-19 | 2022-11-01 | 南通立信自动化有限公司 | HMI control system of automobile instrument |
CN115953764A (en) * | 2023-03-13 | 2023-04-11 | 深圳魔视智能科技有限公司 | Vehicle sentinel method, device, equipment and storage medium based on aerial view |
CN117423093A (en) * | 2023-12-18 | 2024-01-19 | 深圳市深航华创汽车科技有限公司 | Driving detection method, device, equipment and storage medium based on driving recorder |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1837803A2 (en) * | 2006-03-24 | 2007-09-26 | MobilEye Technologies, Ltd. | Headlight, taillight and streetlight detection |
US7786898B2 (en) * | 2006-05-31 | 2010-08-31 | Mobileye Technologies Ltd. | Fusion of far infrared and visible images in enhanced obstacle detection in automotive applications |
CN104851146A (en) * | 2015-05-11 | 2015-08-19 | 苏州三体智能科技有限公司 | Interactive driving record navigation security system |
CN105095869A (en) * | 2015-07-24 | 2015-11-25 | 深圳市佳信捷技术股份有限公司 | Pedestrian detection method and apparatus |
CN106295459A (en) * | 2015-05-11 | 2017-01-04 | 青岛若贝电子有限公司 | Based on machine vision and the vehicle detection of cascade classifier and method for early warning |
CN107856671A (en) * | 2017-01-24 | 2018-03-30 | 问众智能信息科技(北京)有限公司 | A kind of method and system that road conditions identification is carried out by drive recorder |
CN108082107A (en) * | 2017-12-19 | 2018-05-29 | 奇瑞汽车股份有限公司 | Information prompting method, device and computer readable storage medium |
-
2018
- 2018-09-25 CN CN201811117981.2A patent/CN109664820A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1837803A2 (en) * | 2006-03-24 | 2007-09-26 | MobilEye Technologies, Ltd. | Headlight, taillight and streetlight detection |
US7786898B2 (en) * | 2006-05-31 | 2010-08-31 | Mobileye Technologies Ltd. | Fusion of far infrared and visible images in enhanced obstacle detection in automotive applications |
CN104851146A (en) * | 2015-05-11 | 2015-08-19 | 苏州三体智能科技有限公司 | Interactive driving record navigation security system |
CN106295459A (en) * | 2015-05-11 | 2017-01-04 | 青岛若贝电子有限公司 | Based on machine vision and the vehicle detection of cascade classifier and method for early warning |
CN105095869A (en) * | 2015-07-24 | 2015-11-25 | 深圳市佳信捷技术股份有限公司 | Pedestrian detection method and apparatus |
CN107856671A (en) * | 2017-01-24 | 2018-03-30 | 问众智能信息科技(北京)有限公司 | A kind of method and system that road conditions identification is carried out by drive recorder |
CN108082107A (en) * | 2017-12-19 | 2018-05-29 | 奇瑞汽车股份有限公司 | Information prompting method, device and computer readable storage medium |
Non-Patent Citations (1)
Title |
---|
朱道明,蔡锐,谭子毅,冯玉岗: "《建筑安防技术》", 31 January 2013, 东华大学出版社 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110312106A (en) * | 2019-07-30 | 2019-10-08 | 广汽蔚来新能源汽车科技有限公司 | Display methods, device, computer equipment and the storage medium of image |
CN110570689A (en) * | 2019-09-05 | 2019-12-13 | 成都亿盟恒信科技有限公司 | vehicle monitoring system based on driving record and anti-collision early warning |
CN110688943A (en) * | 2019-09-25 | 2020-01-14 | 武汉光庭信息技术股份有限公司 | Method and device for automatically acquiring image sample based on actual driving data |
CN111126807A (en) * | 2019-12-12 | 2020-05-08 | 浙江大华技术股份有限公司 | Stroke segmentation method and device, storage medium and electronic device |
CN111126807B (en) * | 2019-12-12 | 2023-10-10 | 浙江大华技术股份有限公司 | Stroke segmentation method and device, storage medium and electronic device |
CN111091591B (en) * | 2019-12-23 | 2023-09-26 | 阿波罗智联(北京)科技有限公司 | Collision detection method and device, electronic equipment and storage medium |
CN111091591A (en) * | 2019-12-23 | 2020-05-01 | 百度国际科技(深圳)有限公司 | Collision detection method and device, electronic equipment and storage medium |
CN111666839A (en) * | 2020-05-25 | 2020-09-15 | 东华大学 | Road pedestrian detection system based on improved Faster RCNN |
CN112185146A (en) * | 2020-09-14 | 2021-01-05 | 智慧互通科技有限公司 | Early warning method and system for non-vehicle target |
CN113283311A (en) * | 2021-05-07 | 2021-08-20 | 恒大新能源汽车投资控股集团有限公司 | Animal driving-away method and device for vehicle |
CN113501003A (en) * | 2021-06-30 | 2021-10-15 | 深圳市路卓科技有限公司 | Driving assistance prompting method, device, equipment, storage medium and program product |
CN113501003B (en) * | 2021-06-30 | 2022-09-30 | 深圳市路卓科技有限公司 | Driving assistance prompting method, device, equipment, storage medium and program product |
CN114290989A (en) * | 2021-12-21 | 2022-04-08 | 东软睿驰汽车技术(沈阳)有限公司 | Prompting method, vehicle and computer readable storage medium |
CN115273552A (en) * | 2022-09-19 | 2022-11-01 | 南通立信自动化有限公司 | HMI control system of automobile instrument |
CN115953764A (en) * | 2023-03-13 | 2023-04-11 | 深圳魔视智能科技有限公司 | Vehicle sentinel method, device, equipment and storage medium based on aerial view |
CN117423093A (en) * | 2023-12-18 | 2024-01-19 | 深圳市深航华创汽车科技有限公司 | Driving detection method, device, equipment and storage medium based on driving recorder |
CN117423093B (en) * | 2023-12-18 | 2024-03-29 | 深圳市深航华创汽车科技有限公司 | Driving detection method, device, equipment and storage medium based on driving recorder |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109664820A (en) | Driving reminding method, device, equipment and storage medium based on automobile data recorder | |
Jiang et al. | Real‐time crack assessment using deep neural networks with wall‐climbing unmanned aerial system | |
KR102166458B1 (en) | Defect inspection method and apparatus using image segmentation based on artificial neural network | |
US20210133468A1 (en) | Action Recognition Method, Electronic Device, and Storage Medium | |
CN110728650B (en) | Well lid depression detection method based on intelligent terminal and related equipment | |
CN107305635A (en) | Object identifying method, object recognition equipment and classifier training method | |
US10872251B2 (en) | Automated annotation techniques | |
CN110781836A (en) | Human body recognition method and device, computer equipment and storage medium | |
CN111291601B (en) | Lane line identification method and device and electronic equipment | |
CN108665476A (en) | A kind of pedestrian tracting method and electronic equipment | |
JP7079358B2 (en) | Target detection methods and devices, computer systems and readable storage media | |
CN111738033B (en) | Vehicle driving information determination method and device based on plane segmentation and vehicle-mounted terminal | |
CN111310815A (en) | Image recognition method and device, electronic equipment and storage medium | |
CN114936330A (en) | Method and related device for pushing information in vehicle driving scene | |
CN112232311B (en) | Face tracking method and device and electronic equipment | |
CN111967396A (en) | Processing method, device and equipment for obstacle detection and storage medium | |
US11482007B2 (en) | Event-based vehicle pose estimation using monochromatic imaging | |
CN113034439B (en) | High-speed railway sound barrier defect detection method and device | |
CN108010065A (en) | Low target quick determination method and device, storage medium and electric terminal | |
CN112927303A (en) | Lane line-based automatic driving vehicle-mounted camera pose estimation method and system | |
CN110910628A (en) | Interactive processing method and device for vehicle damage image shooting and electronic equipment | |
CN113033715B (en) | Target detection model training method and target vehicle detection information generation method | |
CN108881846B (en) | Information fusion method and device and computer readable storage medium | |
CN111178181B (en) | Traffic scene segmentation method and related device | |
CN113569911A (en) | Vehicle identification method and device, electronic 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190423 |
|
RJ01 | Rejection of invention patent application after publication |