CN108268831A - The robustness test method and system of a kind of unmanned vehicle vision-based detection - Google Patents
The robustness test method and system of a kind of unmanned vehicle vision-based detection Download PDFInfo
- Publication number
- CN108268831A CN108268831A CN201711248427.3A CN201711248427A CN108268831A CN 108268831 A CN108268831 A CN 108268831A CN 201711248427 A CN201711248427 A CN 201711248427A CN 108268831 A CN108268831 A CN 108268831A
- Authority
- CN
- China
- Prior art keywords
- scene
- unmanned vehicle
- tested
- image
- test
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- 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
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/14—Receivers specially adapted for specific applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
Abstract
The application provides a kind of the robustness test method and system of unmanned vehicle vision-based detection, and the method includes obtain unmanned vehicle acquisition includes the original image for detecting target;Using the corresponding test parameter of scene to be tested, abnormality processing is carried out to the original image, builds the corresponding test image of scene to be tested;Using the vision-based detection for the detection target in original image and test image as a result, obtaining robustness test result of the unmanned vehicle vision-based detection under the scene to be tested.Using the present embodiment described method and system, test scene is more targetedly and repeatable, substantially increases the efficiency of robustness test.
Description
【Technical field】
This application involves field of image recognition more particularly to a kind of unmanned vehicle vision-based detection robustness test method and be
System.
【Background technology】
Visual detection algorithm plays a crucial role in unmanned vehicle system, the unmanned vehicle travelled on road, if
It will be by crossing, it is necessary first to identify traffic lights (hereinafter referred to as signal lamp).
In the prior art, during marker lamp, unmanned vehicle can be clapped signal lamp by filming apparatus
It takes the photograph, the image obtained by filming apparatus only met visual detection algorithm can just learn in the image whether there is signal lamp, believe
The type of signal lamp, color of signal lamp etc., and Decision Control module is sent to, it is made according to testing result by Decision Control module
Meet the operation of traffic rules, that is, stop or current.
Because filming apparatus can face various different scenes, such as in feelings such as sleet greasy weather gas, the movements of filming apparatus angle
Condition, unmanned vehicle possibly can not be identified signal lamp.Thus act of violating regulations may be caused or even cause traffic accident.
In order to ensure safe driving, need under various scenes can correct marker lamp, this requires unmanned vehicle regards
Feel that detection algorithm has high robustness.
In unmanned vehicle development process, need to carry out real roads test, to test out unmanned vehicle in real roads
Whether the vision-based detection of the scene encountered can reach actual demand.But for different scenes, the especially fields such as sleet greasy weather gas
Scape is larger by effect of natural conditions, and there may be not reproducible.In order to complete the test of various different scenes, need to consume
Take more time, manpower, monetary cost.
【Invention content】
The many aspects of the application provide a kind of the robustness test method and system of unmanned vehicle vision-based detection, to test
The robustness of unmanned vehicle vision algorithm.
The one side of the application provides a kind of robustness test method of unmanned vehicle vision-based detection, including:
Obtain the original image for including detection target of unmanned vehicle acquisition;
Using the corresponding test parameter of scene to be tested, abnormality processing is carried out to the original image, builds examination hall to be measured
The corresponding test image of scape;
Using the vision-based detection for the detection target in original image and test image as a result, obtaining the inspection of unmanned vehicle vision
Survey the robustness test result under the scene to be tested.
The aspect and any possible implementation manners as described above, it is further provided a kind of realization method, the acquisition nothing
The original image comprising detection target of people's vehicle acquisition includes:
When monitoring unmanned vehicle and detection target in preset distance range, then the filming apparatus started on unmanned vehicle is clapped
It takes the photograph and stores the original image for including detection target.
The aspect and any possible implementation manners as described above, it is further provided a kind of realization method, the vision inspection
Result is surveyed to include:
Detect at least one of type, color and position of target.
The aspect and any possible implementation manners as described above, it is further provided a kind of realization method, it is described to be tested
Scene includes bad weather scene;
Using the corresponding test parameter of scene to be tested, abnormality processing is carried out to the original image, builds examination hall to be measured
The corresponding test image of scape includes:
The original image is carried out plus made an uproar according to meteorologic parameter, brightness processed, obtains the corresponding survey of bad weather scene
Attempt picture.
The aspect and any possible implementation manners as described above, it is further provided a kind of realization method, it is described to be tested
Scene includes filming apparatus position mobile context;
Using the corresponding test parameter of scene to be tested, abnormality processing is carried out to the original image, builds examination hall to be measured
The corresponding test image of scape includes:
According to location information parameter of the filming apparatus in unmanned vehicle, mobile, scaling processing is carried out to the original image,
Obtain the corresponding test image of filming apparatus position mobile context.
The aspect and any possible implementation manners as described above, it is further provided a kind of realization method, it is described to be tested
Scene includes filming apparatus angle mobile context;
Using the corresponding test parameter of scene to be tested, abnormality processing is carried out to the original image, builds examination hall to be measured
The corresponding test image of scape includes:
According to attitude information parameter of the filming apparatus in unmanned vehicle, mobile, rotation processing is carried out to described image, is obtained
The corresponding test image of filming apparatus angle mobile context.
The aspect and any possible implementation manners as described above, it is further provided a kind of realization method, it is described to utilize needle
To in original image and test image detection target carry out vision-based detection as a result, obtaining unmanned vehicle under the scene to be tested
The robustness test result of vision-based detection includes:
The vision-based detection result carried out for the detection target in original image and test image is compared, obtains nothing
Error rate of people's vehicle vision-based detection under scene to be tested.
The one side of the application provides a kind of robustness test system of unmanned vehicle vision-based detection, including:
Original image acquisition module, for obtaining the original image for including detection target of unmanned vehicle acquisition;
Image processing module, for using the corresponding test parameter of scene to be tested, being carried out to the original image abnormal
Processing, builds the corresponding test image of scene to be tested;
Vision-based detection module, for utilizing the vision-based detection knot for the detection target in original image and test image
Fruit obtains robustness test result of the unmanned vehicle vision-based detection under the scene to be tested.
The aspect and any possible implementation manners as described above, it is further provided a kind of realization method, the original graph
As acquisition module is specifically used for:
When monitoring unmanned vehicle and detection target in preset distance range, then the filming apparatus started on unmanned vehicle is clapped
It takes the photograph and stores the original image for including detection target.
The aspect and any possible implementation manners as described above, it is further provided a kind of realization method, the vision inspection
Result is surveyed to include:
Detect at least one of type, color and position of target.
The aspect and any possible implementation manners as described above, it is further provided a kind of realization method, it is described to be tested
Scene includes bad weather scene;
Described image processing module is specifically used for:
The original image is carried out plus made an uproar according to meteorologic parameter, brightness processed, obtains the corresponding survey of bad weather scene
Attempt picture.
The aspect and any possible implementation manners as described above, it is further provided a kind of realization method, it is described to be tested
Scene includes filming apparatus position mobile context;
Described image processing module is specifically used for:
According to location information parameter of the filming apparatus in unmanned vehicle, mobile, scaling processing is carried out to the original image,
Obtain the corresponding test image of filming apparatus position mobile context.
The aspect and any possible implementation manners as described above, it is further provided a kind of realization method, it is described to be tested
Scene includes filming apparatus angle mobile context;
Described image processing module is specifically used for:
According to attitude information parameter of the filming apparatus in unmanned vehicle, mobile, rotation processing is carried out to described image, is obtained
The corresponding test image of filming apparatus angle mobile context.
The aspect and any possible implementation manners as described above, it is further provided a kind of realization method, the vision inspection
Module is surveyed to be specifically used for:
The vision-based detection result carried out for the detection target in original image and test image is compared, obtains nothing
Error rate of people's vehicle vision-based detection under scene to be tested.
The another aspect of the application provides a kind of equipment, which is characterized in that the equipment includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processing
Device realizes any above-mentioned method.
The another aspect of the application provides a kind of computer readable storage medium, is stored thereon with computer program, special
Sign is that the program realizes any above-mentioned method when being executed by processor.
By the technical solution it is found that the embodiment of the present application can effectively test the robustness of unmanned vehicle vision-based detection.
【Description of the drawings】
It, below will be to embodiment or description of the prior art in order to illustrate more clearly of the technical solution in the embodiment of the present application
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is some realities of the application
Example is applied, it for those of ordinary skill in the art, without having to pay creative labor, can also be attached according to these
Figure obtains other attached drawings.
Fig. 1 is the flow diagram of the robustness test method of unmanned vehicle vision-based detection that one embodiment of the application provides;
Fig. 2 is that the robustness for the unmanned vehicle vision-based detection that another embodiment of the application provides tests the structural representation of system
Figure;
Fig. 3 is the block diagram suitable for being used for realizing the exemplary computer system/server of the embodiment of the present invention.
【Specific embodiment】
Purpose, technical scheme and advantage to make the embodiment of the present application are clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical solution in the embodiment of the present application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
The whole other embodiments obtained without creative efforts, shall fall in the protection scope of this application.
In addition, the terms "and/or", only a kind of incidence relation for describing affiliated partner, represents there may be
Three kinds of relationships, for example, A and/or B, can represent:Individualism A exists simultaneously A and B, these three situations of individualism B.Separately
Outside, character "/" herein, it is a kind of relationship of "or" to typically represent forward-backward correlation object.
Fig. 1 is the flow diagram of the robustness test method of unmanned vehicle vision-based detection that one embodiment of the application provides,
As shown in Figure 1, include the following steps:
Step S11, the original video for including detection target of unmanned vehicle acquisition is obtained;
Step S12, according to the test parameter of scene to be tested in test request, exception is carried out to the original video
Reason, builds the corresponding test video of scene to be tested;
Step S13, using the vision-based detection for the detection target in original video and test video as a result, obtaining nobody
Robustness test result of the vehicle vision-based detection under the scene to be tested.
In a kind of preferred implementation of step S11,
Original video with detection target in actual test scene is shot by the filming apparatus on unmanned vehicle, in this reality
It applies in example, the monitoring objective is by taking signal lamp as an example, including following sub-step:
Sub-step S111 builds test map corresponding with unmanned vehicle test site.
In the present embodiment, the test map of test site can be built first.
When structure tests map, at least one can be drawn according to the height of the coordinate of each point of test site, each point
A test map;Existing high-precision map can also be used, modifies to it, obtains can be adapted for test site extremely
Few test map.Wherein, the location information and directional information of signal lamp are included in the test map.
Sub-step S112 determines the expectation driving trace from preset initial position to final position on test map.
After structure completes above-mentioned test map, the initial position of unmanned vehicle can be determined to end on above-mentioned test map
The expectation driving trace that stop bit is put.
Sub-step S113, it would be desirable to driving trace is sent to unmanned vehicle so that unmanned vehicle on test site desirably
Driving trace travels.
Above-mentioned expectation driving trace can be sent to unmanned vehicle by server after above-mentioned expectation driving trace is determined.
Unmanned vehicle after above-mentioned expectation driving trace is had received, can desirably driving trace from initial position set out traveling to terminate
Position.It is understood that test map can also be sent jointly to unmanned vehicle by server simultaneously.
Sub-step S114 controls the filming apparatus on unmanned vehicle to shoot and store the original video comprising signal lamp,
In a kind of preferred implementation of the present embodiment, the filming apparatus on unmanned vehicle can also be controlled to shoot and stored
Original image comprising signal lamp, is directly stored with image mode.
In the present embodiment, during being detected, handling to video, both for the image of a frame frame in video
Detection, the processing of progress.
Preferably, when monitoring on the direction of travel of unmanned vehicle, with signal lamp to be captured in preset distance range
It is interior, then start the video that the shooting of the filming apparatus on unmanned vehicle includes signal lamp.Pass through the location information of unmanned vehicle, signal lamp
Location information can determine the range information of filming apparatus and signal lamp.
Signal lamp to be captured is that unmanned vehicle needs what is shot and detect by crossing, so that it is determining current or stopping
Signal lamp.The signal lamp it is targeted be vehicle on the unmanned vehicle direction of travel.
Pre-determined distance range is numberical range of the preset unmanned vehicle to the distance of signal lamp.Pre-determined distance range can
To be a numerical intervals, such as 40-60 meters or a numerical value, such as 50 meters.
In the present embodiment, vision-based detection can be carried out to each frame image of the original video, and records detection knot
Fruit.The virtual condition of the signal lamp corresponding to each frame image of the original video can also be directly recorded, that is, is not needed to pair
The original video carries out vision-based detection, and only need to obtain signal according to the timestamp of frame image each in the original video
Lamp is in the virtual condition of corresponding time.
The testing result includes the type and color of signal lamp in each frame image, such as:
The signal lamp is motor vehicle signal lamp, and the motor vehicle signal lamp is green light;Or
The signal lamp is motor vehicle signal lamp, and the motor vehicle signal lamp is bright for amber light;Or
The signal lamp is motor vehicle signal lamp, and the motor vehicle signal lamp is when red.
The signal lamp is lane signal lamp, and the lane signal lamp is bright for green arrow lamp;Or
The signal lamp is lane signal lamp, and the lane signal lamp is red fork-shaped lamp.
The signal lamp is directional signal light, and arrow direction is to the left;Or
The signal lamp is directional signal light, and arrow direction is upward;Or
The signal lamp is directional signal light, and arrow direction is to the right.
The testing result can also include the position of signal lamp in each frame image.
Preferably, the testing result further includes the location information of the corresponding unmanned vehicle of each frame image, so as to subsequently into
Row comparison.The information in geographical location of the location information of unmanned vehicle where unmanned vehicle, which can utilize nobody
What the IMS inertial navigation systems or GPS system of vehicle were got.
Preferably, it based on ROS this robot operating system is core that unmanned vehicle, which is, the data of unmanned vehicle at runtime
It can be stored as the bag files that form is .bag.The detailed of all topic in unmanned vehicle ROS operating systems can be recorded in bag files
Information, the topic perceived including corresponding filming apparatus topic and signal lamp.Filming apparatus topic is output to signal lamp sense
Know this topic, perceive this topic by signal lamp detects whether presence signal lamp and signal according to filming apparatus topic
The position of lamp, type, color.
In a kind of preferred implementation of step S12,
When receiving test request, according to the corresponding test parameter of scene to be tested in test request, to described original
Each frame image of video carries out abnormality processing, builds the corresponding test video of scene to be tested.
The test request includes testing map, scene to be tested, wherein, scene to be tested includes:Bad weather, bat
Take the photograph mobile, filming apparatus angle movement of setting position etc.;The test parameter of bad weather scene is meteorologic parameter, filming apparatus position
The test parameter for putting mobile context is the test of location information, filming apparatus angle mobile context of the filming apparatus in unmanned vehicle
Parameter is the attitude information of filming apparatus.
Meteorologic parameter is the specific meteorologic parameters such as rain, snow, mist, sand and dust, haze, cloudy day.Position of the filming apparatus in unmanned vehicle
It is the information for indicating position of the filming apparatus in unmanned vehicle to put information parameter.Attitude information parameter is the posture with filming apparatus
Relevant information indicates the posture of filming apparatus.
By the setting to meteorologic parameter, the scene to be measured under inclement weather conditions can be realized;By to filming apparatus
The setting of location information in unmanned vehicle can realize the scene to be measured under the situation of movement of filming apparatus position;By to clapping
The setting of the attitude information of device is taken the photograph, can realize the scene to be measured under filming apparatus angle situation of movement;
Preferably, above-mentioned parameter can be carried out at the same time setting, to realize the scene to be measured under complex situations.It is for example, severe
Under weather, mobile scene all occurs for filming apparatus position and angle.
The original video stored in extraction video container is joined according to the corresponding test of scene to be tested in test request
Several each frames in the original video carry out abnormality processing, and the abnormal image Data Synthesis that abnormality processing is obtained is to be measured
The corresponding test video of examination hall scape.
Extract first with the relevant topic of video, video is stored in topic with compressed form, extraction side
Method is topic all in the entire bag files of traversal, select specify with the relevant topic of signal lamp.Then by signal lamp pair
The processing of mono- frame frames of topic answered, is converted to the manageable forms of OpenCV firstly the need of by signal lamp topic here
Each frame image in the original video move using the computer visions such as OpenCV library, is scaled, partially
It moves, rotation processing, generates corresponding abnormal image;
Preferably, the location information parameter according to filming apparatus in unmanned vehicle carries out described image at mobile, scaling
Reason, obtains the corresponding test image of filming apparatus position mobile context;
According to the attitude information parameter of filming apparatus, mobile, rotation processing is carried out to described image, obtains filming apparatus angle
Spend the corresponding test image of mobile context.
Due to the computer visions such as OpenCV library can not to image carry out plus make an uproar, brightness processed, so need using its
His image processing tool carries out plus makes an uproar to each frame image in video according to meteorologic parameter, brightness processed, generates bad weather
The corresponding test image of scene.
The video data that the test image of generation is converted to ROS by OpenCV to read is used as test video, from
And be written in the corresponding test video topic of scene to be tested, it is stored as the file that form is .bag.
In a kind of preferred implementation of step S13,
Using the vision-based detection carried out for the detection target in original video and test video as a result, obtaining described to be measured
The robustness test result of unmanned vehicle vision-based detection under the scape of examination hall.
Unmanned vehicle vision-based detection is carried out according to the corresponding test video of the scene to be tested, records testing result.
Newly-generated bag files are played on unmanned vehicle operating system ROS, while enabling signal lamp perceives this topic,
The position of presence signal lamp and signal lamp, type, face are detected whether according to the corresponding test video topic of scene to be tested
Color.
According to the corresponding test video of the scene to be tested carry out unmanned vehicle vision-based detection testing result include it is each
The type and color of signal lamp in frame image, such as:
The signal lamp is motor vehicle signal lamp, and the motor vehicle signal lamp is green light;Or
The signal lamp is motor vehicle signal lamp, and the motor vehicle signal lamp is bright for amber light;Or
The signal lamp is motor vehicle signal lamp, and the motor vehicle signal lamp is when red.
The signal lamp is lane signal lamp, and the lane signal lamp is bright for green arrow lamp;Or
The signal lamp is lane signal lamp, and the lane signal lamp is that red fork-shaped lamp or arrow lamp are bright.
The signal lamp is directional signal light, and the arrow direction is to the left;Or
The signal lamp is directional signal light, and arrow direction is upward;Or
The signal lamp is directional signal light, and arrow direction is to the right.
The testing result can also include the position of signal lamp in each frame image.
Preferably, the testing result further includes the location information of the corresponding unmanned vehicle of each frame image, the position of unmanned vehicle
Confidence breath is to be shot in actual test scene during the video with signal lamp by the filming apparatus carried on unmanned vehicle
The information in the geographical location where the unmanned vehicle of record.
Preferably, the testing result of the testing result of original video test video corresponding with scene to be tested is carried out pair
Than obtaining error rate of the unmanned vehicle vision algorithm under scene to be tested, determining that can unmanned vehicle under the scene to be tested
Normal operation.The virtual condition of the testing result of scene video to be tested and signal lamp can also be compared.
For example, under different test scenes, in corresponding frame, unmanned vehicle visual detection algorithm detects signal lamp accurate
The information comparison such as true rate, can obtain robustness of the unmanned vehicle visual detection algorithm to different test scenes.
Specific aim improvement is carried out to unmanned vehicle vision algorithm according to the robustness test result, enhances visual detection algorithm
Robustness.
The robustness test method for the unmanned vehicle vision-based detection that above-described embodiment of the application provides, test scene have more
Specific aim and repeatability substantially increase the efficiency of robustness test.
It should be noted that for aforementioned each method embodiment, in order to be briefly described, therefore it is all expressed as a series of
Combination of actions, but those skilled in the art should know, the application is not limited by described sequence of movement because
According to the application, certain steps may be used other sequences or be carried out at the same time.Secondly, those skilled in the art should also know
It knows, embodiment described in this description belongs to preferred embodiment, involved action and module not necessarily the application
It is necessary.
In the described embodiment, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiment.
Fig. 2 is that the robustness for the unmanned vehicle vision-based detection that another embodiment of the application provides tests the structural representation of system
Figure, as shown in Fig. 2, including with lower module:
Original video acquisition module 21, for obtaining the original video for including detection target of unmanned vehicle acquisition;
Video processing module 22, for the test parameter according to scene to be tested in test request, to the original video
Abnormality processing is carried out, builds the corresponding test video of scene to be tested;
Vision-based detection module 23, for utilizing the vision-based detection knot for the detection target in original video and test video
Fruit obtains robustness test result of the unmanned vehicle vision-based detection under the scene to be tested.
In a kind of preferred implementation of original video acquisition module 21,
Original video with detection target in actual test scene is shot by the filming apparatus on unmanned vehicle, in this reality
It applies in example, the monitoring objective is by taking signal lamp as an example.
Structure test map corresponding with unmanned vehicle test site.
In the present embodiment, the test map of test site can be built first.
When structure tests map, at least one can be drawn according to the height of the coordinate of each point of test site, each point
A test map;Existing high-precision map can also be used, modifies to it, obtains can be adapted for test site extremely
Few test map.Wherein, the location information and directional information of signal lamp are included in the test map.
The expectation driving trace from preset initial position to final position is determined on test map.
After structure completes above-mentioned test map, the initial position of unmanned vehicle can be determined to end on above-mentioned test map
The expectation driving trace that stop bit is put.
It will it is expected that driving trace is sent to unmanned vehicle, so that unmanned vehicle desirably driving trace row on test site
It sails.
Above-mentioned expectation driving trace can be sent to unmanned vehicle by server after above-mentioned expectation driving trace is determined.
Unmanned vehicle after above-mentioned expectation driving trace is had received, can desirably driving trace from initial position set out traveling to terminate
Position.It is understood that test map can also be sent jointly to unmanned vehicle by server simultaneously.
Filming apparatus on control unmanned vehicle shoots and stores the original video comprising signal lamp,
In a kind of preferred implementation of the present embodiment, the filming apparatus on unmanned vehicle can also be controlled to shoot and stored
Original image comprising signal lamp, is directly stored with image mode.
In the present embodiment, during being detected, handling to video, both for the image of a frame frame in video
Detection, the processing of progress.
Preferably, when monitoring on the direction of travel of unmanned vehicle, with signal lamp to be captured in preset distance range
It is interior, then start the video that the shooting of the filming apparatus on unmanned vehicle includes signal lamp.Pass through the location information of unmanned vehicle, signal lamp
Location information can determine the range information of filming apparatus and signal lamp.
Signal lamp to be captured is that unmanned vehicle needs what is shot and detect by crossing, so that it is determining current or stopping
Signal lamp.The signal lamp it is targeted be vehicle on the unmanned vehicle direction of travel.
Pre-determined distance range is numberical range of the preset unmanned vehicle to the distance of signal lamp.Pre-determined distance range can
To be a numerical intervals, such as 40-60 meters or a numerical value, such as 50 meters.
In the present embodiment, vision-based detection can be carried out, and record testing result to each frame image of the original video.
The virtual condition of the signal lamp corresponding to each frame image of the video can also be directly recorded, that is, is not needed to described original
Video carries out vision-based detection, and only need to obtain signal lamp in correspondence according to the timestamp of frame image each in the original video
The virtual condition of time.
The testing result includes the type and color of signal lamp in each frame image, such as:
The signal lamp is motor vehicle signal lamp, and the motor vehicle signal lamp is green light;Or
The signal lamp is motor vehicle signal lamp, and the motor vehicle signal lamp is bright for amber light;Or
The signal lamp is motor vehicle signal lamp, and the motor vehicle signal lamp is when red.
The signal lamp is lane signal lamp, and the lane signal lamp is bright for green arrow lamp;Or
The signal lamp is lane signal lamp, and the lane signal lamp is red fork-shaped lamp.
The signal lamp is directional signal light, and arrow direction is to the left;Or
The signal lamp is directional signal light, and arrow direction is upward;Or
The signal lamp is directional signal light, and arrow direction is to the right.
The testing result can also include the position of signal lamp in each frame image.
Preferably, the testing result further includes the location information of the corresponding unmanned vehicle of each frame image, so as to subsequently into
Row comparison.The information in geographical location of the location information of unmanned vehicle where unmanned vehicle, which can utilize nobody
What the IMS inertial navigation systems or GPS system of vehicle were got.
Preferably, it based on ROS this robot operating system is core that unmanned vehicle, which is, the data of unmanned vehicle at runtime
It can be stored as the bag files that form is .bag.The detailed of all topic in unmanned vehicle ROS operating systems can be recorded in bag files
Information, the topic perceived including corresponding filming apparatus topic and signal lamp.Filming apparatus topic is output to signal lamp sense
Know this topic, perceive this topic by signal lamp detects whether presence signal lamp and signal according to filming apparatus topic
The position of lamp, type, color.
In a kind of preferred implementation of image processing module 22,
When receiving test request, image processing module 22 is joined according to the corresponding test of scene to be tested in test request
Number carries out abnormality processing to each frame image of the original video, builds the corresponding test video of scene to be tested.
The test request includes testing map, scene to be tested, wherein, scene to be tested includes:Bad weather, bat
Take the photograph mobile, filming apparatus angle movement of setting position etc.;The test parameter of bad weather scene is meteorologic parameter, filming apparatus position
The test parameter for putting mobile context is the test of location information, filming apparatus angle mobile context of the filming apparatus in unmanned vehicle
Parameter is the attitude information of filming apparatus.
Meteorologic parameter is the specific meteorologic parameters such as rain, snow, mist, sand and dust, haze, cloudy day.Position of the filming apparatus in unmanned vehicle
It is the information for indicating position of the filming apparatus in unmanned vehicle to put information parameter.Attitude information parameter is the posture with filming apparatus
Relevant information, the posture of records photographing device.
By the setting to meteorologic parameter, the scene to be measured under inclement weather conditions can be realized;By to filming apparatus
The setting of location information in unmanned vehicle can realize the scene to be measured under the situation of movement of filming apparatus position;By to clapping
The setting of the attitude information of device is taken the photograph, can realize the scene to be measured under filming apparatus angle situation of movement.
Preferably, above-mentioned parameter can be carried out at the same time setting, to realize the scene to be measured under complex situations.It is for example, severe
Under weather, mobile scene all occurs for filming apparatus position and angle.
The original video stored in extraction video container is joined according to the corresponding test of scene to be tested in test request
Several each frames in the original video carry out abnormality processing, and the abnormal image Data Synthesis that abnormality processing is obtained is to be measured
The corresponding test video of examination hall scape.
Extract first with the relevant topic of video, video is stored in topic with compressed form, extraction side
Method is topic all in the entire bag files of traversal, select specify with the relevant topic of signal lamp.Then by signal lamp pair
The processing of mono- frame frames of topic answered, is converted to the manageable forms of OpenCV firstly the need of by signal lamp topic here
Each frame image in the original video move using the computer visions such as OpenCV library, is scaled, partially
It moves, rotation processing, generates corresponding abnormal image;
Preferably, the location information parameter according to filming apparatus in unmanned vehicle carries out described image at mobile, scaling
Reason, obtains the corresponding test image of filming apparatus position mobile context;
According to the attitude information parameter of filming apparatus, mobile, rotation processing is carried out to described image, obtains filming apparatus angle
Spend the corresponding test image of mobile context.
It makes an uproar since the computer visions such as OpenCV library can not carry out image to add, brightness processed, so needing to utilize other
Image processing tool carries out plus makes an uproar to each frame image in video according to meteorologic parameter, brightness processed, obtains bad weather field
The corresponding test image of scape.
The video data that the test image of generation is converted to ROS by OpenCV to read is used as test video, from
And be written in the corresponding test video topic of scene to be tested, it is stored as the file that form is .bag.
In a kind of preferred implementation of vision-based detection module 23,
Vision-based detection module 23 utilizes the vision-based detection knot carried out for the detection target in original video and test video
Fruit obtains the robustness test result of unmanned vehicle vision-based detection under the scene to be tested.
Unmanned vehicle vision-based detection is carried out according to the corresponding test video of the scene to be tested, records testing result.
Newly-generated bag files are played on unmanned vehicle operating system ROS, while enabling signal lamp perceives this topic,
The position of presence signal lamp and signal lamp, type, face are detected whether according to the corresponding test video topic of scene to be tested
Color.
According to the corresponding test video of the scene to be tested carry out unmanned vehicle vision-based detection testing result include it is each
The type and color of signal lamp in frame image, such as:
The signal lamp is motor vehicle signal lamp, and the motor vehicle signal lamp is green light;Or
The signal lamp is motor vehicle signal lamp, and the motor vehicle signal lamp is bright for amber light;Or
The signal lamp is motor vehicle signal lamp, and the motor vehicle signal lamp is when red.
The signal lamp is lane signal lamp, and the lane signal lamp is bright for green arrow lamp;Or
The signal lamp is lane signal lamp, and the lane signal lamp is that red fork-shaped lamp or arrow lamp are bright.
The signal lamp is directional signal light, and the arrow direction is to the left;Or
The signal lamp is directional signal light, and arrow direction is upward;Or
The signal lamp is directional signal light, and arrow direction is to the right.
The testing result can also include the position of signal lamp in each frame image.
Preferably, the testing result further includes the location information of the corresponding unmanned vehicle of each frame image, the position of unmanned vehicle
Confidence breath is to be shot in actual test scene during the video with signal lamp by the filming apparatus carried on unmanned vehicle
The information in the geographical location where the unmanned vehicle of record.
Preferably, the testing result of the testing result of original video test video corresponding with scene to be tested is carried out pair
Than obtaining error rate of the unmanned vehicle vision algorithm under scene to be tested, determining that can unmanned vehicle under the scene to be tested
Normal operation.The virtual condition of the testing result of scene video to be tested and signal lamp can also be compared.
For example, under different test scenes, in corresponding frame, unmanned vehicle visual detection algorithm detects signal lamp accurate
The information comparison such as true rate, can obtain robustness of the unmanned vehicle visual detection algorithm to different test scenes.
Specific aim improvement is carried out to unmanned vehicle vision algorithm according to the robustness test result, enhances visual detection algorithm
Robustness.
The robustness test system for the unmanned vehicle vision-based detection that above-described embodiment of the application provides, test scene have more
Specific aim and repeatability substantially increase the efficiency of robustness test.
In several embodiments provided herein, it should be understood that disclosed method and apparatus can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
Only a kind of division of logic function can have other dividing mode in actual implementation, such as multiple units or component can be tied
It closes or is desirably integrated into another system or some features can be ignored or does not perform.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be the INDIRECT COUPLING or logical by some interfaces, device or unit
Letter connection can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separate, be shown as unit
The component shown may or may not be physical unit, you can be located at a place or can also be distributed to multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in each embodiment of the application can be integrated in a processing unit, it can also
That each unit is individually physically present, can also two or more units integrate in a unit.The integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of hardware adds SFU software functional unit.
Fig. 3 shows the frame suitable for being used for the exemplary computer system/server 012 for realizing embodiment of the present invention
Figure.The computer system/server 012 that Fig. 3 is shown is only an example, function that should not be to the embodiment of the present invention and use
Range band carrys out any restrictions.
As shown in figure 3, computer system/server 012 is showed in the form of universal computing device.Computer system/clothes
The component of business device 012 can include but is not limited to:One or more processor or processing unit 016, system storage
028, the bus 018 of connection different system component (including system storage 028 and processing unit 016).
Bus 018 represents one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using the arbitrary bus structures in a variety of bus structures.It lifts
For example, these architectures include but not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Computer system/server 012 typically comprises a variety of computer system readable media.These media can be appointed
What usable medium that can be accessed by computer system/server 012, including volatile and non-volatile medium, movably
With immovable medium.
System storage 028 can include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 030 and/or cache memory 032.Computer system/server 012 may further include other
Removable/nonremovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 034 can
For reading and writing immovable, non-volatile magnetic media (Fig. 3 do not show, commonly referred to as " hard disk drive ").Although in Fig. 3
Be not shown, can provide for move non-volatile magnetic disk (such as " floppy disk ") read-write disc driver and pair can
The CD drive that mobile anonvolatile optical disk (such as CD-ROM, DVD-ROM or other optical mediums) is read and write.In these situations
Under, each driver can be connected by one or more data media interfaces with bus 018.Memory 028 can include
At least one program product, the program product have one group of (for example, at least one) program module, these program modules are configured
To perform the function of various embodiments of the present invention.
Program/utility 040 with one group of (at least one) program module 042, can be stored in such as memory
In 028, such program module 042 includes --- but being not limited to --- operating system, one or more application program, other
Program module and program data may include the realization of network environment in each or certain combination in these examples.Journey
Sequence module 042 usually performs function and/or method in embodiment described in the invention.
Computer system/server 012 can also with one or more external equipments 014 (such as keyboard, sensing equipment,
Display 024 etc.) communication, in the present invention, computer system/server 012 communicates with outside radar equipment, can also be with
One or more enables a user to the equipment interacted with the computer system/server 012 communication and/or with causing the meter
Any equipment that calculation machine systems/servers 012 can communicate with one or more of the other computing device (such as network interface card, modulation
Demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 022.Also, computer system/clothes
Being engaged in device 012 can also be by network adapter 020 and one or more network (such as LAN (LAN), wide area network (WAN)
And/or public network, such as internet) communication.As shown in the figure, network adapter 020 by bus 018 and computer system/
Other modules communication of server 012.It should be understood that although being not shown in Fig. 3, computer system/server 012 can be combined
Using other hardware and/or software module, including but not limited to:Microcode, device driver, redundant processing unit, external magnetic
Dish driving array, RAID system, tape drive and data backup storage system etc..
Processing unit 016 is stored in the program in system storage 028 by operation, described in the invention so as to perform
Function and/or method in embodiment.
Above-mentioned computer program can be set in computer storage media, i.e., the computer storage media is encoded with
Computer program, the program by one or more computers when being performed so that one or more computers are performed in the present invention
State the method flow shown in embodiment and/or device operation.
With time, the development of technology, medium meaning is more and more extensive, and the route of transmission of computer program is no longer limited by
Tangible medium, can also directly be downloaded from network etc..The arbitrary combination of one or more computer-readable media may be used.
Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer-readable storage medium
Matter for example may be-but not limited to-electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device or
The arbitrary above combination of person.The more specific example (non exhaustive list) of computer readable storage medium includes:There are one tools
Or the electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM),
Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light
Memory device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer readable storage medium can
To be any tangible medium for including or storing program, the program can be commanded execution system, device or device use or
Person is in connection.
Computer-readable signal media can include in a base band or as a carrier wave part propagation data-signal,
Wherein carry computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, which can send, propagate or
Transmission for by instruction execution system, device either device use or program in connection.
The program code included on computer-readable medium can be transmitted with any appropriate medium, including --- but it is unlimited
In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
It can write to perform the computer that operates of the present invention with one or more programming language or combinations
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully performs, partly perform on the user computer on the user computer, the software package independent as one performs, portion
Divide and partly perform or perform on a remote computer or server completely on the remote computer on the user computer.
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including LAN (LAN) or
Wide area network (WAN) be connected to subscriber computer or, it may be connected to outer computer (such as is provided using Internet service
Quotient passes through Internet connection).
Finally it should be noted that:Above example is only to illustrate the technical solution of the application, rather than its limitations;Although
The application is described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that:It still may be used
To modify to the technical solution recorded in foregoing embodiments or carry out equivalent replacement to which part technical characteristic;
And these modification or replace, each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (16)
1. a kind of robustness test method of unmanned vehicle vision-based detection, which is characterized in that including:
Obtain the original image for including detection target of unmanned vehicle acquisition;
Using the corresponding test parameter of scene to be tested, abnormality processing is carried out to the original image, builds scene pair to be tested
The test image answered;
Existed using the vision-based detection for the detection target in original image and test image as a result, obtaining unmanned vehicle vision-based detection
Robustness test result under the scene to be tested.
2. the according to the method described in claim 1, it is characterized in that, original for including detection target for obtaining unmanned vehicle acquisition
Beginning image includes:
When monitoring unmanned vehicle and detection target in preset distance range, then the filming apparatus started on unmanned vehicle is shot simultaneously
Storage includes the original image of detection target.
3. according to the method described in claim 1, it is characterized in that, the vision-based detection result includes:
Detect at least one of type, color and position of target.
4. according to the method described in claim 1, it is characterized in that, the scene to be tested includes bad weather scene;
Using the corresponding test parameter of scene to be tested, abnormality processing is carried out to the original image, builds scene pair to be tested
The test image answered includes:
The original image is carried out plus made an uproar according to meteorologic parameter, brightness processed, obtains the corresponding test chart of bad weather scene
Picture.
5. according to the method described in claim 1, it is characterized in that, the scene to be tested includes filming apparatus position moving field
Scape;
Using the corresponding test parameter of scene to be tested, abnormality processing is carried out to the original image, builds scene pair to be tested
The test image answered includes:
According to location information parameter of the filming apparatus in unmanned vehicle, mobile, scaling processing is carried out to the original image, is obtained
The corresponding test image of filming apparatus position mobile context.
6. according to the method described in claim 1, it is characterized in that, the scene to be tested includes filming apparatus angle moving field
Scape;
Using the corresponding test parameter of scene to be tested, abnormality processing is carried out to the original image, builds scene pair to be tested
The test image answered includes:
According to attitude information parameter of the filming apparatus in unmanned vehicle, mobile, rotation processing is carried out to described image, is shot
The corresponding test image of design factors mobile context.
It is 7. according to the method described in claim 1, it is characterized in that, described using for the inspection in original image and test image
The vision-based detection of target progress is surveyed as a result, obtaining the robustness test result packet of unmanned vehicle vision-based detection under the scene to be tested
It includes:
The vision-based detection result carried out for the detection target in original image and test image is compared, obtains unmanned vehicle
Error rate of the vision-based detection under scene to be tested.
8. a kind of robustness test system of unmanned vehicle vision-based detection, which is characterized in that including:
Original image acquisition module, for obtaining the original image for including detection target of unmanned vehicle acquisition;
For utilizing the corresponding test parameter of scene to be tested, abnormality processing is carried out to the original image for image processing module,
Build the corresponding test image of scene to be tested;
Vision-based detection module, for utilizing the vision-based detection for the detection target in original image and test image as a result, obtaining
To robustness test result of the unmanned vehicle vision-based detection under the scene to be tested.
9. system according to claim 8, which is characterized in that the original image acquisition module is specifically used for:
When monitoring unmanned vehicle and detection target in preset distance range, then the filming apparatus started on unmanned vehicle is shot simultaneously
Storage includes the original image of detection target.
10. system according to claim 8, which is characterized in that the vision-based detection result includes:
Detect at least one of type, color and position of target.
11. system according to claim 8, which is characterized in that the scene to be tested includes bad weather scene;
Described image processing module is specifically used for:
The original image is carried out plus made an uproar according to meteorologic parameter, brightness processed, obtains the corresponding test chart of bad weather scene
Picture.
12. system according to claim 8, which is characterized in that the scene to be tested is moved including filming apparatus position
Scene;
Described image processing module is specifically used for:
According to location information parameter of the filming apparatus in unmanned vehicle, mobile, scaling processing is carried out to the original image, is obtained
The corresponding test image of filming apparatus position mobile context.
13. system according to claim 8, which is characterized in that the scene to be tested is moved including filming apparatus angle
Scene;
Described image processing module is specifically used for:
According to attitude information parameter of the filming apparatus in unmanned vehicle, mobile, rotation processing is carried out to described image, is shot
The corresponding test image of design factors mobile context.
14. system according to claim 8, which is characterized in that the vision-based detection module is specifically used for:
The vision-based detection result carried out for the detection target in original image and test image is compared, obtains unmanned vehicle
Error rate of the vision-based detection under scene to be tested.
15. a kind of equipment, which is characterized in that the equipment includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processors are real
The now method as described in any in claim 1-7.
16. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The method as described in any in claim 1-7 is realized during execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711248427.3A CN108268831A (en) | 2017-12-01 | 2017-12-01 | The robustness test method and system of a kind of unmanned vehicle vision-based detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711248427.3A CN108268831A (en) | 2017-12-01 | 2017-12-01 | The robustness test method and system of a kind of unmanned vehicle vision-based detection |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108268831A true CN108268831A (en) | 2018-07-10 |
Family
ID=62771819
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711248427.3A Pending CN108268831A (en) | 2017-12-01 | 2017-12-01 | The robustness test method and system of a kind of unmanned vehicle vision-based detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108268831A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112200217A (en) * | 2020-09-09 | 2021-01-08 | 天津津航技术物理研究所 | Identification algorithm evaluation method and system based on infrared image big data |
CN112614372A (en) * | 2020-12-24 | 2021-04-06 | 奇瑞汽车股份有限公司 | Method and device for vehicle to safely pass through crossroad |
CN112699765A (en) * | 2020-12-25 | 2021-04-23 | 北京百度网讯科技有限公司 | Method and device for evaluating visual positioning algorithm, electronic equipment and storage medium |
CN112995656A (en) * | 2021-03-04 | 2021-06-18 | 黑芝麻智能科技(上海)有限公司 | Anomaly detection method and system for image processing circuit |
WO2022068468A1 (en) * | 2020-09-29 | 2022-04-07 | 京东科技信息技术有限公司 | Robot testing site and robot testing method |
CN115222610A (en) * | 2022-03-11 | 2022-10-21 | 广州汽车集团股份有限公司 | Image method, image device, electronic equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105954048A (en) * | 2016-07-07 | 2016-09-21 | 百度在线网络技术(北京)有限公司 | Method for testing normal driving of unmanned vehicle and device thereof |
CN106096192A (en) * | 2016-06-27 | 2016-11-09 | 百度在线网络技术(北京)有限公司 | The construction method of the test scene of a kind of automatic driving vehicle and device |
CN107330105A (en) * | 2017-07-07 | 2017-11-07 | 上海木爷机器人技术有限公司 | The robustness evaluating method and device of a kind of retrieving similar images algorithm |
-
2017
- 2017-12-01 CN CN201711248427.3A patent/CN108268831A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106096192A (en) * | 2016-06-27 | 2016-11-09 | 百度在线网络技术(北京)有限公司 | The construction method of the test scene of a kind of automatic driving vehicle and device |
CN105954048A (en) * | 2016-07-07 | 2016-09-21 | 百度在线网络技术(北京)有限公司 | Method for testing normal driving of unmanned vehicle and device thereof |
CN107330105A (en) * | 2017-07-07 | 2017-11-07 | 上海木爷机器人技术有限公司 | The robustness evaluating method and device of a kind of retrieving similar images algorithm |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112200217A (en) * | 2020-09-09 | 2021-01-08 | 天津津航技术物理研究所 | Identification algorithm evaluation method and system based on infrared image big data |
CN112200217B (en) * | 2020-09-09 | 2023-06-09 | 天津津航技术物理研究所 | Identification algorithm evaluation method and system based on infrared image big data |
WO2022068468A1 (en) * | 2020-09-29 | 2022-04-07 | 京东科技信息技术有限公司 | Robot testing site and robot testing method |
CN112614372A (en) * | 2020-12-24 | 2021-04-06 | 奇瑞汽车股份有限公司 | Method and device for vehicle to safely pass through crossroad |
CN112699765A (en) * | 2020-12-25 | 2021-04-23 | 北京百度网讯科技有限公司 | Method and device for evaluating visual positioning algorithm, electronic equipment and storage medium |
CN112995656A (en) * | 2021-03-04 | 2021-06-18 | 黑芝麻智能科技(上海)有限公司 | Anomaly detection method and system for image processing circuit |
CN115222610A (en) * | 2022-03-11 | 2022-10-21 | 广州汽车集团股份有限公司 | Image method, image device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108268831A (en) | The robustness test method and system of a kind of unmanned vehicle vision-based detection | |
CN107153363B (en) | Simulation test method, device, equipment and readable medium for unmanned vehicle | |
CN108318043A (en) | Method, apparatus for updating electronic map and computer readable storage medium | |
CN109931945B (en) | AR navigation method, device, equipment and storage medium | |
CN109345510A (en) | Object detecting method, device, equipment, storage medium and vehicle | |
CN109343061A (en) | Transducer calibration method, device, computer equipment, medium and vehicle | |
CN109345596A (en) | Multisensor scaling method, device, computer equipment, medium and vehicle | |
CN109101861A (en) | Obstacle identity recognition methods, device, equipment and storage medium | |
CN109271944A (en) | Obstacle detection method, device, electronic equipment, vehicle and storage medium | |
CN111856963B (en) | Parking simulation method and device based on vehicle-mounted looking-around system | |
CN109598066A (en) | Effect evaluation method, device, equipment and the storage medium of prediction module | |
CN109145680A (en) | A kind of method, apparatus, equipment and computer storage medium obtaining obstacle information | |
CN109116374A (en) | Determine the method, apparatus, equipment and storage medium of obstacle distance | |
CN107450088A (en) | A kind of location Based service LBS augmented reality localization method and device | |
CN109032103A (en) | Test method, device, equipment and the storage medium of automatic driving vehicle | |
CN109211575A (en) | Pilotless automobile and its field test method, apparatus and readable medium | |
CN108230437A (en) | Scene reconstruction method and device, electronic equipment, program and medium | |
CN109344804A (en) | A kind of recognition methods of laser point cloud data, device, equipment and medium | |
CN108399752A (en) | A kind of driving infractions pre-judging method, device, server and medium | |
CN106023622B (en) | A kind of method and apparatus of determining traffic lights identifying system recognition performance | |
CN109435955A (en) | A kind of automated driving system performance estimating method, device, equipment and storage medium | |
CN113535569B (en) | Control effect determination method for automatic driving | |
CN109961522A (en) | Image projecting method, device, equipment and storage medium | |
CN108876857A (en) | Localization method, system, equipment and the storage medium of automatic driving vehicle | |
CN110097121A (en) | A kind of classification method of driving trace, 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: 20180710 |
|
RJ01 | Rejection of invention patent application after publication |