CN115373327B - Traffic scene monitoring system and method applied to intelligent automobile - Google Patents
Traffic scene monitoring system and method applied to intelligent automobile Download PDFInfo
- Publication number
- CN115373327B CN115373327B CN202211309665.1A CN202211309665A CN115373327B CN 115373327 B CN115373327 B CN 115373327B CN 202211309665 A CN202211309665 A CN 202211309665A CN 115373327 B CN115373327 B CN 115373327B
- Authority
- CN
- China
- Prior art keywords
- real
- intelligent automobile
- value corresponding
- pixel point
- foreground picture
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012544 monitoring process Methods 0.000 title claims abstract description 33
- 230000007246 mechanism Effects 0.000 claims abstract description 48
- 238000001514 detection method Methods 0.000 claims abstract description 46
- 238000004458 analytical method Methods 0.000 claims abstract description 42
- 230000009471 action Effects 0.000 claims abstract description 10
- 238000010276 construction Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000002372 labelling Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000012946 outsourcing Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241001506766 Xanthium Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0428—Safety, monitoring
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24024—Safety, surveillance
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a traffic scene monitoring system applied to an intelligent automobile, which comprises: the electronic auxiliary mechanism is arranged in the intelligent automobile and used for switching from an automatic driving mode to a non-automatic driving mode when receiving a scene complex detection signal based on driving foreground picture analysis; the state detection mechanism is used for sending an acquisition starting command when the intelligent automobile runs; and the foreground acquisition mechanism is used for starting the driving foreground picture acquisition action when receiving the acquisition starting command. The invention also relates to a traffic scene monitoring method applied to the intelligent automobile. The traffic scene monitoring system and the method applied to the intelligent automobile are convenient to control and stable to operate. The dangerous scene can be preliminarily and normally identified by adopting a targeted numerical analysis mechanism, and meanwhile, the original manual judgment mechanism is kept and a numerical analysis trigger mode based on whether the intelligent automobile is started or not is established, so that the overall performance of the intelligent automobile is effectively maintained.
Description
Technical Field
The invention relates to the field of intelligent automobiles, in particular to a traffic scene monitoring system and method applied to an intelligent automobile.
Background
The intelligent vehicle is a comprehensive system integrating functions of environmental perception, planning decision, multi-level auxiliary driving and the like, intensively applies technologies such as computer, modern sensing, information fusion, communication, artificial intelligence, automatic control and the like, and is a typical high and new technology complex. Research on intelligent vehicles is mainly focused on improving the safety and comfort of automobiles and providing excellent human-vehicle interaction interfaces. In recent years, intelligent vehicles have become hot spots for the research in the field of vehicle engineering in the world and new power for the growth of the automobile industry, and many developed countries incorporate the intelligent vehicles into intelligent transportation systems which are intensively developed.
However, it is confusing for developers of smart vehicles to determine a safety scenario of the auto-driving mode application, in other words, to determine a dangerous scenario of exiting the auto-driving mode application, and if this problem is not solved accurately and properly, the auto-driving function of the smart vehicle becomes a cocklebur.
In the prior art:
for example, patent application publication No. CN114880283A discloses a method, an apparatus, a device and a storage medium for constructing an automatic driving scene library, wherein the method includes: acquiring an automatic driving scene construction file set, and determining current automatic driving scene information according to the automatic driving scene construction file set, wherein the current automatic driving scene information comprises the types of a current constructable automatic driving scene library and scene type data corresponding to the types; determining a required outsourcing scene data set according to the automatic driving scene library requirement and the current automatic driving scene information; acquiring the required outsourcing scene data set; and constructing a corresponding automatic driving scene library according to the outsourcing scene data set and the automatic driving scene construction file set. According to the method, the virtual scene can be constructed through massive automatic driving scene library data, then, the automatic driving system is comprehensively and strictly tested and verified, and the problem that the construction method of the automatic driving virtual scene is lacked in the prior art is solved.
The application publication No. CN114741787A discloses a scene data acquisition and automatic labeling method, system and storage medium for high-level automatic driving simulation test, and the application labels the scene through a labeling model and a deep learning model and acquires corresponding scene data, so that automatic labeling of the automatic driving scene can be realized, the acquisition efficiency of the intelligent driving auxiliary scene is improved, and the acquisition precision of the intelligent driving auxiliary scene is enhanced; moreover, by cleaning the data, the method is convenient for screening and counting scenes and beneficial to developing automatic driving simulation test scenes; the method solves the problems that the existing manual automatic driving scene labeling method is low in efficiency and difficult in data quality guarantee.
Patent application publication No. CN114579748A discloses a method for constructing an autonomous traffic system functional architecture. The method comprises the following steps: constructing an optimized density peak value clustering model facing to the multi-attribute text; improving a word frequency and reverse document frequency calculation formula; calculating the space dimension coordinates of the multi-attribute text by applying a text vector space model; optimizing a density peak value clustering algorithm by a Gaussian function and a decision value; evaluating a clustering result by using the contour coefficient; and dividing the functions of the autonomous traffic system under the road automatic driving scene into 4 layers of autonomous perception, autonomous learning, autonomous decision and autonomous response according to the clustering result, drawing a functional architecture diagram, and supporting service realization. The application provides reference for the construction of the autonomous traffic system functional architecture, promotes the construction of a new generation of traffic system functional architecture, and promotes the development of the autonomous traffic system theoretical system.
However, how to determine the dangerous scene exiting from the automatic driving mode application is difficult because the traffic environment of the intelligent vehicle is complex, and it is difficult to obtain a normalized processing mode to realize the initial judgment of various dangerous scenes.
Disclosure of Invention
In order to solve the problems, the invention provides a traffic scene monitoring system and a traffic scene monitoring method applied to an intelligent automobile, which can adopt a targeted numerical analysis mechanism to carry out preliminary normalized identification on a dangerous scene needing to exit an automatic driving mode application, and simultaneously keep the original manual judgment mechanism and establish a numerical analysis trigger mode based on whether the intelligent automobile is started or not, thereby ensuring the safety of the intelligent automobile and improving the energy saving performance of the intelligent automobile.
According to an aspect of the present invention, there is provided a traffic scene monitoring system applied to an intelligent automobile, the system including:
the electronic auxiliary mechanism is arranged in the intelligent automobile and used for switching from a non-automatic driving mode to an automatic driving mode when receiving a scene simple detection signal and switching from the automatic driving mode to the non-automatic driving mode when receiving a scene complex detection signal;
the state detection mechanism is used for sending a collection starting command when the real-time rotating speed of an output main shaft of a motor of the intelligent automobile is greater than or equal to a set rotating speed threshold value;
the foreground acquisition mechanism is arranged at the front end of the intelligent automobile, connected with the state detection mechanism and used for starting the acquisition action of the foreground picture of the intelligent automobile to acquire the corresponding real-time foreground picture when receiving an acquisition starting command;
the first analysis component is connected with the foreground acquisition mechanism and is used for acquiring each depth of field value corresponding to each pixel point in the central area of the real-time foreground picture and each pixel value corresponding to each pixel point in the central area of the real-time foreground picture;
the second analysis component is connected with the first analysis component and is used for sending a scene complexity detection signal when a certain sub-picture exists in the central area of the real-time foreground picture, the mean square deviation of each depth of field value corresponding to each pixel point of the certain sub-picture is less than or equal to a set mean square deviation limit and the repeatability of each pixel value corresponding to each pixel point of the certain sub-picture is less than or equal to a set repeatability threshold;
the second analysis component is further configured to send a scene simple detection signal when a certain sprite does not exist in the central region of the real-time foreground picture, the mean square deviation of each depth of field value corresponding to each pixel point of the certain sprite is less than or equal to a set mean square deviation limit, and the repetition degree of each pixel value corresponding to each pixel point of the certain sprite is less than or equal to a set repetition degree threshold.
According to another aspect of the present invention, there is also provided a traffic scene monitoring method applied to an intelligent automobile, the method including:
the method comprises the steps that an electronic auxiliary mechanism is used, is arranged in the intelligent automobile and is used for switching from a non-automatic driving mode to an automatic driving mode when a scene simple detection signal is received and switching from the automatic driving mode to the non-automatic driving mode when a scene complex detection signal is received;
the using state detection mechanism is used for sending a collecting and starting command when the real-time rotating speed of an output main shaft of a motor of the intelligent automobile is greater than or equal to a set rotating speed threshold value;
the using foreground acquisition mechanism is arranged at the front end of the intelligent automobile, connected with the state detection mechanism and used for starting the acquisition action of the foreground picture of the intelligent automobile to acquire the corresponding real-time foreground picture when receiving an acquisition starting command;
using a first analysis component connected with the foreground acquisition mechanism and used for acquiring each depth of field value corresponding to each pixel point in the central area of the real-time foreground picture and each pixel value corresponding to each pixel point in the central area of the real-time foreground picture;
using a second analysis component, connected to the first analysis component, for generating a scene complexity detection signal when a certain sub-picture exists in the central region of the real-time foreground picture, and the mean square deviation of each depth of field value corresponding to each pixel point of the certain sub-picture is less than or equal to a set mean square deviation limit and the repetition degree of each pixel value corresponding to each pixel point of the certain sub-picture is less than or equal to a set repetition degree threshold;
the second analysis component is further configured to send a scene simple detection signal when a certain sprite does not exist in the central region of the real-time foreground picture, the mean square deviation of each depth of field value corresponding to each pixel point of the certain sprite is less than or equal to a set mean square deviation limit, and the repetition degree of each pixel value corresponding to each pixel point of the certain sprite is less than or equal to a set repetition degree threshold.
The traffic scene monitoring system and method applied to the intelligent automobile are convenient to operate and control and stable in operation. The dangerous scene can be preliminarily and normally identified by adopting a targeted numerical analysis mechanism, and meanwhile, the original manual judgment mechanism is kept and a numerical analysis trigger mode based on whether the intelligent automobile is started or not is established, so that the overall performance of the intelligent automobile is effectively maintained.
Drawings
Embodiments of the invention will now be described with reference to the accompanying drawings, in which:
fig. 1 is a block diagram illustrating a traffic scene monitoring system applied to an intelligent vehicle according to an embodiment a of the present invention.
Fig. 2 is a flowchart illustrating steps of a traffic scene monitoring method applied to an intelligent automobile according to embodiment B of the present invention.
Detailed Description
Embodiments of a traffic scene monitoring system and method applied to an intelligent vehicle according to the present invention will be described in detail with reference to the accompanying drawings.
Example A
Fig. 1 is a block diagram illustrating a structure of a traffic scene monitoring system applied to an intelligent vehicle according to an embodiment a of the present invention, where the system includes:
the electronic auxiliary mechanism is arranged in the intelligent automobile and used for switching from a non-automatic driving mode to an automatic driving mode when receiving a scene simple detection signal and switching from the automatic driving mode to the non-automatic driving mode when receiving a scene complex detection signal;
the state detection mechanism is used for sending a collection starting command when the real-time rotating speed of an output main shaft of a motor of the intelligent automobile is greater than or equal to a set rotating speed threshold value;
the foreground acquisition mechanism is arranged at the front end of the intelligent automobile, connected with the state detection mechanism and used for starting the acquisition action of the foreground picture of the intelligent automobile to acquire the corresponding real-time foreground picture when receiving an acquisition starting command;
the first analysis component is connected with the foreground acquisition mechanism and is used for acquiring each depth of field value corresponding to each pixel point in the central area of the real-time foreground picture and each pixel value corresponding to each pixel point in the central area of the real-time foreground picture;
the second analysis component is connected with the first analysis component and is used for sending a scene complexity detection signal when a certain sub-picture exists in the central area of the real-time foreground picture, the mean square deviation of each depth of field value corresponding to each pixel point of the certain sub-picture is less than or equal to a set mean square deviation limit and the repeatability of each pixel value corresponding to each pixel point of the certain sub-picture is less than or equal to a set repeatability threshold;
the second analysis component is further configured to send a scene simple detection signal when a certain sprite does not exist in the central region of the real-time foreground picture, the mean square deviation of each depth of field value corresponding to each pixel point of the certain sprite is less than or equal to a set mean square deviation limit, and the repetition degree of each pixel value corresponding to each pixel point of the certain sprite is less than or equal to a set repetition degree threshold;
illustratively, the first analysis component and the second analysis component may be implemented using FPGA devices, CPLD devices, or PLD devices;
and realizing the model selection operation of the specific device type of the FPGA device, the CPLD device or the PLD device according to the maximum operand requirements of the first analysis component and the second analysis component.
Next, a detailed description will be given of a specific structure of the traffic scene monitoring system applied to the intelligent automobile according to the present invention.
The traffic scene monitoring system applied to the intelligent automobile can further comprise:
the manual control component is arranged in the intelligent automobile and used for realizing the switching from the non-automatic driving mode to the automatic driving mode and the switching from the automatic driving mode to the non-automatic driving mode of the intelligent automobile under the manual control;
wherein the priority of mode switching of the manual control part is greater than the priority of mode switching of the electronic assisting mechanism.
In the traffic scene monitoring system applied to the intelligent automobile:
when a certain sprite exists in the central region of the real-time foreground picture, the mean square error of each depth of field value corresponding to each pixel point of the certain sprite is less than or equal to a set mean square error limit, and the repeatability of each pixel value corresponding to each pixel point of the certain sprite is less than or equal to a set repeatability threshold, sending a scene complexity detection signal comprises: each pixel value corresponding to each pixel point of the certain sprite is each color channel value corresponding to each pixel point of the certain sprite;
wherein, when a certain sprite exists in the central region of the real-time foreground picture, the mean square error of each depth of field value corresponding to each pixel point of the certain sprite is less than or equal to a set mean square error limit, and the repetition degree of each pixel value corresponding to each pixel point of the certain sprite is less than or equal to a set repetition degree threshold, the sending the scene complexity detection signal further comprises: for each pixel value corresponding to each pixel point of the certain sprite, the more the pixel values with repeated numerical values are, the greater the repetition degree of each pixel value corresponding to each pixel point of the certain sprite is;
wherein, each pixel value corresponding to each pixel point of the certain sprite respectively is each color channel value corresponding to each pixel point of the certain sprite respectively, and includes: the color channel is at least one of a red-green channel, a black-white channel and a yellow-blue channel;
wherein, each pixel value corresponding to each pixel point of the certain sprite is each color channel value corresponding to each pixel point of the certain sprite, and the method further comprises: the red green channel, the black and white channel, and the yellow and blue channel are under the LAB space.
And in the traffic scene monitoring system applied to the intelligent automobile:
acquiring each depth of field value corresponding to each pixel point in the central area of the real-time foreground picture and each pixel value corresponding to each pixel point in the central area of the real-time foreground picture respectively comprises: the central area of the real-time foreground picture is an image block which is at the central position of the real-time foreground picture and occupies a preset proportional numerical value of the area of the real-time foreground picture;
the image block, in which the central area of the real-time foreground picture is the central position of the real-time foreground picture and occupies a preset proportional value of the area of the real-time foreground picture, includes: the value of the preset proportion value is between one third and one half;
and the state detection mechanism is also used for sending out a collection pause command when the real-time rotating speed of the output main shaft of the motor of the intelligent automobile is less than the set rotating speed threshold value.
Example B
Fig. 2 is a flowchart illustrating steps of a traffic scene monitoring method applied to an intelligent automobile according to embodiment B of the present invention, where the method includes:
the method comprises the steps that an electronic auxiliary mechanism is arranged in the intelligent automobile and used for switching from a non-automatic driving mode to an automatic driving mode when a scene simple detection signal is received and switching from the automatic driving mode to the non-automatic driving mode when a scene complex detection signal is received;
the using state detection mechanism is used for sending a collecting and starting command when the real-time rotating speed of an output main shaft of a motor of the intelligent automobile is greater than or equal to a set rotating speed threshold value;
the using foreground acquisition mechanism is arranged at the front end of the intelligent automobile, connected with the state detection mechanism and used for starting the acquisition action of the foreground picture of the intelligent automobile to acquire the corresponding real-time foreground picture when receiving an acquisition starting command;
using a first analysis component connected with the foreground acquisition mechanism and used for acquiring each depth of field value corresponding to each pixel point in the central area of the real-time foreground picture and each pixel value corresponding to each pixel point in the central area of the real-time foreground picture;
using a second analysis component, connected to the first analysis component, for generating a scene complexity detection signal when a certain sub-picture exists in the central region of the real-time foreground picture, and the mean square deviation of each depth of field value corresponding to each pixel point of the certain sub-picture is less than or equal to a set mean square deviation limit and the repetition degree of each pixel value corresponding to each pixel point of the certain sub-picture is less than or equal to a set repetition degree threshold;
the second analysis component is further configured to send a scene simple detection signal when a certain sprite does not exist in the central region of the real-time foreground picture, the mean square deviation of each depth of field value corresponding to each pixel point of the certain sprite is less than or equal to a set mean square deviation limit, and the repetition degree of each pixel value corresponding to each pixel point of the certain sprite is less than or equal to a set repetition degree threshold;
illustratively, the first analysis component and the second analysis component may be implemented using an FPGA device, a CPLD device, or a PLD device;
and realizing the model selection operation of the specific device type of the FPGA device, the CPLD device or the PLD device according to the maximum operand requirements of the first analysis component and the second analysis component.
Next, the following further description is made on specific steps of the traffic scene monitoring method applied to the intelligent automobile.
The traffic scene monitoring method applied to the intelligent automobile can further comprise the following steps:
the intelligent automobile automatic control system comprises a manual control component, a control component and a control component, wherein the manual control component is arranged in the intelligent automobile and used for realizing the switching from a non-automatic driving mode to an automatic driving mode and the switching from the automatic driving mode to the non-automatic driving mode of the intelligent automobile under manual control;
wherein the priority of mode switching of the manual control part is greater than the priority of mode switching of the electronic assisting mechanism.
In the traffic scene monitoring method applied to the intelligent automobile:
when a certain sprite exists in the central region of the real-time foreground picture, the mean square error of each depth of field value corresponding to each pixel point of the certain sprite is less than or equal to a set mean square error limit, and the repeatability of each pixel value corresponding to each pixel point of the certain sprite is less than or equal to a set repeatability threshold, sending a scene complexity detection signal comprises: each pixel value corresponding to each pixel point of the certain sprite is each color channel value corresponding to each pixel point of the certain sprite;
wherein, when a certain sprite exists in the central region of the real-time foreground picture, the mean square error of each depth of field value corresponding to each pixel point of the certain sprite is less than or equal to a set mean square error limit, and the repetition degree of each pixel value corresponding to each pixel point of the certain sprite is less than or equal to a set repetition degree threshold, the sending the scene complexity detection signal further comprises: for each pixel value corresponding to each pixel point of the certain sprite, the more the pixel values with repeated numerical values are, the greater the repetition degree of each pixel value corresponding to each pixel point of the certain sprite is;
wherein, each pixel value corresponding to each pixel point of the certain sprite respectively is each color channel value corresponding to each pixel point of the certain sprite respectively, and includes: the color channel is at least one of a red-green channel, a black-white channel and a yellow-blue channel;
wherein, each pixel value corresponding to each pixel point of the certain sprite is each color channel value corresponding to each pixel point of the certain sprite, and the method further comprises: the red green channel, the black and white channel, and the yellow blue channel are under the LAB space.
And in the traffic scene monitoring method applied to the intelligent automobile:
acquiring each depth of field value corresponding to each pixel point in the central area of the real-time foreground picture and each pixel value corresponding to each pixel point in the central area of the real-time foreground picture respectively comprises: the central area of the real-time foreground picture is an image block which is at the central position of the real-time foreground picture and occupies a preset proportional numerical value of the area of the real-time foreground picture;
the image block of which the central area is the central position of the real-time foreground picture and occupies a preset proportional value of the area of the real-time foreground picture comprises the following steps: the value of the preset proportion value is between one third and one half;
and the state detection mechanism is also used for sending out a collection pause command when the real-time rotating speed of the output main shaft of the motor of the intelligent automobile is less than the set rotating speed threshold value.
In addition, in the traffic scene monitoring system and method applied to the smart car, a layer-by-layer sharpening component may be further included, the layer-by-layer sharpening component is disposed between the foreground acquisition mechanism and the first analysis component, and is configured to perform layer-by-layer sharpening processing of edge sharpening, contrast enhancement, and impulse noise elimination on the received real-time foreground picture, the layer-by-layer sharpening component includes a first processing unit, a second processing unit, and a third processing unit, and is configured to perform edge sharpening, contrast enhancement, and impulse noise elimination, respectively, and the layer-by-layer sharpening component is further configured to replace the real-time foreground picture with the real-time foreground picture that is subjected to the layer-by-layer sharpening processing, and send the real-time foreground picture to the first analysis component.
According to the embodiment, the invention has the following technical effects:
the method comprises the steps that firstly, customized analysis is carried out on a central area in an imaging picture of a driving foreground of the intelligent automobile, so that when a sub-picture with small depth-of-field value difference and large content complexity of each pixel point exists, a complex scene in front of the intelligent automobile is judged, and an automatic driving mode is automatically exited to reduce potential safety hazards;
secondly, specifically, when a certain sub-picture exists in the central area of an imaging picture of a driving foreground of the intelligent automobile, the mean square deviation of each depth of field value corresponding to each pixel point of the certain sub-picture is less than or equal to a set mean square deviation limit, and the repetition degree of each pixel value corresponding to each pixel point of the certain sub-picture is less than or equal to a set repetition degree threshold, judging that a complex scene appears in front of the intelligent automobile;
and thirdly, only when the real-time rotating speed of the output main shaft of the motor of the intelligent automobile is larger than or equal to the set rotating speed threshold value, the imaging of the driving prospect of the intelligent automobile is triggered, and therefore the energy-saving performance of the intelligent automobile is improved.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (8)
1. A traffic scene monitoring system applied to an intelligent automobile is characterized by comprising:
the electronic auxiliary mechanism is arranged in the intelligent automobile and used for switching from a non-automatic driving mode to an automatic driving mode when receiving a scene simple detection signal and switching from the automatic driving mode to the non-automatic driving mode when receiving a scene complex detection signal;
the state detection mechanism is used for sending a collection starting command when the real-time rotating speed of an output main shaft of a motor of the intelligent automobile is greater than or equal to a set rotating speed threshold value;
the foreground acquisition mechanism is arranged at the front end of the intelligent automobile, connected with the state detection mechanism and used for starting an acquisition action of a foreground picture of the intelligent automobile to acquire a corresponding real-time foreground picture when receiving an acquisition starting command;
the first analysis component is connected with the foreground acquisition mechanism and is used for acquiring each depth of field value corresponding to each pixel point in the central area of the real-time foreground picture and each pixel value corresponding to each pixel point in the central area of the real-time foreground picture;
the second analysis component is connected with the first analysis component and is used for sending a scene complexity detection signal when a certain sub-picture exists in the central area of the real-time foreground picture, the mean square deviation of each depth value corresponding to each pixel point of the certain sub-picture is less than or equal to a set mean square deviation limit and the repetition degree of each pixel value corresponding to each pixel point of the certain sub-picture is less than or equal to a set repetition degree threshold;
wherein, each pixel value corresponding to each pixel point of the certain sprite is each color channel value corresponding to each pixel point of the certain sprite, and the color channel is at least one of a red-green channel, a black-white channel and a yellow-blue channel, and the red-green channel, the black-white channel and the yellow-blue channel are in an LAB space;
for each pixel value corresponding to each pixel point of the certain sprite, the more the pixel values with repeated numerical values, the greater the repetition degree of each pixel value corresponding to each pixel point of the certain sprite;
the second analysis component is further configured to send a scene simple detection signal when a certain sprite does not exist in the central region of the real-time foreground picture, the mean square deviation of each depth of field value corresponding to each pixel point of the certain sprite is less than or equal to a set mean square deviation limit, and the repetition degree of each pixel value corresponding to each pixel point of the certain sprite is less than or equal to a set repetition degree threshold.
2. The traffic scene monitoring system applied to the intelligent automobile according to claim 1, wherein the system further comprises:
the manual control component is arranged in the intelligent automobile and used for realizing the switching from the non-automatic driving mode to the automatic driving mode and the switching from the automatic driving mode to the non-automatic driving mode of the intelligent automobile under manual control;
wherein the priority of mode switching of the manual control part is greater than the priority of mode switching of the electronic assisting mechanism.
3. The traffic scene monitoring system applied to the intelligent automobile according to any one of claims 1-2, characterized in that:
acquiring each depth of field value corresponding to each pixel point in the central area of the real-time foreground picture and each pixel value corresponding to each pixel point in the central area of the real-time foreground picture respectively comprises: the central area of the real-time foreground picture is an image block which is located in the center of the real-time foreground picture and occupies a preset proportional value of the area of the real-time foreground picture.
4. The traffic scene monitoring system applied to the intelligent automobile according to claim 3, wherein:
the image block, in which the central area of the real-time foreground picture is the central position of the real-time foreground picture and occupies a preset proportional value of the area of the real-time foreground picture, includes: the value of the preset proportion value is between one third and one half;
and the state detection mechanism is also used for sending out a collection pause command when the real-time rotating speed of the output spindle of the motor of the intelligent automobile is less than the set rotating speed threshold value.
5. A traffic scene monitoring method applied to an intelligent automobile is characterized by comprising the following steps:
the method comprises the steps that an electronic auxiliary mechanism is used, is arranged in the intelligent automobile and is used for switching from a non-automatic driving mode to an automatic driving mode when a scene simple detection signal is received and switching from the automatic driving mode to the non-automatic driving mode when a scene complex detection signal is received;
the using state detection mechanism is used for sending a collecting and starting command when the real-time rotating speed of an output main shaft of a motor of the intelligent automobile is greater than or equal to a set rotating speed threshold value;
the using foreground acquisition mechanism is arranged at the front end of the intelligent automobile, connected with the state detection mechanism and used for starting an acquisition action of a foreground picture of the intelligent automobile to acquire a corresponding real-time foreground picture when receiving an acquisition starting command;
using a first analysis component connected with the foreground acquisition mechanism for acquiring each depth of field value corresponding to each pixel point in the central area of the real-time foreground picture and each pixel value corresponding to each pixel point in the central area of the real-time foreground picture;
using a second analysis component, connected to the first analysis component, for generating a scene complexity detection signal when a certain sub-picture exists in the central region of the real-time foreground picture, and the mean square deviation of each depth of field value corresponding to each pixel point of the certain sub-picture is less than or equal to a set mean square deviation limit and the repetition degree of each pixel value corresponding to each pixel point of the certain sub-picture is less than or equal to a set repetition degree threshold;
wherein, each pixel value corresponding to each pixel point of the certain sprite is each color channel value corresponding to each pixel point of the certain sprite, and the color channel is at least one of a red-green channel, a black-white channel and a yellow-blue channel, and the red-green channel, the black-white channel and the yellow-blue channel are in an LAB space;
for each pixel value corresponding to each pixel point of the certain sprite, the more the pixel values with repeated numerical values are, the greater the repetition degree of each pixel value corresponding to each pixel point of the certain sprite is;
the second analysis component is further configured to send a scene simple detection signal when a certain sprite does not exist in the central region of the real-time foreground picture, the mean square deviation of each depth of field value corresponding to each pixel point of the certain sprite is less than or equal to a set mean square deviation limit, and the repetition degree of each pixel value corresponding to each pixel point of the certain sprite is less than or equal to a set repetition degree threshold.
6. The traffic scene monitoring method applied to the intelligent automobile according to claim 5, characterized in that the method further comprises:
the automatic control system comprises a manual control component, a control component and a control component, wherein the manual control component is arranged in the intelligent automobile and used for realizing the switching from a non-automatic driving mode to an automatic driving mode and the switching from the automatic driving mode to the non-automatic driving mode of the intelligent automobile under the manual control;
wherein the priority of mode switching of the manual control part is greater than the priority of mode switching of the electronic assisting mechanism.
7. The traffic scene monitoring method applied to the intelligent automobile according to any one of claims 5 to 6, characterized in that:
acquiring each depth of field value corresponding to each pixel point in the central area of the real-time foreground picture and each pixel value corresponding to each pixel point in the central area of the real-time foreground picture respectively comprises: and the central area of the real-time foreground picture is an image block which is at the central position of the real-time foreground picture and occupies a preset proportional numerical value of the area of the real-time foreground picture.
8. The traffic scene monitoring method applied to the intelligent automobile according to claim 7, wherein:
the image block of which the central area is the central position of the real-time foreground picture and occupies a preset proportional value of the area of the real-time foreground picture comprises the following steps: the value of the preset proportion value is between one third and one half;
and the state detection mechanism is also used for sending out a collection pause command when the real-time rotating speed of the output main shaft of the motor of the intelligent automobile is less than the set rotating speed threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211309665.1A CN115373327B (en) | 2022-10-25 | 2022-10-25 | Traffic scene monitoring system and method applied to intelligent automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211309665.1A CN115373327B (en) | 2022-10-25 | 2022-10-25 | Traffic scene monitoring system and method applied to intelligent automobile |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115373327A CN115373327A (en) | 2022-11-22 |
| CN115373327B true CN115373327B (en) | 2022-12-27 |
Family
ID=84074341
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211309665.1A Active CN115373327B (en) | 2022-10-25 | 2022-10-25 | Traffic scene monitoring system and method applied to intelligent automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115373327B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118411310A (en) * | 2024-05-23 | 2024-07-30 | 南京昊红樱智能科技有限公司 | Image quality enhancement system for autopilot |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160135069A (en) * | 2015-05-15 | 2016-11-24 | 주식회사 한글과컴퓨터 | Artificial intelligence autonomous smart car and method for operating thereof |
| WO2020181421A1 (en) * | 2019-03-08 | 2020-09-17 | SZ DJI Technology Co., Ltd. | Techniques for switching between manual and autonomous control for a movable object |
| CN110435672A (en) * | 2019-08-11 | 2019-11-12 | 西藏宁算科技集团有限公司 | One kind is based on scene anticipation safe driving householder method and its system |
| CN210042007U (en) * | 2019-09-10 | 2020-02-07 | 浙江晶鲸科技有限公司 | Image acquisition device suitable for automatic driving distance measurement |
| CN110884500A (en) * | 2019-10-31 | 2020-03-17 | 苏州智加科技有限公司 | Method and device for controlling vehicle, electronic equipment and storage medium |
| CN113120002A (en) * | 2021-05-07 | 2021-07-16 | 宝能(广州)汽车研究院有限公司 | Automatic driving permission method, device, electronic equipment and storage medium |
| CN113851000A (en) * | 2021-09-10 | 2021-12-28 | 泰州蝶金软件有限公司 | Command analysis system based on cloud computing |
| CN113807306A (en) * | 2021-09-28 | 2021-12-17 | 江苏泰扬金属制品有限公司 | Information analysis system using cloud service |
| CN113869224B (en) * | 2021-09-29 | 2022-04-26 | 深圳市康士达科技有限公司 | Driving assistance system based on target judgment |
-
2022
- 2022-10-25 CN CN202211309665.1A patent/CN115373327B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115373327A (en) | 2022-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Al-Kharusi et al. | Intelligent parking management system based on image processing | |
| CN101443789B (en) | video segmentation using statistical pixel modeling | |
| CN113343461A (en) | Simulation method and device for automatic driving vehicle, electronic equipment and storage medium | |
| US10717442B2 (en) | Method and apparatus for determining a presently existing driving situation | |
| CN109993138A (en) | A kind of car plate detection and recognition methods and device | |
| CN115373327B (en) | Traffic scene monitoring system and method applied to intelligent automobile | |
| CN113642474A (en) | Hazardous area personnel monitoring method based on YOLOV5 | |
| Mohandes et al. | Preference‐based smart parking system in a university campus | |
| CN111295666A (en) | Lane line detection method, device, control equipment and storage medium | |
| CN111182503A (en) | Intelligent vehicle insurance evaluation method and system based on multi-data fusion analysis | |
| CN116071557A (en) | Long tail target detection method, computer readable storage medium and driving device | |
| CN113297939A (en) | Obstacle detection method, system, terminal device and storage medium | |
| CN111507269B (en) | Parking space state identification method and device, storage medium and electronic device | |
| CN112509321A (en) | Unmanned aerial vehicle-based driving control method and system for urban complex traffic situation and readable storage medium | |
| CN113837222A (en) | Cloud-edge cooperative machine learning deployment application method and device for millimeter wave radar intersection traffic monitoring system | |
| CN111860048A (en) | Intelligent road information analysis method | |
| CN112215042A (en) | Parking space limiter identification method and system and computer equipment | |
| CN112598007B (en) | Method, device and equipment for screening picture training set and readable storage medium | |
| CN116563801A (en) | Traffic accident detection method, device, electronic equipment and medium | |
| CN109977844A (en) | One kind giving precedence to pedestrian's control system and control method based on image recognition motor vehicle | |
| KR20230104592A (en) | Method and system for annotating sensor data | |
| CN114998889A (en) | Intelligent identification method and system for immersive three-dimensional image | |
| CN114419586A (en) | Fine-grained road area identification method, scene switching control method and device | |
| CN114627400A (en) | Lane congestion detection method and device, electronic equipment and storage medium | |
| CN112644559B (en) | Method, apparatus, device and medium for determining display state of track section |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |