CN113205704A - Blind area detection method and device for large vehicle and storage medium - Google Patents
Blind area detection method and device for large vehicle and storage medium Download PDFInfo
- Publication number
- CN113205704A CN113205704A CN202110296657.7A CN202110296657A CN113205704A CN 113205704 A CN113205704 A CN 113205704A CN 202110296657 A CN202110296657 A CN 202110296657A CN 113205704 A CN113205704 A CN 113205704A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- warning
- warning line
- target
- line
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
Abstract
The invention discloses a blind area detection method for a large vehicle, which comprises the following steps: firstly, a camera is installed on a vehicle body at the side of a vehicle, and meanwhile, a first warning line is set at a position which is away from the vehicle body at the side of the vehicle by a corresponding distance, and a second warning line is set at a position which is away from the vehicle body in front of the vehicle by a corresponding distance; then when the vehicle stops, determining an early warning trigger condition according to the first warning line, the second warning line and the image shot by the camera; and in the running process of the vehicle, acquiring images shot by the camera in real time, judging whether to trigger early warning according to the images shot by the camera and the early warning triggering condition, and sending early warning prompt to a driver when the early warning is triggered. The invention solves the problems of high equipment cost, inconvenient installation and the like of vehicle blind area detection in the prior art. The invention also discloses a blind area detection device and a storage medium for the large-scale vehicle.
Description
Technical Field
The present invention relates to vehicle blind area detection, and more particularly, to a method and apparatus for detecting a blind area of a large vehicle, and a storage medium.
Background
To the blind area detection of vehicle among the prior art, generally adopt the mode of camera and millimeter wave radar to improve the early warning of vehicle distance, but this kind of mode needs additionally to install a plurality of sensors and realizes the detection etc. of vehicle distance, and its equipment cost is higher, simultaneously, still need do calibration to camera, millimeter wave radar equipment, and the installation is complicated.
Disclosure of Invention
In order to overcome the defects of the prior art, one of the objectives of the present invention is to provide a method for detecting a blind area of a large vehicle, which can solve the problems of high equipment cost, inconvenient equipment installation, etc. in the prior art for detecting the blind area of the vehicle.
The invention also aims to provide a blind area detection device for a large vehicle, which can solve the problems of high equipment cost, inconvenience in equipment installation and the like of vehicle blind area detection in the prior art.
The invention further aims to provide a storage medium which can solve the problems of high equipment cost, inconvenience in equipment installation and the like of vehicle blind area detection in the prior art.
One of the purposes of the invention is realized by adopting the following technical scheme:
a blind area detection method for a large vehicle, comprising:
setting: the method comprises the following steps that a camera is installed on a vehicle body at the side of a vehicle, a first warning line is set at a position which is away from the vehicle body at the side of the vehicle by a corresponding distance, and a second warning line is set at a position which is away from the vehicle body in front of the vehicle by a corresponding distance; when the camera is mounted on a vehicle body at the side of the vehicle, the optical axis of a lens of the camera is parallel to the ground and is parallel to the side face of the vehicle body;
a calibration step: when the vehicle stops, determining an early warning triggering condition according to the first warning line, the second warning line and the image shot by the camera;
a detection step: in the running process of the vehicle, acquiring an image shot by a camera in real time, and judging whether to trigger early warning according to the image shot by the camera and the early warning triggering condition;
a reminding step: and when the early warning is triggered, sending early warning reminding to the driver.
Further, the first warning lines comprise first one-meter warning lines, first two-meter warning lines and first three-meter warning lines; the distance between the first one-meter warning line and the vehicle body on the side of the vehicle is 1 meter, the distance between the first two-meter warning line and the vehicle body on the side of the vehicle is 2 meters, and the distance between the first three-meter warning line and the vehicle body on the side of the vehicle is 3 meters; the second guard line is 3 meters from the body in front of the vehicle.
Further, the calibrating step includes:
setting a calibration point: setting at least two calibration points on the first warning line and setting at least two calibration points on the second warning line;
a function determination step: determining a first warning line early warning machine judgment function according to all the calibration points on the first warning line, determining a second warning line early warning judgment function according to all the calibration points on the second warning line, and determining an early warning trigger condition and an early warning level according to the first warning line, the second warning line, the first warning line early warning machine judgment function and the second warning line early warning judgment function.
Further, the function determining step includes: firstly, obtaining an image shot by a camera, extracting pixel coordinate values of each warning line and a calibration point on each warning line from the image, and then obtaining a corresponding warning line early warning judgment function according to the pixel coordinate index of the calibration point on each warning line.
Further, the detecting step further comprises: and processing and identifying the image shot by the camera acquired in real time by adopting a target detection neural network to obtain a target and a pixel coordinate value of the target, and substituting the pixel coordinate value of the target into each warning line warning judgment function to judge whether to trigger warning or not.
Further, the processing and identifying the image shot by the camera acquired in real time by using the target detection neural network to obtain the target and the pixel coordinate value of the target specifically includes: firstly, scaling an original size of an image shot by a camera acquired in real time into a first size; then, normalizing the zoomed image through a target detection neural network to obtain a normalized target of the target; and finally, restoring the size of the target according to the normalized coordinates of the target to obtain the pixel coordinate value of the target.
Further, the target detection neural network is any one of a CNN target detection neural network, a MOBILESSD neural network, an RCNN neural network, a FASTER-RCNN neural network, and a YOLO neural network.
Further, the targets include pedestrians and non-motor vehicles.
The second purpose of the invention is realized by adopting the following technical scheme:
a blind area detection apparatus for a large vehicle, comprising a memory on which a blind area detection program is stored that is executable on a processor, the blind area detection program being a computer program, and the processor, when executing the blind area detection program, implementing the steps of a blind area detection method for a large vehicle as employed in one of the objects of the present invention.
The third purpose of the invention is realized by adopting the following technical scheme:
a storage medium which is a computer-readable storage medium having stored thereon a blind area detection program which is a computer program that, when executed by a processor, implements the steps of a blind area detection method for a large vehicle as employed in one of the objects of the present invention.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the camera is arranged on the side of the vehicle, and then when the vehicle is static, the corresponding warning line is set to realize the calibration of the camera and set the early warning triggering condition, so that whether the position of the identified target can trigger the early warning is judged in the running process of the vehicle, and the target detection of the blind area is further realized.
Drawings
FIG. 1 is a schematic diagram of the positions of a vehicle, a camera and a warning line in the blind zone detection method for a large vehicle according to the present invention;
FIG. 2 is a flow chart of a blind zone detection method for a large vehicle according to the present invention;
FIG. 3 is a flowchart of step S2 in FIG. 2;
FIG. 4 is a flowchart of step S3 in FIG. 2;
fig. 5 is a block diagram of a blind area detection device for a large vehicle according to the present invention.
In the figure: 11. a memory; 12. a processor; 13. a communication bus; 14. a network interface.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and the detailed description, and it should be noted that any combination of the embodiments or technical features described below can be used to form a new embodiment without conflict.
Aiming at the problems of high equipment cost, complex equipment installation and the like in the vehicle blind area detection in the prior art, the invention provides the blind area detection method for the large-sized vehicle, which can be realized by only needing a single camera and performing simple calibration, has simple installation, low equipment cost and lower vehicle transformation cost, and is particularly suitable for the blind area detection of the large-sized vehicle.
As shown in fig. 2, the present invention provides a preferred embodiment, a blind area detection method for a large vehicle, comprising the steps of:
step S1 is to mount the camera on the vehicle body at the side of the vehicle, and set a first warning line at a position at a distance corresponding to the vehicle body at the side of the vehicle, and a second warning line at a position at a distance corresponding to the vehicle body at the front of the vehicle.
Preferably, in order to ensure that the camera can completely cover the blind area of the vehicle, when the camera in this embodiment is mounted on the vehicle body at the side of the vehicle, the optical axis of the lens of the camera is ensured to be parallel to the ground, and simultaneously, the optical axis of the lens is parallel to the vehicle body measuring surface.
In addition, since the vehicle has both left and right sides, the two cameras are provided on the vehicle body on the left side of the vehicle and on the vehicle body on the right side of the vehicle.
Preferably, the present invention is described by taking a camera mounted on one side of a vehicle as an example: after the camera installation is accomplished, still include:
and step S2, when the vehicle stops, determining an early warning trigger condition according to the first warning line, the second warning line and the image shot by the camera.
Preferably, as shown in fig. 1, the first warning line includes a first one-meter warning line, a first two-meter warning line and a first three-meter warning line. The distance between the first one-meter warning line and the vehicle body on the side of the vehicle is 1 meter, the distance between the first two-meter warning line and the vehicle body on the side of the vehicle is 2 meters, and the distance between the first three-meter warning line and the vehicle body on the side of the vehicle is three meters; the second guard line is 3 meters from the body in front of the vehicle.
As can be seen from fig. 1, the area between the guard line and the vehicle body is generally a dangerous area, that is, when an object is within the area, it is considered that a warning is required to the driver. Therefore, the corresponding early warning triggering condition is set. Namely: when the target is obtained, whether the position where the target is located falls into the dangerous area or not is detected to judge whether early warning is triggered or not.
Preferably, when the early warning judgment condition is set, as shown in fig. 3, the method specifically includes:
step S21, setting a calibration point on the first warning line and setting a calibration point on the second warning line. Preferably, there are at least two index points per warning line.
Step S22, determining a first warning line early warning machine judgment function according to all the calibration points on the first warning line, determining a second warning line early warning judgment function according to all the calibration points on the second warning line, and determining an early warning trigger condition and an early warning level according to the first warning line, the second warning line, the first warning line early warning machine judgment function, and the second warning line early warning judgment function.
Preferably, when the warning line determination function is set, an image captured by the camera is obtained first, and pixel coordinate values of each warning line and a calibration point on each warning line are extracted from the image, and then a corresponding warning line early warning determination function is obtained according to the pixel coordinate indication of the calibration point on each warning line.
Specifically, for the second cordline function: the first index point F1 and the second index point F2 are set on the second warning line. The pixel coordinate values of the first calibration point F1 and the second calibration point F2 can be obtained according to the image shot by the camera, and then the first warning line early warning judgment function is determined according to the pixel coordinate value of the first calibration point F1 and the pixel coordinate value of the second calibration point F2. Preferably, the first and second calibration points F1 and F2 can be set according to actual requirements.
Similarly, a first one-meter warning line early warning judgment function is calculated according to the third calibration point P10 and the fourth calibration point P11.
And calculating to obtain a first two-meter warning line early warning judgment function according to the fifth calibration point P20 and the sixth calibration point P21.
And calculating to obtain a first three-meter warning line early warning judgment function according to the seventh calibration point P30 and the eighth calibration point P31.
Preferably, the cordage function is a linear equation. As can be seen from the figure, two points determine a straight line, and therefore, the guard line can be expressed by a straight line equation.
Preferably, the embodiment also sets the early warning level according to the distance between the target and the vehicle body. As shown in fig. 1, for example: when the region between the first meter warning line and the vehicle body is set, the danger coefficient is considered to be the highest, the early warning level is 1 level, and corresponding early warning levels are set in sequence in the same way. Preferably, the setting of the early warning level is not limited to the scheme provided in this embodiment, and may be specifically set according to actual requirements.
Preferably, there are a plurality of cameras arranged on one side of the vehicle body, and then calibration is performed for each camera according to the method.
And step S3, acquiring images shot by the camera in real time in the running process of the vehicle, and judging whether to trigger early warning according to the images shot by the camera and the early warning triggering condition.
Preferably, as shown in fig. 4, step S3 further includes: and step S31, processing the image shot by the camera acquired in real time by adopting a target detection neural network and identifying to obtain a target and pixel coordinate values of the target.
Preferably, the target detection neural network in this embodiment may be implemented by any one of the following methods: CCN target detection neural network, mobielssd neural network, RCNN neural network, FASTER-RCNN neural network, YOLO neural network.
Preferably, step S31 further includes: firstly, scaling an original size of an image shot by a camera acquired in real time into a first size; then, normalizing the zoomed image through a target detection neural network to obtain a normalized target of the target; and finally, restoring the size of the target according to the normalized coordinates of the target to obtain the pixel coordinate value of the target. Wherein the first size is 300 x 300.
Wherein the pixel coordinate value of the target is equal to the pixel coordinate value of the center of the lower edge of the target position. That is, the midpoint of the lower edge of the target position is located at the position of the target landing point.
Preferably, the objects in this embodiment include pedestrians and non-motor vehicles.
And step S32, substituting the pixel coordinate values of the target into each warning line pre-tightening judgment function to judge whether to trigger early warning.
Specifically, for example, when the target is between the second warning line and the vehicle body, it is considered that the warning is triggered. Meanwhile, the early warning level can be judged by substituting the pixel coordinate point of the target in the image into the result value of each warning line function. That is, the distance of the target with respect to the vehicle body is judged to determine the warning level.
And step S4, when the early warning is triggered, sending early warning reminding to the driver.
Specifically, the corresponding warning lamp and warning bell can be installed in the cab. And sending a reminder to the driver through an early warning lamp and/or an early warning bell.
The invention provides a blind area detection device for a large vehicle. As shown in fig. 5, an embodiment of the present invention provides a blind area detection device for a large vehicle, which has a schematic internal structure.
In the present embodiment, the blind area detection device for a large vehicle may be a PC (Personal Computer), or may be a terminal device such as a smartphone, a tablet Computer, or a mobile Computer. This a blind area detection device for large vehicle includes at least: a processor 12, a communication bus 13, a network interface 14, and a memory 11.
The memory 11 includes at least one type of readable storage medium, which includes a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like. The memory 11 may in some embodiments be an internal storage unit of a blind spot detection device for a large vehicle, for example a hard disk of the blind spot detection device for a large vehicle. The memory 11 may be an external storage device of the blind spot detection apparatus for the large vehicle in other embodiments, such as a plug-in hard disk provided on the blind spot detection apparatus for the large vehicle, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the memory 11 may also include both an internal storage unit of the blind area detection apparatus for a large vehicle and an external storage device. The memory 11 may be used not only to store application software installed in a blind area detection device for a large vehicle and various types of data, such as codes of a blind area detection program, etc., but also to temporarily store data that has been output or is to be output.
The processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data Processing chip in some embodiments, and is used for executing program codes or Processing data stored in the memory 11, such as executing a blind spot detection program.
The communication bus 13 is used to realize connection communication between these components.
The network interface 14 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), typically used to establish a communication link between the blind spot detection apparatus for large vehicles and other electronic devices.
Optionally, the blind area detection device for a large vehicle may further include a user interface, the user interface may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface may further include a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the blind spot detection device for large vehicles and for displaying a visual user interface.
While FIG. 5 shows only a blind spot detection arrangement for a large vehicle with components 11-14 and a blind spot detection routine, those skilled in the art will appreciate that the configuration shown in FIG. 5 does not constitute a limitation of a blind spot detection arrangement for a large vehicle, and may include fewer or more components than shown, or some components in combination, or a different arrangement of components.
In the embodiment of the blind area detection apparatus for a large vehicle shown in fig. 5, a blind area detection program is stored in the memory 11; the processor 12, when executing the blind spot detection program stored in the memory 11, implements the following steps:
setting: the method comprises the following steps that a camera is installed on a vehicle body at the side of a vehicle, a first warning line is set at a position which is away from the vehicle body at the side of the vehicle by a corresponding distance, and a second warning line is set at a position which is away from the vehicle body in front of the vehicle by a corresponding distance; when the camera is mounted on a vehicle body at the side of the vehicle, the optical axis of a lens of the camera is parallel to the ground and is parallel to the side face of the vehicle body;
a calibration step: when the vehicle stops, determining an early warning triggering condition according to the first warning line, the second warning line and the image shot by the camera;
a detection step: in the running process of the vehicle, acquiring an image shot by a camera in real time, and judging whether to trigger early warning according to the image shot by the camera and the early warning triggering condition;
a reminding step: and when the early warning is triggered, sending early warning reminding to the driver.
Further, the first warning lines comprise first one-meter warning lines, first two-meter warning lines and first three-meter warning lines; the distance between the first one-meter warning line and the vehicle body on the side of the vehicle is 1 meter, the distance between the first two-meter warning line and the vehicle body on the side of the vehicle is 2 meters, and the distance between the first three-meter warning line and the vehicle body on the side of the vehicle is 3 meters; the second guard line is 3 meters from the body in front of the vehicle.
Further, the calibrating step includes:
setting a calibration point: setting at least two calibration points on the first warning line and setting at least two calibration points on the second warning line;
a function determination step: determining a first warning line early warning machine judgment function according to all the calibration points on the first warning line, determining a second warning line early warning judgment function according to all the calibration points on the second warning line, and determining an early warning trigger condition and an early warning level according to the first warning line, the second warning line, the first warning line early warning machine judgment function and the second warning line early warning judgment function.
Further, the function determining step includes: firstly, obtaining an image shot by a camera, extracting pixel coordinate values of each warning line and a calibration point on each warning line from the image, and then obtaining a corresponding warning line early warning judgment function according to the pixel coordinate index of the calibration point on each warning line.
Further, the detecting step further comprises: and processing and identifying the image shot by the camera acquired in real time by adopting a target detection neural network to obtain a target and a pixel coordinate value of the target, and substituting the pixel coordinate value of the target into each warning line warning judgment function to judge whether to trigger warning or not.
Further, the processing and identifying the image shot by the camera acquired in real time by using the target detection neural network to obtain the target and the pixel coordinate value of the target specifically includes: firstly, scaling an original size of an image shot by a camera acquired in real time into a first size; then, normalizing the zoomed image through a target detection neural network to obtain a normalized target of the target; and finally, restoring the size of the target according to the normalized coordinates of the target to obtain the pixel coordinate value of the target.
Further, the target detection neural network is any one of a CNN target detection neural network, a MOBILESSD neural network, an RCNN neural network, a FASTER-RCNN neural network, and a YOLO neural network.
Further, the targets include pedestrians and non-motor vehicles.
Preferably, the present invention further provides an embodiment, which is a storage medium, the storage medium being a computer readable storage medium having stored thereon a blind area detection program, the blind area detection program being a computer program, the blind area detection program, when executed by a processor, implementing the steps of:
setting: the method comprises the following steps that a camera is installed on a vehicle body at the side of a vehicle, a first warning line is set at a position which is away from the vehicle body at the side of the vehicle by a corresponding distance, and a second warning line is set at a position which is away from the vehicle body in front of the vehicle by a corresponding distance; when the camera is mounted on a vehicle body at the side of the vehicle, the optical axis of a lens of the camera is parallel to the ground and is parallel to the side face of the vehicle body;
a calibration step: when the vehicle stops, determining an early warning triggering condition according to the first warning line, the second warning line and the image shot by the camera;
a detection step: in the running process of the vehicle, acquiring an image shot by a camera in real time, and judging whether to trigger early warning according to the image shot by the camera and the early warning triggering condition;
a reminding step: and when the early warning is triggered, sending early warning reminding to the driver.
Further, the first warning lines comprise first one-meter warning lines, first two-meter warning lines and first three-meter warning lines; the distance between the first one-meter warning line and the vehicle body on the side of the vehicle is 1 meter, the distance between the first two-meter warning line and the vehicle body on the side of the vehicle is 2 meters, and the distance between the first three-meter warning line and the vehicle body on the side of the vehicle is 3 meters; the second guard line is 3 meters from the body in front of the vehicle.
Further, the calibrating step includes:
setting a calibration point: setting at least two calibration points on the first warning line and setting at least two calibration points on the second warning line;
a function determination step: determining a first warning line early warning machine judgment function according to all the calibration points on the first warning line, determining a second warning line early warning judgment function according to all the calibration points on the second warning line, and determining an early warning trigger condition and an early warning level according to the first warning line, the second warning line, the first warning line early warning machine judgment function and the second warning line early warning judgment function.
Further, the function determining step includes: firstly, obtaining an image shot by a camera, extracting pixel coordinate values of each warning line and a calibration point on each warning line from the image, and then obtaining a corresponding warning line early warning judgment function according to the pixel coordinate index of the calibration point on each warning line.
Further, the detecting step further comprises: and processing and identifying the image shot by the camera acquired in real time by adopting a target detection neural network to obtain a target and a pixel coordinate value of the target, and substituting the pixel coordinate value of the target into each warning line warning judgment function to judge whether to trigger warning or not.
Further, the processing and identifying the image shot by the camera acquired in real time by using the target detection neural network to obtain the target and the pixel coordinate value of the target specifically includes: firstly, scaling an original size of an image shot by a camera acquired in real time into a first size; then, normalizing the zoomed image through a target detection neural network to obtain a normalized target of the target; and finally, restoring the size of the target according to the normalized coordinates of the target to obtain the pixel coordinate value of the target.
Further, the target detection neural network is any one of a CNN target detection neural network, a MOBILESSD neural network, an RCNN neural network, a FASTER-RCNN neural network, and a YOLO neural network.
Further, the targets include pedestrians and non-motor vehicles.
The above embodiments are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby, and any insubstantial changes and substitutions made by those skilled in the art based on the present invention are within the protection scope of the present invention.
Claims (10)
1. A blind area detection method for a large vehicle, characterized by comprising:
setting: the method comprises the following steps that a camera is installed on a vehicle body at the side of a vehicle, a first warning line is set at a position which is away from the vehicle body at the side of the vehicle by a corresponding distance, and a second warning line is set at a position which is away from the vehicle body in front of the vehicle by a corresponding distance; when the camera is mounted on a vehicle body at the side of the vehicle, the optical axis of a lens of the camera is parallel to the ground and is parallel to the side face of the vehicle body;
a calibration step: when the vehicle stops, determining an early warning triggering condition according to the first warning line, the second warning line and the image shot by the camera;
a detection step: in the running process of the vehicle, acquiring an image shot by a camera in real time, and judging whether to trigger early warning according to the image shot by the camera and the early warning triggering condition;
a reminding step: and when the early warning is triggered, sending early warning reminding to the driver.
2. The blind area detection method for a large vehicle according to claim 1, wherein said first guard line includes a first one-meter guard line, a first two-meter guard line and a first three-meter guard line; the distance between the first one-meter warning line and the vehicle body on the side of the vehicle is 1 meter, the distance between the first two-meter warning line and the vehicle body on the side of the vehicle is 2 meters, and the distance between the first three-meter warning line and the vehicle body on the side of the vehicle is 3 meters; the second guard line is 3 meters from the body in front of the vehicle.
3. The blind area detection method for the large vehicle according to claim 1, wherein the calibration step includes:
setting a calibration point: setting at least two calibration points on the first warning line and setting at least two calibration points on the second warning line;
a function determination step: determining a first warning line early warning machine judgment function according to all the calibration points on the first warning line, determining a second warning line early warning judgment function according to all the calibration points on the second warning line, and determining an early warning trigger condition and an early warning level according to the first warning line, the second warning line, the first warning line early warning machine judgment function and the second warning line early warning judgment function.
4. The blind area detection method for the large vehicle according to claim 3, wherein the function determination step includes: firstly, obtaining an image shot by a camera, extracting pixel coordinate values of each warning line and a calibration point on each warning line from the image, and then obtaining a corresponding warning line early warning judgment function according to the pixel coordinate index of the calibration point on each warning line.
5. The blind area detection method for a large vehicle according to claim 4, characterized in that the detection step further comprises: and processing and identifying the image shot by the camera acquired in real time by adopting a target detection neural network to obtain a target and a pixel coordinate value of the target, and substituting the pixel coordinate value of the target into each warning line warning judgment function to judge whether to trigger warning or not.
6. The method according to claim 5, wherein the step of processing and recognizing the image captured by the camera acquired in real time by using the target detection neural network to obtain the target and the pixel coordinate value of the target specifically comprises: firstly, scaling an original size of an image shot by a camera acquired in real time into a first size; then, normalizing the zoomed image through a target detection neural network to obtain a normalized target of the target; and finally, restoring the size of the target according to the normalized coordinates of the target to obtain the pixel coordinate value of the target.
7. The blind spot detection method for large vehicles according to claim 5, wherein the object detection neural network is any one of CNN object detection neural network, mobields neural network, RCNN neural network, FASTER-RCNN neural network, and YOLO neural network.
8. The blind spot detection method for large vehicles according to claim 5, wherein the objects include pedestrians and non-motor vehicles.
9. A blind area detection apparatus for a large vehicle, comprising a memory and a processor, the memory having stored thereon a blind area detection program executable on the processor, the blind area detection program being a computer program, characterized in that: the processor, when executing the blind spot detection program, carries out the steps of a method for detecting blind spots for a large vehicle according to any one of claims 1 to 8.
10. A storage medium that is a computer-readable storage medium having a blind area detection program stored thereon, the blind area detection program being a computer program, characterized in that: the blind spot detection program when executed by a processor implements the steps of a method for detecting blind spots for a large vehicle as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110296657.7A CN113205704B (en) | 2021-03-19 | 2021-03-19 | Blind area detection method and device for large vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110296657.7A CN113205704B (en) | 2021-03-19 | 2021-03-19 | Blind area detection method and device for large vehicle and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113205704A true CN113205704A (en) | 2021-08-03 |
| CN113205704B CN113205704B (en) | 2022-06-24 |
Family
ID=77025535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110296657.7A Active CN113205704B (en) | 2021-03-19 | 2021-03-19 | Blind area detection method and device for large vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113205704B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080309516A1 (en) * | 2007-05-03 | 2008-12-18 | Sony Deutschland Gmbh | Method for detecting moving objects in a blind spot region of a vehicle and blind spot detection device |
| CN102632839A (en) * | 2011-02-15 | 2012-08-15 | 汽车零部件研究及发展中心有限公司 | Back sight image cognition based on-vehicle blind area early warning system and method |
| CN108152808A (en) * | 2017-11-23 | 2018-06-12 | 安徽四创电子股份有限公司 | A kind of circumference intelligent predicting method for early warning based on millimetre-wave radar |
| CN109084724A (en) * | 2018-07-06 | 2018-12-25 | 西安理工大学 | A kind of deep learning barrier distance measuring method based on binocular vision |
| CN110674703A (en) * | 2019-09-05 | 2020-01-10 | 北京正安维视科技股份有限公司 | Video tripwire alarm counting method and flow in intelligent monitoring |
| CN111942282A (en) * | 2019-05-17 | 2020-11-17 | 比亚迪股份有限公司 | Vehicle and driving blind area early warning method, device and system thereof and storage medium |
| CN112158197A (en) * | 2020-08-21 | 2021-01-01 | 恒大新能源汽车投资控股集团有限公司 | Vehicle blind area obstacle avoiding method, device and system |
-
2021
- 2021-03-19 CN CN202110296657.7A patent/CN113205704B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080309516A1 (en) * | 2007-05-03 | 2008-12-18 | Sony Deutschland Gmbh | Method for detecting moving objects in a blind spot region of a vehicle and blind spot detection device |
| CN102632839A (en) * | 2011-02-15 | 2012-08-15 | 汽车零部件研究及发展中心有限公司 | Back sight image cognition based on-vehicle blind area early warning system and method |
| CN108152808A (en) * | 2017-11-23 | 2018-06-12 | 安徽四创电子股份有限公司 | A kind of circumference intelligent predicting method for early warning based on millimetre-wave radar |
| CN109084724A (en) * | 2018-07-06 | 2018-12-25 | 西安理工大学 | A kind of deep learning barrier distance measuring method based on binocular vision |
| CN111942282A (en) * | 2019-05-17 | 2020-11-17 | 比亚迪股份有限公司 | Vehicle and driving blind area early warning method, device and system thereof and storage medium |
| CN110674703A (en) * | 2019-09-05 | 2020-01-10 | 北京正安维视科技股份有限公司 | Video tripwire alarm counting method and flow in intelligent monitoring |
| CN112158197A (en) * | 2020-08-21 | 2021-01-01 | 恒大新能源汽车投资控股集团有限公司 | Vehicle blind area obstacle avoiding method, device and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113205704B (en) | 2022-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107392103B (en) | Method and device for detecting road lane line and electronic equipment | |
| CN106952303B (en) | Vehicle distance detection method, device and system | |
| CN103093181B (en) | A kind of method and apparatus of license plate image location | |
| US10339396B2 (en) | Vehicle accessibility determination device | |
| WO2019000945A1 (en) | On-board camera-based distance measurement method and apparatus, storage medium, and electronic device | |
| CN112037521B (en) | Vehicle type identification method and hazardous chemical substance vehicle identification method | |
| CN107527017B (en) | Parking space detection method and system, storage medium and electronic equipment | |
| CN109118797B (en) | Information sharing method, device, equipment and storage medium | |
| CN111881832A (en) | Lane target detection method, device, equipment and computer readable storage medium | |
| CN112534469A (en) | Image detection method, image detection device, image detection apparatus, and medium | |
| CN109740526B (en) | Signal lamp identification method, device, equipment and medium | |
| CN113344906B (en) | Camera evaluation method and device in vehicle-road cooperation, road side equipment and cloud control platform | |
| CN113205704B (en) | Blind area detection method and device for large vehicle and storage medium | |
| CN113838125A (en) | Target position determining method and device, electronic equipment and storage medium | |
| CN109444905B (en) | Dynamic object detection method and device based on laser and terminal equipment | |
| CN114332818B (en) | Obstacle detection method and device and electronic equipment | |
| CN113112551B (en) | Camera parameter determining method and device, road side equipment and cloud control platform | |
| CN116071562A (en) | Plant seed identification method and device, electronic equipment and storage medium | |
| CN116030139A (en) | Camera detection method and device, electronic equipment and vehicle | |
| CN104931024A (en) | Obstacle detection device | |
| CN113807209A (en) | Parking space detection method and device, electronic equipment and storage medium | |
| CN104299002B (en) | A kind of tower crane image detecting method based on monitoring system | |
| CN111218894B (en) | Control method and device of light-emitting guide facility, electronic equipment and system | |
| CN113902740A (en) | Construction method of image blurring degree evaluation model | |
| CN112686203A (en) | Vehicle safety warning device detection method based on space prior |
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 |