CN107187436A - The method and apparatus for preventing mis-accelerator pressing - Google Patents

The method and apparatus for preventing mis-accelerator pressing Download PDF

Info

Publication number
CN107187436A
CN107187436A CN201710365451.9A CN201710365451A CN107187436A CN 107187436 A CN107187436 A CN 107187436A CN 201710365451 A CN201710365451 A CN 201710365451A CN 107187436 A CN107187436 A CN 107187436A
Authority
CN
China
Prior art keywords
monitoring
designated area
pixel
accelerator
dimensional entropy
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
Application number
CN201710365451.9A
Other languages
Chinese (zh)
Other versions
CN107187436B (en
Inventor
杨海军
陈新
陈效华
曹增良
刘华仁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
BAIC Motor Co Ltd
Beijing Automotive Research Institute Co Ltd
Original Assignee
BAIC Motor Co Ltd
Beijing Automotive Research Institute Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by BAIC Motor Co Ltd, Beijing Automotive Research Institute Co Ltd filed Critical BAIC Motor Co Ltd
Priority to CN201710365451.9A priority Critical patent/CN107187436B/en
Publication of CN107187436A publication Critical patent/CN107187436A/en
Application granted granted Critical
Publication of CN107187436B publication Critical patent/CN107187436B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60T—VEHICLE BRAKE CONTROL SYSTEMS OR PARTS THEREOF; BRAKE CONTROL SYSTEMS OR PARTS THEREOF, IN GENERAL; ARRANGEMENT OF BRAKING ELEMENTS ON VEHICLES IN GENERAL; PORTABLE DEVICES FOR PREVENTING UNWANTED MOVEMENT OF VEHICLES; VEHICLE MODIFICATIONS TO FACILITATE COOLING OF BRAKES
    • B60T7/00—Brake-action initiating means
    • B60T7/12—Brake-action initiating means for automatic initiation; for initiation not subject to will of driver or passenger
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
    • B60K28/00—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions
    • B60K28/02—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the driver
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads

Landscapes

  • Engineering & Computer Science (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)

Abstract

The present disclosure proposes a kind of method and apparatus for preventing mis-accelerator pressing, applied to vehicle, it is related to control field, this method includes：The current throttle aperture gathered according to current time determines whether throttle is promptly trampled.Monitor and whether there is barrier in the designated area in the monitoring image of picture pick-up device collection, designated area is region of the region correspondence of vehicle front preset range in monitoring image.When it is determined that throttle is promptly trampled, and there is barrier in designated area, according to the corresponding speed of acquisition time and preset vehicle speed, it is determined whether there is risk.When it is determined that there is risk, brake instruction is sent to electronic control unit, and control oil circuit to stop oil transportation.The disclosure can improve the manipulation degree of the degree of accuracy for judging mis-accelerator pressing and vehicle.

Description

Method and device for preventing mistaken stepping on accelerator
Technical Field
The disclosure relates to the field of control, in particular to a method and a device for preventing mistaken stepping on an accelerator.
Background
In the process of vehicle running, when emergency braking is needed in a special situation, a driver is required to loosen an accelerator pedal, transfer a foot to a brake pedal and step on the brake pedal violently, and in the process, due to the reasons of fatigue driving, inattentive attention, excessive tension, insufficient experience and the like of the driver, the problem that the accelerator pedal is mistakenly taken as the brake pedal can be caused, so that serious traffic accidents are caused. In the prior art, whether the accelerator is mistakenly stepped is determined by the opening angle of the accelerator opening in a short time, the accuracy of judging the mistaken stepping on the accelerator is not high, meanwhile, in the prior art, when the mistaken stepping on the accelerator is determined, an oil path is controlled to delay oil delivery, and the control degree of a vehicle is low for the situation that the speed needs to be increased in a short time.
Disclosure of Invention
The disclosure provides a method and a device for preventing mistaken stepping on an accelerator, which are used for solving the problems that the accuracy of judging mistaken stepping on the accelerator is not high and the control degree of a vehicle is low.
In order to achieve the above object, according to a first aspect of an embodiment of the present disclosure, there is provided a method for preventing mistaken stepping on a gas, applied to a vehicle, the method including:
determining whether the accelerator is emergently trodden according to the current accelerator opening acquired at the current time;
monitoring whether an obstacle exists in a designated area in a monitoring image acquired by a camera device, wherein the designated area is an area in the monitoring image corresponding to an area in a preset range in front of the vehicle;
when it is determined that the accelerator is emergently stepped and an obstacle exists in the designated area, determining whether a risk exists according to the vehicle speed corresponding to the acquisition time and a preset vehicle speed;
and when the risk is determined, sending a braking instruction to the electronic control unit, and controlling the oil way to stop oil transportation.
Optionally, whether there is an obstacle in the specified area in the monitoring image that monitoring camera equipment gathered includes:
acquiring the monitoring image acquired by the camera equipment at a preset frequency;
and determining whether an obstacle exists in the designated area or not according to the two-dimensional entropy of the monitoring image.
Optionally, the monitoring images include n monitoring images that are continuously acquired, and determining whether an obstacle exists in the designated area according to the two-dimensional entropy of the monitoring images includes:
respectively carrying out histogram equalization processing on designated areas of n continuously acquired monitoring images to obtain an equalized gray value of each pixel in the designated areas of the n monitoring images;
acquiring two-dimensional entropy of the designated areas of the n monitoring images according to the equalized gray value of each pixel in the designated areas of the n monitoring images;
determining whether an obstacle exists in the designated area according to the two-dimensional entropy and a reference two-dimensional entropy of the designated area of the n monitoring images, wherein the reference two-dimensional entropy is the two-dimensional entropy when no obstacle exists in the designated area;
and when the two-dimensional entropy of the designated area of the n monitoring images is larger than the reference two-dimensional entropy, determining that an obstacle exists in the designated area, wherein n is a positive integer.
Optionally, the obtaining the two-dimensional entropy of the n monitoring images according to the gray balance value of the n monitoring images includes:
calculating the pixel gray distribution characteristics of the designated areas of the n monitoring images according to the equalized gray value of each pixel in the designated areas of the n monitoring images and the neighborhood gray average value of each pixel;
calculating the two-dimensional entropy of the designated area of the n monitoring images according to the pixel gray scale distribution characteristics of the designated area of the n monitoring images;
wherein the formula for calculating the pixel gray scale distribution characteristics comprises:
pij＝f(Gi,Ei)/N
wherein p isijFor the pixel gray distribution characteristics, GiEqualized gray value for the ith pixel in a designated area of any one of the monitored images, EiIs the gray level mean of the pixels in the neighborhood of the ith pixel, f (G)i,Ei) A binary group (G) composed of the equalized gray value of the ith pixel and the gray average value of the pixels in the neighborhood of the ith pixeli,Ei) N represents the number of pixels in a specified area of the monitored image, wherein 1 ≦ Gi≤255，1≤Ei≤255；
The formula for calculating the two-dimensional entropy includes:
and H is the two-dimensional entropy of the monitoring image.
Optionally, before determining whether an obstacle exists in the designated area according to the two-dimensional entropy of the monitored image, the method further includes:
and determining the area of the preset range in front of the vehicle, which corresponds to the area in the monitoring image, as the designated area according to a world coordinate system, a camera equipment coordinate system, a pixel coordinate system and an included angle between the camera equipment and the world coordinate system.
Optionally, the determining whether the accelerator is suddenly stepped according to the current accelerator opening acquired at the current time includes:
saving the current time and the current accelerator opening as a first key value pair;
determining whether the current accelerator opening is larger than a first opening threshold value;
when the current accelerator opening is larger than the first opening threshold, obtaining a second key value pair of which the accelerator opening is smaller than a second opening threshold from stored historical key value pairs, wherein the second opening threshold is smaller than the first opening threshold, and the difference between the first opening threshold and the second opening threshold is larger than a preset difference;
determining whether the difference value between the acquisition time of the second key-value pair and the current time is less than or equal to a preset time threshold value;
when the difference value between the acquisition time and the current time is less than or equal to the preset time threshold value, determining that the accelerator is emergently stepped on;
and when the difference value between the acquisition time and the current time is greater than the preset time threshold value, determining that the accelerator is not emergently trodden.
Optionally, determining whether a risk exists according to the vehicle speed corresponding to the acquisition time and a preset vehicle speed includes:
when the vehicle speed is greater than or equal to the preset vehicle speed, determining that a risk exists;
and when the vehicle speed is less than the preset vehicle speed, determining that no risk exists.
Optionally, the method further includes:
and when the risk is determined, sending prompt information to the vehicle, wherein the prompt information is used for giving an alarm prompt to a user.
According to a second aspect of the embodiments of the present disclosure, there is provided an apparatus for preventing a driver from stepping on an accelerator mistakenly, the apparatus being applied to a vehicle, the apparatus including:
the pedaling detection module is used for determining whether the accelerator is pedaled emergently according to the current accelerator opening acquired at the current time;
the monitoring module is used for monitoring whether an obstacle exists in a designated area in a monitoring image acquired by the camera equipment, wherein the designated area is an area in a preset range in front of the vehicle, and the area corresponds to the monitoring image;
the risk detection module is used for determining whether a risk exists or not according to the vehicle speed corresponding to the acquisition time and a preset vehicle speed when the accelerator is determined to be emergently stepped and an obstacle exists in the specified area;
and the control module is used for sending a braking instruction to the electronic control unit and controlling the oil way to stop oil transportation when the risk is determined.
Optionally, the monitoring module includes:
the acquisition submodule is used for acquiring the monitoring image acquired by the camera shooting equipment at a preset frequency;
and the monitoring submodule is used for determining whether the barrier exists in the designated area or not according to the two-dimensional entropy of the monitored image.
Optionally, the monitoring images include n continuously acquired monitoring images, and the monitoring sub-module is configured to:
respectively carrying out histogram equalization processing on designated areas of n continuously acquired monitoring images to obtain an equalized gray value of each pixel in the designated areas of the n monitoring images;
acquiring two-dimensional entropy of the designated areas of the n monitoring images according to the equalized gray value of each pixel in the designated areas of the n monitoring images;
determining whether an obstacle exists in the designated area according to the two-dimensional entropy and a reference two-dimensional entropy of the designated area of the n monitoring images, wherein the reference two-dimensional entropy is the two-dimensional entropy when no obstacle exists in the designated area;
and when the two-dimensional entropy of the designated area of the n monitoring images is larger than the reference two-dimensional entropy, determining that an obstacle exists in the designated area, wherein n is a positive integer.
Optionally, the monitoring submodule is configured to:
calculating the pixel gray distribution characteristics of the designated areas of the n monitoring images according to the equalized gray value of each pixel in the designated areas of the n monitoring images and the neighborhood gray average value of each pixel;
calculating the two-dimensional entropy of the designated area of the n monitoring images according to the pixel gray scale distribution characteristics of the designated area of the n monitoring images;
wherein the formula for calculating the pixel gray scale distribution characteristics comprises:
pij＝f(Gi,Ei)/N
wherein p isijFor the pixel gray distribution characteristics, GiEqualized gray value for the ith pixel in a designated area of any one of the monitored images, EiIs the gray level mean of the pixels in the neighborhood of the ith pixel, f (G)i,Ei) A binary group (G) composed of the equalized gray value of the ith pixel and the gray average value of the pixels in the neighborhood of the ith pixeli,Ei) N represents the number of pixels in a specified area of the monitored image, wherein 1 ≦ Gi≤255，1≤Ei≤255；
The formula for calculating the two-dimensional entropy includes:
and H is the two-dimensional entropy of the monitoring image.
Optionally, the monitoring module further includes:
and the area detection submodule is used for determining an area corresponding to the area in the monitoring image in the preset range in front of the vehicle as the designated area according to a world coordinate system, a camera equipment coordinate system, a pixel coordinate system and an included angle between the camera equipment and the world coordinate system before determining whether the designated area has the obstacle according to the two-dimensional entropy of the monitoring image.
Optionally, the step detection module includes:
the information storage submodule is used for storing the current time and the current accelerator opening as a first key value pair;
the accelerator opening identification submodule is used for determining whether the current accelerator opening is larger than a first opening threshold value;
the information acquisition submodule is used for acquiring a second key value pair of which the throttle opening is smaller than a second throttle opening threshold from stored historical key value pairs when the current throttle opening is larger than the first throttle opening threshold, wherein the second throttle opening threshold is smaller than the first throttle opening threshold, and the difference between the first throttle opening threshold and the second throttle opening threshold is larger than a preset difference;
the acquisition time identification submodule is used for determining whether the difference value between the acquisition time of the second key value pair and the current time is less than or equal to a preset time threshold value;
the determining submodule is used for determining that the accelerator is emergently trodden when the difference value between the acquisition time and the current time is smaller than or equal to the preset time threshold;
the determining submodule is further used for determining that the accelerator is not emergently stepped on when the difference value between the acquisition time and the current time is larger than the preset time threshold.
Optionally, the risk detection module is configured to:
when the vehicle speed is greater than or equal to the preset vehicle speed, determining that a risk exists;
and when the vehicle speed is less than the preset vehicle speed, determining that no risk exists.
Optionally, the apparatus further comprises:
and the prompting module is used for sending prompting information to the vehicle when the risk is determined to exist, and the prompting information is used for giving an alarm to a user.
According to the technical scheme, whether the accelerator is emergently trodden or not is determined according to the change of the accelerator opening in a short time, whether a barrier exists in the designated area or not is determined through the acquired monitoring image, and when the accelerator is emergently trodden and the barrier exists in the designated area, whether the risk exists or not is determined according to the relation between the current vehicle speed and the preset vehicle speed. When the risk exists in the judgment, the vehicle is controlled to brake, oil transportation of the oil way is stopped, and the effect of improving the accuracy of judging the mistaken stepping on the accelerator and the control degree of the vehicle is achieved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
FIG. 1 is a flow chart illustrating a method of preventing false tip-in, according to an exemplary embodiment;
FIG. 2 is a flow chart illustrating another method of preventing false tip-in, according to an exemplary embodiment;
FIG. 3 is a flow chart illustrating yet another method of preventing false tip-in, according to an exemplary embodiment;
FIG. 4a is a schematic diagram of a world coordinate system and an imaging device coordinate system;
FIG. 4b is a schematic diagram of a pixel coordinate system;
FIG. 5 is a flow chart illustrating yet another method of preventing false tip-in according to an exemplary embodiment;
FIG. 6 is a flow chart illustrating yet another method of preventing false tip-in, according to an exemplary embodiment;
FIG. 7 is a block diagram illustrating an apparatus for preventing false tip-in, according to an exemplary embodiment;
FIG. 8 is a block diagram illustrating another arrangement for preventing false tip-in, according to an exemplary embodiment;
FIG. 9 is a block diagram illustrating yet another arrangement for preventing false tip-in, according to an exemplary embodiment;
FIG. 10 is a block diagram illustrating yet another arrangement for preventing false tip-in, according to an exemplary embodiment;
FIG. 11 is a block diagram illustrating yet another apparatus for preventing false tip-in, according to an exemplary embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Before introducing the method and the device for preventing stepping on the accelerator mistakenly provided by the present disclosure, an application scenario related to various embodiments of the present disclosure is first introduced. The application scene is that when the vehicle runs and needs emergency braking under special conditions, the condition of stepping on an accelerator pedal suddenly occurs due to misoperation of a driver, wherein the vehicle can be an automobile, and the automobile is not limited to a traditional automobile, a pure electric automobile or a hybrid automobile.
FIG. 1 is a flow chart illustrating a method of preventing false tip-in, as shown in FIG. 1, for use with a vehicle, according to an exemplary embodiment, including:
and step 101, determining whether the accelerator is emergently stepped according to the current accelerator opening acquired at the current time.
For example, the degree of urgency of the accelerator being stepped on may be determined by the amount of change in the accelerator opening, for example, when the accelerator opening is changed from small to large for a preset time and the change exceeds a preset value, which indicates that the accelerator opening is sharply increased in a short time, it may be determined that the accelerator is stepped on urgently.
And 102, monitoring whether an obstacle exists in a designated area in a monitoring image acquired by the camera equipment, wherein the designated area is an area in the monitoring image corresponding to an area in a preset range in front of the vehicle.
In the process of driving, obstacles capable of influencing vehicles are all located in a certain rectangular area in front of a vehicle head, when the obstacles enter the area, traffic accidents are possible, and if the accelerator is mistakenly used as a brake at the moment, great harm is caused to a driver and the surrounding environment. Monitoring images can be acquired in real time at a certain acquisition frequency by arranging camera equipment on the vehicle, and whether barriers exist in corresponding areas in front of the vehicle head or not is judged. The camera device may be arranged to be turned on automatically when the vehicle is started, or turned on again when the vehicle speed exceeds a set speed.
And 103, when the accelerator is determined to be emergently stepped and an obstacle exists in the designated area, determining whether a risk exists according to the vehicle speed corresponding to the acquisition time and a preset vehicle speed.
It should be noted that, on the premise that the accelerator is urgently stepped and an obstacle exists, when the vehicle running speed is low, the change of the speed of the suddenly stepped accelerator is not large, so that risks to the surrounding environment and pedestrians are not brought, and when the vehicle running speed exceeds a preset value, the risk is determined.
And 104, when the risk is determined, sending a braking instruction to the electronic control unit, and controlling the oil way to stop oil transportation.
For example, when it is determined that there is a risk, a brake command may be transmitted to the electronic control unit through a CAN (Controller Area Network) bus or a LIN (Local Interconnect Network) bus, so as to actively decelerate the vehicle, and at the same time, control the oil passage to stop oil supply, cut off power of the vehicle, and passively decelerate the vehicle. Thereby avoiding the occurrence of traffic accidents.
FIG. 2 is a flow chart illustrating another method for preventing false tip-in, according to an exemplary embodiment, as shown in FIG. 2, step 102 includes:
and step 1021, acquiring a monitoring image acquired by the camera at a preset frequency.
And step 1022, determining whether an obstacle exists in the designated area or not according to the two-dimensional entropy of the monitoring image.
Optionally, the monitoring images may include n monitoring images continuously acquired (for example, 3 frames of images continuously acquired), and step 1022 includes:
firstly, histogram equalization processing is respectively carried out on designated areas of n continuously acquired monitoring images, and an equalized gray value of each pixel in the designated areas of the n monitoring images is obtained.
For example, in step 1021, n monitoring images continuously acquired by the image pickup apparatus at a preset frequency may be stored. The histogram equalization processing is performed on the designated areas of the n monitoring images, and can be understood as a mode for enabling the gray values of the pixels in the images to be uniformly distributed. The processing mode can comprise: (1) and acquiring the gray value of each pixel in the designated area of each image in the n monitoring images. (2) And acquiring the gray value cumulative distribution rate of the designated area of each image according to the gray value of each pixel in the designated area of each image. (3) And according to the gray value cumulative distribution rate of the designated area of each image and the neighborhood gray average value of each pixel, carrying out equalization processing on the gray value of each pixel in each image to obtain the equalized gray value of each pixel in the designated area of each image. The neighborhood gray average value of each pixel is the average value of the gray values of 8 adjacent pixels of each pixel, and the gray value of each pixel after equalization is the equalized gray value of each pixel.
And secondly, acquiring the two-dimensional entropy of the designated area of the n monitoring images according to the equalized gray value of each pixel in the designated area of the n monitoring images.
The one-dimensional entropy of the image can only represent the aggregation characteristics of the image gray scale distribution, and cannot reflect the spatial characteristics of the image gray scale distribution. Therefore, on the basis of the one-dimensional entropy, the two-dimensional entropy is obtained by introducing the neighborhood gray level mean value of each pixel and is used for reflecting the spatial characteristics of image gray level distribution.
And finally, determining whether the barrier exists in the designated area or not according to the two-dimensional entropy of the designated area of the n monitoring images and the reference two-dimensional entropy, wherein the reference two-dimensional entropy is the two-dimensional entropy when the barrier does not exist in the designated area.
For example, a certain number of monitoring images may be continuously acquired in an initial state of vehicle start, and the reference two-dimensional entropy may be acquired as a reference image. For example, 3 monitoring images are continuously acquired, and the two-dimensional entropy H of a specified area of the 3 monitoring images is calculated1、H2And H3Then the maximum value H is foundmaxMinimum value HminAnd average valueHavgIf (H) is satisfiedmax—Hmin)<(Havg0.05), the change of the 3 monitoring images is not large, and the reference two-dimensional entropy can be set to be HavgAnd 2, if the detected image does not meet the preset standard, taking the 1 st monitored image as a standard without the obstacle, and setting the two-dimensional entropy of the standard as H1*2。
And when the two-dimensional entropy of the designated area of the n monitoring images is larger than the reference two-dimensional entropy, determining that an obstacle exists in the designated area, wherein n is a positive integer.
Taking n as 3 as an example, that is, when monitoring is performed, 3 consecutive monitoring images may also be used as a determination basis, and when the two-dimensional entropy of the designated area of the 3 consecutive monitoring images is greater than the reference two-dimensional entropy, it is determined that an obstacle exists in the designated area. For example, if the two-dimensional entropy of only the designated area of the 1 st monitoring image in the 3 monitoring images is greater than the reference two-dimensional entropy, an object which is quickly moved from the front of the vehicle may exist at the corresponding acquisition time, and the driving is not threatened, and if the two-dimensional entropy of the designated area which is satisfied by all the 3 continuous monitoring images is greater than the reference two-dimensional entropy, a stable obstacle exists in the front of the vehicle. It should be noted that n-3 is merely exemplary, and other values may be adopted, and the specific value of n may be set according to actual circumstances.
Optionally, obtaining the two-dimensional entropy of the n monitoring images according to the gray level balance value of the n monitoring images includes:
firstly, calculating the pixel gray distribution characteristics of the designated area of the n monitoring images according to the equalized gray value of each pixel in the designated area of the n monitoring images and the neighborhood gray average value of each pixel.
And secondly, calculating the two-dimensional entropy of the designated area of the n monitoring images according to the pixel gray distribution characteristics of the designated area of the n monitoring images.
The formula for calculating the pixel gray distribution characteristics comprises the following steps:
pij＝f(Gi,Ei)/N
wherein p isijAs a characteristic of the gray-scale distribution of the pixel, GiEqualized gray value for the ith pixel in a designated area of any one of the monitored images, EiThe gray level mean value of the neighborhood pixels of the ith pixel, f (G)i,Ei) Is a binary group (G) composed of equalized gray value of the ith pixel and average gray value of adjacent pixels of the ith pixeli,Ei) N represents the number of pixels in a specified area of the monitored image, where 1 ≦ Gi≤255，1≤Ei≤255。
The formula for calculating the two-dimensional entropy includes:
wherein H is the two-dimensional entropy of the monitoring image.
Fig. 3 is a flowchart illustrating another method for preventing false gas step according to an exemplary embodiment, where before step 1022, as shown in fig. 3, the method further includes:
and step 1023, determining an area in the monitoring image corresponding to the area in the preset range in front of the vehicle as a designated area according to the world coordinate system, the camera equipment coordinate system, the pixel coordinate system and the included angle between the camera equipment and the world coordinate system.
For example, a world coordinate system (Ov, Xv, Yv, Zv), i.e., a coordinate system with Ov as an origin and Xv, Yv, Zv as three coordinate axes, and an image capturing device coordinate system (Oc, Xc, Yc, Zc), i.e., a coordinate system with Oc as an origin and Xc, Yc, Zc as three coordinate axes (also referred to as a camera coordinate system), are shown in fig. 4 a. The pixel coordinate system (Ot, u, v) with Ot as the origin and u, v as two coordinate axes is shown in fig. 4b (also called image coordinate system). Wherein, Ov is on the intersection point of the vertical central line of the vehicle and the ground, XV points to the front of the longitudinal axis of the vehicle, Yv points to the vertical direction of the longitudinal axis of the vehicleAnd Zv is directed vertically above the longitudinal axis of the vehicle. Oc is the optical center of the camera device, the roll angle with respect to the vehicle is phi (clockwise tilt is positive when viewed in the direction of travel of the vehicle), the pitch angle is theta (positive pointing upward), and the direction angle is theta(positive on the left of the axis of the vehicle body), the coordinate t of the optical center Oc in the world coordinate system is (l, d, h), that is, the image pickup apparatus is disposed at a position h from the ground, l from the vehicle head, and d from the center line of the vehicle. If there is a point pv (xv, yv, zv) in the world coordinate system, and its coordinate in the coordinate system of the image pickup device is pc (xc, yc, zc), the coordinate transformation relationship between pc (xc, yc, zc) and pv (xv, yv, zv) can be established through rotation and translation transformation.
Wherein R isc vRepresenting a rotation matrix, T, converted from the coordinate system of the camera to the world coordinate systemc vA translation vector is represented that is translated from the origin of the coordinate system of the image capture apparatus to the origin of the world coordinate system. In addition, R isc vIs Rx、Ry、RzThe product of the three matrices. Wherein,
and establishing a corresponding relation between the world coordinate system and the pixel coordinate system.
Wherein f isxAnd fy、(cx,cy) Are all intrinsic parameter matrices of the camera device, fxAnd fyIs the focal length in pixel unit, fxRepresenting the inverse of the physical dimension, f, of each pixel in the Xc axisyRepresenting the inverse of the corresponding physical dimension of each pixel on the Yc-axis. (c)x,cy) Is a reference point, i.e. the optical center of the image, cxA coordinate value of Oc on the u-axis, cyRepresents the coordinate value of Oc on the v-axis.
In fig. 4b, the monitoring image acquired by the image pickup apparatus has a width w and a height h. If the safe driving distance of the vehicle is set to be 3m ahead of the vehicle head and the preset ranges 2m away from the left and right sides are set, then (xv ═ 3, yv ═ 2) and (xv ═ 3, yv ═ 2) can be respectively substituted into formula 2 to obtain the shaded area in the graph, namely the designated area in the monitored image, as shown in fig. 4b, the preset ranges 3m ahead of the vehicle head and 2m away from the left and right sides are a trapezoidal area in the detected image, the upper bottom is sw, the height is sh, and the lower bottom is w, wherein the units of w, h, sw and sh are pixels, and therefore the number of pixels N in the designated area is equal to (sw + w) sh/2.
Fig. 5 is a flowchart illustrating another method for preventing mistaken stepping on the accelerator according to an exemplary embodiment, and as shown in fig. 5, the step of determining whether the accelerator is suddenly stepped on according to the current accelerator opening collected at the current time in step 101 may specifically include the following steps:
in step 1011, the current time and the current accelerator opening are saved as a first key value pair.
For example, the accelerator opening degree CAN be acquired through a sensor, the accelerator opening degree and the acquisition time are used as a key value pair and are sent to an industrial personal computer through a CAN bus or a LIN bus, and then the key value pair is stored, wherein the stored structure CAN be in a two-dimensional array form or a linked list structure, and the storage mode CAN be local storage or cloud storage. The sensor can be a magnetoelectric sensor, a piezoelectric sensor, a photoelectric sensor and the like and is used for acquiring the opening degree of the accelerator pedal. The first key-value pair represents a key-value pair consisting of the current time and the current accelerator opening.
At step 1012, it is determined whether the current accelerator opening is greater than a first opening threshold.
And 1013, when the current accelerator opening is larger than the first opening threshold, obtaining a second key value pair with the accelerator opening smaller than a second opening threshold from the stored historical key value pairs, wherein the second opening threshold is smaller than the first opening threshold, and the difference between the first opening threshold and the second opening threshold is larger than a preset difference.
It should be noted that the first opening threshold and the second opening threshold are used to determine the magnitude of the change of the accelerator opening amplitude, the second opening threshold is smaller than the first opening threshold, and the difference between the first opening threshold and the second opening threshold, that is, the sensitivity to the magnitude of the change of the accelerator opening amplitude, may be set according to different needs of a vehicle usage scenario. When it is determined that the current accelerator opening is larger than the first opening threshold, query can be performed in the historical key value pairs, and a second key value pair with the accelerator opening smaller than the second opening threshold is found.
Step 1014, determining whether the difference between the collection time of the second key-value pair and the current time is less than or equal to a preset time threshold.
And step 1015, when the difference between the acquisition time and the current time is less than or equal to the preset time threshold, determining that the accelerator is emergently stepped on.
And step 1016, when the difference value between the acquisition time and the current time is greater than a preset time threshold value, determining that the accelerator is not emergently stepped on.
For example, the preset time threshold is used to determine whether the accelerator opening is greatly changed within a short time, for example, the preset time threshold may be set to 30ms, and the preset time threshold may be set to a recommended value when the vehicle leaves a factory, or may be adjusted according to the driving habit and the driving environment of the driver. When the difference value between the acquisition time of the second key value pair and the current time is smaller than or equal to a preset time threshold value, the throttle opening is greatly changed in a short time, namely the throttle is emergently trodden.
Optionally, when it is determined that the accelerator is urgently stepped on and an obstacle exists in the designated area in step 103, the step of determining whether a risk exists according to the vehicle speed corresponding to the acquisition time and the preset vehicle speed may include:
and determining that the risk exists when the vehicle speed is greater than or equal to the preset vehicle speed.
And when the vehicle speed is less than the preset vehicle speed, determining that no risk exists.
For example, the preset vehicle speed is used to determine whether the current running speed of the vehicle is at risk when the accelerator is suddenly stepped. For example, the preset vehicle speed may be a low speed, for example, set to 20km/h, and under the condition that the vehicle speed is low, the vehicle speed will not be increased to a high speed in a short time even if the driver steps on the accelerator suddenly, so that when the vehicle speed is confirmed to be within 20km/h, the vehicle speed will not cause harm or has low risk to the driver and the surrounding environment, and it can be considered that no risk exists; however, the vehicle speed becomes higher if the accelerator is stepped on suddenly when the vehicle speed has reached a certain speed, and therefore, when it is determined that the driver has stepped on the accelerator suddenly and the vehicle speed has reached more than 20km/h, it is considered that the driver and the surrounding environment are harmed, i.e., it is determined that there is a risk.
FIG. 6 is a flow chart illustrating yet another method for preventing false tip-in, according to an exemplary embodiment, as shown in FIG. 6, the method further comprising:
and 105, when the risk is determined, sending prompt information to the vehicle, wherein the prompt information is used for giving an alarm prompt to a user.
For example, when it is determined that there is a risk, the prompt information may be divided into a sound prompt and a signal light prompt, for example, a horn of the vehicle may be controlled by the industrial control unit to emit a warning sound, a dashboard of the vehicle may be controlled to display a warning symbol to remind the driver that there is a risk and that the driver should stop stepping on the accelerator.
In summary, the method and the device for detecting the accelerator pedal opening determine whether the accelerator is emergently trodden according to the change of the accelerator opening in a short time, determine whether an obstacle exists in the designated area through the acquired monitoring image, and determine whether the accelerator is in danger according to the relation between the current vehicle speed and the preset vehicle speed under the condition that the two conditions that the accelerator is emergently trodden and the obstacle exists in the designated area are met simultaneously. When the risk exists in the judgment, the vehicle is controlled to brake, oil transportation of the oil way is stopped, and the effect of improving the accuracy of judging the mistaken stepping on the accelerator and the control degree of the vehicle is achieved.
Fig. 7 is a block diagram illustrating an apparatus for preventing a false tip-in, according to an exemplary embodiment, and as shown in fig. 7, the apparatus 200 is applied to a vehicle, and includes:
and the stepping detection module 201 is used for determining whether the accelerator is stepped on emergently according to the current accelerator opening acquired at the current time.
The monitoring module 202 is configured to monitor whether an obstacle exists in a designated area in a monitoring image acquired by the camera device, where the designated area is an area in the monitoring image corresponding to an area in a preset range in front of the vehicle.
And the risk detection module 203 is used for determining whether a risk exists according to the vehicle speed corresponding to the acquisition time and a preset vehicle speed when the accelerator is determined to be emergently stepped and an obstacle exists in the designated area.
And the control module 204 is used for sending a braking instruction to the electronic control unit and controlling the oil path to stop oil transportation when the risk is determined.
FIG. 8 is a block diagram illustrating another apparatus for preventing false tip-in, according to an exemplary embodiment, where the monitoring module 202, as shown in FIG. 8, includes:
the acquisition submodule 2021 is configured to acquire a monitoring image acquired by the image capturing apparatus at a preset frequency.
And the monitoring submodule 2022 is configured to determine whether an obstacle exists in the designated area according to the two-dimensional entropy of the monitored image.
Optionally, the monitoring images include n monitoring images acquired continuously, and the monitored sub-module 2022 is configured to:
and respectively carrying out histogram equalization processing on the designated areas of the n continuously acquired monitoring images to obtain the equalized gray value of each pixel in the designated areas of the n monitoring images.
And acquiring the two-dimensional entropy of the designated area of the n monitoring images according to the equalized gray value of each pixel in the designated area of the n monitoring images.
And determining whether the barrier exists in the designated area or not according to the two-dimensional entropy of the designated area of the n monitoring images and the reference two-dimensional entropy, wherein the reference two-dimensional entropy is the two-dimensional entropy when the barrier does not exist in the designated area.
And when the two-dimensional entropy of the designated area of the n monitoring images is larger than the reference two-dimensional entropy, determining that an obstacle exists in the designated area, wherein n is a positive integer.
Optionally, the monitoring sub-module 2022 is specifically configured to:
and calculating the pixel gray distribution characteristics of the designated areas of the n monitoring images according to the equalized gray value of each pixel in the designated areas of the n monitoring images and the neighborhood gray average value of each pixel.
And calculating the two-dimensional entropy of the designated area of the n monitoring images according to the pixel gray scale distribution characteristics of the designated area of the n monitoring images.
The formula for calculating the pixel gray distribution characteristics comprises the following steps:
pij＝f(Gi,Ei)/N
wherein p isijIs a pixelCharacteristic of gray scale distribution, GiEqualized gray value for the ith pixel in a designated area of any one of the monitored images, EiThe gray level mean value of the neighborhood pixels of the ith pixel, f (G)i,Ei) Is a binary group (G) composed of equalized gray value of the ith pixel and average gray value of adjacent pixels of the ith pixeli,Ei) N represents the number of pixels in a specified area of the monitored image, where 1 ≦ Gi≤255，1≤Ei≤255。
The formula for calculating the two-dimensional entropy includes:
wherein H is the two-dimensional entropy of the monitoring image.
FIG. 9 is a block diagram illustrating yet another apparatus for preventing false tip-in, according to an exemplary embodiment, where the monitoring module 202 further includes, as shown in FIG. 9:
and the region detection submodule 2023 is configured to determine, before the monitoring submodule 2022 performs the step of determining whether an obstacle exists in the designated region according to the two-dimensional entropy of the monitored image, a region in the monitored image corresponding to a region in a preset range in front of the vehicle as the designated region according to the world coordinate system, the camera coordinate system, the pixel coordinate system, and an included angle between the camera and the world coordinate system.
Fig. 10 is a block diagram illustrating still another apparatus for preventing false stepping on the accelerator according to an exemplary embodiment, and as shown in fig. 10, the stepping detection module 201 includes:
the information storage sub-module 2011 is configured to store the current time and the current accelerator opening as the first key value pair.
The accelerator opening recognition sub-module 2012 is configured to determine whether the current accelerator opening is greater than a first opening threshold.
The information obtaining submodule 2013 is configured to, when the current accelerator opening is greater than a first opening threshold, obtain, in a stored historical key value pair, a second key value pair in which the accelerator opening is smaller than a second opening threshold, where the second opening threshold is smaller than the first opening threshold, and a difference between the first opening threshold and the second opening threshold is greater than a preset difference.
And an acquisition time identification sub-module 2014, configured to determine whether a difference between the acquisition time of the second key-value pair and the current time is less than or equal to a preset time threshold.
The determining submodule 2015 is used for determining that the accelerator is emergently stepped when the difference value between the acquisition time and the current time is smaller than or equal to a preset time threshold.
The determining submodule 2015 is further configured to determine that the accelerator is not urgently stepped on when a difference between the acquisition time and the current time is greater than a preset time threshold.
Optionally, the risk detection module 203 is configured to:
and determining that the risk exists when the vehicle speed is greater than or equal to the preset vehicle speed.
And when the vehicle speed is less than the preset vehicle speed, determining that no risk exists.
Fig. 11 is a block diagram illustrating still another apparatus for preventing false stepping on a gas according to an exemplary embodiment, as shown in fig. 11, further comprising:
and the prompting module 205 is used for sending prompting information to the vehicle when the risk is determined to exist, wherein the prompting information is used for giving an alarm prompt to a user.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
In summary, the method and the device for detecting the accelerator pedal opening determine whether the accelerator is emergently trodden according to the change of the accelerator opening in a short time, determine whether an obstacle exists in the designated area through the acquired monitoring image, and determine whether the accelerator is in danger according to the relation between the current vehicle speed and the preset vehicle speed under the condition that the two conditions that the accelerator is emergently trodden and the obstacle exists in the designated area are met simultaneously. When the risk exists in the judgment, the vehicle is controlled to brake, oil transportation of the oil way is stopped, and the effect of improving the accuracy of judging the mistaken stepping on the accelerator and the control degree of the vehicle is achieved.
Preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and other embodiments of the present disclosure may be easily conceived by those skilled in the art within the technical spirit of the present disclosure after considering the description and practicing the present disclosure, and all fall within the protection scope of the present disclosure.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. Meanwhile, any combination can be made between various different embodiments of the disclosure, and the disclosure should be regarded as the disclosure of the disclosure as long as the combination does not depart from the idea of the disclosure. The present disclosure is not limited to the precise structures that have been described above, and the scope of the present disclosure is limited only by the appended claims.

Claims (16)

1. A method for preventing mistaken stepping on the accelerator is applied to a vehicle, and is characterized by comprising the following steps:
determining whether the accelerator is emergently trodden according to the current accelerator opening acquired at the current time;
monitoring whether an obstacle exists in a designated area in a monitoring image acquired by a camera device, wherein the designated area is an area in the monitoring image corresponding to an area in a preset range in front of the vehicle;
when it is determined that the accelerator is emergently stepped and an obstacle exists in the designated area, determining whether a risk exists according to the vehicle speed corresponding to the acquisition time and a preset vehicle speed;
and when the risk is determined, sending a braking instruction to the electronic control unit, and controlling the oil way to stop oil transportation.
2. The method according to claim 1, wherein the monitoring whether an obstacle exists in a specified area in a monitoring image acquired by the camera device comprises:
acquiring the monitoring image acquired by the camera equipment at a preset frequency;
and determining whether an obstacle exists in the designated area or not according to the two-dimensional entropy of the monitoring image.
3. The method of claim 2, wherein the monitored images comprise n continuously acquired monitored images, and the determining whether the obstacle exists in the designated area according to the two-dimensional entropy of the monitored images comprises:
respectively carrying out histogram equalization processing on designated areas of n continuously acquired monitoring images to obtain an equalized gray value of each pixel in the designated areas of the n monitoring images;
acquiring two-dimensional entropy of the designated areas of the n monitoring images according to the equalized gray value of each pixel in the designated areas of the n monitoring images;
determining whether an obstacle exists in the designated area according to the two-dimensional entropy and a reference two-dimensional entropy of the designated area of the n monitoring images, wherein the reference two-dimensional entropy is the two-dimensional entropy when no obstacle exists in the designated area;
and when the two-dimensional entropy of the designated area of the n monitoring images is larger than the reference two-dimensional entropy, determining that an obstacle exists in the designated area, wherein n is a positive integer.
4. The method according to claim 3, wherein the obtaining the two-dimensional entropy of the n monitoring images according to the gray balance values of the n monitoring images comprises:
calculating the pixel gray distribution characteristics of the designated areas of the n monitoring images according to the equalized gray value of each pixel in the designated areas of the n monitoring images and the neighborhood gray average value of each pixel;
calculating the two-dimensional entropy of the designated area of the n monitoring images according to the pixel gray scale distribution characteristics of the designated area of the n monitoring images;
wherein the formula for calculating the pixel gray scale distribution characteristics comprises:
pij＝f(Gi,Ei)/N
wherein p isijFor the pixel gray distribution characteristics, GiEqualized gray value for the ith pixel in a designated area of any one of the monitored images, EiIs the gray level mean of the pixels in the neighborhood of the ith pixel, f (G)i,Ei) A binary group (G) composed of the equalized gray value of the ith pixel and the gray average value of the pixels in the neighborhood of the ith pixeli,Ei) N represents the number of pixels in a specified area of the monitored image, wherein 1 ≦ Gi≤255，1≤Ei≤255；
The formula for calculating the two-dimensional entropy includes:
<mrow> <mi>H</mi> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>0</mn> </mrow> <mn>255</mn> </munderover> <msub> <mi>p</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>*</mo> <msub> <mi>logp</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> </mrow>
and H is the two-dimensional entropy of the monitoring image.
5. The method of claim 2, further comprising, prior to said determining whether an obstacle is present in said designated area based on the two-dimensional entropy of said monitored image:
and determining the area of the preset range in front of the vehicle, which corresponds to the area in the monitoring image, as the designated area according to a world coordinate system, a camera equipment coordinate system, a pixel coordinate system and an included angle between the camera equipment and the world coordinate system.
6. The method of claim 1, wherein the determining whether the throttle is suddenly stepped according to the current throttle opening collected at the current time comprises:
saving the current time and the current accelerator opening as a first key value pair;
determining whether the current accelerator opening is larger than a first opening threshold value;
when the current accelerator opening is larger than the first opening threshold, obtaining a second key value pair of which the accelerator opening is smaller than a second opening threshold from stored historical key value pairs, wherein the second opening threshold is smaller than the first opening threshold, and the difference between the first opening threshold and the second opening threshold is larger than a preset difference;
determining whether the difference value between the acquisition time of the second key-value pair and the current time is less than or equal to a preset time threshold value;
when the difference value between the acquisition time and the current time is less than or equal to the preset time threshold value, determining that the accelerator is emergently stepped on;
and when the difference value between the acquisition time and the current time is greater than the preset time threshold value, determining that the accelerator is not emergently trodden.
7. The method according to claim 6, wherein the determining whether a risk exists according to the vehicle speed corresponding to the acquisition time and a preset vehicle speed comprises:
when the vehicle speed is greater than or equal to the preset vehicle speed, determining that a risk exists;
and when the vehicle speed is less than the preset vehicle speed, determining that no risk exists.
8. The method according to any of claims 1-7, wherein the method further comprises:
and when the risk is determined, sending prompt information to the vehicle, wherein the prompt information is used for giving an alarm prompt to a user.
9. A device for preventing mistaken stepping on the accelerator is applied to a vehicle and is characterized by comprising:
the pedaling detection module is used for determining whether the accelerator is pedaled emergently according to the current accelerator opening acquired at the current time;
the monitoring module is used for monitoring whether an obstacle exists in a designated area in a monitoring image acquired by the camera equipment, wherein the designated area is an area in a preset range in front of the vehicle, and the area corresponds to the monitoring image;
the risk detection module is used for determining whether a risk exists or not according to the vehicle speed corresponding to the acquisition time and a preset vehicle speed when the accelerator is determined to be emergently stepped and an obstacle exists in the specified area;
and the control module is used for sending a braking instruction to the electronic control unit and controlling the oil way to stop oil transportation when the risk is determined.
10. The apparatus of claim 9, wherein the monitoring module comprises:
the acquisition submodule is used for acquiring the monitoring image acquired by the camera shooting equipment at a preset frequency;
and the monitoring submodule is used for determining whether the barrier exists in the designated area or not according to the two-dimensional entropy of the monitored image.
11. The apparatus of claim 10, wherein the monitoring images comprise n monitoring images acquired in succession, the monitoring sub-module being configured to:
respectively carrying out histogram equalization processing on designated areas of n continuously acquired monitoring images to obtain an equalized gray value of each pixel in the designated areas of the n monitoring images;
acquiring two-dimensional entropy of the designated areas of the n monitoring images according to the equalized gray value of each pixel in the designated areas of the n monitoring images;
determining whether an obstacle exists in the designated area according to the two-dimensional entropy and a reference two-dimensional entropy of the designated area of the n monitoring images, wherein the reference two-dimensional entropy is the two-dimensional entropy when no obstacle exists in the designated area;
and when the two-dimensional entropy of the designated area of the n monitoring images is larger than the reference two-dimensional entropy, determining that an obstacle exists in the designated area, wherein n is a positive integer.
12. The apparatus of claim 11, wherein the monitoring submodule is configured to:
calculating the pixel gray distribution characteristics of the designated areas of the n monitoring images according to the equalized gray value of each pixel in the designated areas of the n monitoring images and the neighborhood gray average value of each pixel;
calculating the two-dimensional entropy of the designated area of the n monitoring images according to the pixel gray scale distribution characteristics of the designated area of the n monitoring images;
wherein the formula for calculating the pixel gray scale distribution characteristics comprises:
pij＝f(Gi,Ei)/N
wherein p isijFor the pixel gray distribution characteristics, GiEqualized gray value for the ith pixel in a designated area of any one of the monitored images, EiIs the gray level mean of the pixels in the neighborhood of the ith pixel, f (G)i,Ei) A binary group (G) composed of the equalized gray value of the ith pixel and the gray average value of the pixels in the neighborhood of the ith pixeli,Ei) N represents the number of pixels in a specified area of the monitored imageWherein 1 is less than or equal to Gi≤255，1≤Ei≤255；
The formula for calculating the two-dimensional entropy includes:
<mrow> <mi>H</mi> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>0</mn> </mrow> <mn>255</mn> </munderover> <msub> <mi>p</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>*</mo> <msub> <mi>logp</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> </mrow>
and H is the two-dimensional entropy of the monitoring image.
13. The apparatus of claim 10, wherein the monitoring module further comprises:
and the area detection submodule is used for determining an area corresponding to the area in the monitoring image in the preset range in front of the vehicle as the designated area according to a world coordinate system, a camera equipment coordinate system, a pixel coordinate system and an included angle between the camera equipment and the world coordinate system before determining whether the designated area has the obstacle according to the two-dimensional entropy of the monitoring image.
14. The apparatus of claim 9, wherein the tread detection module comprises:
the information storage submodule is used for storing the current time and the current accelerator opening as a first key value pair;
the accelerator opening identification submodule is used for determining whether the current accelerator opening is larger than a first opening threshold value;
the information acquisition submodule is used for acquiring a second key value pair of which the throttle opening is smaller than a second throttle opening threshold from stored historical key value pairs when the current throttle opening is larger than the first throttle opening threshold, wherein the second throttle opening threshold is smaller than the first throttle opening threshold, and the difference between the first throttle opening threshold and the second throttle opening threshold is larger than a preset difference;
the acquisition time identification submodule is used for determining whether the difference value between the acquisition time of the second key value pair and the current time is less than or equal to a preset time threshold value;
the determining submodule is used for determining that the accelerator is emergently trodden when the difference value between the acquisition time and the current time is smaller than or equal to the preset time threshold;
the determining submodule is further used for determining that the accelerator is not emergently stepped on when the difference value between the acquisition time and the current time is larger than the preset time threshold.
15. The apparatus of claim 14, wherein the risk detection module is configured to:
when the vehicle speed is greater than or equal to the preset vehicle speed, determining that a risk exists;
and when the vehicle speed is less than the preset vehicle speed, determining that no risk exists.
16. The apparatus according to any of claims 9-15, wherein the apparatus further comprises:
and the prompting module is used for sending prompting information to the vehicle when the risk is determined to exist, and the prompting information is used for giving an alarm to a user.
CN201710365451.9A 2017-05-22 2017-05-22 The method and apparatus for preventing mis-accelerator pressing Active CN107187436B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710365451.9A CN107187436B (en) 2017-05-22 2017-05-22 The method and apparatus for preventing mis-accelerator pressing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710365451.9A CN107187436B (en) 2017-05-22 2017-05-22 The method and apparatus for preventing mis-accelerator pressing

Publications (2)

Publication Number Publication Date
CN107187436A true CN107187436A (en) 2017-09-22
CN107187436B CN107187436B (en) 2019-07-26

Family

ID=59875936

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710365451.9A Active CN107187436B (en) 2017-05-22 2017-05-22 The method and apparatus for preventing mis-accelerator pressing

Country Status (1)

Country Link
CN (1) CN107187436B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109353217A (en) * 2018-10-31 2019-02-19 重庆长安汽车股份有限公司 A kind of traffic safety control method, apparatus and system
CN109606107A (en) * 2019-01-28 2019-04-12 哈工大机器人（岳阳）军民融合研究院 Electronic accelerator system with Anti-mis-stepping function
CN110103910A (en) * 2019-05-29 2019-08-09 广州小鹏汽车科技有限公司 A kind of brake control method of vehicle, device, system and vehicle
CN110228454A (en) * 2019-06-18 2019-09-13 威马智慧出行科技（上海）有限公司 Automotive throttle prevents from accidentally stepping on method, electronic equipment and automobile
CN110415204A (en) * 2019-03-22 2019-11-05 泰州三凯工程技术有限公司 Reliable safety traffic control system
CN113815411A (en) * 2020-06-19 2021-12-21 比亚迪股份有限公司 Calibration method and device, storage medium, new energy automobile and control method
CN113978477A (en) * 2021-09-24 2022-01-28 合众新能源汽车有限公司 Method for correcting mistaken stepping of accelerator pedal
CN114851843A (en) * 2022-03-11 2022-08-05 湖北文理学院 Automobile accelerator mistaken stepping prevention control device

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080008355A1 (en) * 2006-07-05 2008-01-10 Fujitsu Ten Limited Image recognition apparatus, image recognition method, and vehicle control apparatus
JP2013233893A (en) * 2012-05-10 2013-11-21 Mitsubishi Motors Corp Running control device
CN204527174U (en) * 2015-02-13 2015-08-05 重庆交通大学 Mis-accelerator pressing dead-man's device
CN205554112U (en) * 2016-05-03 2016-09-07 湖南科技大学 Miss intelligence anticollision initiative control system that steps on gas
CN106143144A (en) * 2015-04-28 2016-11-23 上海日野发动机有限公司 The intelligent safety control system of vehicle and vehicle

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080008355A1 (en) * 2006-07-05 2008-01-10 Fujitsu Ten Limited Image recognition apparatus, image recognition method, and vehicle control apparatus
JP2013233893A (en) * 2012-05-10 2013-11-21 Mitsubishi Motors Corp Running control device
CN204527174U (en) * 2015-02-13 2015-08-05 重庆交通大学 Mis-accelerator pressing dead-man's device
CN106143144A (en) * 2015-04-28 2016-11-23 上海日野发动机有限公司 The intelligent safety control system of vehicle and vehicle
CN205554112U (en) * 2016-05-03 2016-09-07 湖南科技大学 Miss intelligence anticollision initiative control system that steps on gas

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
谈凛，叶忻泉等: "汽车油门防误踩系统设计", 《温州大学学报·自然科学版》 *

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109353217A (en) * 2018-10-31 2019-02-19 重庆长安汽车股份有限公司 A kind of traffic safety control method, apparatus and system
CN109606107A (en) * 2019-01-28 2019-04-12 哈工大机器人（岳阳）军民融合研究院 Electronic accelerator system with Anti-mis-stepping function
CN110415204A (en) * 2019-03-22 2019-11-05 泰州三凯工程技术有限公司 Reliable safety traffic control system
CN110415204B (en) * 2019-03-22 2020-07-10 施伟红 Reliable type safe driving control system
CN110103910A (en) * 2019-05-29 2019-08-09 广州小鹏汽车科技有限公司 A kind of brake control method of vehicle, device, system and vehicle
CN110228454A (en) * 2019-06-18 2019-09-13 威马智慧出行科技（上海）有限公司 Automotive throttle prevents from accidentally stepping on method, electronic equipment and automobile
CN113815411A (en) * 2020-06-19 2021-12-21 比亚迪股份有限公司 Calibration method and device, storage medium, new energy automobile and control method
CN113815411B (en) * 2020-06-19 2023-11-14 比亚迪股份有限公司 Calibration method and device, storage medium, new energy automobile and control method
CN113978477A (en) * 2021-09-24 2022-01-28 合众新能源汽车有限公司 Method for correcting mistaken stepping of accelerator pedal
CN113978477B (en) * 2021-09-24 2024-04-05 合众新能源汽车股份有限公司 Correction method for mistaken stepping of accelerator pedal
CN114851843A (en) * 2022-03-11 2022-08-05 湖北文理学院 Automobile accelerator mistaken stepping prevention control device

Also Published As

Publication number Publication date
CN107187436B (en) 2019-07-26

Similar Documents

Publication Publication Date Title
CN107187436B (en) The method and apparatus for preventing mis-accelerator pressing
CN112987759A (en) Image processing method, device and equipment based on automatic driving and storage medium
JP6459659B2 (en) Image processing apparatus, image processing method, driving support system, program
KR101083885B1 (en) Intelligent driving assistant systems
US20020154217A1 (en) Apparatus and method of recognizing vehicle travelling behind
CN108162858B (en) Vehicle-mounted monitoring device and method thereof
JP4707067B2 (en) Obstacle discrimination device
WO2019192145A1 (en) Method and apparatus for adjusting field of view of panoramic image, storage medium, and electronic device
US20140071240A1 (en) Free space detection system and method for a vehicle using stereo vision
CN112158197B (en) Vehicle blind area obstacle avoiding method, device and system
JP2002308030A (en) Periphery monitoring system for vehicle
TW201144115A (en) Dual vision front vehicle safety alarm device and method thereof
KR20170127036A (en) Method and apparatus for detecting and assessing road reflections
JP6315308B2 (en) Control object identification device, mobile device control system, and control object recognition program
CN111052174A (en) Image processing apparatus, image processing method, and program
JP2020164316A (en) Monitoring device
CN114763136A (en) Guide vehicle driving auxiliary system based on deep learning
CN116486351A (en) Driving early warning method, device, equipment and storage medium
CN112009470A (en) Vehicle running control method, device, equipment and storage medium
JP2009241636A (en) Driving support system
JP2013244852A (en) Device, method and program of parking support
CN116691722A (en) Early warning method and device for vehicle collision, electronic equipment and storage medium
US11383733B2 (en) Method and system for detecting a dangerous driving condition for a vehicle, and non-transitory computer readable medium storing program for implementing the method
JP3226699B2 (en) Perimeter monitoring device for vehicles
KR102174423B1 (en) Method And Apparatus for Detection of Parking Loss for Automatic Parking

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