CN110633699A - Visual detection method for parking behavior of interaction area of AGV intelligent parking system - Google Patents
Visual detection method for parking behavior of interaction area of AGV intelligent parking system Download PDFInfo
- Publication number
- CN110633699A CN110633699A CN201910955499.4A CN201910955499A CN110633699A CN 110633699 A CN110633699 A CN 110633699A CN 201910955499 A CN201910955499 A CN 201910955499A CN 110633699 A CN110633699 A CN 110633699A
- Authority
- CN
- China
- Prior art keywords
- vehicle body
- vehicle
- area
- value
- coordinate
- 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
-
- E—FIXED CONSTRUCTIONS
- E04—BUILDING
- E04H—BUILDINGS OR LIKE STRUCTURES FOR PARTICULAR PURPOSES; SWIMMING OR SPLASH BATHS OR POOLS; MASTS; FENCING; TENTS OR CANOPIES, IN GENERAL
- E04H6/00—Buildings for parking cars, rolling-stock, aircraft, vessels or like vehicles, e.g. garages
- E04H6/42—Devices or arrangements peculiar to garages, not covered elsewhere, e.g. securing devices, safety devices, monitoring and operating schemes; centering devices
- E04H6/426—Parking guides
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Abstract
The invention discloses a visual detection method for parking behaviors of an interactive area of an AGV intelligent parking system, which accurately identifies vehicle targets in the interactive area of the AGV intelligent parking system through vision, extracts and analyzes information such as vehicle body oblique angles, vehicle body positions and the like when the vehicle targets are in a static state, realizes effective identification of various parking behaviors, judges whether the parking behaviors of the vehicles are standard or not, provides effective information for an automatic parking robot to carry the vehicles, and thus effectively improves the intelligent level of management of the AGV parking system.
Description
Technical Field
The invention relates to the technical field of intelligent parking system design and management, in particular to a visual detection method for parking behaviors of an interactive area of an AGV intelligent parking system.
Background
At present, with the rapid increase of the number of motor vehicles kept in China, the problem of difficult parking is increasingly highlighted. The AGV intelligent parking system can effectively relieve the problem of difficult parking, however, the parking states of the interaction area of the system are various, and when the automatic parking robot does not reach the vicinity of the vehicle, the specific position of the vehicle in the interaction area and the oblique angle of the vehicle body are difficult to rapidly judge only by a sensor arranged on the automatic parking robot, so that the working efficiency of the system is influenced. In addition, since the interaction area of the parking system is influenced by environmental conditions, the normal working space of the parking robot is limited, and the parking robot cannot drill into the bottom of the vehicle anyway, which means that certain parking states of the vehicle, such as the vehicle body having an excessively large oblique angle, the vehicle body exceeding the working boundary of the interaction area, and the like, influence the normal operation of the system. The invention defines the parking behavior which does not influence the normal operation of the automatic parking robot as the standard parking behavior, otherwise, the parking behavior is defined as the illegal parking behavior.
Therefore, the invention hopes to extract the accurate position of the vehicle in the interactive area and judge whether the parking behavior of the vehicle is standard or not by designing a visual detection method for the parking behavior of the interactive area of the AGV intelligent parking system, thereby providing effective information for the automatic parking robot to carry the vehicle.
Disclosure of Invention
The invention aims to overcome the defects and shortcomings of the prior art, provides a visual detection method for parking behaviors in an interaction area of an AGV intelligent parking system, has the characteristics of simple structure, convenience in use, low cost and the like, accurately identifies vehicle targets in the interaction area of the AGV intelligent parking system through vision, extracts and analyzes information such as vehicle body oblique angles, vehicle body positions and the like when the vehicle targets are in a static state, realizes effective identification of various parking behaviors, judges whether the parking behaviors of the vehicles are standard or not, provides effective information for an automatic parking robot to carry the vehicles, and accordingly effectively improves the intelligent level of management of the AGV parking system.
In order to achieve the purpose, the technical scheme provided by the invention is as follows: the visual detection method for the parking behavior of the interactive area of the AGV intelligent parking system comprises the following steps of:
1) video information of an interaction area of the AGV intelligent parking system is acquired through a camera arranged right above the interaction area of the AGV intelligent parking system, the video information is transmitted to a computer, and then video frames are preprocessed through the computer;
2) obtaining a foreground image by adopting a moving target detection algorithm, extracting contours of the foreground image, calculating the area of a minimum circumscribed rectangle of each contour, and setting a threshold range of the area of a vehicle; if the area of the minimum circumscribed rectangle of the outline exceeds the threshold range of the area of the vehicle, the outline is judged to be a non-vehicle target; if the area of the minimum circumscribed rectangle of the outline is within the threshold range of the area of the vehicle, the outline is judged to be a vehicle target, the minimum circumscribed rectangle of the outline is the minimum circumscribed rectangle of the vehicle body, and the angle of the minimum circumscribed rectangle of the outline is the oblique angle of the vehicle body;
3) after the vehicle target is obtained, calculating the mass center coordinate of the vehicle target of the continuous video frames and the average value of the mass center coordinate displacement, and simultaneously setting a displacement threshold; if the average value is larger than the displacement threshold value, the vehicle target is judged to be in a motion state; if the average value is less than or equal to the displacement threshold value, determining that the vehicle target is in a static state; adopting a pixel coordinate system as a common coordinate system where all coordinate values in the image are located, wherein the origin of the pixel coordinate system is at the upper left corner of the image, the horizontal direction is the x axis, the horizontal coordinate value is increased to the right, the longitudinal direction is the y axis, and the vertical coordinate value is increased to the lower side;
4) after the vehicle target is judged to be in a static state, the coordinates of four vertexes of the minimum external rectangle of the vehicle body are calculated by utilizing the minimum external rectangle of the vehicle body and the oblique angle of the vehicle body obtained in the state;
5) setting threshold value ranges of horizontal and vertical coordinates and allowable threshold values of a vehicle body oblique angle of an interaction area of the AGV intelligent parking system; in a static state of a vehicle target, if coordinates of four vertexes of a minimum external rectangle of a vehicle body are within threshold values of horizontal and vertical coordinates of an interaction area of the AGV intelligent parking system, and an oblique angle of the vehicle body is within an allowable threshold value of the oblique angle of the vehicle body, determining that the parking behavior is standard; and if the coordinates of the four vertexes of the minimum external rectangle of the vehicle body are not completely in the threshold ranges of the horizontal coordinate and the vertical coordinate of the interaction area of the AGV intelligent parking system, or the oblique angle of the vehicle body exceeds the allowable threshold value of the oblique angle of the vehicle body, judging that the illegal parking behavior is caused.
In the step 1), the camera is installed right above the interaction area of the AGV intelligent parking system, collects video information containing the complete interaction area of the AGV intelligent parking system from a top view angle, and transmits the video information to the computer.
In step 2), a moving object detection algorithm is adopted to obtain a foreground image, contour extraction is carried out on the foreground image, and a contour set S ═ C is obtainedi1,2,3, …, n, where C isiRepresenting the ith contour in S, and n representing the number of contours in S; calculate the minimum bounding rectangle R of each contour in SiI ═ 1,2,3, …, n, the condition will not be met: t is1≤Ai≤T2Is removed from S to obtain the vehicle target, wherein aiRepresents RiArea of (d), T1And T2Respectively representing the minimum and maximum thresholds for the set vehicle area.
In step 3), the centroid coordinate PC (x) of the vehicle target is calculated according to the following equationPC,yPC):
In the formula, A represents a pixel area occupied by a vehicle target; k represents the total number of pixel points in the area A; x is the number ofmAnd ymRespectively representing the abscissa value and the ordinate value of the pixel point in the area A;
the mean value s of the centroid coordinate displacements for successive k frames is calculated according to the following equation:
in the formula (x)i+1,yi+1)、(xi,yi) Respectively representing the coordinates of the centroid at the (i + 1) th frame and the ith frame;
s is compared with a set displacement threshold T3Comparing if s is less than or equal to T3If the target is in the static state, the target is judged to be in the moving state, otherwise, the target is judged to be in the static state.
In the step 4), under the pixel coordinate system, the x axis rotates anticlockwise, and the first side of the minimum circumscribed rectangle of the vehicle body is firstly met and defined as LHThe other with LHThe mutually perpendicular sides are defined as LWAnd the oblique angle theta of the vehicle body is x and LHThe value range of theta is [0 degrees and 90 degrees ];
in a static state, the vehicle body is divided into three states of left deviation, right deviation and body straightening according to different oblique angles of the vehicle body; when L isH>LWWhen the vehicle body deviates to the right; when L isH<LWIn time, two cases are distinguished: when theta is larger than 0 DEG, the vehicle body deviates to the left, and when theta is equal to 0 DEG, the vehicle body is straight;
among the four vertex coordinates of the minimum bounding rectangle of the vehicle body, the vertex point with the maximum longitudinal coordinate value is defined as P0 (x)P0,yP0) If the ordinate values of the two vertexes are maximum, the vertex having the maximum ordinate value and the minimum abscissa value is defined as P0 (x)P0,yP0) And the other three vertexes are represented by P0 (x)P0,yP0) As a starting point, sequentially defined as P1 (x) in clockwise orderP1,yP1)、P2(xP2,yP2)、P3(xP3,yP3);
Utilize minimum external rectangle limit L of automobile bodyH、LWBody lean angle θ and centroid coordinate PC (x) of vehicle targetPC,yPC) And calculating the coordinates P0 (x) of four vertexes of the minimum circumscribed rectangle of the vehicle bodyP0,yP0)、P1(xP1,yP1)、P2(xP2,yP2)、P3(xP3,yP3):
In the step 5), under the pixel coordinate system, the x axis rotates anticlockwise, and the first side of the minimum circumscribed rectangle of the vehicle body is firstly met and defined as LHThe other with LHThe mutually perpendicular sides are defined as LWAnd the oblique angle theta of the vehicle body is x and LHThe value range of theta is [0 degrees and 90 degrees ];
under the static state, the vehicle body is divided into three states of left deviation, right deviation and body straightening according to different oblique angles of the vehicle body. When L isH>LWWhen the vehicle body deviates to the right; when L isH<LWIn time, two cases are distinguished: when theta is larger than 0 DEG, the vehicle body deviates to the left, and when theta is equal to 0 DEG, the vehicle body is straight;
among the four vertex coordinates of the minimum bounding rectangle of the vehicle body, the vertex point with the maximum longitudinal coordinate value is defined as P0 (x)P0,yP0) If the ordinate values of the two vertexes are maximum, the vertex having the maximum ordinate value and the minimum abscissa value is defined as P0 (x)P0,yP0) And the other three vertexes are represented by P0 (x)P0,yP0) As a starting point, sequentially defined as P1 (x) in clockwise orderP1,yP1)、P2(xP2,yP2)、P3(xP3,yP3);
Setting the range of the abscissa threshold value of the interaction area of the AGV intelligent parking system as [ x ]PP1,xPP2]The range of the vertical coordinate threshold is [ y ]PP1,yPP2]And allowable threshold value theta of vehicle body oblique angleP,θPThe absolute value of an acute angle included angle formed by an axis where the vehicle driving direction is located and an axis where the vehicle body is right straight;
the coordinates P0 (x) of the four vertices of the minimum bounding rectangle of the vehicle body are determined according to the following equationP0,yP0)、P1(xP1,yP1)、P2(xP2,yP2)、P3(xP3,yP3) Whether the threshold ranges of the horizontal coordinate and the vertical coordinate in the interaction area of the AGV intelligent parking system are met:
if not, judging that the vehicle is in illegal parking behavior; if yes, continuously judging whether the vehicle body inclined angle theta meets one of the following conditions:
if so, judging that the parking behavior is standardized; if not, the illegal parking behavior is determined.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the specific position and the oblique angle of the vehicle body in the parking interaction area of the AGV intelligent parking system are extracted, effective information is provided for the automatic parking robot to carry the vehicle, and the working efficiency of the system is improved.
2. And judging whether the parking behavior is standard or not, so as to meet the normal operation of the AGV intelligent parking system.
3. The motion state of the vehicle is tracked in real time, and whether the vehicle is in a static state or not is effectively judged.
4. The device is convenient to install, low in cost, simple in detection algorithm, good in real-time performance and suitable for general application.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a schematic diagram of three states of the vehicle parking according to the present invention.
FIG. 3 is a schematic diagram of a vehicle exceeding a threshold range of a system interaction area in accordance with the present invention.
FIG. 4 is a schematic diagram of the vehicle body with a slant angle meeting the specification of the present invention.
FIG. 5 is a schematic diagram of the vehicle body oblique angle not meeting the specification in the present invention.
Detailed Description
The following is a further description with reference to specific examples.
Referring to fig. 1, the visual detection method for the parking behavior of the interactive area of the AGV intelligent parking system provided by the embodiment includes the following steps:
step 1: video information containing the complete interactive area of the AGV intelligent parking system is collected at a overlooking angle through a camera arranged right above the interactive area of the AGV intelligent parking system, the video information is transmitted to a computer, and then video frame images are preprocessed through an image enhancement technology on the computer. The image preprocessing method includes image graying, histogram equalization processing, and the like.
Step 2: extracting the background of the image by Gaussian mixture modeling, separating a foreground image by adopting a background difference method, and performing morphological processing, shadow detection and elimination on the foreground image. Carrying out contour extraction on the foreground image to obtain a contour set S ═ Ci1,2,3, …, n, where C isiRepresents the ith contour in S and n represents the number of contours in S. Calculate the minimum bounding rectangle R of each contour in SiI ═ 1,2,3, …, n, the condition will not be met: t is1≤Ai≤T2Is eliminated from S, thereby obtaining a vehicle target, wherein AiRepresents RiArea of (d), T1And T2Respectively representing the minimum and maximum thresholds for the set vehicle area.
And step 3: the centroid coordinate PC (x) of the vehicle target is calculated according to the following equationPC,yPC):
In the formula, A represents a pixel area occupied by a vehicle target; k represents the total number of pixel points in the area A; x is the number ofmAnd ymRespectively representing the abscissa value and the ordinate value of the pixel point in the area A.
The mean value s of the centroid coordinate displacements for successive k frames is calculated according to the following equation:
in the formula (x)i+1,yi+1)、(xi,yi) Representing the coordinates of the centroid at frame i +1 and frame i, respectively.
S is compared with a set displacement threshold T3Comparing if s is less than or equal to T3If the target is in the static state, the target is judged to be in the moving state, otherwise, the target is judged to be in the static state.
And 4, step 4: referring to FIG. 2, in the pixel coordinate system, the x-axis rotates counterclockwise, and the first side of the minimum bounding rectangle of the vehicle body is first defined as LHThe other with LHThe mutually perpendicular sides are defined as LWAnd the oblique angle theta of the vehicle body is x and LHThe angle of the side theta is in the range of 0 DEG and 90 deg.
Under the static state, the vehicle body is divided into three states of left deviation, right deviation and body straightening according to different oblique angles of the vehicle body. When L isH>LWWhen the vehicle body deviates to the right; when L isH<LWIn this case, the vehicle body is deviated to the left when θ > 0 °, and the vehicle body is straight when θ is 0 °.
Among the four vertex coordinates of the minimum bounding rectangle of the vehicle body, the vertex point with the maximum longitudinal coordinate value is defined as P0 (x)P0,yP0) If the ordinate values of the two vertexes are maximum, the vertex having the maximum ordinate value and the minimum abscissa value is defined as P0 (x)P0,yP0) And the other three vertexes are represented by P0 (x)P0,yP0) As a starting point, sequentially defined as P1 (x) in clockwise orderP1,yP1)、P2(xP2,yP2)、P3(xP3,yP3)。
Utilize minimum external rectangle limit L of automobile bodyH、LWBody lean angle θ and centroid coordinate PC (x) of vehicle targetPC,yPC) And calculating the coordinates P0 (x) of four vertexes of the minimum circumscribed rectangle of the vehicle bodyP0,yP0)、P1(xP1,yP1)、P2(xP2,yP2)、P3(xP3,yP3):
Step (ii) of5: and judging whether the parking is standard or not. Setting the range of the abscissa threshold value of the interaction area of the AGV intelligent parking system as [ x ]PP1,xPP2]The range of the vertical coordinate threshold is [ y ]PP1,yPP2]And allowable threshold value theta of vehicle body oblique angleP,θPThe absolute value of the acute angle included angle formed by the axis where the vehicle driving direction is located and the axis where the vehicle body is right straight.
The coordinates P0 (x) of the four vertices of the minimum bounding rectangle of the vehicle body are determined according to the following equationP0,yP0)、P1(xP1,yP1)、P2(xP2,yP2)、P3(xP3,yP3) Whether the threshold ranges of the horizontal coordinate and the vertical coordinate in the interaction area of the AGV intelligent parking system are met:
if the condition is not met, referring to the condition shown in FIG. 3, judging that the parking behavior is illegal; if yes, continuously judging whether the vehicle body inclined angle theta meets one of the following conditions:
if the parking behavior is satisfied, referring to fig. 4, judging that the parking behavior is normative; if not, see FIG. 5, it is determined as an illegal parking maneuver.
The above-mentioned embodiments are merely preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, so that the changes in the shape and principle of the present invention should be covered within the protection scope of the present invention.
Claims (6)
- The visual detection method for the parking behavior of the interactive area of the AGV intelligent parking system is characterized by comprising the following steps of:1) video information of an interaction area of the AGV intelligent parking system is acquired through a camera arranged right above the interaction area of the AGV intelligent parking system, the video information is transmitted to a computer, and then video frames are preprocessed through the computer;2) obtaining a foreground image by adopting a moving target detection algorithm, extracting contours of the foreground image, calculating the area of a minimum circumscribed rectangle of each contour, and setting a threshold range of the area of a vehicle; if the area of the minimum circumscribed rectangle of the outline exceeds the threshold range of the area of the vehicle, the outline is judged to be a non-vehicle target; if the area of the minimum circumscribed rectangle of the outline is within the threshold range of the area of the vehicle, the outline is judged to be a vehicle target, the minimum circumscribed rectangle of the outline is the minimum circumscribed rectangle of the vehicle body, and the angle of the minimum circumscribed rectangle of the outline is the oblique angle of the vehicle body;3) after the vehicle target is obtained, calculating the mass center coordinate of the vehicle target of the continuous video frames and the average value of the mass center coordinate displacement, and simultaneously setting a displacement threshold; if the average value is larger than the displacement threshold value, the vehicle target is judged to be in a motion state; if the average value is less than or equal to the displacement threshold value, determining that the vehicle target is in a static state; adopting a pixel coordinate system as a common coordinate system where all coordinate values in the image are located, wherein the origin of the pixel coordinate system is at the upper left corner of the image, the horizontal direction is the x axis, the horizontal coordinate value is increased to the right, the longitudinal direction is the y axis, and the vertical coordinate value is increased to the lower side;4) after the vehicle target is judged to be in a static state, the coordinates of four vertexes of the minimum external rectangle of the vehicle body are calculated by utilizing the minimum external rectangle of the vehicle body and the oblique angle of the vehicle body obtained in the state;5) setting threshold value ranges of horizontal and vertical coordinates and allowable threshold values of a vehicle body oblique angle of an interaction area of the AGV intelligent parking system; in a static state of a vehicle target, if coordinates of four vertexes of a minimum external rectangle of a vehicle body are within threshold values of horizontal and vertical coordinates of an interaction area of the AGV intelligent parking system, and an oblique angle of the vehicle body is within an allowable threshold value of the oblique angle of the vehicle body, determining that the parking behavior is standard; and if the coordinates of the four vertexes of the minimum external rectangle of the vehicle body are not completely in the threshold ranges of the horizontal coordinate and the vertical coordinate of the interaction area of the AGV intelligent parking system, or the oblique angle of the vehicle body exceeds the allowable threshold value of the oblique angle of the vehicle body, judging that the illegal parking behavior is caused.
- 2. The visual inspection method of AGV intelligent parking system interaction area parking behavior according to claim 1, wherein: in the step 1), the camera is installed right above the interaction area of the AGV intelligent parking system, collects video information containing the complete interaction area of the AGV intelligent parking system from a top view angle, and transmits the video information to the computer.
- 3. The visual inspection method of AGV intelligent parking system interaction area parking behavior according to claim 1, wherein: in step 2), a moving object detection algorithm is adopted to obtain a foreground image, contour extraction is carried out on the foreground image, and a contour set S ═ C is obtainedi1,2,3, …, n, where C isiRepresenting the ith contour in S, and n representing the number of contours in S; calculate the minimum bounding rectangle R of each contour in SiI ═ 1,2,3, …, n, the condition will not be met: t is1≤Ai≤T2Is removed from S to obtain the vehicle target, wherein aiRepresents RiArea of (d), T1And T2Respectively representing the minimum and maximum thresholds for the set vehicle area.
- 4. The visual inspection method of AGV intelligent parking system interaction area parking behavior according to claim 1, wherein: in step 3), the centroid coordinate PC (x) of the vehicle target is calculated according to the following equationPC,yPC):In the formula, A represents a pixel area occupied by a vehicle target; k represents the total number of pixel points in the area A; x is the number ofmAnd ymRespectively representing the abscissa value and the ordinate value of the pixel point in the area A;the mean value s of the centroid coordinate displacements for successive k frames is calculated according to the following equation:in the formula (x)i+1,yi+1)、(xi,yi) Respectively representing the coordinates of the centroid at the (i + 1) th frame and the ith frame;s is compared with a set displacement threshold T3Comparing if s is less than or equal to T3If the target is in the static state, the target is judged to be in the moving state, otherwise, the target is judged to be in the static state.
- 5. The visual inspection method of AGV intelligent parking system interaction area parking behavior according to claim 1, wherein: in the step 4), under the pixel coordinate system, the x axis rotates anticlockwise, and the first side of the minimum circumscribed rectangle of the vehicle body is firstly met and defined as LHThe other with LHThe mutually perpendicular sides are defined as LWAnd the oblique angle theta of the vehicle body is x and LHThe value range of theta is [0 degrees and 90 degrees ];in a static state, the vehicle body is divided into three states of left deviation, right deviation and body straightening according to different oblique angles of the vehicle body; when L isH>LWWhen the vehicle body deviates to the right; when L isH<LWIn time, two cases are distinguished: when theta is larger than 0 DEG, the vehicle body deviates to the left, and when theta is equal to 0 DEG, the vehicle body is straight;among the four vertex coordinates of the minimum bounding rectangle of the vehicle body, the vertex point with the maximum longitudinal coordinate value is defined as P0 (x)P0,yP0) If the ordinate values of the two vertexes are maximum, the vertex having the maximum ordinate value and the minimum abscissa value is defined as P0 (x)P0,yP0) And the other three vertexes are represented by P0 (x)P0,yP0) As a starting point, sequentially defined as P1 (x) in clockwise orderP1,yP1)、P2(xP2,yP2)、P3(xP3,yP3);Utilize minimum external rectangle limit L of automobile bodyH、LWBody lean angle θ and centroid coordinate PC (x) of vehicle targetPC,yPC) And calculating the coordinates P0 (x) of four vertexes of the minimum circumscribed rectangle of the vehicle bodyP0,yP0)、P1(xP1,yP1)、P2(xP2,yP2)、P3(xP3,yP3):
- 6. The visual inspection method of AGV intelligent parking system interaction area parking behavior according to claim 1, wherein: in step 5), under the pixel coordinate system, the x axis rotates anticlockwise, and the first side of the minimum circumscribed rectangle of the vehicle body is firstly encountered to be defined as LHThe other with LHThe mutually perpendicular sides are defined as LWAnd the oblique angle theta of the vehicle body is x and LHThe value range of theta is [0 degrees and 90 degrees ];in a static state, the vehicle body is divided into three states of left deviation, right deviation and body straightening according to different oblique angles of the vehicle body; when L isH>LWWhen the vehicle body deviates to the right; when L isH<LWIn time, two cases are distinguished: when theta is larger than 0 DEG, the vehicle body deviates to the left, and when theta is equal to 0 DEG, the vehicle body is straight;among the four vertex coordinates of the minimum bounding rectangle of the vehicle body, the vertex point with the maximum longitudinal coordinate value is defined as P0 (x)P0,yP0) If the ordinate values of the two vertexes are maximum, the vertex having the maximum ordinate value and the minimum abscissa value is defined as P0 (x)P0,yP0) And the other three vertexes are represented by P0 (x)P0,yP0) As a starting point, sequentially defined as P1 (x) in clockwise orderP1,yP1)、P2(xP2,yP2)、P3(xP3,yP3);Setting the range of the abscissa threshold value of the interaction area of the AGV intelligent parking system as [ x ]PP1,xPP2]The range of the vertical coordinate threshold is [ y ]PP1,yPP2]And allowable threshold value theta of vehicle body oblique angleP,θPThe absolute value of an acute angle included angle formed by an axis where the vehicle driving direction is located and an axis where the vehicle body is right straight;judging the four vertexes of the minimum circumscribed rectangle of the vehicle body according to the following formulaLabel P0 (x)P0,yP0)、P1(xP1,yP1)、P2(xP2,yP2)、P3(xP3,yP3) Whether the threshold ranges of the horizontal coordinate and the vertical coordinate in the interaction area of the AGV intelligent parking system are met:if not, judging that the vehicle is in illegal parking behavior; if yes, continuously judging whether the vehicle body inclined angle theta meets one of the following conditions:if so, judging that the parking behavior is standardized; if not, the illegal parking behavior is determined.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910955499.4A CN110633699B (en) | 2019-10-09 | 2019-10-09 | Visual detection method for parking behavior of interaction area of AGV intelligent parking system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910955499.4A CN110633699B (en) | 2019-10-09 | 2019-10-09 | Visual detection method for parking behavior of interaction area of AGV intelligent parking system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110633699A true CN110633699A (en) | 2019-12-31 |
CN110633699B CN110633699B (en) | 2021-05-11 |
Family
ID=68976235
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910955499.4A Active CN110633699B (en) | 2019-10-09 | 2019-10-09 | Visual detection method for parking behavior of interaction area of AGV intelligent parking system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110633699B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114627676A (en) * | 2022-02-24 | 2022-06-14 | 深圳市小马控股有限公司 | Intelligent vehicle parking method, system, server and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103112453A (en) * | 2013-02-01 | 2013-05-22 | 奇瑞汽车股份有限公司 | Intelligence parking auxiliary system |
US20140266803A1 (en) * | 2013-03-15 | 2014-09-18 | Xerox Corporation | Two-dimensional and three-dimensional sliding window-based methods and systems for detecting vehicles |
CN107609491A (en) * | 2017-08-23 | 2018-01-19 | 中国科学院声学研究所 | A kind of vehicle peccancy parking detection method based on convolutional neural networks |
CN108275147A (en) * | 2018-01-25 | 2018-07-13 | 浙江吉利汽车研究院有限公司 | A kind of control method and its control system for vehicle parking |
-
2019
- 2019-10-09 CN CN201910955499.4A patent/CN110633699B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103112453A (en) * | 2013-02-01 | 2013-05-22 | 奇瑞汽车股份有限公司 | Intelligence parking auxiliary system |
US20140266803A1 (en) * | 2013-03-15 | 2014-09-18 | Xerox Corporation | Two-dimensional and three-dimensional sliding window-based methods and systems for detecting vehicles |
CN107609491A (en) * | 2017-08-23 | 2018-01-19 | 中国科学院声学研究所 | A kind of vehicle peccancy parking detection method based on convolutional neural networks |
CN108275147A (en) * | 2018-01-25 | 2018-07-13 | 浙江吉利汽车研究院有限公司 | A kind of control method and its control system for vehicle parking |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114627676A (en) * | 2022-02-24 | 2022-06-14 | 深圳市小马控股有限公司 | Intelligent vehicle parking method, system, server and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110633699B (en) | 2021-05-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109684921B (en) | Road boundary detection and tracking method based on three-dimensional laser radar | |
CN112396650B (en) | Target ranging system and method based on fusion of image and laser radar | |
CN113156421A (en) | Obstacle detection method based on information fusion of millimeter wave radar and camera | |
CN107133973B (en) | Ship detection method in bridge collision avoidance system | |
Yan et al. | A method of lane edge detection based on Canny algorithm | |
EP3258686B1 (en) | Entry possibility determining device for vehicle | |
CN110414385B (en) | Lane line detection method and system based on homography transformation and characteristic window | |
Lim et al. | Vision‐based Lane‐Vehicle Detection and Tracking | |
CN113370977A (en) | Intelligent vehicle forward collision early warning method and system based on vision | |
KR101483742B1 (en) | Lane Detection method for Advanced Vehicle | |
CN113850872A (en) | Service area parking line pressing detection method based on high-level video | |
CN114549549B (en) | Dynamic target modeling tracking method based on instance segmentation in dynamic environment | |
CN110633699B (en) | Visual detection method for parking behavior of interaction area of AGV intelligent parking system | |
Wang et al. | An improved hough transform method for detecting forward vehicle and lane in road | |
CN113269838B (en) | Obstacle visual detection method based on FIRA platform | |
KR101998584B1 (en) | Lane detection apparatus and lane detection method | |
Zhang et al. | Real-time obstacle detection based on stereo vision for automotive applications | |
CN107944350B (en) | Monocular vision road identification method based on appearance and geometric information fusion | |
CN112733678A (en) | Ranging method, ranging device, computer equipment and storage medium | |
Fu et al. | Multi-lanes detection based on panoramic camera | |
CN110796023B (en) | Recognition method for parking state wheel positions in interaction area of AGV intelligent parking system | |
CN111260709B (en) | Ground-assisted visual odometer method for dynamic environment | |
CN112348853B (en) | Particle filter tracking method based on infrared saliency feature fusion | |
CN114661051A (en) | Front obstacle avoidance system based on RGB-D | |
Lee et al. | Visual odometry for absolute position estimation using template matching on known environment |
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 |