CN116767146A - Intelligent recognition system for vehicle type - Google Patents
Intelligent recognition system for vehicle type Download PDFInfo
- Publication number
- CN116767146A CN116767146A CN202310790525.9A CN202310790525A CN116767146A CN 116767146 A CN116767146 A CN 116767146A CN 202310790525 A CN202310790525 A CN 202310790525A CN 116767146 A CN116767146 A CN 116767146A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- appearance
- washed
- intelligent
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005406 washing Methods 0.000 claims abstract description 88
- 238000000034 method Methods 0.000 claims abstract description 20
- 230000002159 abnormal effect Effects 0.000 claims abstract description 9
- 230000003993 interaction Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 9
- SAZUGELZHZOXHB-UHFFFAOYSA-N acecarbromal Chemical compound CCC(Br)(CC)C(=O)NC(=O)NC(C)=O SAZUGELZHZOXHB-UHFFFAOYSA-N 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 238000013524 data verification Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 abstract description 5
- 238000004140 cleaning Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60S—SERVICING, CLEANING, REPAIRING, SUPPORTING, LIFTING, OR MANOEUVRING OF VEHICLES, NOT OTHERWISE PROVIDED FOR
- B60S3/00—Vehicle cleaning apparatus not integral with vehicles
- B60S3/04—Vehicle cleaning apparatus not integral with vehicles for exteriors of land vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
Abstract
The invention discloses an intelligent vehicle type recognition system, relates to the technical field of intelligent vehicle washing, and solves the technical problems that in the prior art, when a vehicle type is recognized through a vehicle VIN code, the acquisition difficulty of the vehicle VIN code is high, the privacy of a vehicle owner can be violated, and the vehicle washing experience of the vehicle owner is influenced; according to the method, the size characteristics and the line characteristics of the vehicle to be washed are extracted based on the appearance data of the vehicle to be washed, a target vehicle type is obtained in a database in a matching mode, and intelligent vehicle washing equipment is controlled to wash vehicles based on the target vehicle type; according to the method, the appearance characteristics of the vehicle to be washed are extracted, so that the target vehicle type is matched, the matching efficiency of the target vehicle type is improved, and the privacy of a vehicle owner is prevented from being revealed; the method comprises the steps of judging whether the relative positions of a vehicle to be washed and intelligent vehicle washing equipment are abnormal or not on the basis of a target vehicle type; if yes, moving the vehicle to be washed or intelligent vehicle washing equipment; the method judges the relative position of the vehicle to be washed and the intelligent vehicle washing equipment based on the vehicle type size, and avoids damage to the vehicle to be washed in the vehicle washing process caused by measurement errors.
Description
Technical Field
The invention belongs to the field of intelligent car washing, relates to an intelligent car type recognition technology for car washing equipment, and particularly relates to an intelligent car type recognition system.
Background
Most of automatic car washing equipment controls car brush assemblies according to fixed paths, but the measured content of different car types is different in shape and line. If the brush assembly is controlled to operate on the same fixed path for all vehicles, either damage to the vehicle or reduced cleaning efficiency and quality can occur.
The prior art (the invention patent application with publication number of CN 105205468A) discloses a car washing device, a car washing system and a car washing method for automatically identifying car types, wherein a car VIN code of a car to be washed is acquired through an image acquisition device, and is analyzed according to a preset rule and then compared with information in a VIN database to obtain the model information of the car. In the prior art, a vehicle needs to be identified according to a vehicle VIN code, but the vehicle VIN code is generally positioned at a certain position in the vehicle, so that the acquisition difficulty is high; and most car owners are careful in privacy, and cannot accept that the VIN codes of the car are used at will.
The invention provides an intelligent vehicle type recognition system for solving the problems.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art; therefore, the invention provides an intelligent vehicle type recognition system, which is used for solving the technical problems that the acquisition difficulty of the vehicle VIN code is high and the privacy of a vehicle owner can be violated to influence the vehicle washing experience of the vehicle owner when the vehicle type is recognized through the vehicle VIN code in the prior art.
To achieve the above object, a first aspect of the present invention provides an intelligent vehicle type recognition system, including: the central control module is connected with the data interaction module and the car washing control module; the data interaction module is respectively connected with the data acquisition equipment and the intelligent terminal; the car washing control module is used for controlling intelligent car washing equipment; the central control module acquires appearance data of the vehicle to be washed through the data acquisition equipment; extracting the size characteristics and the line characteristics of the vehicle to be washed based on the appearance data, and integrating the size characteristics and the line characteristics into a characteristic sequence; matching the feature sequences in a database, and determining a target vehicle type after verification by an intelligent terminal; judging whether the relative positions of the vehicle to be washed and intelligent vehicle washing equipment are abnormal or not on the basis of the target vehicle type; if yes, moving the vehicle to be washed or intelligent vehicle washing equipment; and if not, controlling the intelligent car washing equipment to wash the car based on the target car type.
When the existing intelligent car washing equipment is used for washing cars, the car can generally move according to a fixed path to finish the car task. In order to avoid damage to the vehicle during the vehicle washing process, the profile enclosed by the fixed path needs to be as large as possible, so that the vehicle brush assembly is difficult to sufficiently clean when cleaning some vehicles with smaller sizes, and the cleaning efficiency is affected. The vehicle type recognition method based on the vehicle VIN codes disclosed in the prior art may cause privacy leakage of the vehicle owner due to the recognition and the use non-standardization of the vehicle VIN codes, and the vehicle VIN codes are difficult to acquire through the image acquisition device, so that the vehicle washing efficiency is affected.
According to the invention, the appearance data of the vehicle to be washed is obtained through the data acquisition equipment, and the characteristic sequence of the vehicle to be washed is identified according to the appearance data, wherein the characteristic sequence is a characteristic which is not changed or is slightly changed in the using process of the vehicle. And matching and determining a target vehicle type in a database according to the characteristic sequence, and controlling and adjusting the intelligent vehicle washing equipment based on the target vehicle type. According to the intelligent car washing equipment, the appearance data of the car to be washed is reasonably extracted according to the control requirement of the intelligent car washing equipment, and the accurate and efficient control of the intelligent car washing equipment is realized on the basis of avoiding privacy leakage of car owners.
The central control module is respectively communicated and/or electrically connected with the data interaction module and the car washing control module; the car washing control module controls intelligent car washing equipment according to a target car type and monitors a car washing state; the data interaction module is respectively in communication and/or electrical connection with the data acquisition equipment and the intelligent terminal.
The central control module is responsible for processing the data acquired by the data acquisition equipment, and the data interaction module is responsible for data acquisition control and necessary data preprocessing. The data acquisition device is mainly used for acquiring appearance data of the vehicle to be washed, wherein the appearance data comprises appearance images acquired by the image acquisition device or appearance scanning points acquired by the three-dimensional scanning device. The intelligent terminal is used for verifying a target vehicle type and displaying a vehicle washing state and mainly comprises an intelligent mobile phone or a computer.
Preferably, the central control module obtains appearance data of the vehicle to be washed through a data acquisition device, including: determining that the vehicle to be washed is in a collectable range of the data collection equipment; appearance data of a plurality of sides of the vehicle to be washed are collected through the data collecting equipment.
The appearance data in the present invention includes at least a top side appearance image, one side appearance image of a front side or a rear side, one side appearance image of a left side or a right side; namely, the top side appearance image of the vehicle to be washed is acquired through overlooking view angles, the left side appearance image is acquired through left side view angles or the right side appearance image is acquired through right side view angles, the front side appearance image is acquired through front side view angles or the rear side appearance image is acquired through rear side view angles. The appearance image can be directly acquired through the image acquisition equipment, and also can be obtained by analyzing the appearance scanning point. Obviously, the appearance data of the vehicle to be detected can be obtained by arranging data acquisition equipment in intelligent vehicle washing equipment or on a vehicle washing route, the data acquisition mode is simple, and the acquisition cost is low; and the data processing time can be offset by the arrangement on the car washing necessary route, so that the control efficiency of the intelligent car washing equipment is improved.
The appearance data of the present invention includes at least three-side appearance data, and the top-side appearance image is required, and the left-right and front-rear opposite sides are optionally selected. The corresponding characteristics of the three-side appearance data can accurately identify the corresponding vehicle type, so that the data processing amount is effectively reduced; and the left, right, front and back opposite sides only need one optional side, so that the data fault tolerance rate can be effectively improved.
Preferably, the extracting the dimensional features and the line features of the vehicle to be washed based on the appearance data includes: extracting appearance data of a plurality of sides of a vehicle to be washed, and obtaining appearance sizes of the sides after data processing; determining a plurality of appearance lines from a top view angle on the basis of the plurality of side appearance data; extracting line features corresponding to a plurality of appearance lines.
The data processing of the present invention includes data verification and data correction. And the data verification is to verify whether the appearance data meets the requirements or not through a preset verification rule, and reject the data which does not meet the requirements. The appearance data acquired by the data acquisition device may have a certain distortion (such as distortion of an image), and the distortion needs to be corrected. And obtaining appearance sizes corresponding to a plurality of sides according to the processed data. After the appearance sizes of the sides of the vehicle to be washed are obtained, a plurality of appearance lines are determined by taking the overlooking angle as a core. Extracting line features of a plurality of appearance lines according to the set feature extraction rules.
The present invention extracts a feature sequence for identifying a vehicle model based on appearance data of a vehicle to be washed. The identification elements are constructed from the two angles of the appearance size and the line characteristics, so that the element extraction efficiency can be improved, and the matching efficiency and the matching precision of the vehicle type of the vehicle to be washed are facilitated.
Preferably, the determining a plurality of appearance lines from a top view on the basis of the plurality of side appearance data includes: extracting a top side appearance image under a overlooking view angle, and determining a roof center point in the top side appearance image as a reference point I; and determining a plurality of second reference points on other side edge lines in the top side appearance image, and connecting the first reference points with the second reference points to obtain a plurality of appearance lines.
According to the invention, the roof center point is determined in the top side appearance image under the overlooking view, the second reference points are determined on other side edge lines in the top side appearance image, and the second reference points are connected with the roof center point to obtain a plurality of appearance lines. When determining the roof center point, firstly determining the roof outline from the top side appearance image, and determining the roof center point in the roof outline; of course, other points may be determined as reference points one in other preferred embodiments.
In the invention, a certain gradient exists between the plane of each side of the vehicle to be washed and the plane of the adjacent side, so that other side edge lines of the top side appearance image refer to contour lines of other sides (left side, right side, front side or rear side according to appearance data determination) in a top view, and at least one point is selected as a reference point two on each other side. In order to standardize the determination standard of the second reference point, the point with the largest number of adjacent sides contacted on the contour line can be uniformly selected as the second reference point, for example, the intersection points of the front side, the left side and the top side of the vehicle to be washed on the contour line of the left front side can be determined as the second reference point.
Preferably, the extracting line features corresponding to the appearance lines includes: calculating the line sizes of a plurality of appearance lines under the overlooking view angle; identifying any contour line of the vehicle to be washed, which is intersected by a plurality of appearance lines; dividing the corresponding appearance line into two line segments through the contour line, and marking the proportion of the line segments at the two ends as line proportion; and integrating the line size and the line proportion corresponding to each appearance line into line characteristics.
After the appearance line is determined, any contour line which is intersected by the appearance line can be selected, and the appearance line is divided into two line segments in the contour line. And integrating the ratio of the two line segments as the line ratio and the line size of the appearance line into a line characteristic.
The line characteristics in the invention are all obtained by calculation based on the previously obtained data, and the data processing efficiency can be improved without additional data or other auxiliary equipment, thereby being beneficial to the subsequent matching of target vehicle types.
Preferably, the matching in the database by the feature sequence includes: the characteristic sequence of the vehicle to be washed is called; matching in a database through size features and line features in the feature sequence respectively to obtain the matching degree with the vehicle types in each database; and marking the vehicle model in the library with the highest matching degree as a target vehicle model.
After the feature sequences corresponding to the vehicles to be washed are determined, the content in the feature sequences is sequentially extracted and matched in the database, and the vehicle model with the highest matching degree is the target vehicle model. A plurality of vehicle models are stored in the database, and each vehicle model has a feature sequence associated therewith.
The matching between the characteristic sequences of the invention is to compare the relevant data of which vehicle type in the database with the closest data of the vehicle to be washed, and only the data comparison is involved. The whole comparison process is simpler, and errors in the data processing process can be avoided on the basis of ensuring the matching efficiency.
Preferably, the determining whether the relative position of the vehicle to be washed and the intelligent vehicle washing device is abnormal based on the target vehicle type includes: extracting the size of a vehicle model corresponding to the target vehicle model; determining a plurality of corner points of a vehicle to be washed on the basis of the size of the vehicle type; and when the relative distances between the boundary points and the intelligent car washing equipment are within the range of the distance threshold value, judging that the relative positions are normal.
After the vehicle type size is matched with the target vehicle type corresponding to the vehicle to be detected, the vehicle type size corresponding to the target vehicle type is used as the size of the vehicle to be washed. And selecting a plurality of points on the boundary of the target vehicle type as boundary points, and controlling the intelligent vehicle washing equipment to run according to the target vehicle type when the boundary points are all in the vehicle washing range of the intelligent vehicle washing equipment so as to finish the cleaning of the vehicle to be washed. The invention replaces the actual measurement size of the vehicle to be washed by the vehicle type size of the target vehicle type, so as to avoid inaccurate actual measurement size caused by errors in the measurement process.
It should be noted that, intelligent carwash equipment can be according to the automatic adjustment travel path of different target motorcycle types to guarantee that the distance of car brush subassembly and waiting to wash the car is moderate, can also avoid waiting to wash the car and cause the harm on the basis of guaranteeing the cleaning performance.
Compared with the prior art, the invention has the beneficial effects that:
1. the method extracts the size characteristics and the line characteristics of the vehicle to be washed based on the appearance data of the vehicle to be washed, and integrates the size characteristics and the line characteristics into a characteristic sequence; the method comprises the steps that a target vehicle type is obtained through matching of a feature sequence in a database, and intelligent vehicle washing equipment is controlled to wash vehicles based on the target vehicle type; according to the invention, the appearance characteristics of the vehicle to be washed are extracted so as to match the target vehicle type, and the privacy leakage of the vehicle owner is avoided by improving the matching efficiency of the target vehicle type.
2. The method comprises the steps of judging whether the relative positions of a vehicle to be washed and intelligent vehicle washing equipment are abnormal or not on the basis of a target vehicle type; if yes, moving the vehicle to be washed or intelligent vehicle washing equipment; if not, controlling the intelligent car washing equipment to wash the car based on the target car type; according to the method, the relative position of the vehicle to be washed and the intelligent vehicle washing equipment is judged based on the vehicle type size of the target vehicle type, and the damage to the vehicle to be washed in the vehicle washing process caused by measurement errors is avoided.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the system principle of the present invention;
FIG. 2 is a schematic diagram of the method steps of the present invention;
fig. 3 is an image of the top side of the vehicle to be car-washed according to the present invention.
Description of the embodiments
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, an embodiment of a first aspect of the present invention provides an intelligent vehicle type recognition system, including a hub control module, and a data interaction module and a vehicle washing control module connected with the hub control module; the data interaction module is respectively connected with the data acquisition equipment and the intelligent terminal; the car washing control module is used for controlling intelligent car washing equipment; the central control module acquires appearance data of the vehicle to be washed through the data acquisition equipment; extracting the size characteristics and the line characteristics of the vehicle to be washed based on the appearance data, and integrating the size characteristics and the line characteristics into a characteristic sequence; matching the feature sequences in a database, and determining a target vehicle type after verification by an intelligent terminal; judging whether the relative positions of the vehicle to be washed and intelligent vehicle washing equipment are abnormal or not on the basis of the target vehicle type; if yes, moving the vehicle to be washed or intelligent vehicle washing equipment; and if not, controlling the intelligent car washing equipment to wash the car based on the target car type.
The first step of the embodiment is that a central control module obtains appearance data of a vehicle to be washed through data acquisition equipment; and extracting the size characteristics and the line characteristics of the vehicle to be washed based on the appearance data, and integrating the size characteristics and the line characteristics into a characteristic sequence.
Before the intelligent car washing equipment, the necessary way for the car to be washed to reach the intelligent car washing equipment is provided with data acquisition equipment. When the vehicle to be washed passes through the necessary road, the appearance data of the vehicle to be detected is collected through the data collecting equipment, and the appearance data is sent to the central control module through the data interaction module.
The collection angles corresponding to the data collection device in this embodiment include a top view angle, a front view angle, a rear view angle, a left view angle, and a right view angle. When the vehicle to be washed passes through the necessary road, the top side appearance image meeting the requirements is acquired from the overlook angle, and the right side angle and the rearview angle also need to acquire the appearance image meeting the requirements.
After the appearance data of the vehicle to be washed is acquired, necessary data correction is performed so that the appearance data matches the actual situation. The appearance size of the appearance image corresponding to each acquisition angle can be calculated, wherein the appearance size mainly refers to the length, the width and the gradient. The corresponding length, width, gradient and the like of each vehicle model are different, so that the matching of the target vehicle model is facilitated. In other preferred embodiments, the appearance size may also be an image area corresponding to each of the appearance images of the acquired angles.
Referring to fig. 3, a roof center point of the vehicle to be washed is determined as a reference point one, namely a point a in fig. 3; taking intersection points of the right side, the front side and the top side of the vehicle to be washed as a reference point II, namely a point B; the intersection points of the right side, the rear side and the top side of the vehicle to be washed are also used as a reference point II, namely a point C. Then the first reference point and the second reference point are connected to obtain an appearance line AB and an appearance line AC.
The lengths of the appearance lines AB and AC next need to be calculated as one line feature. As can be seen from fig. 3, the front side profile of the roof intersects the appearance line AB and the rear side profile of the roof intersects the appearance line AC. The appearance line AB is divided into two line segments, namely AE and EB; the appearance line AC is divided into two line segments, namely AF and FC; AE/EB and AF/FC can be taken as one line feature.
And integrating the obtained appearance size, appearance line length and corresponding line proportion into a characteristic sequence of the vehicle to be detected. And the content in the feature sequence can be different along with the size and design language of the vehicle model, so that the target vehicle model corresponding to the vehicle to be detected can be accurately identified.
The second step of the embodiment is to determine the target vehicle type after the verification of the intelligent terminal through matching the characteristic sequences in the database; judging whether the relative positions of the vehicle to be washed and intelligent vehicle washing equipment are abnormal or not on the basis of the target vehicle type; if yes, moving the vehicle to be washed or intelligent vehicle washing equipment; and if not, controlling the intelligent car washing equipment to wash the car based on the target car type.
Extracting a characteristic sequence of a vehicle to be detected, and firstly, matching in a database based on the appearance size to obtain a group of vehicle types meeting the requirements; and comparing the line size and the line characteristics of the vehicle types with those of the vehicle to be detected, and selecting the vehicle type with the smallest error as the target vehicle type.
And displaying the selected target vehicle type through the intelligent terminal, wherein if errors exist, the vehicle owner can manually change the selection, and if the vehicle owner does not perform any intervention, the intelligent vehicle washing equipment can be controlled according to the target vehicle type. The intervention here includes a touch screen operation or a voice operation.
After determining the target vehicle model, the vehicle model size is extracted. Firstly, two points (such as two headlights) on the front side of a vehicle to be washed are selected as boundary points, whether the distance between the boundary points and intelligent vehicle washing equipment meets the set range requirement is judged, and if so, the two points are determined on the rear side of the vehicle to be washed according to the size of the vehicle model and are used as the boundary points. And judging whether the distance between the boundary points at the rear side and the intelligent car washing equipment is within a distance range, and if the distances between all the boundary points and the intelligent car washing equipment are within a set distance range, judging that the position of the car to be washed is normal, so that automatic car washing can be performed.
Before automatic car washing starts, the moving path of the intelligent car washing equipment is automatically set according to the target car type. And controlling the intelligent car washing equipment according to the set moving path to complete automatic car washing. In the car washing process, the car washing state can be monitored through the intelligent terminal, and after the washing is finished, the washing is finished through the intelligent terminal.
The working principle of the invention is as follows: obtaining appearance data of a vehicle to be washed; and extracting the size characteristics and the line characteristics of the vehicle to be washed based on the appearance data, and integrating the size characteristics and the line characteristics into a characteristic sequence. Matching the feature sequences in a database, and determining a target vehicle type after verification by an intelligent terminal; and judging whether the relative positions of the vehicle to be washed and the intelligent vehicle washing equipment are abnormal or not on the basis of the target vehicle type. If yes, moving the vehicle to be washed or intelligent vehicle washing equipment; and if not, controlling the intelligent car washing equipment to wash the car based on the target car type.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (8)
1. Intelligent recognition system of motorcycle type includes: the central control module is connected with the data interaction module and the car washing control module; the data interaction module is respectively connected with the data acquisition equipment and the intelligent terminal; the car washing control module is used for controlling intelligent car washing equipment; the method is characterized in that:
the central control module acquires appearance data of the vehicle to be washed through the data acquisition equipment; extracting the size characteristics and the line characteristics of the vehicle to be washed based on the appearance data, and integrating the size characteristics and the line characteristics into a characteristic sequence; the data acquisition equipment comprises image acquisition equipment or three-dimensional scanning equipment; and
matching the feature sequences in a database, and determining a target vehicle type after verification by an intelligent terminal; judging whether the relative positions of the vehicle to be washed and intelligent vehicle washing equipment are abnormal or not on the basis of the target vehicle type; if yes, moving the vehicle to be washed or intelligent vehicle washing equipment; and if not, controlling the intelligent car washing equipment to wash the car based on the target car type.
2. The intelligent vehicle type recognition system according to claim 1, wherein the hub control module obtains appearance data of the vehicle to be washed through a data acquisition device, comprising:
determining that the vehicle to be washed is in a collectable range of the data collection equipment;
the method comprises the steps of collecting appearance data of a plurality of sides of a vehicle to be washed through data collecting equipment; wherein the appearance data includes at least a top side appearance image, one of a front side or a rear side appearance image, one of a left side or a right side appearance image.
3. The intelligent vehicle model identification system of claim 1, wherein the extracting dimensional features and line features of the vehicle to be washed based on the appearance data comprises:
extracting appearance data of a plurality of sides of a vehicle to be washed, and obtaining appearance sizes of the sides after data processing; wherein the data processing includes data verification and data correction;
determining a plurality of appearance lines from a top view angle on the basis of the plurality of side appearance data; extracting line features corresponding to a plurality of appearance lines; wherein the line features include line length and line segment proportions.
4. The intelligent recognition system of a vehicle model of claim 3, wherein the determining a plurality of appearance lines from a top view perspective based on the plurality of side appearance data comprises:
extracting a top side appearance image under a overlooking view angle, and determining a roof center point in the top side appearance image as a reference point I;
and determining a plurality of second reference points on other side edge lines in the top side appearance image, and connecting the first reference points with the second reference points to obtain a plurality of appearance lines.
5. The intelligent recognition system of claim 3, wherein the extracting line features corresponding to the appearance lines comprises:
calculating the line sizes of a plurality of appearance lines under the overlooking view angle;
identifying any contour line of the vehicle to be washed, which is intersected by a plurality of appearance lines; dividing the corresponding appearance line into two line segments through the contour line, and marking the proportion of the line segments at the two ends as line proportion;
and integrating the line size and the line proportion corresponding to each appearance line into line characteristics.
6. The intelligent vehicle model identification system of claim 1, wherein the matching in the database by the feature sequence comprises:
the characteristic sequence of the vehicle to be washed is called;
matching in a database through size features and line features in the feature sequence respectively to obtain the matching degree with the vehicle types in each database; and marking the vehicle model in the library with the highest matching degree as a target vehicle model.
7. The intelligent recognition system of a vehicle type according to claim 1, wherein the determining whether the relative position of the vehicle to be washed and the intelligent vehicle washing device is abnormal based on the target vehicle type comprises:
extracting the size of a vehicle model corresponding to the target vehicle model;
determining a plurality of corner points of a vehicle to be washed on the basis of the size of the vehicle type; and when the relative distances between the boundary points and the intelligent car washing equipment are within the range of the distance threshold value, judging that the relative positions are normal.
8. The intelligent vehicle type recognition system according to claim 1, wherein the central control module is respectively in communication and/or electrical connection with the data interaction module and the vehicle washing control module; the car washing control module controls intelligent car washing equipment according to a target car type and monitors a car washing state;
the data interaction module is respectively communicated and/or electrically connected with the data acquisition equipment and the intelligent terminal; the intelligent terminal is used for verifying a target vehicle type and displaying a vehicle washing state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310790525.9A CN116767146A (en) | 2023-06-30 | 2023-06-30 | Intelligent recognition system for vehicle type |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310790525.9A CN116767146A (en) | 2023-06-30 | 2023-06-30 | Intelligent recognition system for vehicle type |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116767146A true CN116767146A (en) | 2023-09-19 |
Family
ID=87992812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310790525.9A Pending CN116767146A (en) | 2023-06-30 | 2023-06-30 | Intelligent recognition system for vehicle type |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116767146A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220402524A1 (en) * | 2021-06-21 | 2022-12-22 | Toyota Jidosha Kabushiki Kaisha | Driving control device, storage medium storing driving control program, and driving control system |
-
2023
- 2023-06-30 CN CN202310790525.9A patent/CN116767146A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220402524A1 (en) * | 2021-06-21 | 2022-12-22 | Toyota Jidosha Kabushiki Kaisha | Driving control device, storage medium storing driving control program, and driving control system |
| US12084089B2 (en) * | 2021-06-21 | 2024-09-10 | Toyota Jidosha Kabushiki Kaisha | Driving control device, storage medium storing driving control program, and driving control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9014432B2 (en) | License plate character segmentation using likelihood maximization | |
| CN116767146A (en) | Intelligent recognition system for vehicle type | |
| CN113096130B (en) | Method and device for detecting object defects | |
| CN108629763B (en) | Disparity map judging method and device and terminal | |
| CN104778444A (en) | Method for analyzing apparent characteristic of vehicle image in road scene | |
| CN112115904A (en) | License plate detection and identification method and device and computer readable storage medium | |
| CN112598922B (en) | Parking space detection method, device, equipment and storage medium | |
| CN103440503A (en) | Vehicle body color detection and identification method | |
| CN113341396B (en) | Robot and charging pile identification method and device thereof | |
| CN111931673B (en) | Method and device for checking vehicle detection information based on vision difference | |
| CN108515945A (en) | Automatic car washing method, automatic car washing device and automatic car washing system | |
| CN108052921B (en) | Lane line detection method, device and terminal | |
| CN111753716A (en) | Parking line pressing detection method and server | |
| CN111626995A (en) | Intelligent insert detection method and device for workpiece | |
| CN110443653A (en) | Order processing method, apparatus and electronic equipment | |
| CN103544495A (en) | Method and system for recognizing of image categories | |
| CN111177878B (en) | Derived simulation scene screening method, device and terminal | |
| CN112213579A (en) | Method and device for identifying faults of turnout switch machine | |
| CN110267231A (en) | It is a kind of based on the parking stall recognition methods of bluetooth RSSI, apparatus and system | |
| CN112016514B (en) | Traffic sign recognition method, device, equipment and storage medium | |
| CN115331193A (en) | Parking space identification method, parking space identification system, electronic equipment and storage medium | |
| CN110570317A (en) | Method and device for vehicle nuclear damage | |
| CN114495056A (en) | Parking lot pillar detection method, detection device, vehicle and storage medium | |
| CN109993066B (en) | Sideline-oriented vehicle positioning method and system | |
| CN111652222A (en) | License plate positioning method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |