CN112699823A - Fixed-point returning method for sharing electric vehicle - Google Patents
Fixed-point returning method for sharing electric vehicle Download PDFInfo
- Publication number
- CN112699823A CN112699823A CN202110007623.1A CN202110007623A CN112699823A CN 112699823 A CN112699823 A CN 112699823A CN 202110007623 A CN202110007623 A CN 202110007623A CN 112699823 A CN112699823 A CN 112699823A
- Authority
- CN
- China
- Prior art keywords
- electric vehicle
- parking
- shared electric
- point
- vehicle
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000005070 sampling Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Images
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
- 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
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0645—Rental transactions; Leasing transactions
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
- G07F17/0042—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for hiring of objects
- G07F17/0057—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for hiring of objects for the hiring or rent of vehicles, e.g. cars, bicycles or wheelchairs
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/20—Information sensed or collected by the things relating to the thing itself
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/10—Detection; Monitoring
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/20—Analytics; Diagnosis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/60—Positioning; Navigation
Abstract
The invention discloses a fixed-point returning method for sharing an electric vehicle, which comprises the steps of snapshotting a parking area by installing a camera at the position of a vehicle head, acquiring a large number of samples, learning and training sample data to obtain a training model of the parking area, and identifying the samples by using video snapshotted pictures before a user stops; the sample discerns can be accurate acquirees parking area's datum line and parking sign, just can judge the vehicle and park whether standardizedly when parkking like this, utilizes IMU position appearance to obtain the automobile body state, judges whether the automobile body falls down.
Description
Technical Field
The invention relates to the fields of computer vision, internet data processing technology and three-dimensional sensing, in particular to a computer vision-based fusion sensing accurate parking method, device, equipment and storage medium.
Background
The shared electric vehicle is a transportation tool which provides convenience for people to go out at present, achieves the purpose of going out through a leasing mode, and makes great contribution to green and environment-friendly going out. Compare in traditional trip mode like bus, taxi etc. the sharing electric motor car has satisfied mobility promptly and has satisfied the long-time purpose of remotely riding, makes our trip more convenient. However, the shared electric vehicle can be parked anywhere and randomly, which seriously affects the appearance of a city and may have traffic hidden troubles.
However, the current commonly used parking positioning scheme: the parking spot is judged by GPS positioning, but the GPS positioning is easily interfered, the precision can only reach about 50 meters, and the error is too large. The method judges parking by spike positioning, the spike positioning precision can reach 2-3 meters, but the positioning is too time-consuming, the user experience is poor, the two methods cannot achieve the problem of parking direction and cannot achieve ordered parking
Therefore, it is important for those skilled in the art to develop a method for accurately and orderly parking shared electric vehicles at parking spots, so that the city can be kept clean and orderly, and the operation difficulty and cost can be reduced.
Disclosure of Invention
In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is a method for enabling a shared electric vehicle to be parked at a parking spot accurately and orderly.
In order to achieve the above object, the present invention provides a fixed point returning method for a shared electric vehicle, comprising the steps of:
(1) arranging a camera device, an IMU device and a GPS device on the shared electric vehicle; the camera device is arranged at the head of the shared electric vehicle;
(2) when a user carries out a car returning operation on terminal equipment including a mobile phone, a server acquires the current GPS positioning of a shared electric car, searches a P point of a car returning point closest to the current shared electric car, judges whether the shared electric car is in the range of the P point, and if not, the server returns information that the car returning is not allowed to the user; if the shared electric vehicle is in the range of the point P, the server sends a photographing instruction to the photographing device, and the photographing device takes a snapshot of the current image and transmits the snapshot to the server;
(3) the server imports the captured images into a model trained in advance, and cuts out parking areas and identifications thereof in the images through a full convolution network FCN model; and if the parking area identification is not detected in the segmented image, the server returns information which does not allow parking to the user.
Further, the model in step (3) is trained according to the following steps:
(a) obtaining a sample of model training input: acquiring an image sample through a camera device arranged at the vehicle head, and marking a parking area to obtain a corresponding binary mask;
(b) preprocessing an input image;
(c) extracting parking identification features by using a convolutional neural network construction module;
(d) and (6) deriving model parameters.
Further, in step (b), scaling the long side of the input image to 256, scaling the short side equally, and aligning the shortfalls and the complement 0 to obtain an RGB input image X with a size of 256 × 3; and carrying out the same scaling operation on the corresponding binary mask to obtain a training mask Y.
Furthermore, the module consists of an encoding sub-module and a decoding sub-module, wherein the encoding sub-module consists of an encoding convolutional layer and a down-sampling layer, and the decoding sub-module consists of a decoding convolutional layer and an up-sampling layer; after the input image is subjected to encoding and decoding processes, a parking mark probability map M with the size of 256 × 1 is obtained.
Further, in step (c), the window is slid to scan the image and find the area where the target exists, and the position and size thereof are finely adjusted; if a plurality of anchor points are mutually overlapped, the anchor point with the highest foreground score is reserved, and the rest anchor points are discarded, so that the final regional proposal is obtained.
Further, the method also comprises the following steps: (4) if the parking area identification is detected in the segmented image, binarization is carried out to obtain a contour map of the segmented image, contour matching is carried out, whether the direction of the vehicle head is vertical to a parking datum line is judged, and if the parking direction deviates beyond a set range, the server returns information which does not allow parking to a user.
Further, the method also comprises the following steps: (5) the method comprises the steps that 6 DOF parameters of the shared electric vehicle are measured by the IMU, the DOF data are analyzed through a falling detection algorithm, whether the vehicle is in a falling state or not is judged, and if the vehicle is in the falling state, the server returns information that the vehicle returning is not allowed to the user.
Further, the method also comprises the following steps: (6) and if the conditions are met, the server returns the information of allowing the car to return to the user and records the image.
Further, in step (2), after the camera device receives the photographing instruction sent by the server, 3I frames within the last 3 seconds are acquired in the video stream.
The invention has the technical effects that:
1. make shared electric motor car park more accurate and standard, can put in order, shared electric motor car is no longer in a jumble and disorderly for the road is no longer dirty and disorderly.
2. The vehicle is not placed in order when the operation and maintenance personnel need to frequently go to the parking spot, and the operation and maintenance cost can be saved.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
FIG. 1 is a general flow chart of a preferred embodiment of the present invention;
FIG. 2 is a flow chart of model training in a preferred embodiment of the present invention;
FIG. 3 is a schematic diagram of a parking area and a logo area segmented from an image according to a preferred embodiment of the present invention;
fig. 4, 5 and 6 are schematic diagrams illustrating parking area identification detection in a preferred embodiment of the present invention.
Detailed Description
The technical contents of the preferred embodiments of the present invention will be more clearly and easily understood by referring to the drawings attached to the specification. The present invention may be embodied in many different forms of embodiments and the scope of the invention is not limited to the embodiments set forth herein.
According to the method, the camera is arranged at the position of the vehicle head, the parking area is captured, a large number of samples are obtained, the sample data are subjected to learning training to obtain a training model of the parking area, and then a user uses video capture pictures to perform sample identification before parking; the sample discerns the regional of acquireing the parking that can be accurate to and the parking datum line, just can judge whether the vehicle parks standardizedly when parkking like this. And obtaining the state of the vehicle body by utilizing the IMU pose, and judging whether the vehicle body falls down.
Through the steps, the shared electric vehicle can be parked more accurately and standardly and can be placed orderly.
The specific algorithm flow is shown in fig. 1:
the whole algorithm comprises a vehicle body camera module stage, a parking area mask training stage, a parking identification stage and a fine parking direction stage;
the first stage is to obtain a sample input by model training, the second stage is to train parking area data and parking direction mask data in advance, and the third stage is to recognize by using video snapshot before the user stops; the fourth stage of accurately acquiring the parking area and the parking reference line by identification is to apply the IMU data and the network parameters to identify the direction, the inclination and whether to fix the point or not of the vehicle body
The specific implementation flow of the algorithm is as follows:
1. obtaining samples of model training inputs
And a vehicle body camera module is used for collecting a large number of image samples to mark the parking area. Samples as input for model training
2. Model training is shown in FIG. 2
1) And (4) inputting data, collecting different parking identification data, marking the parking identification and the direction, and obtaining a corresponding binary mask.
2) The data preprocessing is used for preprocessing the input image, the long edge of the original image is scaled to 256, the short edge is scaled in an equal proportion, the defects are compensated by 0, and the RGB input image X with the size of 256X 3 is obtained. And carrying out the same scaling operation on the corresponding binary mask to obtain a training mask Y.
3) The region division utilizes a convolutional neural network construction module to extract parking identification features. The module consists of an encoding sub-module and a decoding sub-module, wherein the encoding sub-module consists of a series of convolutional layers and down-sampling layers, and the decoding sub-module consists of a series of convolutional layers and up-sampling layers. After the input image is subjected to encoding and decoding processes, a parking mark probability map M with the size of 256 × 1 is obtained.
4) The feature extraction utilizes a convolutional neural network to extract specific features, and different convolutional kernels extract different features.
5) The mask refines the sliding window to scan the image and find the area where the target is present and fine-tunes its position and size. If there are multiple anchor points (anchors) overlapping each other, we will retain the anchor with the highest foreground score and discard the rest (non-maxima suppression). We then get the final region proposal.
6) And (6) deriving model parameters.
3. When the user parks, the user uses the video snapshot to identify
1) When a user clicks a returning button, current positioning is acquired from a central control once, and then the nearest returning point (namely P point) of the current vehicle position is acquired in a GEO searching mode; it is then determined whether the vehicle is within the p-point range.
2) And if the vehicle is at the point p at the moment, then sending a photographing instruction to the camera through the central control in an asynchronous mode. After the camera obtains the instruction, 3I frames within nearly 3 seconds are acquired in the video stream of the camera, and the continuity and the definition of the image are ensured.
3) And (3) the captured image and the model obtained in the step (2) and trained by the mask are divided into a parking area and an identification area in the image through a Full Convolution Network (FCN) model. As shown in fig. 3.
4) If the parking area identification is detected in the segmented image, judging whether the user can park; if the current vehicle position is not detected, the current vehicle position is not in the range of the point p, and the user is not allowed to return to the vehicle. As shown in fig. 4.
5) If a parking area identification area, such as a black line area in fig. 5 and 6, is detected in the segmented image, then binarization is performed to obtain a contour map, contour matching is performed to judge whether the direction of the vehicle head is vertical to a parking reference line, and if the direction of the identification area does not meet the specification, the user is not allowed to park
6) And measuring 6 DOF parameters of the vehicle by using an inertial measurement unit IMU, analyzing the DOF data by a falling detection algorithm, and judging whether the vehicle is in a falling state. If the user is in the dumping state, the user is not allowed to stop
7) If the above conditions are met, returning the car is allowed, and the image is recorded
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (9)
1. A fixed-point returning method for sharing an electric vehicle is characterized by comprising the following steps:
(1) arranging a camera device, an IMU device and a GPS device on the shared electric vehicle; the camera device is arranged at the head of the shared electric vehicle;
(2) when a user carries out a car returning operation on terminal equipment including a mobile phone, a server acquires the current GPS positioning of a shared electric car, searches a P point of a car returning point closest to the current shared electric car, judges whether the shared electric car is in the range of the P point, and if not, the server returns information that the car returning is not allowed to the user; if the shared electric vehicle is in the range of the point P, the server sends a photographing instruction to the photographing device, and the photographing device takes a snapshot of the current image and transmits the snapshot to the server;
(3) the server imports the captured images into a model trained in advance, and cuts out parking areas and identifications thereof in the images through a full convolution network FCN model; and if the parking area identification is not detected in the segmented image, the server returns information which does not allow parking to the user.
2. The fixed-point returning method for the shared electric vehicle as claimed in claim 2, wherein the model in the step (3) is trained according to the following steps:
(a) obtaining a sample of model training input: acquiring an image sample through a camera device arranged at the vehicle head, and marking a parking area to obtain a corresponding binary mask;
(b) preprocessing an input image;
(c) extracting parking identification features by using a convolutional neural network construction module;
(d) and (6) deriving model parameters.
3. The fixed-point returning method for the shared electric vehicle according to claim 2, wherein in the step (b), the long side of the input image is scaled to 256, the short side is scaled in an equal ratio, and the shortfalls are aligned with 0, so as to obtain the RGB input image X with the size of 256 × 3; and carrying out the same scaling operation on the corresponding binary mask to obtain a training mask Y.
4. The fixed-point returning method for the shared electric vehicle of claim 3, wherein in the step (c), the module is composed of an encoding sub-module and a decoding sub-module, wherein the encoding sub-module is composed of an encoding convolutional layer and a down-sampling layer, and the decoding sub-module is composed of a decoding convolutional layer and an up-sampling layer; after the input image is subjected to encoding and decoding processes, a parking mark probability map M with the size of 256 × 1 is obtained.
5. The fixed-point returning method for a shared electric vehicle as claimed in claim 4, wherein in the step (c), the window is slid to scan the image and find the area where the target exists, and the position and size thereof are finely adjusted; if a plurality of anchor points are mutually overlapped, the anchor point with the highest foreground score is reserved, and the rest anchor points are discarded, so that the final regional proposal is obtained.
6. The fixed-point returning method for the shared electric vehicle as claimed in claim 5, further comprising the steps of: (4) if the parking area identification is detected in the segmented image, binarization is carried out to obtain a contour map of the segmented image, contour matching is carried out, whether the direction of the vehicle head is vertical to a parking datum line is judged, and if the parking direction deviates beyond a set range, the server returns information which does not allow parking to a user.
7. The fixed-point returning method for the shared electric vehicle as claimed in claim 6, further comprising the steps of: (5) the method comprises the steps that 6 DOF parameters of the shared electric vehicle are measured by the IMU, the DOF data are analyzed through a falling detection algorithm, whether the vehicle is in a falling state or not is judged, and if the vehicle is in the falling state, the server returns information that the vehicle returning is not allowed to the user.
8. The fixed-point returning method for the shared electric vehicle as claimed in claim 7, further comprising the steps of: (6) and if the conditions are met, the server returns the information of allowing the car to return to the user and records the image.
9. The fixed-point returning method for the shared electric vehicle as claimed in claim 8, wherein in the step (2), after the camera device receives the photographing instruction sent by the server, 3I frames within the last 3 seconds are obtained in the video stream.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110007623.1A CN112699823A (en) | 2021-01-05 | 2021-01-05 | Fixed-point returning method for sharing electric vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110007623.1A CN112699823A (en) | 2021-01-05 | 2021-01-05 | Fixed-point returning method for sharing electric vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112699823A true CN112699823A (en) | 2021-04-23 |
Family
ID=75514723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110007623.1A Pending CN112699823A (en) | 2021-01-05 | 2021-01-05 | Fixed-point returning method for sharing electric vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112699823A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112950922A (en) * | 2021-01-26 | 2021-06-11 | 浙江得图网络有限公司 | Fixed-point returning method for sharing electric vehicle |
| CN113421382A (en) * | 2021-06-01 | 2021-09-21 | 杭州鸿泉物联网技术股份有限公司 | Method, system, equipment and storage medium for detecting standard parking of shared electric bill |
| CN113486812A (en) * | 2021-07-08 | 2021-10-08 | 浙江得图网络有限公司 | Riding safety control system and control method |
| CN114358863A (en) * | 2021-11-23 | 2022-04-15 | 摩拜(北京)信息技术有限公司 | Shared vehicle returning processing method and device and shared vehicle |
| CN115019498A (en) * | 2022-05-13 | 2022-09-06 | 深圳市锐明技术股份有限公司 | Parking management method and system |
| CN116504092A (en) * | 2023-04-24 | 2023-07-28 | 深圳市泰比特科技有限公司 | Method, device, equipment and storage medium for calibrating parking position of shared vehicle |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108061876A (en) * | 2017-11-15 | 2018-05-22 | 阿里巴巴集团控股有限公司 | A kind of vehicle positioning method and device |
| CN109446973A (en) * | 2018-10-24 | 2019-03-08 | 中车株洲电力机车研究所有限公司 | A kind of vehicle positioning method based on deep neural network image recognition |
| CN109993789A (en) * | 2017-12-29 | 2019-07-09 | 杭州海康威视数字技术股份有限公司 | A kind of the separated of shared bicycle stops determination method, device and camera |
| CN111401247A (en) * | 2020-03-17 | 2020-07-10 | 杭州趣维科技有限公司 | Portrait segmentation method based on cascade convolution neural network |
| CN111784924A (en) * | 2020-06-24 | 2020-10-16 | 摩拜(北京)信息技术有限公司 | Parking control method of vehicle, electronic equipment and shared vehicle system |
| CN111862475A (en) * | 2020-05-21 | 2020-10-30 | 北京骑胜科技有限公司 | Vehicle parking method and device, electronic equipment and readable storage medium |
| CN112116412A (en) * | 2020-08-12 | 2020-12-22 | 北京骑胜科技有限公司 | Parking information interaction method and device, two-wheel vehicle, electronic equipment and storage medium |
| CN112150729A (en) * | 2020-09-21 | 2020-12-29 | 北京骑胜科技有限公司 | Parking information interaction method and device, electronic equipment and storage medium |
-
2021
- 2021-01-05 CN CN202110007623.1A patent/CN112699823A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108061876A (en) * | 2017-11-15 | 2018-05-22 | 阿里巴巴集团控股有限公司 | A kind of vehicle positioning method and device |
| CN109993789A (en) * | 2017-12-29 | 2019-07-09 | 杭州海康威视数字技术股份有限公司 | A kind of the separated of shared bicycle stops determination method, device and camera |
| CN109446973A (en) * | 2018-10-24 | 2019-03-08 | 中车株洲电力机车研究所有限公司 | A kind of vehicle positioning method based on deep neural network image recognition |
| CN111401247A (en) * | 2020-03-17 | 2020-07-10 | 杭州趣维科技有限公司 | Portrait segmentation method based on cascade convolution neural network |
| CN111862475A (en) * | 2020-05-21 | 2020-10-30 | 北京骑胜科技有限公司 | Vehicle parking method and device, electronic equipment and readable storage medium |
| CN111784924A (en) * | 2020-06-24 | 2020-10-16 | 摩拜(北京)信息技术有限公司 | Parking control method of vehicle, electronic equipment and shared vehicle system |
| CN112116412A (en) * | 2020-08-12 | 2020-12-22 | 北京骑胜科技有限公司 | Parking information interaction method and device, two-wheel vehicle, electronic equipment and storage medium |
| CN112150729A (en) * | 2020-09-21 | 2020-12-29 | 北京骑胜科技有限公司 | Parking information interaction method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| XIN XIA等: ""Automated Vehicle Attitude and Lateral Velocity Estimation Using a 6-D IMU Aided by Vehicle Dynamics"", 《2018 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV)》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112950922A (en) * | 2021-01-26 | 2021-06-11 | 浙江得图网络有限公司 | Fixed-point returning method for sharing electric vehicle |
| CN113421382A (en) * | 2021-06-01 | 2021-09-21 | 杭州鸿泉物联网技术股份有限公司 | Method, system, equipment and storage medium for detecting standard parking of shared electric bill |
| CN113421382B (en) * | 2021-06-01 | 2022-08-30 | 杭州鸿泉物联网技术股份有限公司 | Detection method, system, equipment and storage medium for shared electric bill standard parking |
| CN113486812A (en) * | 2021-07-08 | 2021-10-08 | 浙江得图网络有限公司 | Riding safety control system and control method |
| CN114358863A (en) * | 2021-11-23 | 2022-04-15 | 摩拜(北京)信息技术有限公司 | Shared vehicle returning processing method and device and shared vehicle |
| CN115019498A (en) * | 2022-05-13 | 2022-09-06 | 深圳市锐明技术股份有限公司 | Parking management method and system |
| CN116504092A (en) * | 2023-04-24 | 2023-07-28 | 深圳市泰比特科技有限公司 | Method, device, equipment and storage medium for calibrating parking position of shared vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112699823A (en) | Fixed-point returning method for sharing electric vehicle | |
| CN112184818B (en) | Vision-based vehicle positioning method and parking lot management system applying same | |
| CN106919915B (en) | Map road marking and road quality acquisition device and method based on ADAS system | |
| CN110619279B (en) | Road traffic sign instance segmentation method based on tracking | |
| CN112200172B (en) | Driving region detection method and device | |
| CN110487562A (en) | One kind being used for unpiloted road-holding ability detection system and method | |
| CN107992819B (en) | Method and device for determining vehicle attribute structural features | |
| US11361556B2 (en) | Deterioration diagnosis device, deterioration diagnosis system, deterioration diagnosis method, and storage medium for storing program | |
| CN107305627A (en) | A kind of automobile video frequency monitoring method, server and system | |
| CN105702048A (en) | Automobile-data-recorder-based illegal lane occupation identification system and method for automobile on highway | |
| JP6595375B2 (en) | Traffic condition analysis device, traffic condition analysis method, and traffic condition analysis program | |
| CN105184301B (en) | A kind of method that vehicle heading is differentiated using four-axle aircraft | |
| CN112950922B (en) | Fixed-point returning method for sharing electric vehicle | |
| CN112381014A (en) | Illegal parking vehicle detection and management method and system based on urban road | |
| CN111832388B (en) | Method and system for detecting and identifying traffic sign in vehicle running | |
| CN110135216B (en) | Method and device for detecting lane number change area in electronic map and storage equipment | |
| CN110852236A (en) | Target event determination method and device, storage medium and electronic device | |
| Sebsadji et al. | Robust road marking extraction in urban environments using stereo images | |
| Yamazaki et al. | Vehicle extraction and speed detection from digital aerial images | |
| CN113903008A (en) | Ramp exit vehicle violation identification method based on deep learning and trajectory tracking | |
| Hsu et al. | Design and implementation of an intelligent road detection system with multisensor integration | |
| Kaushik et al. | Pothole Detection System: A Review of Different Methods Used for Detection | |
| Kiew et al. | Vehicle route tracking system based on vehicle registration number recognition using template matching algorithm | |
| JPWO2012014972A1 (en) | Vehicle behavior analysis apparatus and vehicle behavior analysis program | |
| Coronado et al. | Detection and classification of road signs for automatic inventory systems using computer vision |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210423 |
|
| RJ01 | Rejection of invention patent application after publication |