CN110599800A - Parking lot parking space state monitoring system and monitoring method - Google Patents
Parking lot parking space state monitoring system and monitoring method Download PDFInfo
- Publication number
- CN110599800A CN110599800A CN201910904792.8A CN201910904792A CN110599800A CN 110599800 A CN110599800 A CN 110599800A CN 201910904792 A CN201910904792 A CN 201910904792A CN 110599800 A CN110599800 A CN 110599800A
- Authority
- CN
- China
- Prior art keywords
- parking space
- data
- vehicle
- coordinate
- mean
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
- G08G1/144—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces on portable or mobile units, e.g. personal digital assistant [PDA]
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/146—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas where the parking area is a limited parking space, e.g. parking garage, restricted space
Abstract
The invention discloses a parking lot parking space state monitoring system and a monitoring method, wherein the system comprises a radar acquisition module, a vehicle monitoring module and a monitoring module, wherein the radar acquisition module is used for acquiring vehicle motion information; the data processing module is electrically connected with the radar acquisition module and is used for processing data information acquired by the radar acquisition module to obtain the current position of the vehicle; the parking space state indicator light is electrically connected with the data processing module; a central controller electrically connected with each module; and the client is electrically connected with the central controller. The monitoring method comprises the following steps: the radar acquisition module acquires electromagnetic wave data information reflected by the vehicle and sends the electromagnetic wave data information to the data processing module; the data processing module processes the data information to obtain coordinate data representing the current position of the vehicle; comparing the coordinate data of the current position of the vehicle with the coordinate data of the parking space, and judging whether the current position of the vehicle is on the parking space; the indicator light displays the parking space state. The invention realizes parking space monitoring by using the millimeter wave radar, and has the remarkable advantages of high precision and low implementation cost.
Description
Technical Field
The invention relates to parking space monitoring in a parking lot, in particular to a parking space monitoring system in the parking lot and a parking space monitoring method in the parking lot.
Background
With the great increase of the holding amount of urban automobiles, the management pressure of urban parking spaces is also increasing. The existing parking space state identification systems of underground parking lots usually mainly monitor parking spaces by using cameras, geomagnetic sensors, ultrasonic detectors, infrared correlation sensors and the like, and a marker needs to be arranged in each parking space or a related sensor needs to be arranged, so that the cost is greatly increased; laser radar has a major challenge in vehicle scale production and cost control. Therefore, a new parking space monitoring system/method suitable for an underground parking lot is urgently needed to be provided.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a parking space monitoring system based on radar in a parking lot, and the invention also aims to provide a parking space monitoring method in a parking lot so as to realize real-time monitoring of the parking space state.
The technical scheme is as follows: a parking lot parking space state monitoring system comprises: the radar acquisition module is arranged on a wall of the parking lot and used for acquiring data information of electromagnetic waves reflected by the vehicle; the data processing module is electrically connected with the radar acquisition module and is used for processing data information acquired by the radar acquisition module to obtain coordinate data representing the current position of the vehicle; the indicating lamps are correspondingly arranged on each parking space, are electrically connected with the data processing module and are used for indicating the state of the parking space, and the central controller is electrically connected with the radar acquisition module, the data processing module and the indicating lamps respectively; and the mobile client is in wireless connection with the central controller and is used for displaying the parking space state information of the parking lot.
The parking space state monitoring method based on the parking space state monitoring system of the parking lot according to claim 1, comprising the following steps:
step 1, a radar acquisition module acquires electromagnetic wave data information reflected by a vehicle and sends the electromagnetic wave data information to a data processing module; the data information comprises real-time position coordinates of the vehicle;
step 2, the data processing module processes the data information of the vehicle to obtain coordinate data representing the current position of the vehicle;
step 3, comparing the coordinate data of the current position of the vehicle with the coordinate data of the parking space of the parking lot, and judging whether the current position of the vehicle is on the parking space;
and 4, displaying the parking space state by the indicator lamp.
Further, in step 2, the specific steps of the data processing module for processing the acquired vehicle data information are as follows:
static target data collected by a radar collection module are removed, and dynamic target data information is obtained;
carrying out abnormal point detection and filtering on the dynamic target data information to obtain processed vehicle data information, specifically, taking N frame data for judgment, if the number of coordinate points in one frame is less than a, not carrying out any processing, and if the number of coordinate points in one frame is more than or equal to a, carrying out abnormal point detection and filtering processing, wherein N is more than or equal to 6 and less than or equal to 20, and a is more than or equal to 2 and less than or equal to 5;
and carrying out weighted summation on the coordinate data in the processed vehicle data information to obtain coordinate data representing the current position of the vehicle.
Further, abnormal point detection and filtering are carried out on the dynamic target data information, and processed vehicle data information is obtained, and the method specifically comprises the following steps:
(1) training and constructing t decision trees corresponding to the random forest by using coordinate point data in the dynamic target data, wherein t is more than or equal to 1;
(2) calculating the height average value of the coordinate point data to be detected in each tree according to the number of layers;
(3) and calculating an abnormal probability score according to the height average value, and judging whether the coordinate point is an abnormal point or not according to comparison between the abnormal probability score and a preset threshold value.
Further, the formula for calculating the anomaly probability score according to the height average value is as follows:
wherein h ist(x)、ht(y) is the data point xi，yiCorresponding to the number of layers, E (h), (x) and E (h), (y) are height average values, and the value range of s (x, n) is [0, 1%]The closer the value is to 1, the greater the probability of being an outlier; wherein n is the number of samples, and the expression of c (n) is as follows:
where, the harmonic number h (i) ≈ ln (i) + ξ, i ═ n-1, ξ is an euler constant, and ξ ═ 0.5772156649.
And when the abnormal probability score is larger than a preset threshold value, the corresponding coordinate point is an abnormal point. Preferably, the value of the preset threshold is 0.6-0.7.
Further, performing weighted summation on the coordinate data in the processed vehicle data information to obtain coordinate data representing the current position of the vehicle, specifically, calculating the final position coordinate by using the following formula:
(x,y)＝((ω1*meanx1+ω2*meanx2)/2，(ω1*meany1+ω2*meany2)/2)
wherein (mean)x1，meany1) Average coordinate values of all data points reserved for the previous N/2 frames, (mean)x2，meany2) The average coordinate value of all data points reserved for the next N/2 frames, ω 1 is (mean)x1，meany1) ω 2 is (mean)x2，meany2) Weight coefficient of (2), 0.4 ≤ ω 1<0.5，0.5<ω2≤0.6。
Further, the specific steps of step 3 are as follows:
calculating coordinates A (x, y), B (x, y), C (x, y) and D (x, y) of four corner points of each parking space, wherein the range surrounded by the four corner points is a parking space region ROI; and when the coordinate data of the current position of the vehicle is in the ROI coordinate range, judging that the parking space is occupied.
Compared with the prior art, the invention has the following remarkable advantages: 1. the real-time monitoring of the parking spaces of the parking lot is realized based on the millimeter wave radar, the parking lot can adapt to various weather conditions, is slightly influenced by environmental interference, and is high in positioning precision (reaching 5 cm). 2. The detectable range of the radar is 80 meters in the longitudinal direction, the horizontal angle is 120 degrees, all parking space monitoring can be realized only by arranging 7-8 millimeter-wave radars in the parking lot range of 3000 square meters, the cost is low, and the arrangement is easy. 3. And the collected data is subjected to noise processing and abnormal point processing, so that the accurate monitoring of the parking space is further improved.
Drawings
FIG. 1 is a schematic structural diagram of a parking space status monitoring system of a parking lot according to the present invention;
fig. 2 is a schematic view of the arrangement of radar in a parking lot plan;
FIG. 3 is a schematic diagram of data point distribution of a single vehicle in a current frame;
FIG. 4 is a schematic flow chart of the data processing module processing the collected vehicle data information;
FIG. 5 is a flow chart of an isolated forest method;
FIG. 6 is a diagram showing the relationship between E (h), (x) and s (x, n).
Detailed Description
The invention adopts the millimeter wave radar to realize the detection of the parking space, and the millimeter wave radar has the advantages of all-weather long-distance detection, simple circuit, low cost and easy realization of batch arrangement in the parking lot. Electromagnetic waves transmitted by the millimeter wave radar can be strongly reflected after encountering metal objects, reflected echoes are received by the radar, and parameter information such as distance, speed, angle, Doppler and the like of the metal objects can be obtained according to transmitted and received electromagnetic wave data information. The vehicle can be understood as a large metal object actually, and the millimeter wave radar detection precision reaches about 5cm, so the vehicle position can be detected accurately through the millimeter wave radar, and the vehicle space occupation condition can be judged according to the positions of the vehicle and the parking space. The invention is further described in detail below with reference to the drawings and examples.
As shown in fig. 1, the parking space state monitoring system of the present invention includes a client, a central controller, a radar collection module, a data processing module, and an indicator light, wherein the radar collection module includes a plurality of millimeter wave radars, as shown in fig. 2, the millimeter wave radars are installed on a wall at one end of a main road, and an indicator light is installed above each parking space. The system collects the motion data of the vehicles entering the parking lot in real time, outputs the coordinate positions of the vehicles and judges whether the positions are within the range of parking spaces, namely whether the parking spaces are occupied.
Based on the system, the method for monitoring the parking space state comprises the following steps:
the method comprises the following steps that firstly, a radar acquisition module is used for acquiring data information of a vehicle, wherein the data information comprises real-time position coordinates of the vehicle, the detectable range of the radar is 80 meters in the longitudinal direction, the horizontal angle is 120 degrees, all parking spaces can be monitored by arranging 7-8 millimeter-wave radars in a parking lot range of 3000 square meters, the cost is low, and the arrangement is easy; the radar acquisition module can acquire data information of electromagnetic waves reflected by the vehicle, wherein the data information comprises positions x and y, time parameters and vx、vyFor example, as shown in fig. 3, data points of one frame of a single vehicle detected by a radar are not few abnormal points with large jitter, which may cause erroneous determination of the parking space state and need to be filtered.
Step two, as shown in fig. 4, the data processing module is configured to process the acquired vehicle data information to obtain coordinate data representing a current position of the vehicle:
1. the radar can detect a static target and a dynamic target, the speed of the static target is 0, the Doppler value is also 0, and only the information of the final moving vehicle is left after the static target data point with the Doppler value of 0 is removed.
2. Taking N frames of data to judge abnormal points, wherein the specific number of the frames is determined according to the radar acquisition frequency, the frequency is about 20ms, and the N can be within a range of 6-20; if the number of data points in one frame is less than a, no processing is carried out; if the number of data points in one frame is more than or equal to a, abnormal point filtering processing is carried out, wherein a is more than or equal to 2 and less than or equal to 5, and is preferably 3; it should be noted that, because the data volume collected by the far field (greater than 20m) is small, if the number of data points in one frame is less than 3, and then the abnormal points are removed, the number of points is less, and the determination is not easy to be made, so that more data information is retained as much as possible for the determination of the far field.
In the step, an isolated forest method is adopted to detect abnormal points:
(1) training and constructing t decision trees corresponding to the random forest, wherein the decision trees are generally called iTrees with t being more than or equal to 1 and are random binary trees;
(1.1) the data in the present invention is characterized by two dimensions (x, y), where x represents the abscissa of the coordinate point and y represents the ordinate of the coordinate point; given n coordinate points as sample data, corresponding to a data set X ═ X1,…,xnY ═ Y1,…,yn}， I is more than or equal to 1 and less than or equal to n, psi samples are respectively randomly extracted from X, Y to be used as training samples of the tree and are put into the root node of the tree; hereinafter all indicated by xiFor example, yiThe same process is carried out;
(1.2) randomly selecting a feature from psi samples, randomly selecting a value p under the feature (p is between the maximum value and the minimum value of the samples), performing binary division on the samples, and dividing samples which are smaller than the value to the left of a node and dividing samples which are larger than or equal to the value to the right of the node. The above process is then repeated on the left and right datasets, respectively, until the dataset has only one record or a defined height of the tree is reached.
(1.3) firstly, traversing each iTree to obtain the layer number h of the detected data point which finally falls on any t-th iTreet(x)。ht(x) What is represented is the depth of the tree, meaning that several edges need to be traversed from the root node of the tree to reach the leaf nodes. The height of the root node is 0, and the closer to the root node, the ht(x) The smaller; on the contrary, the method can be used for carrying out the following steps,then h ist(x) The larger the size.
Since there is less abnormal data and the eigenvalues are very different from the normal data. Thus, when constructing an iTree, the outlier data is very close to the root, while the normal data is very far from the root. The result of one iTree is often not credible, and the IForest algorithm constructs a plurality of binary trees through multiple sampling. And finally integrating the results of all the trees and calculating the abnormal score of the data point.
(2) The average E (h (x)) of the height of the sample points to be detected per tree is calculated. Where E (h (x)) represents the average height among all itrees, the lower the height, the higher the anomaly score.
(3) According to E (h (x)), judging xiWhether it is an outlier. The anomaly probability score is calculated using the following formula:
s(x)＝2-E(h(x))
however, the above problem is that without normalization, for example, when there are many data points, the height of the tree as a whole may be high, and it may be necessary to divide the abnormal points many times, so we use a term c (n) for normalization. If there are n samples, then the average path length for an unsuccessful search is:
where H (i) is the harmonic number (harmonic number), where i is taken to be (n-1), the harmonic number H (i) can be approximated as: h (i) ≈ ln (i) + ξ, ξ is an euler constant, ξ ═ 0.5772156649. .
Since c (n) represents the average height at n sample points, we use to normalize h (x), then the normalized anomaly score is:
as can be seen from the expression of s (x, n), if the height E (h (x)) → 0, s (x, n) → 1, i.e., the probability of being an outlier is 100%. As shown in fig. 5, it can be seen that d is most likely to be an outlier because it was isolated at the earliest. A threshold value for s (x, n) is set, preferably 0.6-0.7, and points above the threshold value are considered outliers. FIG. 6 shows the relationship between E (h (x)) and s (x, n).
3. The remaining coordinate point [ x ] is retained1,…,xn-1]，[y1,…,yn-1]And are in one-to-one correspondence (when abnormal point judgment is made, coordinates x and y are respectively judged, and when x is abnormal data elimination, the corresponding y is also deleted).
4. Average mean of all data points retained in the first N/2 framesx1、meany1Average mean of all data points retained for the next N/2 framesx2、meany2. Although the position of the object in the N frames is not greatly different, the next N/2 frames are closer to the current time, and the position of the current time is more important and accurate, so the mean is givenx2、meany2Higher weight, but considering that the difference between the previous and next N/2 frames is not significant, the weight coefficients should not differ too much, and the coordinate of the final point is obtained according to the following formula:
(x,y)＝((ω1*meanx1+ω2*meanx2)/2，(ω1*meany1+ω2*meany2) And/2), wherein ω 1 and ω 2 are weight coefficients of the preceding N/2 frame and the following N/2 frame, respectively, 0.4 ≦ ω 1 < 0.5, 0.5 ≦ ω 2 ≦ 0.6, ω 1 is preferably 0.4, and ω 2 is preferably 0.6.
Comparing the coordinate data of the current position of the vehicle with the coordinate data of the parking space of the parking lot, and judging whether the current position of the vehicle is on the parking space, wherein the method specifically comprises the following steps:
and calculating four corner coordinates A (x, y), B (x, y), C (x, y) and D (x, y) of each parking space, wherein the range surrounded by the four corners is the parking space region ROI. When the coordinate data of the current position of the vehicle is in the ROI coordinate range, judging that the parking space is occupied;
and step four, displaying the parking space state by the indicator lamp. When the parking space is empty, the indicator light turns green; when the parking space is occupied, the indicator light turns red.
As shown in fig. 2, a specific range of each parking spot can be obtained. The parking space is properly enlarged by 10cm to be used as a final target area ROI, so that the situation that the parking space is not detected when the vehicle is parked at one side close to the parking space is prevented. When the point (x, y) obtained in the step 4 enters the ROI, the parking space is occupied, and an indicator lamp above the parking space turns red; when (x, y) leaves the ROI, the parking space is free, and the indicator light above the parking space turns green.
Claims (9)
1. The utility model provides a parking area parking stall state monitoring system which characterized in that includes:
the radar acquisition module is arranged on a wall of the parking lot and used for acquiring data information of electromagnetic waves reflected by the vehicle;
the data processing module is electrically connected with the radar acquisition module and is used for processing data information acquired by the radar acquisition module to obtain coordinate data representing the current position of the vehicle;
the indicating lamps are correspondingly arranged on each parking space, are electrically connected with the data processing module and are used for indicating the state of the parking space;
the central controller is electrically connected with the radar acquisition module, the data processing module and the indicator lamp respectively;
and the mobile client is in wireless connection with the central controller and is used for displaying the parking space state information of the parking lot.
2. The parking space state monitoring method based on the parking space state monitoring system of the parking lot according to claim 1, characterized by comprising the following steps:
step 1, a radar acquisition module acquires electromagnetic wave data information reflected by a vehicle and sends the electromagnetic wave data information to a data processing module; the data information comprises real-time position coordinates of the vehicle;
step 2, the data processing module processes the data information of the vehicle to obtain coordinate data representing the current position of the vehicle;
step 3, comparing the coordinate data of the current position of the vehicle with the coordinate data of the parking space of the parking lot, and judging whether the current position of the vehicle is on the parking space;
and 4, displaying the parking space state by the indicator lamp.
3. The parking space state monitoring method according to claim 2, wherein in the step 2, the data processing module is used for processing the collected vehicle data information, and the specific steps are as follows:
step 21, eliminating static target data acquired by a radar acquisition module to obtain dynamic target data information;
step 22, performing anomaly point detection and filtering on the dynamic target data information to obtain processed vehicle data information, specifically, taking N frames of data to judge, if the number of coordinate points in one frame is less than a, not performing any processing, and if the number of coordinate points in one frame is more than or equal to a, performing anomaly point detection and filtering processing, wherein N is more than or equal to 6 and less than or equal to 20, and a is more than or equal to 2 and less than or equal to 5;
and 23, carrying out weighted summation on the coordinate data in the processed vehicle data information to obtain coordinate data representing the current position of the vehicle.
4. The parking space state monitoring method according to claim 3, wherein in step 22, the specific steps of performing anomaly point detection on the dynamic target data are as follows:
(1) training and constructing t decision trees corresponding to the random forest by using coordinate point data in the dynamic target data, wherein t is more than or equal to 1;
(2) calculating the height average value of the coordinate point data to be detected in each tree according to the number of layers;
(3) and calculating an abnormal probability score according to the height average value, and judging whether the coordinate point is an abnormal point or not according to comparison between the abnormal probability score and a preset threshold value.
5. The parking space state monitoring method according to claim 4, wherein the formula for calculating the abnormal probability score according to the height average value is as follows;
wherein, h (x) and h (y) are the number of layers, E (h (x) and E (h (y)) are the average height, the value ranges of s (x, n) and s (y, n) are [0, 1], and the closer to 1, the higher the probability of being an abnormal point is; wherein x represents the abscissa of the coordinate point, y represents the ordinate of the coordinate, n is the number of samples, and the expression of c (n) is:
where, the harmonic number h (i) ≈ ln (i) + ξ, i ═ n-1, ξ is an euler constant, and ξ ═ 0.5772156649.
6. The parking space state monitoring method according to claim 4, wherein in the step (3), when the abnormal probability score is greater than a preset threshold, the corresponding coordinate point is an abnormal point.
7. The parking space state monitoring method according to claim 6, characterized in that: the value of the preset threshold is 0.6-0.7.
8. The parking space state monitoring method according to claim 3, wherein in step 23, the position coordinates of the vehicle are calculated by using the following formula:
(x，y)＝((ω1*meanx1+ω2*meanx2)/2，(ω1*meany1+ω2*meany2)/2)
wherein (mean)x1，meany1) Average coordinate values of all data points reserved for the previous N/2 frames, (mean)x2，meany2) The average coordinate value of all data points reserved for the next N/2 frames, ω 1 is (mean)x1，meany1) ω 2 is (mean)x2，meany2) The weight coefficient of omega 1 is more than or equal to 0.4 and less than 0.5, and omega 2 is more than 0.5 and less than or equal to 0.6.
9. The parking space state monitoring method according to claim 2, wherein the specific steps of the step 3 are as follows:
calculating coordinates A (x, y), B (x, y), C (x, y) and D (x, y) of four corner points of each parking space, wherein the range surrounded by the four corner points is a parking space region ROI; and when the coordinate data of the current position of the vehicle is in the ROI coordinate range, judging that the parking space is occupied.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910904792.8A CN110599800A (en) | 2019-09-24 | 2019-09-24 | Parking lot parking space state monitoring system and monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910904792.8A CN110599800A (en) | 2019-09-24 | 2019-09-24 | Parking lot parking space state monitoring system and monitoring method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110599800A true CN110599800A (en) | 2019-12-20 |
Family
ID=68863066
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910904792.8A Pending CN110599800A (en) | 2019-09-24 | 2019-09-24 | Parking lot parking space state monitoring system and monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110599800A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112541981A (en) * | 2020-11-03 | 2021-03-23 | 山东中创软件商用中间件股份有限公司 | ETC portal system early warning method, device, equipment and medium |
| CN112820096A (en) * | 2020-12-30 | 2021-05-18 | 中联重科股份有限公司 | Remote control system and method for engineering machinery supporting leg and engineering machinery |
| CN114999217A (en) * | 2022-05-27 | 2022-09-02 | 北京筑梦园科技有限公司 | Vehicle detection method and device and parking management system |
| CN115050192A (en) * | 2022-06-09 | 2022-09-13 | 南京矽典微系统有限公司 | Parking space detection method based on millimeter wave radar and application |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060119473A1 (en) * | 1998-08-06 | 2006-06-08 | Altra Technologies Incorporated | System and method of avoiding collisions |
| CN206400780U (en) * | 2016-06-30 | 2017-08-11 | 深圳市金溢科技股份有限公司 | A kind of radar module recognized for parking stall and parking stall identifying system |
| CN107341964A (en) * | 2017-03-27 | 2017-11-10 | 小儒技术（深圳）有限公司 | A kind of method for detecting parking stalls and device |
| CN110135614A (en) * | 2019-03-26 | 2019-08-16 | 广东工业大学 | It is a kind of to be tripped prediction technique based on rejecting outliers and the 10kV distribution low-voltage of sampling techniques |
-
2019
- 2019-09-24 CN CN201910904792.8A patent/CN110599800A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060119473A1 (en) * | 1998-08-06 | 2006-06-08 | Altra Technologies Incorporated | System and method of avoiding collisions |
| CN206400780U (en) * | 2016-06-30 | 2017-08-11 | 深圳市金溢科技股份有限公司 | A kind of radar module recognized for parking stall and parking stall identifying system |
| CN107341964A (en) * | 2017-03-27 | 2017-11-10 | 小儒技术（深圳）有限公司 | A kind of method for detecting parking stalls and device |
| CN110135614A (en) * | 2019-03-26 | 2019-08-16 | 广东工业大学 | It is a kind of to be tripped prediction technique based on rejecting outliers and the 10kV distribution low-voltage of sampling techniques |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112541981A (en) * | 2020-11-03 | 2021-03-23 | 山东中创软件商用中间件股份有限公司 | ETC portal system early warning method, device, equipment and medium |
| CN112820096A (en) * | 2020-12-30 | 2021-05-18 | 中联重科股份有限公司 | Remote control system and method for engineering machinery supporting leg and engineering machinery |
| CN114999217A (en) * | 2022-05-27 | 2022-09-02 | 北京筑梦园科技有限公司 | Vehicle detection method and device and parking management system |
| CN115050192A (en) * | 2022-06-09 | 2022-09-13 | 南京矽典微系统有限公司 | Parking space detection method based on millimeter wave radar and application |
| CN115050192B (en) * | 2022-06-09 | 2023-11-21 | 南京矽典微系统有限公司 | Parking space detection method based on millimeter wave radar and application |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110599800A (en) | Parking lot parking space state monitoring system and monitoring method | |
| CN110532889B (en) | Track foreign matter detection method based on rotor unmanned aerial vehicle and YOLOv3 | |
| Catapang et al. | Obstacle detection using a 2D LIDAR system for an Autonomous Vehicle | |
| CN108345823B (en) | Obstacle tracking method and device based on Kalman filtering | |
| CN103559508B (en) | A kind of based on continuous Adaboost video vehicle detection method | |
| CN112101278A (en) | Hotel point cloud classification method based on k nearest neighbor feature extraction and deep learning | |
| CN1940591A (en) | System and method of target tracking using sensor fusion | |
| CN101794437B (en) | Method for detecting abnormal target in hyperspectral remotely sensed image | |
| CN111880196A (en) | Unmanned mine car anti-interference method, system and computer equipment | |
| CN114612795A (en) | Laser radar point cloud-based road surface scene target identification method | |
| CN110717496B (en) | Complex scene tree detection method based on neural network | |
| CN114488194A (en) | Method for detecting and identifying targets under structured road of intelligent driving vehicle | |
| CN115064009B (en) | Terminal area unmanned aerial vehicle and man-machine conflict risk level classification method | |
| CN115641553B (en) | Online detection device and method for invaders in heading machine working environment | |
| CN115840205B (en) | Terrain area metering method and system based on laser radar technology | |
| CN110703272B (en) | Surrounding target vehicle state estimation method based on vehicle-to-vehicle communication and GMPHD filtering | |
| CN113256990B (en) | Method and system for collecting road vehicle information by radar based on clustering algorithm | |
| CN114545387A (en) | High-altitude parabolic detection and discrimination method based on millimeter wave radar data fitting | |
| CN113970734A (en) | Method, device and equipment for removing snowing noise of roadside multiline laser radar | |
| CN111736156B (en) | Upwind area identification method and device based on weather radar | |
| CN113687429A (en) | Device and method for determining boundary of millimeter wave radar monitoring area | |
| US20230314169A1 (en) | Method and apparatus for generating map data, and non-transitory computer-readable storage medium | |
| CN109389053B (en) | Method and system for detecting position information of vehicle to be detected around target vehicle | |
| CN106249241B (en) | A kind of self-adapting clutter power statistic algorithm | |
| CN111239717B (en) | Water surface obstacle detection method based on X-band radar |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191220 |