KR20220118211A - Parking Information System Linked to Vehicle Navigation and Calendar Applications in Smartphones - Google Patents

Abstract

The present invention relates to a parking information providing system linked with a vehicle navigation and schedule management application in a smartphone, and more specifically, to a parking information providing system linked with a vehicle navigation and schedule management application in a smartphone, which is linked to schedule information written on a smartphone and a vehicle navigation system to select a parking lot near the destination written in the schedule, and clearly informs a required door-to-door time to the destination to a user in consideration of a congestion level inside and outside the parking lot and the walking time from the parking surface within the parking lot to the destination, to promote efficient movement and schedule management.

Description

Parking Information System Linked to Vehicle Navigation and Calendar Applications in Smartphones}

The present invention relates to a parking information providing system in connection with a vehicle navigation and schedule management application in a smartphone, and more specifically, by identifying a user's or driver's personal schedule, providing parking information near a corresponding destination, And it relates to a parking information providing system linked to a vehicle navigation and schedule management application in a smartphone that provides a more accurate door-to-door time required to a user by identifying the time required to arrive at a destination through walking congestion.

Existing parking (parking) information providing systems and methods are based on the destination (or current location) of the parking lot location (proximity, accessibility, etc.), parking fee (including discount information), parking lot availability (real-time number of parking spaces) As a standard, we take a method of recommending a parking lot to the user. In addition, the most commonly used LPR-based parking management system used ultrasonic sensors and loop sensors installed in units of parking spaces to check whether each parking space is occupied. A technology to check whether an individual parking surface is occupied using an image was developed, and initially it was a method of detecting or recognizing stoppers or parking dividing lines installed in units of parking surfaces. It became possible to accurately calculate the number of available parking spaces even in the case of various unmanned parking behaviors, which enabled the user (driver, etc.) to reserve and use a specific parking space.

On the other hand, in real life, depending on the user's (driver's) personal reasons or external factors, the situation of arriving earlier than the original plan (schedule, event, appointment, etc.) or arriving late or late frequently occurs. However, in such cases Edo’s existing parking (parking) information providing system and its method are later than originally planned, and regardless of the name, information is provided based on the location of the parking lot, parking fee, and the number of available parking spaces. The distance to the plane, the congestion level of the same section, and the distance from the parking available parking side to the entrance, ELV, stairs, escalator, etc. of the destination are not considered. cases are occurring.

Accordingly, the present invention utilizes schedule information (event name, start time, end time, location, attendees, etc.) of the user (driver, etc.) written in the scheduler, etc. When it is set to provide parking (park) information in consideration of information, the distance of the operating section, the congestion level of the operating section, the distance of the parking section, the congestion degree of the parking section, the distance of the walking section (walking section A), the congestion degree of the walking section An object of the present invention is to provide a system and method for providing parking (parking) information to users (drivers, etc.) in consideration of any one or more of (the number of ELVs waiting in the walking section B, the number of available ELVs, etc.).

The present invention provides vehicle navigation and schedule management in a smartphone that guides the user to a more accurate door-to-door time to the destination by utilizing the personal schedule information registered in the user's smartphone and the congestion information of the parking lot and nearby areas. Its purpose is to provide a parking information providing system linked to the application.

The parking information providing system in connection with the vehicle navigation and schedule management application in the smartphone according to the present invention for solving the present invention is installed in each parking lot, and the parking section 103 from the circuit breaker 101 to the available parking surface 102 ) one or more cameras 100 to obtain a parking lot image including; The total distance (201) of the parking section (103), the number of unparked vehicles (202) located in the parking section (103) detected from the image acquired by the camera (100), the camera (100) a parking section analysis unit 200 that analyzes the required parking time 204 using any one or more of the speeds 203 of unparked vehicles located in the parking section 103 detected from the image obtained by ; and a tardy time calculation unit 300 for calculating a tardy time 303 by comparing the estimated arrival time 301 to the destination calculated by the navigation and the scheduled start time 302 at the entered destination. When the tardy time calculated by the tardy time calculation unit 300 is equal to or greater than the preset time 401, the time 403 including the required travel time 402 and the required parking time 204 to the destination calculated by the navigation. A walking section analysis unit 400 that provides parking information according to ; further comprising, the camera 100 additionally acquires an image of the parking surface, and an occupancy detection unit 500 for detecting whether an individual parking surface is occupied from the image obtained by the camera 100; The tardy time calculation unit 300 compares the estimated arrival time 304 to each parking lot calculated by the navigation and the scheduled start time 302 at the entered destination to provide the tardy time 303 ), and the tardy time calculation unit 300 uses the schedule start time 302 at the destination input by the user into the schedule management program. A parking information provision system is provided.

Additionally, as an additional matter for smooth operation of the system, the occupancy detection unit 500 additionally detects any one or more of the distance 501 between vehicles and the distance 502 between the vehicle and the outermost part of the parking area. , classifies that the corresponding parking surface is not occupied only when the distance is greater than or equal to a preset distance, and when a plurality of parking available parking surfaces 102 exist, the parking available parking surface 102 with the minimum required parking time 204 In addition to providing parking information for the parking lot based on When there are a plurality of available parking surfaces 102, the sum of the required parking time 204 and the walking time 405 is the minimum to provide parking information of the corresponding parking lot based on the parking available parking surface 102. It provides a parking information providing system in connection with vehicle navigation and schedule management applications in the smartphone.

The present invention measures the congestion level of roadways and pedestrians in and around the parking lot by linking with the parking lot using a parking management system based on computer vision technology such as multi-object recognition and multi-object tracking, and the individual registered in the smartphone. By recognizing the user's clear destination by using the schedule and providing the required time to a more specific destination, efficient movement and schedule management of system or service users can be promoted.

1 is an example of an operating method of a parking information providing system in connection with a vehicle navigation and schedule management application in a smartphone.

The present invention will be described in detail with reference to the accompanying drawings as follows.

1 is a schematic representation of an operating method of a parking information providing system in connection with a vehicle navigation and schedule management application in a smartphone according to the present invention, and is largely a parking lot recommendation/selection step, a parking surface recommendation/selection step, a required time calculation step is divided into

In the case of the parking lot selection step, it starts with the step of extracting the user's schedule-related data written in the schedule management application in the user's smartphone from the schedule data receiver. The schedule data receiver extracts the schedule start time and destination through natural language processing (NLP). For the natural language processing, LSTM (Long Short-Term Memory) RNN, RoBERTa (A Robustly Optimized BERT Pretraining Approach, 2019.07.), ERNIE (Enhanced Representation through Knowledge Integration, 2019.04.), SpanBert (Improving Pre-training by Representing and Language models using artificial intelligence such as Predicting Spans, 2019.07.), XLNet (Generalized Autoregressive Pretraining for Language Understanding, 2019.06.), and MASS (Masked Sequence to Sequence Pre-training for Language Generation, 2019.05.) can be used, and English In consideration of the unique characteristics of Korean and other Korean languages, KorBERT, a Korean language model released by the Electronics and Telecommunications Research Institute (ETRI) in 2019, can also be used. The user schedule destination and schedule start time data extracted from the schedule data receiving unit are transmitted to the navigation and latent time calculation unit, respectively.

In the navigation, by using the destination information extracted from the schedule data receiving unit, information about parking lots near the destination is searched and the corresponding parking lots are transmitted to the parking lot selection unit. At this time, distance information from the destination to the parking lot is also transmitted.

The parking lot selection unit sets a candidate group of parking lots received from the navigation, and finally selects the parking lot closest to the destination among the candidate groups as the parking lot to guide the user and delivers it to the navigation system. However, if the parking lot is full, the parking lot next to the car is finally selected.

The parking information providing system for the implementation of the parking surface recommendation/selection step includes one or more cameras 100 capable of photographing the entrance breaker of the corresponding parking lot, all parking surfaces in the parking lot and walking sections (sidewalks, etc.) near the parking lot, the camera A parking section analysis unit that analyzes the image to calculate the required parking time for each parking surface, a walking segment analysis unit that analyzes the required time of the walking section to the destination by each parking available parking area, It consists of an occupancy detection unit.

The camera 100 is a PTZ camera and a multi-function camera with built-in functions such as arithmetic processing and communication, which are currently widely sold as commercial products, etc. The place of the parking section 103 leading to the possible parking surface 102 and the walking section (sidewalk, etc.) near the parking lot is photographed.

The occupancy detection unit receives the image of the inside of the parking lot photographed by the camera 100, checks whether the vehicle occupies the parking surface partitioned in advance through multi-object detection, and the vehicle is unoccupied, parking available parking The face is transmitted to the parking section analysis section, the walking section analysis section, and the parking face guide section. In the case of the multi-object detection, R-CNN (Region-based Convolutional Neural Network), Fast R-CNN, Faster R-CNN, YOLO (You Only Look Once), SSD (Single Shot Multi-box Detector), Deep SORT ( It can be implemented using algorithms such as Simple Online and Real-Time Tracking) and Hungarian (Kuhn-Munkres). Among the above algorithms, the R-CNN algorithm is the “Rich feature hierarchies for accurate object detection and semantic segmentation Tech report (v5)” announced through CVPR in 2014, and the Fast R-CNN algorithm is the “Fast” announced through ICCV in 2015. R-CNN”, Faster R-CNN algorithm through “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” announced at NIPS in 2015, YOLO v1, v2, v3 algorithm respectively in 2016 CVPR in 2017, CVPR in 2017, “YOLOv3: An Incremental Improvement” presented at arXiv in 2018, etc. Through “Simple Online and Realtime Tracking with a Deep Association Metric” published in has been

The walking section analysis unit receives the destination information, the parking available parking surface, and the photographed image of the walking section near the parking lot from the schedule data receiving unit, the occupancy detection unit, and the camera, respectively, and detects the nearest walking entrance for each parking available parking surface, and provides the information forwarded to the navigation. By adding the time required for the walking section from the corresponding walking entrance to the destination calculated in the navigation with the time required from the parking side to the nearest walking entrance, the required time for the walking section to the destination by parking surface is calculated, and the information is used in the parking section. forwarded to the analysis department.

The parking section analysis unit receives the parking available parking surface, the parking lot interior image, and the walking section required time information for each parking available parking surface from the occupancy detection unit, the camera, and the walking section analysis unit, and performs multi-object detection (MOD) and multiple By using object tracking (MOT) to calculate the location and speed of real-time non-parked vehicles, the parking time required for each available parking surface is calculated. The MOD can be implemented using the above-described algorithms such as R-CNN, Fast R-CNN, Faster R-CNN, YOLO, SSD, Deep SORT, Hungarian, and the like, and the MOT is BOOSTING, Multiple Instance Learning (MIL). , KCF (Kernelized Correlation Filter), Median Flow, TLD (Tracking-Learning-Detection), etc. can be implemented using trackers. Among the above trackers, BOOSTING is described by Helmut Grabner et al., "Real-time tracking via on-line boosting" (2006), and MIL Tracker by Boris Babenko, "Robust Object Tracking with Online Multiple Instance Learning" (2010), The KCF Tracker (kernelized correlation filter) is through Joao F. Henriques et al., “High-Speed Tracking with Kernelized Correlation Filters” (2014), and the Median Flow Tracker is Zdenek Kalal et al., “Forward-Backward Error: Automatic Detection” of Tracking Failures" (2010), TLD Tracker (Tracking - Learning - Detection), Zdenek Kalal et al., "Tracking-Learning-Detection" (2010), MOSSE (Minimum Output Sum of Squared Error) Tracker In David S. Bolme et al., “Visual Object Tracking using Adaptive Correlation Filters” (2010), CSRT Tracker was published in Lukezic, A et al., “Correlation Filter Tracker with Channel and Spatial Reliablity” (2018). there is a bar Traffic models such as Follow-the-leader Model, Optimal Velocity Model (OVM), and Generalized Force Model can be used as traffic models for calculating the required parking time. Through “Nonlinear follow-the-leader models of traffic flow” published by Gazis, Herman and Rothery, OVM was developed as a Generalized Force Model through “Dynamic model of traffic congestion and numerical simulation” published by Bando et al. in 1995. was disclosed through the "Generalized force model of traffic dynamics" published by Helbing and Tilch in 1998. The time required for the walking section to the destination by parking plane received from the walking section analysis section and the calculated parking by parking plane By summing up the required time, the parking side with the minimum required time for each parking side is selected as the minimum required time parking side, and the information is sent to the parking side guide, and the sum of the required parking time for each parking side and the required time for the walking section is the tardy time. passed to the output.

The parking surface guide unit receives information about the available parking surface and the minimum required time parking surface, respectively, from the occupancy detection unit and the parking section analysis unit, and visually provides it to the user. The user is informed of the floor plan divided for each parking surface inside the parking lot through the corresponding guide, and it is red when the corresponding parking surface is occupied by each parking surface. It is displayed in yellow, green when it is currently unoccupied and not designated or reserved by other users, and in blue when the corresponding parking surface is determined to be the parking surface for the minimum required time to the user's destination. When the user clicks on a desired parking surface, the corresponding information is transmitted to the occupancy detection unit, notifying that the user has designated or reserved the corresponding parking surface, and a recommended route inside the parking lot is provided to the user.

The tardy time calculation unit receives the sum of the parking time and walking time for each parking area received from the parking section analysis unit, the navigation unit, and the parking surface guide, the time required to the final selected parking lot, and the final selected parking surface information, Based on the final selected parking surface, the required time from the departure point to the destination and the expected arrival time are calculated and compared with the schedule start time received from the schedule data receiver, if the expected arrival time is later than the schedule start time, the delay Provide the user with a scheduled time.

Claims (8)

One or more cameras 100 installed in each parking lot to obtain a parking lot image including a parking section 103 from the circuit breaker 101 to the parking available parking surface 102; The total distance (201) of the parking section (103), the number of unparked vehicles (202) located in the parking section (103) detected from the image acquired by the camera (100), the camera (100) a parking section analysis unit 200 that analyzes the required parking time 204 using any one or more of the speeds 203 of unparked vehicles located in the parking section 103 detected from the image obtained by ; and a tardy time calculation unit 300 for calculating a tardy time 303 by comparing the estimated arrival time 301 to the destination calculated by the navigation and the scheduled start time 302 at the entered destination. When the tardy time calculated by the tardy time calculation unit 300 is equal to or greater than the preset time 401, the time 403 including the required travel time 402 and the required parking time 204 to the destination calculated by the navigation. Parking information providing system in connection with vehicle navigation and schedule management application in a smartphone, characterized in that it provides parking information according to
The method according to claim 1, wherein
A walking section analysis unit 400 for calculating the walking distance from the parking available parking surface 102 to the destination entrance 404 and the estimated time 405 required to move the distance on foot; Parking information providing system in connection with vehicle navigation and schedule management application in a smartphone, characterized in that
3. The method of claim 2, wherein
The camera 100 additionally acquires an image of the parking surface, and an occupancy detection unit 500 for detecting whether an individual parking surface is occupied from the image obtained by the camera 100; Parking information providing system linked with vehicle navigation and schedule management application in smartphone
The method according to any one of claims 1 to 3,
The tardy time calculation unit 300 calculates the tardy time 303 by comparing the estimated arrival time 304 to each parking lot calculated by the navigation and the scheduled start time 302 at the entered destination. Parking information providing system linked with vehicle navigation and schedule management application in smartphone
The method according to any one of claims 1 to 3,
The tardy time calculation unit 300 utilizes the schedule start time 302 at the corresponding destination input by the user into the schedule management program. Parking information providing system in connection with the vehicle navigation and schedule management application in the smartphone
4. The method according to claim 3,
The occupancy detection unit 500 additionally detects any one or more of the distance 501 between vehicles and the distance 502 between the vehicle and the outermost of the parking area, and only when the distance is greater than or equal to a preset distance, the corresponding parking surface Parking information providing system linked with vehicle navigation and schedule management application in smartphone, characterized in that it is classified as not occupied
7. The method of any one of claims 3 and 6, wherein
In the case where a plurality of available parking surfaces 102 exist, vehicle navigation in a smartphone and Parking information providing system linked with schedule management application
7. The method according to any one of claims 3 to 6,
When there are a plurality of available parking surfaces 102, the sum of the required parking time 204 and the walking time 405 is the minimum to provide parking information of the corresponding parking lot based on the parking available parking surface 102. Parking information providing system linked with vehicle navigation and schedule management application in smartphone

Images