KR-20260063753-A - Method and system for performing CCTV-based path-point autonomous driving guidance for micro-mobility in outdoor GPS shadow areas

KR20260063753AKR 20260063753 AKR20260063753 AKR 20260063753AKR-20260063753-A

Abstract

A method for performing CCTV-based waypoint autonomous driving guidance for micro-mobility in an outdoor GPS blind spot comprises: a step in which a system acquires video data within an outdoor GPS blind spot; a step in which a system generates a grid map based on the acquired video data; a step in which a system detects an object within the video data and maps the detection result to the generated grid map; and a step in which a system generates autonomous driving guidance information based on the mapping result. By doing so, it is possible to contribute to enabling autonomous driving of micro-mobility even in an outdoor GPS blind spot.

Inventors

장수현
신대교
장준혁
장성현
안병만

Assignees

한국전자기술연구원

Dates

Publication Date: 20260507
Application Date: 20241031

Claims (12)

A step in which the system acquires image data within an outdoor GPS blind spot; The system generates a grid map based on acquired image data; The system detects objects within image data and maps the detection results to a generated grid map; and A method for performing CCTV-based waypoint autonomous driving guidance for micro-mobility in an outdoor GPS blind spot, comprising the step of the system generating autonomous driving guidance information based on mapping results.
In claim 1, The step of mapping the detection results to the generated grid map is, A step of detecting parked vehicles within video data and mapping the location of the detected vehicles to a grid map; and A method for performing CCTV-based waypoint autonomous driving guidance for micro-mobility in an outdoor GPS blind spot, characterized by including the step of detecting micro-mobility within video data and mapping the location of the detected micro-mobility to a grid map.
In claim 2, The step of mapping the detection results to the generated grid map is, A method for performing CCTV-based waypoint autonomous driving guidance for micro-mobility in outdoor GPS blind spots, characterized by utilizing a feature distance that reflects appearance similarity when detecting objects within video data.
In claim 3, The step of mapping the detection results to the generated grid map is, A method for performing CCTV-based waypoint autonomous driving guidance for micro-mobility in outdoor GPS blind spots, characterized by calculating a Perspective using Equation 1 to map points of each object to a grid map. (Formula 1)
In claim 4, The step of mapping the detection results to the generated grid map is, A method for performing CCTV-based waypoint autonomous driving guidance for micro-mobility in an outdoor GPS blind spot, characterized by detecting micro-mobility by fusing deep learning-based feature distance and Minkowski distance when micro-mobility is detected in video data and the features of the vehicles are similar to or less than a preset threshold.
In claim 5, The step of mapping the detection results to the generated grid map is, A method for performing CCTV-based waypoint autonomous driving guidance for micro-mobility in an outdoor GPS blind spot, characterized by calculating the similarity of the features of the detected micro-mobility using the Minkowski distance technique to prevent false tracking of the detected micro-mobility when micro-mobility is detected in video data when the features of the micro-mobility and the features of the vehicles are similar to or less than a preset threshold, verifying the accuracy of the micro-mobility detection result, and mapping only the micro-mobility detection result with verified accuracy onto a grid map.
In claim 6, Minkowski Street (D) is, A method for performing CCTV-based waypoint autonomous driving guidance for micro-mobility in outdoor GPS blind spots, characterized by being calculated through the following Equation 2 when using the Minkowski distance method. (Equation 2)
In claim 2, The step of generating autonomous driving guidance information is, A method for performing CCTV-based waypoint autonomous driving guidance for micro-mobility in an outdoor GPS blind spot, characterized by generating autonomous driving guidance information to enable autonomous driving of micro-mobility and providing it to micro-mobility in real time when location information of vehicles and micro-mobility is mapped to a grid map.
In claim 3, The step of generating autonomous driving guidance information is, A method for performing CCTV-based waypoint autonomous driving guidance for micro-mobility in an outdoor GPS blind spot, characterized by providing autonomous driving guidance information to micro-mobility in real time, and providing emergency control information to prevent collision with other objects when other objects approach the vicinity of said micro-mobility.
A communication unit for acquiring image data within an outdoor GPS blind spot; and A CCTV-based waypoint autonomous driving guidance execution system for micro-mobility in outdoor GPS blind spots, comprising: a processor that generates a grid map based on acquired image data, detects objects within the image data, maps the detection results to the generated grid map, and generates autonomous driving guidance information based on the mapping results.
The system generates a grid map based on image data within an outdoor GPS blind spot; A step in which the system detects a parked vehicle within the image data and maps the location of the detected vehicle to a grid map; The system detects micro-mobility within image data and maps the location of the detected micro-mobility to a grid map; and A method for performing CCTV-based waypoint autonomous driving guidance for micro-mobility in an outdoor GPS blind spot, comprising the step of generating autonomous driving guidance information for micro-mobility based on mapping results so that the system enables autonomous driving of micro-mobility.
A grid map generation unit that generates a single grid map based on image data within an outdoor GPS blind spot; Object detection unit for detecting vehicles and micro-mobility within image data; A location point mapping unit that maps the locations of detected vehicles and micro-mobility to a grid map; and A CCTV-based waypoint autonomous driving guidance execution system for micro-mobility in an outdoor GPS blind spot, comprising: a guidance information generation unit that generates autonomous driving guidance information for micro-mobility based on mapping results to enable autonomous driving of micro-mobility.

Description

Method and system for performing CCTV-based path-point autonomous driving guidance for micro-mobility in outdoor GPS shadow areas The present invention relates to a method and system for generating and providing autonomous driving guidance information, and more specifically, to a method and system for generating and providing autonomous driving guidance information for autonomous driving of micro-mobility (e.g., autonomous delivery robots, electric wheelchairs, etc.). Path Guidance technology refers to a technology that recognizes traffic conditions and coordinates to provide information in sections where guidance is required during autonomous driving. Due to the advancement of various sensors, methodologies for performing guidance using sensors such as GPS are being developed. Specifically, existing outdoor autonomous driving micro-mobility services can provide guidance based on waypoints acquired from GPS sensors in wide road conditions where there are no GPS blind spots and waypoint acquisition is easy; however, they have limitations in areas such as parking lots containing high-rise buildings, where GPS blind spots occur, making it difficult to acquire waypoints. In other words, existing outdoor autonomous driving micro-mobility services cannot provide high-precision waypoint autonomous driving guidance services in areas such as parking lots containing high-rise buildings because GPS blind spots make it difficult to acquire waypoints, thus requiring the exploration of a solution for this. FIG. 1 is a drawing provided for the description of the configuration of a CCTV-based waypoint autonomous driving guidance system for micro-mobility in an outdoor GPS blind spot according to an embodiment of the present invention. FIG. 2 is a drawing provided for a more detailed configuration description of the processor illustrated in FIG. 1. FIG. 3 is a diagram illustrating a grid map generated through a CCTV-based waypoint autonomous driving guidance execution system for micro-mobility in an outdoor GPS blind spot according to an embodiment of the present invention. FIG. 4 is a diagram illustrating the use of feature distance reflecting the external similarity between objects through a CCTV-based waypoint autonomous driving guidance system for micro-mobility in an outdoor GPS blind spot according to an embodiment of the present invention. FIG. 5 is a diagram illustrating the mapping of a parked vehicle detected by a CCTV-based waypoint autonomous driving guidance execution system for micro-mobility in an outdoor GPS blind spot according to an embodiment of the present invention onto a grid map. FIG. 6 is a diagram illustrating the mapping of micro-mobility detected by a CCTV-based waypoint autonomous driving guidance execution system for micro-mobility in an outdoor GPS blind spot according to an embodiment of the present invention onto a grid map on which a parked vehicle is mapped. FIG. 7 is a diagram illustrating an example of autonomous driving guidance information being generated and displayed on a grid map through a CCTV-based waypoint autonomous driving guidance execution system for micro-mobility in an outdoor GPS blind spot according to an embodiment of the present invention. FIG. 8 is a diagram illustrating a situation in which a micro-mobility and a driving vehicle approach each other in an outdoor GPS blind spot according to an embodiment of the present invention is displayed on a grid map, and FIG. 9 is a flowchart provided to describe a method for performing CCTV-based waypoint autonomous driving guidance for micro-mobility in an outdoor GPS blind spot according to an embodiment of the present invention. The present invention will be described in more detail below with reference to the drawings. To clearly explain the invention, parts unrelated to the description have been omitted from the drawings, and in the drawings, the width, length, thickness, etc., of the components may be exaggerated for convenience. FIG. 1 is a diagram provided to describe the configuration of a CCTV-based waypoint autonomous driving guidance system for micro-mobility in an outdoor GPS blind spot according to one embodiment of the present invention. The CCTV-based waypoint autonomous driving guidance execution system for micro-mobility in an outdoor GPS blind spot according to the present embodiment (hereinafter collectively referred to as the "system") is configured to utilize video data of the area in an outdoor GPS blind spot to detect parked vehicles, moving vehicles (driving vehicles), pedestrians, and other micro-mobility, and to generate and provide autonomous driving guidance information for the autonomous driving of said micro-mobility. To this end, the system may include a communication unit (100), a processor (200), and a storage unit (300). The communication unit (100) is equipped with a communication module connected to a network and can receive and obtain video data within an outdoor GPS blind spot from a CCTV ca