KR-20260063814-A - Apparatus recognizing accident area for autonomous cooperative driving and method using the same

Abstract

The present invention relates to an accident area recognition device for generating a precision map for autonomous cooperative driving and a method using the same, characterized by comprising: an image collection unit that collects image data captured from a camera provided in the infrastructure; an object recognition unit that recognizes road boundaries and lanes constituting the road and objects located on the road using an artificial intelligence model from the image data; an accident area recognition unit that determines whether it is an accident area using the recognized object information and sets the location of the area where the accident is occurring and the accident section; a map generation unit that maps the accident area to a precision map; and a map transmission unit that transmits the precision map to a map server.

Inventors

• 오광만
• 추연호
• 안웅

Assignees

• (주)테슬라시스템

Dates

Publication Date

20260507

Application Date

20241031

Claims (6)

1. In an accident area recognition device for generating a precision map for autonomous cooperative driving, A video collection unit that collects video data captured from a camera equipped in the infrastructure; An object recognition unit that recognizes road boundaries and lanes constituting the road and objects located on the road using an artificial intelligence model from the above image data; An accident area recognition unit that determines whether it is an accident area by utilizing the above-mentioned recognized object information and sets the location of the area where the accident occurred and the accident section; A map generation unit that maps the above accident area to the above precision map; and An accident area recognition device characterized by comprising a map transmission unit that transmits the above-mentioned precision map to a map server.
2. In paragraph 1, The above object recognition unit is, A road recognition unit that recognizes road boundaries forming a road and lanes within the road to recognize the above accident area; A vehicle recognition unit that recognizes a vehicle located on the above road; A vehicle position tracking unit that tracks the location of the above-mentioned recognized vehicle to track its speed and direction of travel; An accident vehicle determination unit that determines whether the above-mentioned recognized vehicle is an accident vehicle, and An accident area recognition device characterized by comprising a coordinate transformation unit that converts local coordinates within the image into global coordinates to reflect the above location in the above precision map.
3. In paragraph 2, The above accident area recognition unit (130) is, A polygon generation unit that explores the range of the accident area through a polygon; An accident area determination unit that determines an accident area through the above polygon; and An accident area recognition device characterized by comprising a bypass route guidance unit that provides a driving path to bypass or avoid the above-mentioned accident area.
4. In paragraph 1, An accident area recognition device characterized by the above map transmission unit transmitting the above precision map, including the accident area, in real time to an autonomous vehicle located within the coverage range of the above infrastructure using V2X communication.
5. In paragraph 3, An accident area recognition device characterized in that the above polygon is a polygon connecting the outermost edges of the above-recognized vehicle.
6. In a method using an accident area recognition device according to any one of paragraphs 1 to 3, A method using an accident area recognition device comprises a first step of recognizing road boundaries using a camera equipped in the infrastructure to set a road area; A second step of recognizing vehicles that are stopped or in motion among objects located within the above road area and tracking these vehicles; A third step of calculating the speed of the vehicle through the recognized location and distance traveled of the vehicle and converting the location into global coordinates; A fourth step of identifying whether the above-mentioned stopped vehicle is an accident vehicle; Step 5, which involves extracting polygon data to establish the accident area, and A method for recognizing an accident area characterized by comprising a sixth step of mapping the accident area set by the above polygon onto a precision map.

Description

Apparatus recognizing accident area for autonomous cooperative driving and method using the same The present invention relates to an accident area recognition device for autonomous cooperative driving that recognizes the accident area of a vehicle proceeding on the road using a camera installed on infrastructure along the roadside and reflects it in real time on a precision map for autonomous vehicles, and a method using the same. An autonomous vehicle (hereinafter referred to as "autonomous vehicle") has the function of recognizing environmental information necessary for driving, such as the types and locations of objects around the vehicle, using various sensors such as radar and lidar and cameras, and controlling the vehicle based on this information to perform autonomous driving. However, along the routes autonomous vehicles intend to travel, there are always situations where they cannot respond in real time due to traffic accidents, unexpected emergencies, and blind spots. As such, an edge infrastructure system (hereinafter referred to as "infrastructure") equipped with various sensors installed along the roadside is required to recognize the autonomous driving environment of the autonomous vehicle in advance. In addition to the function of detecting objects moving around the road (e.g., people, cars, bicycles, etc.), this infrastructure needs to recognize information on unexpected situations, road surface conditions, traffic accidents, and road accidents, and reflect this in a precision map for autonomous driving. Precision maps for autonomous vehicles can be displayed by classifying them into static elements of a typical road (roadway, lane markings, road markings, locations of traffic lights, traffic signs, etc.) and dynamic elements that change over time (obstacles, accident zones, traffic congestion, surrounding vehicles, pedestrians, etc.). While the purpose of these precision maps is no different from current vehicle navigation maps, they require more accurate location information for static elements and a rapid update cycle for dynamic elements; additionally, they can safely perform autonomous driving functions by selecting the optimal route from the starting point to the destination. In particular, when an accident occurs on a road detectable by the infrastructure, it is necessary to recognize it in advance, reflect it in a precision map, and provide a driving route that allows for detours or avoidance. However, conventional infrastructure merely transmits information about accident situations around the road; it currently fails to provide the means to directly recognize the vehicles involved in the accident installed in the accident zone, accurately define the accident area, and reflect this in a precision map for autonomous driving. Patent Document 1 relates to a method and apparatus for the integrated collection and processing of vehicle and infrastructure sensor data for the efficient provision of dynamic road information. The autonomous driving dynamic map (LDM, Local Dynamic Map) and control system of the center integrate and collect information from external systems such as vehicle sensor data, road infrastructure sensor data, and real-time weather traffic information, systematically process and store it, delete unnecessary data to reduce the amount of data, and organically analyze information on sudden dangerous situations on the road by another analysis system. However, Patent Document 1 does not describe specific means for recognizing accident scenes occurring on the road, nor does it describe technical features for avoiding the range, location, and path of the accident area. FIG. 1 is a configuration diagram showing the configuration of an infrastructure including an accident area recognition device according to an embodiment of the present invention. FIG. 2 is a diagram showing an edge computer driving an accident area recognition device according to an embodiment of the present invention. FIG. 3 is a diagram showing a functional block diagram of an accident area recognition device according to an embodiment of the present invention. FIG. 4 is a diagram showing a functional block diagram of an object recognition unit according to an embodiment of the present invention. FIG. 5 is a drawing showing an example of recognizing a road boundary and a vehicle driving on the road according to an embodiment of the present invention. FIG. 6 is a drawing illustrating an accident scene and an accident vehicle as examples according to an embodiment of the present invention. FIG. 7 is a drawing illustrating the location and speed of an accident vehicle within a road area according to an embodiment of the present invention. FIG. 8 illustrates an example of converting the position of an image acquired from an image camera attached to an infrastructure according to an embodiment of the present invention into global coordinates. FIG. 9 is a diagram showing a functional block diagram of an accident ar