CN-115014370-B - System, method, and computer-readable medium for generating map information

Abstract

The present disclosure provides systems, methods, and computer-readable media for generating map information. The system includes a processor programmed to receive a first image captured by a camera of a first vehicle from the first vehicle, receive a second image captured by a camera of a second vehicle from the second vehicle, analyze the first image and the second image to identify a representation of a plurality of objects belonging to at least one predetermined object class, analyze the first image and the second image to determine a location indicator for each object relative to a road segment, correlate the location indicator for each object, wherein correlating includes determining a refined location for each object based on the determined location indicator, and generate a map based on the refined locations of objects belonging to a particular predetermined object class, the map including a representation of the refined location of one or more objects of the plurality of objects belonging to the particular predetermined object class.

Inventors

• J. Abramson

Assignees

• 御眼视觉技术有限公司

Dates

Publication Date

20260505

Application Date

20200214

Priority Date

20190214

Claims (20)

1. 1. A system for generating map information, the system comprising: At least one processor programmed to: Receiving, from a first vehicle, a first image captured by a camera of the first vehicle during driving of the first vehicle along at least a portion of a road segment; Receiving, from a second vehicle, a second image captured by a camera of the second vehicle during driving of the second vehicle along at least a portion of the road segment; receiving, from a third vehicle, a third image captured by a camera of the third vehicle during driving of the third vehicle along at least a portion of the road segment; analyzing the first image, the second image, and the third image to identify a representation of a plurality of objects, the objects belonging to at least one predetermined object class; Analyzing the first, second, and third images to determine a first, second, and third position indicator of at least one of the plurality of objects relative to the road segment, the first position indicator based on the first image, the second position indicator based on the second image, and the third position indicator based on the third image; associating the location indicator for each of the plurality of objects, wherein the associating comprises: comparing the first, second and third location indicators of the at least one object; determining that the third location indicator is an outlier based on the comparison, and Determining a refined position of the at least one object based on the determined first and second position indicators based on the determination that the third position indicator is an outlier, and Based on the refined position, a map is generated that includes a representation of the refined position of the at least one object.
2. 2. The system of claim 1, wherein the at least one processor is further programmed to transmit the generated map to an external entity.
3. 3. The system of claim 2, wherein the external entity comprises a municipality.
4. 4. The system of claim 1, wherein the map is generated to include objects belonging to a particular predetermined object class, and wherein the particular predetermined object class includes infrastructure objects.
5. 5. The system of claim 4, wherein the infrastructure object comprises a manhole cover.
6. 6. The system of claim 4, wherein the infrastructure object comprises a traffic light.
7. 7. The system of claim 4, wherein the infrastructure object comprises a utility box.
8. 8. The system of claim 4, wherein the infrastructure object comprises a bus stop.
9. 9. The system of claim 4, wherein the infrastructure object comprises a sewer inlet.
10. 10. The system of claim 1, wherein the map comprises a first layer associated with an object of a first object type and a second layer associated with a second object type.
11. 11. A computer-implemented method for generating map information, comprising: Receiving, from a first vehicle, a first image captured by a camera of the first vehicle during driving of the first vehicle along at least a portion of a road segment; Receiving, from a second vehicle, a second image captured by a camera of the second vehicle during driving of the second vehicle along at least a portion of the road segment; receiving, from a third vehicle, a third image captured by a camera of the third vehicle during driving of the third vehicle along at least a portion of the road segment; analyzing the first image, the second image, and the third image to identify a representation of a plurality of objects, the objects belonging to at least one predetermined object class; Analyzing the first, second, and third images to determine a first, second, and third position indicator of at least one of the plurality of objects relative to the road segment, the first position indicator based on the first image, the second position indicator based on the second image, and the third position indicator based on the third image; associating a location indicator for each of the plurality of objects, wherein the associating comprises: comparing the first, second and third location indicators of the at least one object; determining that the third location indicator is an outlier based on the comparison, and Determining a refined position of the at least one object based on the determined first and second position indicators based on the determination that the third position indicator is an outlier, and Based on the refined position, a map is generated that includes a representation of the refined position of the at least one object.
12. 12. The method of claim 11, wherein the at least one processor is further programmed to transmit the generated map to an external entity.
13. 13. The method of claim 12, wherein the external entity comprises a municipality.
14. 14. The method of claim 11, wherein the map is generated to include objects belonging to a particular predetermined object class, and wherein the particular predetermined object class includes infrastructure objects.
15. 15. The method of claim 14, wherein the infrastructure object comprises a manhole cover.
16. 16. The method of claim 14, wherein the infrastructure object comprises a traffic light.
17. 17. The method of claim 14, wherein the infrastructure object comprises a utility box.
18. 18. The method of claim 14, wherein the infrastructure object comprises a bus stop.
19. 19. The method of claim 11, wherein the map comprises a first layer associated with an object of a first object type and a second layer associated with a second object type.
20. 20. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, are configured to cause the at least one processor to: Receiving, from a first vehicle, a first image captured by a camera of the first vehicle during driving of the first vehicle along at least a portion of a road segment; Receiving, from a second vehicle, a second image captured by a camera of the second vehicle during driving of the first vehicle along at least a portion of the road segment; receiving, from a third vehicle, a third image captured by a camera of the third vehicle during driving of the third vehicle along at least a portion of the road segment; analyzing the first image, the second image, and the third image to identify a representation of a plurality of objects, the objects belonging to at least one predetermined object class; Analyzing the first, second, and third images to determine a first, second, and third position indicator of at least one of the plurality of objects relative to the road segment, the first position indicator based on the first image, the second position indicator based on the second image, and the third position indicator based on the third image; associating the location indicator for each of the plurality of objects, wherein the associating comprises: comparing the first, second and third location indicators of the at least one object; determining that the third location indicator is an outlier based on the comparison, and Determining a refined position of the at least one object based on the determined first and second position indicators based on the determination that the third position indicator is an outlier, and Based on the refined position, a map is generated that includes a representation of the refined position of the at least one object.

Description

System, method, and computer-readable medium for generating map information The present application is a divisional application of patent application of application with application number 202080014545.1 (International application number PCT/IB 2020/000115) and the name of "system and method for vehicle navigation", 14 nd day of application of year 2020. Cross Reference to Related Applications The present application claims priority and benefit from U.S. provisional application No. 62/805,646 filed on day 2, month 14 of 2019, and U.S. provisional application No. 62/813,403 filed on day 3, month 4 of 2019. The foregoing application is incorporated by reference in its entirety. Technical Field The present disclosure relates generally to vehicle navigation. Background With the continued advancement of technology, the goal of a fully autonomous vehicle capable of navigating on a roadway is imminent. Autonomous vehicles may need to take into account a wide variety of factors and make appropriate decisions based on those factors to safely and accurately reach the intended destination. For example, an autonomous vehicle may need to process and interpret visual information (e.g., information captured from a camera), information from radar or lidar, and may also use information obtained from other sources (e.g., from a GPS device, a speed sensor, an accelerometer, a suspension sensor, etc.). Meanwhile, in order to navigate to a destination, an autonomous vehicle may also need to recognize its location within a particular road (e.g., a particular lane in a multi-lane road), navigate alongside other vehicles, avoid obstacles and pedestrians, observe traffic signals and signs, and travel from one road to another at an appropriate intersection or junction. Utilizing (harnesss) and interpreting the vast amount of information collected by an autonomous vehicle as it travels to its destination poses many design challenges. The massive amounts of data that an autonomous vehicle may need to analyze, access, and/or store (e.g., captured image data, map data, GPS data, sensor data, etc.) pose challenges that may actually limit or even adversely affect autonomous navigation. Furthermore, if an autonomous vehicle relies on conventional mapping (mapping) techniques to navigate, the massive amounts of data required to store and update the map pose a significant challenge. Disclosure of Invention Embodiments consistent with the present disclosure provide systems and methods for vehicle navigation. The disclosed embodiments may use cameras to provide vehicle navigation features. For example, consistent with the disclosed embodiments, the disclosed systems may include one, two, or more cameras that monitor the environment of the vehicle. The disclosed system may provide a navigational response based on, for example, analysis of images captured by one or more cameras. In one embodiment, a navigation system for a host vehicle may include at least one processor that may be programmed to receive one or more images captured from a host vehicle environment from a camera of the host vehicle. The at least one processor may also be programmed to analyze the one or more images to detect an indicator (indicator) of the intersection. The at least one processor may also be programmed to determine a stop position of the host vehicle relative to the detected intersection based on the output received from the at least one sensor of the host vehicle. The at least one processor may also be programmed to analyze the one or more images to determine if there are indicators of one or more other vehicles in front of the host vehicle. The at least one processor may also be programmed to send an indicator of the stopping position of the host vehicle and whether one or more other vehicles are in front of the host vehicle to the server for updating the road navigation model. In one embodiment, a computer-implemented method for a host vehicle may include receiving, from a host vehicle camera, one or more images captured from an environment of the host vehicle. The method may also include analyzing the one or more images to detect an indicator of the intersection. The method may further include determining a stop position of the vehicle relative to the detected intersection based on the output received from the at least one sensor of the host vehicle. The method may also include analyzing the one or more images to determine if there are indicators of one or more other vehicles in front of the host vehicle. The method may further include sending an indicator of the stopping position of the host vehicle and whether one or more other vehicles are in front of the host vehicle to a server for updating the road navigation model. In one embodiment, a system for updating a road navigation model of a road segment may include at least one processor programmed to receive driving information from each of a plurality of vehicles, the driving information including a stop posi