Systems and methods for vehicle identification

Abstract

Systems and methods for vehicle identification are described herein. A set of vehicle identification information may be obtained from a set of autonomous vehicles. Individual vehicle identification information may convey identifications of one or more vehicles and locations of the one or more vehicles. Vehicle context information for individual vehicles may be determined from the set of vehicle identification information. The vehicle context information for the individual vehicles may describe a context of the individual vehicles. The context may include one or a combination of a speed of travel, a direction of travel, a trajectory, or an identity profile.

What is claimed is: 
     
         1 . A system for vehicle identification, the system comprising:
 one or more processors; and   a memory storing instructions that, when executed by the one or more processors, cause the system to perform:   obtaining, from a plurality of autonomous vehicles, a set of vehicle identification information, wherein each of the set of vehicle identification information is obtained from a corresponding autonomous vehicle in the plurality of autonomous vehicles, and comprises image or video information of identifications and locations of one or more vehicles that are in an environment surrounding the corresponding autonomous vehicle;   identifying a plurality of identifications in the set of vehicle identification information that belong to an individual vehicle, wherein the identifying comprises:
 identifying two or more identifications in the set of vehicle identification information being within a threshold degree of sameness; and 
 identifying two or more identifications in the set of vehicle identification information comprising one or more overlapping parts of a same vehicle; 
   determining vehicle context information of a plurality of individual vehicles based on the plurality of identifications belonging to each of the plurality of individual vehicles;   receiving a request for identifying a target vehicle, wherein the request comprises an identification of the target vehicle; and   identifying and returning vehicle context information of the target vehicle.   
     
     
         2 . The system of  claim 1 , wherein the identifications comprise one or a combination of a license plate number, a color, a make, a model, or a marking. 
     
     
         3 . The system of  claim 1 , wherein the identifications of the one or more vehicles are derived from the image information or the video information through one or more image and/or video processing techniques. 
     
     
         4 . The system of  claim 1 , wherein determining the vehicle context information is further based on comparing individual ones of the identifications and the locations of individual vehicles to other ones of the identifications and the locations of the individual vehicles. 
     
     
         5 . The system of  claim 1 , wherein the obtaining the set of vehicle identification information from the plurality of autonomous vehicles comprises:
 from one of the plurality of autonomous vehicles, obtaining location information of vehicles surrounding the one autonomous vehicle from location sensors of the vehicles, wherein the location sensors include at least one of a GPS, an altimeter, or a pressure sensor.   
     
     
         6 . The system of  claim 1 , wherein the vehicle context information for the target vehicle describes a context of the target vehicle, the context including at least one of: a speed of travel, a direction of travel, or a trajectory. 
     
     
         7 . The system of  claim 1 , wherein the vehicle context information for the target vehicle further comprises an identity profile of the target vehicle, the identity profile representing an identity of the target vehicle as a whole, and wherein the identity profile is determined by combining the two or more identifications determined to be for the same vehicle. 
     
     
         8 . The system of  claim 1 , wherein the system further performs tracking the target vehicle based on the set of vehicle identification information or the vehicle context information. 
     
     
         9 . The system of  claim 1 , wherein the identifying the plurality of identifications in the set of vehicle identification information that belong to the individual vehicle comprises:
 stitching the image or video information comprising the two or more identifications that are within the threshold degree of sameness and comprise the one or more overlapping parts of a same vehicle.   
     
     
         10 . The system of  claim 9 , wherein the stitching comprises one or a combination of feature point detection, image registration, alignment, or composing. 
     
     
         11 . The system of  claim 9 , wherein the determining vehicle context information of the plurality of individual vehicles comprises:
 determining one or a combination of a speed of travel, a direction of travel, or a trajectory of a vehicle based on comparing the locations of the vehicle in the stitched image or video information comprising the vehicle.   
     
     
         12 . A method for vehicle identification, the method comprising:
 obtaining, from a plurality of autonomous vehicles, a set of vehicle identification information, wherein each of the set of vehicle identification information is obtained from a corresponding autonomous vehicle in the plurality of autonomous vehicles, and comprises image or video information of identifications and locations of one or more vehicles that are in an environment surrounding the corresponding autonomous vehicle;   identifying a plurality of identifications in the set of vehicle identification information that belong to an individual vehicle, wherein the identifying comprises:   identifying two or more identifications in the set of vehicle identification information being within a threshold degree of sameness; and   identifying two or more identifications in the set of vehicle identification information comprising one or more overlapping parts of a same vehicle;   determining vehicle context information of a plurality of individual vehicles based on the plurality of identifications belonging to each of the plurality of individual vehicles;   receiving a request for identifying a target vehicle, wherein the request comprises an identification of the target vehicle; and   identifying and returning vehicle context information of the target vehicle.   
     
     
         13 . The method of  claim 12 , wherein the identifications comprise one or a combination of a license plate number, a color, a make, a model, or a marking. 
     
     
         14 . The method of  claim 12 , wherein the identifications of the one or more vehicles are derived from the image information and the video information through one or more image and/or video processing techniques. 
     
     
         15 . The method of  claim 12 , wherein the obtaining the set of vehicle identification information from the plurality of autonomous vehicles comprises:
 from one of the plurality of autonomous vehicles, obtaining location information of vehicles surrounding the one autonomous vehicle from location sensors of the vehicles, wherein the location sensors include at least one of a GPS, an altimeter, or a pressure sensor.   
     
     
         16 . The method of  claim 12 , wherein the vehicle context information for the target vehicle describes a context of the target vehicle, the context including at least one of: a speed of travel, a direction of travel, or a trajectory. 
     
     
         17 . The method of  claim 12 , wherein the identifying the plurality of identifications in the set of vehicle identification information that belong to the individual vehicle comprises:
 stitching the image or video information comprising the two or more identifications that are within the threshold degree of sameness or comprise the one or more overlapping parts of a same vehicle.   
     
     
         18 . The method of  claim 17 , wherein the determining vehicle context information of the plurality of individual vehicles comprises:
 determining one or a combination of a speed of travel, a direction of travel, or a trajectory of a vehicle based on comparing the locations of the vehicle in the stitched image or video information comprising the vehicle.   
     
     
         19 . A non-transitory computer-readable storage medium configured with instructions executable by one or more processors to cause the one or more processors to perform operations comprising:
 obtaining, from a plurality of autonomous vehicles, a set of vehicle identification information, wherein each of the set of vehicle identification information is obtained from a corresponding autonomous vehicle in the plurality of autonomous vehicles, and comprises image or video information of identifications and locations of one or more vehicles that are in an environment surrounding the corresponding autonomous vehicle;   identifying a plurality of identifications in the set of vehicle identification information that belong to an individual vehicle, wherein the identifying comprises:   identifying two or more identifications in the set of vehicle identification information being within a threshold degree of sameness; and   identifying two or more identifications in the set of vehicle identification information comprising one or more overlapping parts of a same vehicle;   determining vehicle context information of a plurality of individual vehicles based on the plurality of identifications belonging to each of the plurality of individual vehicles;   receiving a request for identifying a target vehicle, wherein the request comprises an identification of the target vehicle; and   identifying and returning vehicle context information of the target vehicle.   
     
     
         20 . The non-transitory computer-readable storage medium of  claim 19 , wherein the identifying the plurality of identifications in the set of vehicle identification information that belong to the individual vehicle comprises:
 stitching the image or video information comprising the two or more identifications that are within the threshold degree of sameness or comprise the one or more overlapping parts of a same vehicle.