Real time machine vision system for vehicle control and protection

Abstract

A system, method, and apparatus are disclosed for a machine vision system that incorporates hardware and/or software, remote databases, and algorithms to map assets, evaluate railroad track conditions, and accurately determine the position of a moving vehicle on a railroad track. One benefit of the invention is the possibility of real-time processing of sensor data for guiding operation of the moving vehicle.

What is claimed is: 
     
         1 . A vehicle localization apparatus comprising:
 a GPS receiver mounted to a vehicle, the GPS receiver providing a first geographical position of the vehicle;   a local map cache residing within the vehicle, the local map cache storing a local map of assets comprising, for each asset: a location of the asset, properties associated with the asset, and one or more relationships relative to other assets;   one or more local environment sensors mounted on the vehicle to enable collection of three-dimensional depth data comprising, for observed assets present in a local environment in the vicinity of the vehicle: position data of the observed assets relative to the vehicle, and properties associated with the observed assets;   one or more vehicle computers, the vehicle computers receiving the first geographical position from the GPS receiver to retrieve, from the local map cache, records associated with assets previously mapped in the vicinity of the first geographical position;   a feature extraction component implemented by the vehicle computers, the feature extraction component receiving the local environment sensor three-dimensional depth data to identify and locate observed assets presently within the vicinity of the vehicle; and   a position refinement component implemented by the vehicle computers, the position refinement component comparing the identity and location of observed assets derived from three-dimensional depth data by the feature extraction component, with asset information retrieved from the local map cache, to determine a second position of the vehicle that is refined relative to the first geographical position of the vehicle.   
     
     
         2 . The vehicle localization apparatus of  claim 1 , in which the position refinement component further determines a present state of the vehicle further comprising a vehicle velocity and direction of travel. 
     
     
         3 . The vehicle localization apparatus of  claim 1 , in which the three-dimensional depth data comprises three-dimensional point cloud data. 
     
     
         4 . The vehicle localization apparatus of  claim 1 , further comprising a wireless vehicular communication device via which the local map cache can download local map data from a remote database during vehicle operation. 
     
     
         5 . The vehicle localization apparatus of  claim 1 , in which the one or more local environment sensors comprise one or more of: a LIDAR sensor, a digital camera and a radar sensor. 
     
     
         6 . The vehicle localization apparatus of  claim 1 , in which the local environment assets comprise one or more of signs, roadside safety structures, and semaphores. 
     
     
         7 . The vehicle localization apparatus of  claim 1 , in which the vehicle is a train. 
     
     
         8 . The vehicle localization apparatus of  claim 8 , in which the second position of the vehicle comprises a track identification. 
     
     
         9 . The vehicle localization apparatus of  claim 2 , further comprising an interface component through which the present state of the vehicle can be communicated to one or more vehicle control systems. 
     
     
         10 . A method of updating asset information within a centralized map database implemented by one or more network-connected servers, the method comprising the steps of:
 receiving by the centralized map database a request for map data from a remote vehicle, the remote vehicle having: local environment sensors for procuring three-dimensional depth data descriptive of a local environment in the vicinity of the remote vehicle, and a local map cache;   transmitting a first set of map data from the centralized map database to the remote vehicle in response to the request, the first set of map data comprising asset information, the asset information comprising identification, features and location of one or more assets within a local vicinity of the remote vehicle;   receiving at the centralized map database, from the remote vehicle, a report indicative of one or more differences between the first set of map data and information derived from three-dimensional depth data detected by the remote vehicle's local environment sensors; and   updating the centralized map database based on information within the report.   
     
     
         11 . The method of  claim 10 , in which the three-dimensional depth data comprises three-dimensional point cloud data. 
     
     
         12 . The method of  claim 10 , in which the report comprises identification and location of an asset detected by the remote vehicle local environment sensors that was not present within the centralized map database. 
     
     
         13 . The method of  claim 10 , in which the report comprises identification of an asset present within the centralized map database but not detected by the remote vehicle local environment sensors. 
     
     
         14 . The method of  claim 10 , in which the asset information comprises one or more asset characteristics; and in which the report comprises differences between asset characteristics within the centralized map database and asset characteristics derived from three-dimensional depth data detected by the remote vehicle local environment sensors.