Real-time machine vision and point-cloud analysis for remote sensing and vehicle control

Abstract

Methods and apparatus for real-time machine vision and point-cloud data analysis are provided, for remote sensing and vehicle control. Point cloud data can be analyzed via scalable, centralized, cloudcomputing systems for extraction of asset information and generation of semantic maps. A data storage / preprocessor (1220) subdivides a data set for streaming to a distributed processing unit (1240)and operation via data analysis mechanisms (1250). The output of the processing unit (1240) is aggregated by a map generator (1230). Machine learning components can optimize data analysis mechanismsto improve asset and feature extraction from sensor data. Optimized data analysis mechanisms can be downloaded to vehicles for use in on-board systems analyzing vehicle sensor data. Semantic map datacan be used locally in vehicles, along with onboard sensors, to derive precise vehicle localization and provide input to vehicle to control systems.

Description

[0001] Cross References to Related Applications [0002] This application requires the title "A Scalable Approach To Point-Cloud Data Processing for Railroad Asset Location and Health Monitoring" filed on January 20, 2015 ” of U.S. Provisional Patent Application No. 62 / 105,696, which is hereby incorporated by reference in its entirety. Background technique [0003] Automatic localization of moving vehicles and machine-based remote sensing of the vehicle's local environment are becoming increasingly important in several different fields. One such area is motor vehicle transportation. In recent years, many cars and trucks have implemented on-board Global Positioning System (GPS) receivers and navigation systems, using GPS data to guide drivers. However, as automotive manufacturers seek to implement more advanced driving automation, such as autonomous driving features, GPS-based positioning systems may neither provide sufficiently accurate vehicle positioning, nor do they allow...

AI Technical Summary

Problems solved by technology

Deploying millions of transponders—the transponders used to detect and communicate the presence and location of trains—every 1-15km along the track is not very effective because transponders are vulnerable to environmental conditions, stolen Negative impact, and transponders require regular maintenance, and the data collected may not be used in real time

Obtaining position data only through trackside facilities is not a scalable solution given the cost of utilizing transponders for PTCs throughout the rail network

Furthermore, train control and safety systems cannot rely solely on the Global Positioning System (GPS) as it cannot differentiate between tracks accurately enough, requiring wayside signaling for position calibration

Images