Terrestrial Mapping [2.01]

This Project researches techniques and algorithms for the detection, recognition and analysis of low-level and high-level features from mobile mapping data along urban and rural transport corridors.

Mobile mapping systems use integrated vehicle-borne positioning, imaging and laser scanning sensors to record data that cannot be readily acquired from aerial and satellite platforms. Examples include vertical building facades and street furniture.

Low-level features include edges, corners, planar surfaces, and high-level features include buildings, road signs and the attributes of other man-made and natural features within the transport corridors.

The research will use fused imagery, video, lidar, GNSS and sensor orientation data recorded by mobile mapping platforms to recognise, locate, map and measure the spatial attributes and characteristics of features of interest.

Automatic feature extraction for spatial information product generation is essential for organisations such as local government authorities and other government agencies, as well as for 43pl companies, to more efficiently monitor and manage transport corridor infrastructure and associated assets such as power lines, roads and railways, and street-side furniture.

Highlights

Three PhD students begun their research. Richard Palmer, along with Michael Borck, is working on imagery and ranging data from stereo camera systems, while Abdul Nurunnabi is focusing on point clouds from laser scans.

Michael Borck is currently evaluating low level features to identify which regions are most likely to contain the high level features of interest. He is concentrating on saliency algorithms from the literature and how he can combine them to improve performance.

Richard Palmer is completing a Stanford University course on Artificial Intelligence. He is investigating high level features and machine learning techniques for object recognition, and has been testing a new recognition algorithm with 2D images.

Abdul Nurunnabi has reviewed literature about computer vision, machine learning, photogrammetry and remote sensing. He is analysing robust statistical techniques for automatic feature extraction and error modelling in mobile laser scanning data. He is currently considering the specific needs of using mobile mapping for power line infrastructure analysis.

Researcher David Belton presented a paper on 2D drawing/plan extraction from point clouds to the SSSI conference in Wellington. He is examining mobile mapping laser data from AAM and MAPS to understand accuracy and behaviour and how it is different from traditional static terrestrial laser scanning.  He is identifying issues and is assessing existing calibration and registration models for use in mobile mapping systems.

Project Technology

Geoff West, Project Leader

Project 2.01 Overview

Geoff West, Project Leader

What is unique is the adoption and enhancement of state-of-the-art feature extraction approaches from the computer vision, photogrammetry, image processing and artificial intelligence domains, and the focussing of these methods on solving the problem of automating the spatial data-to-information process for terrestrial mobile mapping systems

Research Themes

  1. Research into the most appropriate low-level feature detectors for 2D imagery and dense 3D point clouds
  2. Research into optimal high-level feature recognition algorithms that use 2D and 3D low-level features to support accurate and reliable user defined high-level feature recognition and positioning
  3. Research into interactive software tools to efficiently configure the recognition process for specific high-level features
  4. Research into software tools to automate specific analysis and feature measurement tasks based on high-level feature attributes

Project Participants

Research & Education - Curtin University

43pl - AAM - FugroGeomatic Technologies - Lester FranksVekta - Whelans

Government - DSE Vic - Landgate WA - LPI NSW