No abstract

There is a demand for regularly updated, broad-scale, accurate land cover information in Victoria from multiple stakeholders. This paper documents the methods used to generate an annual dominant land cover (DLC) map for Victoria, Australia from 2009 to 2013. Vegetation phenology parameters derived from an annual time series of the Moderate Resolution Imaging Spectroradiometer Vegetation Indices 16-day 250 m (MOD13Q1) product were used to generate annual DLC maps, using a three-tiered hierarchical classification scheme. Classification accuracy at the broadest (primary) class level was over 91% for all years, while it ranged from 72 to 81% at the secondary class level. The most detailed class level (tertiary) had accuracy levels ranging from 61 to 68%. The approach used was able to accommodate variable climatic conditions, which had substantial impacts on vegetation growth patterns and agricultural production across the state between both regions and years. The production of an annual dataset with complete spatial coverage for Victoria provides a reliable base data set with an accuracy that is fit-for-purpose for many applications.

Land Use Information is a key dataset required to enable an understanding of the changing nature of our landscapes and the associated influences on natural resources and regional communities. The Victorian Land Use Information System (VLUIS) data product has been created within the State Government of Victoria to support land use assessments. The project began in 2007 using stakeholder engagement to establish product requirements such as format, classification, frequency and spatial resolution. Its genesis is significantly different to traditional methods, incorporating data from a range of jurisdictions to develop land use information designed for regular on-going creation and consistency. Covering the entire landmass of Victoria, the dataset separately describes land tenure, land use and land cover. These variables are co-registered to a common spatial base (cadastral parcels) across the state for the period 2006 to 2013; biennially for land tenure and land use, and annually for land cover. Data is produced as a spatial GIS feature class.

The OBIA approach has potential of OBIA for identifying the locations of commercial piggeries. Further development and testing will determine how generic this approach is in terms of industry type and operation size. The method described is cost-effective, automated and repeatable, and could be used to regularly update existing databases by analysing newly acquired aerial imagery to identify possible land use changes. This would improve the reliability of currently available data and increase the effectiveness of a biosecurity response during an emergency animal disease outbreak.

We present a method for reconstructing the global position of motion capture where position sensing is poor or unavailable. Capture systems, such as IMU suits, can provide excellent pose and orientation data of a capture subject, but otherwise need post processing to estimate global position. We propose a solution that trains a neural network to predict, in real-time, the height and body displacement given a short window of pose and orientation data. Our training dataset contains pre-recorded data with global positions from many different capture subjects, performing a wide variety of activities in order to broadly train a network to estimate on like and unseen activities. We compare training on two network architectures, a universal network (u-net) and a traditional convolutional neural network (CNN) - observing better error properties for the u-net in our results. We also evaluate our method for different classes of motion. We observe high quality results for motion examples with good representation in specialized datasets, while general performance appears better in a more broadly sampled dataset when input motions are far from training examples.