Hedgerows are one of the few remaining natural landscape features within European agricultural areas. To facilitate hedgerow monitoring, cost-effective and accurate mapping of hedgerows across large spatial scales is required. Current methods used for automatic hedgerow detection are overly complicated and generalize poorly to larger areas. We examine the application of transfer learning using two neural networks (Mask R-CNN and DeepLab v3+) for hedgerow mapping in south-eastern Germany using IKONOS imagery. We demonstrate the potential of such networks for hedgerow monitoring by investigating performances across varying input image bands, seasonal imagery, and image augmentation strategies. Both networks successfully detected hedgerows across a large spatial scale (562 km2), with DeepLab v3+ (75% F1-score) outperforming Mask R-CNN. Differences between band combinations were minimal, implying hedgerow detection could be achieved using RGB sensors. Results suggested that using all available training images across seasons is preferred and should have the same model generalizing effects as data augmentation. Experiments with varying data augmentations found augmentations effecting object geometries to greatly increase performance for both networks while results using augmentations modifying pixel spectral values showed concerning effects. Overall, our study finds that transfer learning in neural networks offers a simplified approach that outperforms previously established methods.
The spatial resolution of Landsat imagery has proven to be well suited for the analysis of vegetation patterns and dynamics at regional scale; however, the low temporal frequency is often a limitation for the quantification of vegetation dynamics. The spatial and temporal adaptive reflectance fusion model (STARFM) combines moderate resolution imaging spectrometer (MODIS) and Landsat thematic mapper/enhanced thematic mapper plus (TM/ETM+) imagery to a high spatiotemporal resolution dataset. A time series of 333 STARFM images was generated between February 2000 and September 2007 (8-day interval) at Landsat spatial and spectral resolution for a 12×10 km heterogeneous test area within the North Queensland Savannas. Time series of observed Landsat and predicted STARFM images correlated high for each spectral band (0.89 to 0.99). The STARFM algorithm was tested in a regionalization study where sudden change events were analyzed for a pallustrine wetland. A MODIS subpixel analysis showed a very close relationship between STARFM normalized difference vegetation index (NDVI) data and MODIS NDVI data (root mean square error of 0.027). A phenological description of the major vegetation classes within the region revealed distinct differences and lag times within the ecosystem. The 2004 dry season NDVI minimum-map correlated highly with the validated 2004 foliage projective cover product (r2 = 0.92) from the Queensland Department of Environment and Resource Management.
Land use conversions or changes of land management practices are primary drivers of global environmental change.
'Natural experiment' situations, where some conditions vary, but other potential land use determinants remain relatively
constant, offer unique opportunities to study land use change, its drivers and feedbacks on human-environment systems.
The Chalkidiki peninsula in Northern Greece is an ideal test case to study recent land use transformations and socio-economic
changes (e.g. resulting from accession to the EU) against a stable reference area. Of the three peninsular legs of Cassandra, Sithonia and Athos, the latter harbours the 'Autonomous Monastic State of the Holy Mountain', a sovereign and isolated monastic state. Apart from subsistence agriculture around the monasteries, it represents a
Mediterranean ecosystem in a state virtually unaffected by modern human use. We have used a time series of 22 fully corrected
Landsat-TM and ETM+ data to study land use/land cover change on the
peninsula, and related the results to a similar study in the adjacent County of Lagadas. A diachronic land use change analysis based on SVM classification was conducted using two three image-pairs. Where natural and semi-natural vegetation formations remained stable, trends were calculated using a pixel-wise linear trend analysis of SMA-derived vegetation cover estimates. Results were interpreted using auxiliary data and in relation to the Athos area. Changes were
found to result from discontinuation of extensive land use in Cassandra and Sithonia in favour of intensified agricultural
use and the expansion of tourist activities, complemented by land abandonment in less attractive areas.
KEYWORDS: Landsat, Vegetation, Sensors, Data archive systems, Earth observing sensors, Remote sensing, Time series analysis, Agriculture, Satellites, Point spread functions
The aim of this study was to evaluate the potentials and limits of remote sensing time series regarding change analysis of
drylands. We focussed on the assessment and monitoring of land degradation using different scales of remote sensing
data. Special interest was paid on how the spatial resolutions of different sensors influence the derivation of vegetation
related variables, such as trends in time and the shift of phenological cycles. Hence, a comparison was performed using
high and medium resolution sensors and their suitability for monitoring land degradation will be evaluated.
Long time series of Landsat TM and NOAA AVHRR covering the overlapping time period from 1990 to 2000 were
compared for a test area in the Mediterranean. At local scale additional information was delivered by a multi-seasonal
land use/cover change detection (LUCC) analysis. The test site which is located in Central Macedonia (Greece) is mainly
characterized by long-term, gradual processes mainly driven by grazing and the extension of irrigated arable land.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.