Fuzzy clustering of color and texture features for image segmentation: a study on satellite image retrieval

In this paper, a new image segmentation approach that integrates color and texture features using the fuzzy c-means clustering algorithm is described. To demonstrate the applicability of the proposed approach to satellite image retrieval, an interactive region-based image query system is designed and developed. A database comprising 400 multispectral satellite images is used to evaluate the performance of the system. The results are analyzed and discussed, and a performance comparison with other methods is included. The outcomes reveal that the proposed approach is able to improve the quality of the segmentation results as well as the retrieval performance.

Corner Inlet and Nooramunga Habitat Mapping Project – Part 2 : High resolution mapping and change detection analysis using 2011 Rapid Eye Satellite Image compared to 2009 ALOS Satellite Image

Building on a habitat mapping project completed in 2011, Deakin University was commissioned by Parks Victoria (PV) to apply the same methodology and ground-truth data to a second, more recent and higher resolution satellite image to create habitat maps for areas within the Corner Inlet and Nooramunga Marine and Coastal Park and Ramsar area. A ground-truth data set using in situ video and still photographs was used to develop and assess predictive models of benthic marine habitat distributions incorporating data from both RapidEye satellite imagery (corrected for atmospheric and water column effects by CSIRO) and LiDAR (Light Detection and Ranging) bathymetry. This report describes the results of the mapping effort as well as the methodology used to produce these habitat maps.

Overall accuracies of habitat classifications were good, with error rates similar to or better than the earlier classification (>73 % and kappa values > 0.58 for both study localities). The RapidEye classification failed to accurately detect Pyura and reef habitat classes at the Corner Inlet locality, possibly due to differences in spectral frequencies. For comparison, these categories were combined into a ‘non-seagrass’ category, similar to the one used at the Nooramunga locality in the original classification. Habitats predicted with highest accuracies differed from the earlier classification and were Posidonia in Corner Inlet (89%), and bare sediment (no-visible seagrass class) in Nooramunga (90%). In the Corner Inlet locality reef and Pyura habitat categories were not distinguishable in the repeated classification and so were combined with bare sediments. The majority of remaining classification errors were due to the misclassification of Zosteraceae as bare sediment and vice versa. Dominant habitats were the same as those from the 2011 classification with some differences in extent. For the Corner Inlet study locality the no-visible seagrass category remained the most extensive (9059 ha), followed by Posidonia (5,513 ha) and Zosteraceae (5,504 ha). In Nooramunga no-visible seagrass (6,294 ha), Zosteraceae (3,122 ha) and wet saltmarsh (1,562 ha) habitat classes were most dominant.

Change detection analyses between the 2009 and 2011 imagery were undertaken as part of this project, following the analyses presented in Monk et al. (2011) and incorporating error estimates from both classifications. These analyses indicated some shifts in classification between Posidonia and Zosteraceae as well as a general reduction in the area of Zosteraceae. Issues with classification of mixed beds were apparent, particularly in the main Posidonia bed at Nooramunga where a mosaic of Zosteraceae and Posidonia was seen that was not evident in the ALOS classification. Results of a reanalysis of the 1998-2009 change detection illustrating effects of binning of mixed beds is also provided as an appendix.

This work has been successful in providing baseline maps at an improved level of detail using a repeatable method meaning that any future changes in intertidal and shallow water marine habitats may be assessed in a consistent way with quantitative error assessments. In wider use, these maps should also allow improved conservation planning, advance fisheries and catchment management, and progress infrastructure planning to limit impacts on the Inlet environment.

Integration of 3-PG into SWAT to simulate the growth of evergreen forests

SWAT cannot accurately simulate the seasonal fluctuations or the long-term trend of the Leaf Area Index (LAI) of evergreen forests. This deficiency has detrimental impacts for the prediction of interception and transpiration, two processes that have a significant influence on catchment water yield. This paper details the integration of the forest growth model 3-PG with SWAT to improve the simulation of LAI for evergreen forests. The integrated model, called SWAT/3-PG, was applied to the Woady Yaloak River Catchment in southern Australia where eucalyptus forests and pine plantations account for 30% of the total land use. SWAT/3-PG simulated the LAI of eucalypts and pines more accurately and realistically than the original version of SWAT. Forest LAI simulated by SWAT/3-PG agreed reasonably well with estimates of forest LAI derived independently from a Landsat satellite image. SWAT/3- PG has considerable value as a tool that managers can utilise to predict the impacts of land use change in catchments where evergreen forests are prevalent.

Hybrid image segmentation using fuzzy clustering algorithms satellite imagery searching and retrieval

Satellite image processing is a complex task that has received considerable attention from many researchers. In this paper, an interactive image query system for satellite imagery searching and retrieval is proposed. Like most image retrieval systems, extraction of image features is the most important step that has a great impact on the retrieval performance. Thus, a new technique that fuses color and texture features for segmentation is introduced. Applicability of the proposed technique is assessed using a database containing multispectral satellite imagery. The experiments demonstrate that the proposed segmentation technique is able to improve quality of the segmentation results as well as the retrieval performance.

Spatial patterns, landscape genetics and post virus recovery of blacklip abalone, Haliotis rubra (Leach), in the western commercial fishing zone of Victoria

Historically, collecting nearshore habitat information has been problematic. Existing methods, such as aerial and satellite image interpretation are limited due to the attenuation of light in the water column obscuring the seabed structure. The advent of airborne bathymetric LiDAR (Light Detection and Ranging) systems (laser scanning of the seabed) now provides high-resolution seabed ‘images’ in areas that were previously difficult to survey. LiDAR imagery is available for the entire coastline of Victoria, Australia to depths of around 25 m, after being initially collected for climate change modelling by the Future Coasts Program (http://www.climatechange.vic.gov.au/adapting-to-climate-change/future-coasts). This dataset has provided the opportunity to test its applicability to inform fisheries management. Detailed geophysical information combined with spatially explicit AbTrack GPS located fisheries records and targeted genetic sampling is used in this study to provide a better understanding of the extent of available fishing grounds, direction of fishing effort and stock population structure within the Victorian western zone abalone fishery.
The species distribution modelling technique MaxEnt was used to produce a potential habitat suitability map for abalone in an attempt to capture the effective footprint of the  fishery. Also, by interrogating the spatially defined effort localities, we demonstrate an approach that may be used to identify areas where fishing effort is concentrated, and how this parameter changes temporally.
Despite barriers to adult dispersal (soft sediment barriers between reef patches), the genetic study indicates that larval movement is able to homogenize the gene pool over  large geographic distances. The western, central and eastern zone abalone stocks in Victoria were found to be a single large panmictic unit. This indicates high levels of stock connectivity and no obvious impacts of Abalone Viral Ganglioneuritis (AVG) on the genetic health of western zone stocks. We used detailed seafloor structure information interpreted from LiDAR to inform a replicated hierarchical fine scale genetic sampling design. We demonstrated that there may be extensive migration among abalone stocks across the Victorian abalone fishery.
This is contrary to previous studies that suggest recruitment is highly localised. In combination, these findings provide a valuable insight into the biology of H. rubra and immediate benefits for fisheries management. We discuss these results in the context of predicting resilience and adaptive potential of H. rubra stocks to environmental pressures and the spread of heritable diseases.
Adoption pathways are also provided to benefit future stock augmentation activities to catalyse the recovery of AVG affected reef codes. As larval dispersal is likely to be spatially and temporally variable, some AVG affected stocks are likely to recover through natural recruitment, while others will benefit from augmentation activities to ‘kick-start’ stock recovery. Evidence of neutral genetic homogeneity across Victorian reef codes suggests that the relocation of animals is unlikely to have significant genetic risks; however the potential for locally adaptive genetic differences may exist, and should be taken into consideration in future stock augmentation planning.
When combined, the spatial and genetic analyses provide valuable insights into stock productivity within the western zone fishery. Reefs appear to be expansive and support much available habitat, and the movement of larvae among reef structures is likely to be extensive in this region. Consequently, we propose that colonisation success and productivity is likely to be driven by ecological factors such as resources and/or competition, or physical factors such as wave exposure.

Satellite imagery as a single source of predictor variables for habitat suitability modelling: how Landsat can inform the conservation of a critically endangered lemur

1. Statistical modelling of habitat suitability is an important tool for planning conservation interventions, particularly for areas where species distribution data are expensive or hard to collect. Sometimes however the predictor variables typically used in habitat suitability modelling are themselves difficult to obtain or not meaningful at the geographical extent of the study, as is the case for the Alaotran gentle lemur Hapalemur alaotrensis, a critically endangered lemur confined to the marshes of Lake Alaotra in Madagascar.2. We developed a habitat suitability model where all predictor variables, including vegetation indices and image texture measures at different scales (as surrogates for habitat structure), were derived from Landsat7 satellite imagery. Using relatively few presence records, the maximum entropy (Maxent) approach and AUC were used to assess the performance of candidate predictor variables, for studying the effect of scale, model selection and mapping suitable habitat.3. This study demonstrated the utility of satellite imagery as a single source of predictor variables for a Maxent habitat suitability model at the landscape level, within a restricted geographical extent and with a fine grain, in a case where predictor variables typically used at the macro-scale level (e.g. climatic and topographic) were not applicable.4. In the case of H. alaotrensis, the methodology generated a habitat suitability map to inform conservation management in Lake Alaotra and a replicable protocol to allow rapid updates to habitat suitability maps in the future. The exploration of candidate predictor variables allowed the identification of scales that appear ecologically relevant for the species.5. Synthesis and applications. This study presents a cost-effective combination of maximum entropy habitat suitability modelling and satellite imagery, where all predictor variables are derived solely from Landsat7 images. With a habitat modelling method like Maxent that shows good performance with few presence samples and Landsat images now freely available, the methodology can play an important role in rapid assessments of the status of species at the landscape level in data-poor regions, when typical macro-scale environmental predictors are of little use or difficult to obtain.

Investigating the distribution of acacia longifolia ssp. sophorae in south-west Victoria using satellite remote sensing and GIS

Mapping and analysis of the distribution of environmental weeds is an important component of strategic weed management. Such information is particularly important in managing 'native invaders', where invasion characteristics must be clearly understood prior to any management action being taken. This paper reports on an investigation of the current distribution of the native invader Acacia longifolia ssp. sophorae (Labill.) Court (coast wattle) in south-west Victoria, using remote sensing and Geographic Information Systems (GIS). Coast wattle was successfully mapped from Landsat ETM imagery using a supervised classification procedure, with 82%, of coast wattle shown on the map accurately depicting coast wattle on the ground. An estimated 11,448 ha were classified as supporting coast wattle, representing 12% of native vegetation in the study area. A more detailed GIS analysis in the Lower Glenelg National Park revealed coast wattle has invaded a limited number of vegetation types, and is more prevalent close to roads and within management zones associated with disturbance. The current regional extent of the species means widespread control is unlikely; hence the immediate focus should be on preventing further spread into areas where it is currently absent. Landsat imagery also proved to be a successful tool for mapping large scale coast wattle distribution, and could be used in long-term monitoring of the species.

Evidence for Megalake Chad, north-central Africa, during the late quaternary from satellite data

The existence of a very large Lake Chad during the late Quaternary, Megalake Chad, has long been questioned. A Megalake Chad would present strong evidence for climatic fluctuations of great magnitude during the Holocene in tropical Africa. In this paper we used satellite data from Landsat and Modis sensors to collect and analyse new information on landforms in a 2 000 000 km2 region of the Lake Chad Basin. We detected 2300 km of remains marking the ancient shoreline of Megalake Chad. The satellite data also indicated many Saharan rivers and relict deltas leading to the long paleoshoreline. Large dunefield flattenings were observed and interpreted as the result of wave-cut erosion by the paleolake. Similarities were noticed between the landforms observed along the paleoshoreline of Megalake Chad and that of the former Aral Sea. This finding has significant consequences for reconstructing paleohydrology and paleoenvironments through the Lake Chad basin, and continental climate change.

Wireless sensor networks for in-situ image validation for water and nutrient management

Water and Nitrogen (N) are critical inputs for crop production. Remote sensing data collected from multiple scales, including ground-based, aerial, and satellite, can be used for the formulation of an efficient and cost effective algorithm for the detection of N and water stress. Formulation and validation of such techniques require continuous acquisition of ground based spectral data over the canopy enabling field measurements to coincide exactly with aerial and satellite observations. In this context, a wireless sensor in situ network was developed and this paper describes the results of the first phase of the experiment along with the details of sensor development and instrumentation set up. The sensor network was established based on different spatial sampling strategies and each sensor collected spectral data in seven narrow wavebands (470, 550, 670, 700, 720, 750, 790 nm) critical for monitoring crop growth. Spectral measurements recorded at required intervals (up to 30 seconds) were relayed through a multi-hop wireless network to a base computer at the field site. These data were then accessed by the remote sensing centre computing system through broad band internet. Comparison of the data from the WSN and an industry standard ground based hyperspectral radiometer indicated that there were no significant differences in the spectral measurements for all the wavebands except for 790nm. Combining sensor and wireless technologies provides a robust means of aerial and satellite data calibration and an enhanced understanding of issues of variations in the scale for the effective water and nutrient management in wheat.

An empirical analysis of colour image segmentation using fuzzy c-means clustering

In this paper, an empirical analysis to examine the effects of image segmentation with different colour models using the fuzzy c-means (FCM) clustering algorithm is conducted. A qualitative evaluation method based on human perceptual judgement is used. Two sets of complex images, i.e., outdoor scenes and satellite imagery, are used for demonstration. These images are employed to examine the characteristics of image segmentation using FCM with eight different colour models. The results obtained from the experimental study are compared and analysed. It is found that the CIELAB colour model yields the best outcomes in colour image segmentation with FCM.