An Object-Based Image Analysis Method for Monitoring Land Conversion by Artificial Sprawl Use of RapidEye and IRS Data

Dupuy, Stéphane; Barbe, E.; Balestrat, Maud

doi:10.3390/rs4020404

Cited by 19 publications

(12 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As noted by many authors [36,[39][40][41][42], multi-resolution segmentation is a powerful technique, and the selection of an appropriate scale parameter is crucial for creating meaningful objects. As illustrated in Figure 4, the super-object segments in this study correspond reasonably well to the shrimp pond boundaries.…”

Section: Discussionmentioning

confidence: 99%

“…In addition to these pixel-based approaches, several applications use spatial neighborhood information in object-based classification. Recently, object-based approaches have been applied successfully in many ecology-related remote sensing studies, such as landslide inventories [36], mapping burned areas using different sensors [37,38], monitoring land conversion [39], or assessing forest structural complexity [40]. In mangrove studies, for example, Conchedda et al [41] used an object-based approach to map mangrove cover change in Casamance (Senegal) based on SPOT XS data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Remote Sensing in Mapping Mangrove Ecosystems — An Object-Based Approach

et al. 2013

View full text Add to dashboard Cite

Abstract:Over the past few decades, clearing for shrimp farming has caused severe losses of mangroves in the Mekong Delta (MD) of Vietnam. Although the increasing importance of shrimp aquaculture in Vietnam has brought significant financial benefits to the local communities, the rapid and largely uncontrolled increase in aquacultural area has contributed to a considerable loss of mangrove forests and to environmental degradation. Although different approaches have been used for mangrove classification, no approach to date has addressed the challenges of the special conditions that can be found in the aquaculture-mangrove system in the Ca Mau province of the MD. This paper presents an object-based classification approach for estimating the percentage of mangroves in mixed mangrove-aquaculture farming systems to assist the government to monitor the extent of the shrimp farming area. The method comprises multi-resolution segmentation and classification of SPOT5 data using a decision tree approach as well as local knowledge from the region of interest. The results show accuracies higher than 75% for certain classes at the object level. Furthermore, we successfully detect areas with mixed aquaculture-mangrove land cover with high accuracies. Based on these results, mangrove development, especially within shrimp farming-mangrove systems, can be monitored. However, the mangrove forest cover fraction per object is affected by image segmentation and thus does not always correspond to the real farm boundaries. It remains a serious challenge, then, to accurately map mangrove forest cover within mixed systems.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Remote Sensing in Mapping Mangrove Ecosystems — An Object-Based Approach

et al. 2013

View full text Add to dashboard Cite

show abstract

“…On the one hand, progress in computer science and GIS, especially in object-based image analysis, has revolutionised the processing of VHRSI by providing effective computerassisted classification techniques. Results come close to the quality of manual photo-interpretation while being much faster, cheaper and more reproducible (e.g., Johansen et al, 2010;Dupuy, Barbe & Balestrat, 2012;Tormos et al, 2012). On the other hand, free provision of HSRI at national scales, available annually in France since 2011 (http://www.geosud.teledetection.fr/), is becoming increasingly common.…”

Section: Implications For Management and Future Landscape Approachesmentioning

confidence: 52%

“…Results come close to the quality of manual photo-interpretation while being much faster, cheaper and more reproducible (e.g., Johansen et al, 2010;Dupuy, Barbe & Balestrat, 2012;Tormos et al, 2012). On the one hand, progress in computer science and GIS, especially in object-based image analysis, has revolutionised the processing of VHRSI by providing effective computerassisted classification techniques.…”

Section: Implications For Management and Future Landscape Approachesmentioning

confidence: 70%

High resolution land cover data improve understanding of mechanistic linkages with stream integrity

et al. 2014

View full text Add to dashboard Cite

Summary Recent progress in very high spatial resolution imagery (VHSRI) has increased the availability of fine‐scale land cover data over extensive areas. This new spatial information might improve our understanding of how land cover affects stream ecosystems. Land cover information was investigated in whole catchments and riparian areas in Normandy (France) and related to stream macroinvertebrates at 155 sites. The first model was based on the land cover data obtained via moderate spatial resolution imagery (MSRI) at the catchment scale. The second and the third models were additionally based on riparian land cover data both locally (at the site) and upstream. The riparian land cover data were derived from the MSRI for the second and from the VHSRI for the third model. Riparian vegetation (at a distance from the channel of 5–100 m) was poorly detected by MSRI when compared to VHSRI. The model based on higher resolution data at the riparian scale (i) ensured that relationships identified at the riparian corridor scale were independent from those at whole catchment scale, (ii) identified the influence of riparian vegetation on the aquatic environment as being most pronounced when using data from a 20‐m wide strip (i.e. 20 m on each bank for a total of 40 m) and (iii) disentangled the effects of roads from other urban infrastructure. This study confirms the advantages of using very high resolution data in landscape approaches to the study of aquatic ecosystems. It provides accurate spatial information at the riparian scale that improves interpretation of the influence of land cover on the ecological condition of streams and allows identification of relevant features for management.

show abstract

“…An object-based image analysis method (Dupuy et al . 2012) was used for the observation of land conversion between 2009 and 2014 .…”

Section: Methodsmentioning

confidence: 99%

Remote Sensing of Sustainable Rural-Urban Land Use in Mexico City: A Qualitative Analysis for Reliability and Validity

López¹,

Rosso²,

Scheffran³

et al. 2015

View full text Add to dashboard Cite

Abstract | Mexico City is one of the largest cities on the globe and a site where important transformations of nature reserves into urban areas have been taking place. This paper compared the southern part of Mexico City based on free images available (Landsat – 30m) and high-resolution imagery (RapidEye – 5m) from an explorative qualitative perspective in the logic of reliability and validity. We argue that the resolution of the free imagery available for the assessment of urban development on the structural level of land use is not sufficient to identify the development of specific parts of the city. Despite the fact that the general pattern of changes in land use is observable, changes within the urban structure are difficult to see with a resolution of 30 meters per pixel in the Landsat images. For validity, this analysis is merely graphic, and it shows a promising matching of urban development with environmental and land complaints, nevertheless, a numerical analysis is needed in the future.

show abstract

An Object-Based Image Analysis Method for Monitoring Land Conversion by Artificial Sprawl Use of RapidEye and IRS Data

Cited by 19 publications

References 22 publications

Remote Sensing in Mapping Mangrove Ecosystems — An Object-Based Approach

Remote Sensing in Mapping Mangrove Ecosystems — An Object-Based Approach

High resolution land cover data improve understanding of mechanistic linkages with stream integrity

Remote Sensing of Sustainable Rural-Urban Land Use in Mexico City: A Qualitative Analysis for Reliability and Validity

Contact Info

Product

Resources

About