Multi-scale Image Segmentation and Object-Oriented Processing for Land Cover Classification

Frohn, Robert C.; Chaudhary, Navendu

doi:10.2747/1548-1603.45.4.377

Cited by 15 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the actuality of Nansi Lake wetland and the "Standard of the China wetland resources survey and monitoring techniques" (2009), the object-oriented supervised classification method was used to classify the land use types of Nansi Lake wetland. Firstly, as the phenomenon of "the same spectrum with different objects" existed in natural water, rivers, reservoirs and lakes pond in Nansi Lake wetland, the attributes of spectral, shape, color, size, texture, and adjacent relation were chosen to segment and merge the images to extract the training samples of different objects with the support of the Feature Extraction module [45]. Then, the Compute ROI (region of interest) Separability tool was used for class detection and sample adjustment, and the supervised classification was implemented by K-Nearest-Neighbor method.…”

Section: Classification Of Land Use Typesmentioning

confidence: 99%

LUCC and Ecosystem Service Value Assessment for Wetlands: A Case Study in Nansi Lake, China

Meng

Jiang

2019

Water

View full text Add to dashboard Cite

Wetland is one of the most important ecosystems in the world. A healthy wetland ecosystem is important to the development of a regional and even global economy, and it is also beneficial to the human living conditions. In this paper, remote sensing (RS), landscape metrics were used to analyze the land use/land cover change (LUCC), landscape pattern change and the ecosystem services value (ESV) from 1987 to 2017 in Nansi Lake wetland of China. The results showed: 54.4% of the natural wetlands in Nansi Lake were replaced by constructed wetlands in the past 30 years, the ecosystem was degraded and the landscape structure was fragmented due to the severe drought in 2002 and the development of aquaculture and tourism in recent years. The ESV of Nansi Lake wetland fluctuated from 1987 to 2017, and the average annual ESV ($8134/hm2) was much lower than that of global and China’s wetlands, the LUCC driven by human production and economic development leads to the reduction of ESV, especially the rapid increase of constructed wetlands. Finally, the implications of wetland laws and policies, wetland monitoring, assessment and database construction, and wetland regional development strategies were discussed for wetland protection and management.

show abstract

Section: Classification Of Land Use Typesmentioning

confidence: 99%

LUCC and Ecosystem Service Value Assessment for Wetlands: A Case Study in Nansi Lake, China

Meng

Jiang

2019

Water

View full text Add to dashboard Cite

show abstract

“…The multi-resolution segmentation algorithm has been successfully applied in numerous studies (Frohn and Chaudhary, 2008;Karl, 2010;Karl and Maurer, 2010;Ko et al, 2009;Laliberte et al, 2007a and2007b;Laliberte and Rango, 2009;Lucas et al, 2007;Tian and Chen, 2007) and is a bottom-up segmentation algorithm based on a pairwise region merging technique; it minimizes the average heterogeneity and maximizes object homogeneity (Trimble, 2011) essentially capturing patterns of interest. Through the visual assessment of the segmentation results and several iterative classifi cation trials, scale, shape, and compactness parameters were determined that best represented land cover classes (Table 1) of interest for this particular study.…”

Section: Photogrammetric Engineering and Remote Sensingmentioning

confidence: 99%

“…eCognition allows users to create rule sets to classify image objects into meaningful land cover classes by outputting hundreds of features (spectral, spatial, textural, and contextual information) that describe image objects created during the segmentation process (Benz et al, 2004;Frohn and Chaudhary, 2008;Laliberte et al, 2007a).…”

Section: Subplot Extractionmentioning

confidence: 99%

A Random Set Approach for Modeling Integrated Uncertainties of Traffic Islands Derived from Airborne Laser Scanning Points

Liang¹,

Stein²

2013

photogramm eng remote sensing

View full text Add to dashboard Cite

CaGIS and ASPRS invite you to our joint conference on Imaging and Mapping for Disaster Management. As mapping, GIS, and remote sensing professionals, we understand the key role that accurate, current geospatial information plays in preventing, preparing for, and responding to emergencies on all scales. The combined expertise of CaGIS and ASPRS members is critical in supporting disaster management because it is not enough to collect outstanding data; we must be prepared to quickly and efficiently exploit it in order to enable critical decisions. Most importantly, we must understand the information needs of the decision makers and coordinate geospatial data collections. Technical sessions and exhibit hall hours are on two days -Tuesday (October 29) and Wednesday (October 30). CaGIS/ASPRS 2013 Specialty Conference Imaging and Mapping for Disaster Management: From the Individual to the Global CommunitySan NEW:Three presentations per 90-minute technical session, allowing more time for each presenter and for discussion.More Exhibit hall hours to maximize opportunity to visit the exhibit booths.Exhibitors' Reception -Tuesday night followed by an opportunity for late-night dancing near the Riverwalk -including lessons from at least one of We are looking forward to seeing all of you in San Antonio for some very important work and an opportunity to have some fun deep in the heart of Texas! The ASPRS Manual of Airborne Topographic Lidar covers all the relevant topics relating to the science behind lidar systems, mission planning, data collection and management, quality control/ quality assurance, and product development. Selected topics are discussed in-depth• The Global Navigation Satellite System immediate electronic access to all peer-reviewed articles in this issue is available to aSPrS members at www.asprs.org. Just log in to the aSPrS web site with your membership iD and password and download the articles you need. On the cover: Aero-Graphics recently collected simultaneous HD video, orthoimagery,and high-density lidar data over the Glen Canyon Dam near Page, Arizona. Because of its tremendous ecological impact on the Colorado River, the resulting data provided immense value to the end user for conducting sediment and sandbar erosion studies, fl ood simulation analysis, and rockslide mitigation. A regional power company also utilized the data for transmission line ratings and NERC compliance. A video depicting the synthesis of all three mapping elements is available for viewing at http://www.aero-graphics.com.Aero-Graphics is a privately-owned geospatial services company located in Salt Lake City, Utah. Utilizing the latest in lidar and aerial imaging technology, it has established a nationwide reputation for providing high-quality aerial mapping services on schedule at competitive prices.For further information, please contact us by phone at 801.487.3273 or by email at sales@aero-graphics.com. An improved decision-theoretic rough set model with a comprehensive set of criteria to select key features for guaranteeing ...

show abstract

“…However, the definition of PCC was considered in a few studies, e.g. in the Forest Resources Assessment 2000 (FRA 2000) programme [FAO, 2001], it was defined as the fraction of 1 km 2 blocks covered with canopy of trees in field measurements. Kral [2009] also measured different PCC levels in blocks of 1000 m 2 in field survey and on CIR orthophotos, while Carreiras et al [2006] used dot grid method to distinguish five PCC levels of interest in 120 m × 120 m square plots.…”

Section: Introductionmentioning

confidence: 99%

“…Previous studies have constructed canopy cover maps of large areas from mid or low spatial resolution datasets, such as Landsat Thematic Mapper (TM), NASA Multi-angle Imaging SpectroRadiometer (MISR), and Linear Imaging Self Scanning Sensor (LISS III) [Carreiras et al, 2006;Chopping et al, 2008;Yang et al, 2012] or high spatial resolution datasets, such as Compact Airborne Spectrographic Imager (CASI), Color-Infrared (CIR) orthophotos, and LiDAR [Bunting and Lucas, 2006;Kral, 2009;Mathieu et al, 2013]. The spatial resolution of most satellite remote sensing images is too low to identify many objects from their shape or spatial detail [Schowengerdt, 2007;Frohn and Chaudhary, 2008]. Therefore, remote sensing datasets with appropriate spatial resolution are required in investigations aimed at mapping percent canopy cover (PCC) to provide an apparent view of tree crowns in vegetated areas, e.g.…”

Section: Introductionmentioning

confidence: 99%

A robust approach to generate canopy cover maps using UltraCam-D derived orthoimagery classified by support vector machines in Zagros woodlands, West Iran

Erfanifard

Khodaei

Shamsi

2014

European Journal of Remote Sensing

View full text Add to dashboard Cite

An approach was developed to construct a percent canopy cover (PCC) map of Zagros semi-arid woodlands, West Iran, using UltraCam-D airborne imagery. We detected crowns of Persian oak coppice trees on the imagery by use of the support vector machine (SVM) classifier optimized via Taguchi method. Then, PCC was calculated in raster grids with various block sizes and their accuracy metrics revealed the appropriate sizes. Results showed the optimized SVM success in separating Persian oak crowns as revealed in receiver operating characteristic (ROC) curve analysis (area under curve: AUC ~ 0.82). After filtering the raster maps and reassessing their accuracies, validation outputs of the final PCC map with 3000 m 2 resolution yielded an overall accuracy of 90% (KHAT=0.71) and was introduced as the optimal map in this study.

show abstract

Multi-scale Image Segmentation and Object-Oriented Processing for Land Cover Classification

Cited by 15 publications

References 21 publications

LUCC and Ecosystem Service Value Assessment for Wetlands: A Case Study in Nansi Lake, China

LUCC and Ecosystem Service Value Assessment for Wetlands: A Case Study in Nansi Lake, China

A Random Set Approach for Modeling Integrated Uncertainties of Traffic Islands Derived from Airborne Laser Scanning Points

A robust approach to generate canopy cover maps using UltraCam-D derived orthoimagery classified by support vector machines in Zagros woodlands, West Iran

Contact Info

Product

Resources

About