Object-based Detailed Vegetation Classification with Airborne High Spatial Resolution Remote Sensing Imagery

In this paper, we evaluate the capability of the high spatial resolution airborne Digital Airborne Imaging System (DAIS) imagery for detailed vegetation classification at the alliance level with the aid of ancillary topographic data. Image objects as minimum classification units were generated through the Fractal Net Evolution Approach (FNEA) segmentation using eCognition software. For each object, 52 features were calculated including spectral features, textures, topographic features, and geometric features. After statistically ranking the importance of these features with the classification and regression tree algorithm (CART), the most effective features for classification were used to classify the vegetation. Due to the uneven sample size for each class, we chose a non-parametric (nearest neighbor) classifier. We built a hierarchical classification scheme and selected features for each of the broadest categories to carry out the detailed classification, which significantly improved the accuracy. Pixel-based maximum likelihood classification (MLC) with comparable features was used as a benchmark in evaluating our approach. The objectbased classification approach overcame the problem of saltand-pepper effects found in classification results from traditional pixel-based approaches. The method takes advantage of the rich amount of local spatial information present in the irregularly shaped objects in an image. This classification approach was successfully tested at Point Reyes National Seashore in Northern California to create a comprehensive vegetation inventory. Computer-assisted classification of high spatial resolution remotely sensed imagery has good potential to substitute or augment the present ground-based inventory of National Park lands.

[1]  E. E. Hardy,et al.  A land-use classification system for use with remote sensor data , 1972 .

[2]  James R. Anderson,et al.  A land use and land cover classification system for use with remote sensor data , 1976 .

[3]  R. Kettig,et al.  Classification of Multispectral Image Data by Extraction and Classification of Homogeneous Objects , 1976, IEEE Transactions on Geoscience Electronics.

[4]  M. Barbour,et al.  Terrestrial Plant Ecology , 1981 .

[5]  David A. Landgrebe,et al.  The development of a spectral-spatial classifier for earth observational data , 1980, Pattern Recognit..

[6]  King-Sun Fu,et al.  A survey on image segmentation , 1981, Pattern Recognit..

[7]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[8]  John A. Richards,et al.  Remote Sensing Digital Image Analysis , 1986 .

[9]  Philip J. Howarth,et al.  Performance analyses of probabilistic relaxation methods for land-cover classification☆ , 1989 .

[10]  Morris Goldberg,et al.  Hierarchy in Picture Segmentation: A Stepwise Optimization Approach , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  John A. Richards,et al.  Knowledge-based techniques for multi-source classification , 1990 .

[12]  J. Dubois,et al.  Evaluation Of The Grey-level Co-occurrence Matrix Method For Land-cover Classification Using Spot Imagery , 1990 .

[13]  Jon Sticklen,et al.  Knowledge-based segmentation of Landsat images , 1991, IEEE Trans. Geosci. Remote. Sens..

[14]  Risto Kalliola,et al.  To what extent are vegetation types visible in satellite imagery , 1991 .

[15]  Philip J. Howarth,et al.  Land-use classification of SPOT HRV data using a cover-frequency method , 1992 .

[16]  Peng Gong,et al.  A comparison of spatial feature extraction algorithms for land-use classification with SPOT HRV data , 1992 .

[17]  J. Le Moigne.  Refining Image Segmentation by Integration of Edge and Region Data , 1992, [Proceedings] IGARSS '92 International Geoscience and Remote Sensing Symposium.

[18]  P. Gong,et al.  Frequency-based contextual classification and gray-level vector reduction for land-use identification , 1992 .

[19]  Perry J. Hardin,et al.  Fast Nearest Neighbor Classification Methods for Multispectral Imagery , 1992 .

[20]  Jean-Pierre Gambotto,et al.  A new approach to combining region growing and edge detection , 1993, Pattern Recognit. Lett..

[21]  Giles M. Foody,et al.  Separability of tropical rain-forest types in the Tambopata-Candamo Reserved Zone, Peru , 1994 .

[22]  K. Johnsson.  Segment-based land-use classification from SPOT satellite data , 1994 .

[23]  Peng Gong.  Reducing boundary effects in a kernel-based classifier , 1994 .

[24]  Rolf Adams,et al.  Seeded Region Growing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Extraction of spectral reflectance images from multi-spectral images by the HIS transformation model , 1996 .

[26]  P. Gong,et al.  Integrated Analysis of Spatial Data from Multiple Sources: Using Evidential Reasoning and Artificial Neural Network Techniques for Geological Mapping , 1996 .

[27]  Gregory S. Biging,et al.  An iterative classification approach for mapping natural resources from satellite imagery , 1996 .

[28]  Geoffrey J. Hay,et al.  An object-specific image-texture analysis of H-resolution forest imagery☆ , 1996 .

[29]  Andrew Mehnert,et al.  An improved seeded region growing algorithm , 1997, Pattern Recognit. Lett..

[30]  J San Miguel-Ayanz,et al.  Comparison of single-stage and multi-stage classification approaches for cover type mapping with TM and SPOT data , 1997 .

[31]  Ruiliang Pu,et al.  Conifer species recognition: An exploratory analysis of in situ hyperspectral data , 1997 .

[32]  Jukka Heikkonen,et al.  Land Cover/Land Use Classification of Urban Areas. A Remote Sensing Approach. , 1998 .

[33]  Roland L. Redmond,et al.  Estimation and Mapping of Misclassification Probabilities for Thematic Land Cover Maps , 1998 .

[34]  B. Kartikeyan,et al.  A segmentation approach to classification of remote sensing imagery , 1998 .

[35]  M. Hodgson.  What Size Window for Image Classification? A Cognitive Perspective , 1998 .

[36]  R. Hill.  Image segmentation for humid tropical forest classification in Landsat TM data , 1999 .

[37]  Arno Schäpe,et al.  Multiresolution Segmentation : an optimization approach for high quality multi-scale image segmentation , 2000 .

[38]  W. Gould.  REMOTE SENSING OF VEGETATION, PLANT SPECIES RICHNESS, AND REGIONAL BIODIVERSITY HOTSPOTS , 2000 .

[39]  P. Gong,et al.  Conifer species recognition: Effects of data transformation , 2001 .

[40]  G. Hill,et al.  Vegetation mapping of a tropical freshwater swamp in the Northern Territory, Australia: A comparison of aerial photography, Landsat TM and SPOT satellite imagery , 2001 .

[41]  Pi-Fuei Hsieh,et al.  Effect of spatial resolution on classification errors of pure and mixed pixels in remote sensing , 2001, IEEE Trans. Geosci. Remote. Sens..

[42]  Xie Yuan-dan,et al.  Survey on Image Segmentation , 2002 .

[43]  Mark A. Friedl,et al.  Using prior probabilities in decision-tree classification of remotely sensed data , 2002 .

[44]  Giles M. Foody,et al.  Status of land cover classification accuracy assessment , 2002 .

[45]  DAIS: A DIGITAL AIRBORNE IMAGING SYSTEM , 2002 .

[46]  Kacem Chehdi,et al.  Automatic image segmentation system through iterative edge - region co-operation , 2002, Image Vis. Comput..

[47]  Caren C. Dymond,et al.  Mapping vegetation spatial patterns from modeled water, temperature and solar radiation gradients , 2002 .

[48]  K. Lertzman,et al.  Combining High-Resolution Aerial Photography with Gradient-Directed Transects to Guide Field Sampling and Forest Mapping in Mountainous Terrain , 2003, Forest Science.

[49]  Martin Herold,et al.  Spectral resolution requirements for mapping urban areas , 2003, IEEE Trans. Geosci. Remote. Sens..

[50]  Paul L. Patterson,et al.  Classification accuracy for stratification with remotely sensed data , 2003 .

[51]  M. Herold,et al.  Spatial Metrics and Image Texture for Mapping Urban Land Use , 2003 .

[52]  Manfred Ehlers,et al.  Automated analysis of ultra high resolution remote sensing data for biotope type mapping: new possibilities and challenges , 2003 .

[53]  Gang Xu,et al.  Information fusion for rural land-use classification with high-resolution satellite imagery , 2003, IEEE Trans. Geosci. Remote. Sens..

[54]  D. Roberts,et al.  The effects of vegetation phenology on endmember selection and species mapping in southern California chaparral , 2003 .

[55]  Jon Atli Benediktsson,et al.  Classification and feature extraction for remote sensing images from urban areas based on morphological transformations , 2003, IEEE Trans. Geosci. Remote. Sens..

[56]  Curt H. Davis,et al.  A hierarchical fuzzy classification approach for high-resolution multispectral data over urban areas , 2003, IEEE Trans. Geosci. Remote. Sens..

[57]  M. C. Kiran,et al.  Tree model based eco-climatic vegetation classification and fuzzy mapping in diverse tropical deciduous ecosystems using multi-season NDVI , 2004 .

[58]  Thomas Blaschke,et al.  Image Segmentation Methods for Object-based Analysis and Classification , 2004 .

[59]  U. Benz,et al.  Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information , 2004 .

[60]  G. J. Hay,et al.  A multiscale framework for landscape analysis: Object-specific analysis and upscaling , 2001, Landscape Ecology.

[61]  Alexandre Carleer,et al.  Exploitation of Very High Resolution Satellite Data for Tree Species Identification , 2004 .