Automated rangeland vegetation cover and density estimation using ground digital images and a spectral-contextual classifier

A method to estimate vegetation cover, density and background brightness parameters in a rangeland environment from low-altitude digital images is presented. A digital still-frame camera, mounted on a 5.2 m pole, is used to acquire images of the ground. The acquired images are then processed using an unsupervised spectral-contextual classifier to extract quantitative measurements automatically. The test results show that the extracted cover measures from the fully automated procedure provide an accuracy of 0.89 to 0.99, measured in kappa, compared with 0.36 to 0.58 and 0.79 to 0.95 from k -means clustering and maximum likelihood supervised classifications respectively. For the clump density measure, the proposed method had an error level ranging from 0 to -62%-hundreds of times less than those produced from both k -means and maximum likelihood classifications. The presented method overcomes human subjectivity inherent in other commonly used ground investigation methods for estimating vegetation cover. The results provide an accurate and objective reference for the calibration of models which relate the spectral reflectance recorded by remote sensors to quantitative measures of range condition.

[1]  M. Barrow,et al.  Color Stereophotography for the Measurement of Vegetation , 1967 .

[2]  D. A. Thomas,et al.  Optical properties of leaves of some species in arid South Australia. , 1970 .

[3]  K. F. Wells Measuring vegetation changes on fixed quadrats by vertical ground stereophotography. , 1971 .

[4]  K. Kershaw,et al.  Quantitative and Dynamic Plant Ecology , 1973 .

[5]  J. Besag Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[6]  Peter E. Hart,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[7]  Azriel Rosenfeld,et al.  Scene Labeling by Relaxation Operations , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  Assessment of Ground Photography for Sampling an Atriplex vesicaria Hew. ex Benth. (Bladder Saltbush) Community. , 1976 .

[9]  D. Toll,et al.  Preliminary evidence for the influence of physiography and scale upon the autocorrelation function of remotely sensed data , 1982 .

[10]  R. R. Lamacraft,et al.  Comparison of distance based density estimates for some arid rangeland vegetation , 1983 .

[11]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Ronald J. P. Lyon,et al.  Influence of rock-soil spectral variation on the assessment of green biomass , 1985 .

[13]  J. Besag On the Statistical Analysis of Dirty Pictures , 1986 .

[14]  R. Pech,et al.  Reflectance modelling and the derivation of vegetation indices for an Australian semi-arid shrubland , 1986 .

[15]  Paul J. Curran,et al.  Simple size for ground and remotely sensed data , 1986 .

[16]  Green,et al.  Evaluation of methods of assessing vegetation change in the semi-arid rangelands of southern Australia. , 1987 .

[17]  R. Jackson,et al.  Suitability of spectral indices for evaluating vegetation characteristics on arid rangelands , 1987 .

[18]  G. Pickup,et al.  The use of spectral and spatial variability to monitor cover change on inert landscapes , 1987 .

[19]  李幼升,et al.  Ph , 1989 .

[20]  N. West,et al.  Measurements of Terrestrial Vegetation , 1989 .

[21]  P. S. Eagleson,et al.  The structure of red-infrared scattergrams of semivegetated landscapes , 1989 .

[22]  Anil K. Jain,et al.  Unsupervised texture segmentation using Gabor filters , 1990, 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings.

[23]  Alan R. Gillespie,et al.  Vegetation in deserts. I - A regional measure of abundance from multispectral images. II - Environmental influences on regional abundance , 1990 .

[24]  Anil K. Jain,et al.  Unsupervised texture segmentation using Gabor filters , 1990, 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings.

[25]  B. Choudhury,et al.  Spatial heterogeneity in vegetation canopies and remote sensing of absorbed photosynthetically active radiation: A modeling study , 1992 .

[26]  Douglas Stow,et al.  Assessing the relationship between spectral vegetation indices and shrub cover in the Jornada Basin, New Mexico , 1993 .

[27]  Anil K. Jain,et al.  Texture Analysis , 2018, Handbook of Image Processing and Computer Vision.

[28]  G. Pickup,et al.  Estimating changes in vegetation cover over time in arid rangelands using landsat MSS data , 1993 .

[29]  R. H. Haas,et al.  Evaluating Landsat Thematic Mapper derived vegetation indices for estimating above-ground biomass on semiarid rangelands , 1993 .

[30]  J. Franklin,et al.  Reflectance of vegetation and soil in Chihuahuan desert plant communities from ground radiometry using SPOT wavebands , 1993 .

[31]  Mihran Tucceryan,et al.  Moment-based texture segmentation , 1994 .

[33]  Sara Brogaard,et al.  Ground-truths or Ground-lies? : environmental sampling for remote sensing application exemplified by vegetation cover data , 1997 .

[34]  Qiming Zhou,et al.  Comparison between the Results from Different Ground Vegetation Cover Estimation Methods in a Rangeland Environment , 1998 .

[35]  N. Pérez de la Blanca,et al.  Improving classical contextual classifications , 1998 .

[36]  Qiming Zhou,et al.  On the ground estimation of vegetation cover in Australian rangelands , 1998 .

[37]  I. White,et al.  The distribution of soluble cations within chenopod-patterned ground, arid western New South Wales, Australia , 1999 .

[38]  John A. Richards,et al.  Remote Sensing Digital Image Analysis: An Introduction , 1999 .