Canadian Forest Service Publications

Individual tree crown species recognition: the Nahmint study. 1999. Gougeon, F.A.; Leckie, D.G.; Paradine, D.; Scott, I. Pages 209-223 in D.A. Hill and D.G. Leckie, Editors. International forum: automated interpretation of high spatial resolution digital imagery for forestry, Proceedings: Symposium. February 10-12, 1998, Victoria, British Columbia. Natural Resources Canada, Canadian Forest Service, Pacific Forestry Centre, Victoria, BC.

Year: 1999

Issued by: Pacific Forestry Centre

Catalog ID: 5182

Language: English

CFS Availability: PDF (download)

Mark record

Abstract

The species content of forest stands is an information of paramount importance in conventional forest inventories. Typically, the stands and their content are assessed by human interpretation of aerial photographs. However, using remotely sensed aerial images or digitized aerial photographs of high spatial resolution (10-100 cm/pixel), it is now becoming possible to automatically delineate most of the visible individual tree crowns (ITC) in such images. This led to the development of several ITC multispectral signatures and of an ITC-based supervised classification system making possible ITC species recognition. The resulting information on the individual trees can be preserved, where very detailed information is needed; or collated, to generate very precise information on existing forest stands, or regrouped (statically or dynamically) using new criteria, to help with multi-resource forest management. This paper primarily addresses the species recognition aspects of this new paradigm for generating precise information useful to forest inventories. The ITC-based delineation and classification system is tested with a geometrically corrected 60 cm/pixel casi image of the Nahmint Lake species demonstration area, Vancouver Island, British Columbia. Simple correction curves to compensate for bi-directional reflectance function (BRDF) effects were applied to the multispectral image in spite of the fact that the image had been previously geometrically corrected by the supplier. The ITC-based supervised classification of five western Canadian coniferous species and a generic hardwood class led to an overall classification accuracy of 59.8% when tested with a conventional confusion matrix approach. These low classification results are attributed to the lack of purity of the training and testing areas. A comparison of the species content of more sizable testing areas with their corresponding field transects led to an overall error of 12%, 19.5% when only the dominant species is considered. The paper concludes with a discussion of the research and operational problems to be resolved before the goal of semi-automatic generation of precise forest management inventories is achieved.