Issues in species classification of trees in old growth conifer stands

Leckie, Donald G.; Tinis, Sally; Nelson, Trisalyn A.; Burnett, C.N.; Gougeon, François A.; Cloney, Ed; Paradine, Dennis

doi:10.5589/m05-004

Cited by 82 publications

(49 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The fact that Douglas fir and willow were misclassified as many different species of various tree types, however, may suggest a different cause of some misclassifications. Leckie et al [1] highlight the causes of high spectral variability in old growth forests, which include shadowing, tree health and bidirectional reflectance. Shadowing may best explain the misclassification of Douglas fir as coast live oak throughout the upper portions of the mosaic.…”

Section: Discussionmentioning

confidence: 99%

“…The identification of tree species through remote sensing provides an efficient and potentially cost-effective way to inventory, protect and manage forest resources [1][2][3][4][5]. Detailed and accurate forest maps are crucial for the preparation and monitoring of fire, drought and other forest disturbances caused by climate change [2,6,7].…”

Section: Introductionmentioning

confidence: 99%

“…Remotely-sensed images contain pixels displaying different surface objects with unique reflectance values, allowing for the discrimination of classes, such as trees and vegetation, based on their spectral signatures [8]. Forest classifications have ranged from more general classifications of forest type (deciduous and coniferous trees) [4,9] to narrower focus classifications of single tree species [1,10,11]. Often, the ability to classify individual species is limited, due to the lack of spectral variance, which helps discriminate small spectral differences between species [12].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Tree Species Classification Using Hyperspectral Imagery: A Comparison of Two Classifiers

et al. 2016

View full text Add to dashboard Cite

Abstract:The identification of tree species can provide a useful and efficient tool for forest managers for planning and monitoring purposes. Hyperspectral data provide sufficient spectral information to classify individual tree species. Two non-parametric classifiers, support vector machines (SVM) and random forest (RF), have resulted in high accuracies in previous classification studies. This research takes a comparative classification approach to examine the SVM and RF classifiers in the complex and heterogeneous forests of Muir Woods National Monument and Kent Creek Canyon in Marin County, California. The influence of object-or pixel-based training samples and segmentation size on the object-oriented classification is also explored. To reduce the data dimensionality, a minimum noise fraction transform was applied to the mosaicked hyperspectral image, resulting in the selection of 27 bands for the final classification. Each classifier was also assessed individually to identify any advantage related to an increase in training sample size or an increase in object segmentation size. All classifications resulted in overall accuracies above 90%. No difference was found between classifiers when using object-based training samples. SVM outperformed RF when additional training samples were used. An increase in training samples was also found to improve the individual performance of the SVM classifier.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Tree Species Classification Using Hyperspectral Imagery: A Comparison of Two Classifiers

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Very high resolution (VHR) remotely sensed imagery like QuickBird, IKONOS, and SPOT5 have proven valuable in discriminating various forest species over older generation sensors [1,2], as they can accurately describe the complex spatial patterns typically observed in forested areas. Moreover, a number of recent studies have shown that hyperspectral imagery are particularly useful for discriminating different species of the same genus, which is not always possible using the limited spectral information provided by VHR multispectral images [3][4][5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Decision Fusion Based on Hyperspectral and Multispectral Satellite Imagery for Accurate Forest Species Mapping

et al. 2014

View full text Add to dashboard Cite

This study investigates the effectiveness of combining multispectral very high resolution (VHR) and hyperspectral satellite imagery through a decision fusion approach, for accurate forest species mapping. Initially, two fuzzy classifications are conducted, one for each satellite image, using a fuzzy output support vector machine (SVM). The classification result from the hyperspectral image is then resampled to the multispectral's spatial resolution and the two sources are combined using a simple yet efficient fusion operator. Thus, the complementary information provided from the two sources is effectively exploited, without having to resort to computationally demanding and time-consuming typical data fusion or vector stacking approaches. The effectiveness of the proposed methodology is validated in a complex Mediterranean forest landscape, comprising spectrally similar and spatially intermingled species. The decision fusion scheme resulted in an accuracy increase of 8% compared to the classification using only the multispectral imagery, whereas the increase was even higher compared to the classification using only the hyperspectral satellite image. Perhaps most importantly, its accuracy was significantly higher than alternative multisource fusion approaches, although the latter are characterized by much higher computation, storage, and time requirements.

show abstract

“…This software suite uses a pattern recognition algorithm to systematically scan remotely sensed images and automatically delineate tree crowns. There are many methods that have been proven successful in delineating tree crowns, including local minima value finding, local maxima filtering, template matching, valley finding, three dimensional modeling and wavelet analysis (Brandtberg & Walter, 1998;Chubey, Franklin, & Wulder, 2006;Popescu, Wynne, & Nelson, 2003;Leckie, et al, 2005;Wulder, Niemann, & Goodenough, 2000;Shugart, Bourgeau-Chavez, & Kasischke, 2000;Pouliot, King, Bell, & Pitt, 2002). The software developed by Palace et al (2008) leverages a combination of local minima finding and local maximum filtering.…”

Section: Remote Sensing Analysismentioning

confidence: 99%

Examining Forest Structure in the Mozambican Dry Deciduous Lowland Forest Utilizing In-Situ and Remotely Sensed Measurements and Observations

Heil¹

View full text Add to dashboard Cite

Land use change in the form of deforestation and degradation is contributing to the release of greenhouse gases on the order of 1.2 ±0.7 Gt CO 2 e per year. Emissions of this magnitude suggest that the conversion and disturbance of forests play a significant role in forcing global climate change. Although there is growing recognition of this contribution among scientific and political communities, there is an expressed need for more efficient and accurate methods for assessing the role of forests in shifting climate patterns. Recent efforts to measure and monitor forests on large scales have used remotely sensed data from airborne and spaceborne sensors. This study leverages high spatial resolution remotely sensed data with in-situ field measurements to measure forest structure in the Dry Deciduous Lowland Forests ofMozambique. The approach to analysis was motivated by the importance of three-dimensional forest structure in driving forest dynamics. A novel tree crown analysis methodology was employed in order to calculate select structural properties of forests from remotely sensed data.

show abstract

Issues in species classification of trees in old growth conifer stands

Cited by 82 publications

References 21 publications

Tree Species Classification Using Hyperspectral Imagery: A Comparison of Two Classifiers

Tree Species Classification Using Hyperspectral Imagery: A Comparison of Two Classifiers

Decision Fusion Based on Hyperspectral and Multispectral Satellite Imagery for Accurate Forest Species Mapping

Examining Forest Structure in the Mozambican Dry Deciduous Lowland Forest Utilizing In-Situ and Remotely Sensed Measurements and Observations

Contact Info

Product

Resources

About