JOURNAL ARTICLE

Techniques for object-based classification of urban tree cover from high-resolution multispectral imagery

Brad LehrbassJinfei Wang

Year: 2010 Journal:   Canadian Journal of Remote Sensing Vol: 36 (sup2)Pages: S287-S297   Publisher: Taylor & Francis

Abstract

AbstractA city's trees provide many environmental and social benefits. To ensure the long-term prosperity of its urban forest, a city should have an effective forest management plan that is guided by timely and accurate spatial information. High-spatial-resolution colour-infrared imagery is a commonly available source of forestry information, but accurate automated tree cover extraction in an urban environment remains a challenge. Presented is an effective, semi-automatic, object-based method for urban tree cover extraction, applied to 23?645 ha of 30 cm colour-infrared imagery of London, Ontario, Canada. Detailed methods, including some new techniques, are presented for the empirical selection of segmentation and classification parameters, the selection of subclasses and training samples, rule-based error correction, and image object border smoothing. A majority-voting interpretation of sample points was performed to reduce the subjectivity of the accuracy assessment. A test of the overall classification accuracy using the proposed method on a 2 km × 2 km image tile showed an improvement of 12.8% over that of a traditional maximum likelihood classification. The overall classification accuracy achieved for the entire city was 89.73%, with user's and producer's accuracy for trees of 75.61% and 86.36%, respectively.Les arbres d'une ville fournissent de nombreux avantages environnementaux et sociaux. Pour s'assurer de la richesse long-terme de sa forêt urbaine, une ville doit avoir un plan efficace guidé par des informations spatiales opportunes et précises. L'imagerie couleur-infrarouge de haute résolution est une source abordable d'information forestière, mais l'extraction automatisée exacte du recouvrement des arbres dans des environnements urbains demeure un défi particulier. Présentée est une méthode orientée-objet semi-automatisée efficace pour extraire le taux de recouvrement des arbres urbain, appliquée à de l'imagerie couleur-infrarouge de 30 cm sur 23?645 ha en London, Ontario, Canada. Des méthodes détaillées pour la sélection empirique de paramètres de segmentation et de classification, le choix de classification et d'échantillons d'entrainement, la correction d'erreurs réglementée et pour le lissage des frontières des objets-images sont présentées, ainsi que de nouvelles techniques. Une évaluation d'exactitude basée sur un vote majoritaire réduit la subjectivité de l'interprétation des points d'échantillon. En se servant de la méthode proposée, un test d'exactitude de classification générale d'une image de 2 km × 2 km a démontré une amélioration de 12,8 % sur une classification traditionnelle de probabilité maximum. L'exactitude de classification générale atteint pour la ville entière est 89,73 % avec l'exactitude de l'utilisateur et du producteur à 75,61 % et 86,36 %, respectivement.

Keywords:
Multispectral image Computer science Geography Land cover Smoothing Artificial intelligence Remote sensing Cohen's kappa Contextual image classification Cartography Computer vision Machine learning Image (mathematics) Land use Engineering

Metrics

10
Cited By
1.43
FWCI (Field Weighted Citation Impact)
11
Refs
0.82
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Citation History

Topics

Remote Sensing in Agriculture
Physical Sciences →  Environmental Science →  Ecology
Remote Sensing and LiDAR Applications
Physical Sciences →  Environmental Science →  Environmental Engineering
Remote-Sensing Image Classification
Physical Sciences →  Engineering →  Media Technology

Related Documents

JOURNAL ARTICLE

Detection of urban tree canopy from very high resolution imagery using an object based classification

Sujata KaduBalaji G. HogadeImdad Rizvi

Journal:   International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering Year: 2022 Vol: 12 (4)Pages: 3665-3665
JOURNAL ARTICLE

Object-based urban detailed land cover classification with high spatial resolution IKONOS imagery

Ruiliang PuShawn LandryQian Yu

Journal:   International Journal of Remote Sensing Year: 2011 Vol: 32 (12)Pages: 3285-3308
JOURNAL ARTICLE

Road Network Extraction from High Resolution Multispectral Satellite Imagery Based on Object Oriented Techniques

Minakshi KumarRoop SinghP. L. N. RajuY. V. N. Krishnamurthy

Journal:   ISPRS annals of the photogrammetry, remote sensing and spatial information sciences Year: 2014 Vol: II-8 Pages: 107-110
BOOK-CHAPTER

Urban Forest Tree Classification Using UAV-Based High-Resolution Imagery

Mojdeh MirakiZahra Azizi

Advances in Science, Technology & Innovation/Advances in science, technology & innovation Year: 2022 Pages: 365-368
© 2026 ScienceGate Book Chapters — All rights reserved.