Détail de l'auteur
Auteur Dominique Chabot |
Documents disponibles écrits par cet auteur (2)
Affiner la recherche
Object-based analysis of UAS imagery to map emergent and submerged invasive aquatic vegetation: a case study / Dominique Chabot in Journal of unmanned vehicle systems, 5 (2017)
[article]
Titre : Object-based analysis of UAS imagery to map emergent and submerged invasive aquatic vegetation: a case study Type de document : Imprimé Auteurs : Dominique Chabot ; Christopher Dillon ; Oumer S. Ahmed ; Adam Shemrock Année de publication : 2017 Article en page(s) : 27-33 Catégories : [CBNPMP-Thèmes] Télédétection Résumé : Small unmanned aircraft systems (UAS) combined with automated image analysis may provide an efficient alternative or complement to labour-intensive boat-based monitoring of invasive aquatic vegetation. A small mapping drone was assessed for collecting high-resolution (≤5 cm/pixel) true-colour and near-infrared imagery revealing the distribution of invasive water soldier (Stratiotes aloides) in the Trent–Severn Waterway, Ontario (Canada). We further evaluated the capacity of an object-based image analysis approach based on the Random Forests classification algorithm to map features in the imagery, chiefly emergent and submerged water soldier colonies. The imagery contained flaws and inconsistencies resulting from data collection in suboptimal weather conditions that likely negatively impacted classification performance. Nevertheless, our best-performing classification had a producer’s and user’s accuracy for water soldier of 81% and 74%, respectively, an overall accuracy of 78%, and a kappa value of 61%, indicating “substantial” accuracy. This trial provides an instructive case study on results achieved in a “real-world” application of a UAS for environmental monitoring, notably characterized by time constraints for data collection and analysis. Beyond avoiding data collection in unfavourable weather conditions, adaptations of the image segmentation process and use of a true discrete-band multispectral camera may help to improve classification accuracy, particularly of submerged vegetation. Lien pérenne : DOI : 10.1139/juvs-2016-0009 Permalink : https://biblio.cbnpmp.fr/index.php?lvl=notice_display&id=151518
in Journal of unmanned vehicle systems > 5 (2017) . - 27-33Chabot, D., Dillon, C., Ahmed, OS., Shemrock, A. 2017. Object-based analysis of UAS imagery to map emergent and submerged invasive aquatic vegetation: a case study. Journal of unmanned vehicle systems, 5: 27-33.Documents numériques
Consultable
Article (2017)URL Small unmanned aircraft: precise and convenient new tools for surveying wetlands / Dominique Chabot in Journal of unmanned vehicle systems, 1 (2013)
[article]
Titre : Small unmanned aircraft: precise and convenient new tools for surveying wetlands Type de document : Imprimé Auteurs : Dominique Chabot ; David M. Bird Année de publication : 2013 Article en page(s) : 15-24 Catégories : [CBNPMP-Thèmes] Télédétection Résumé : Unmanned aircraft systems (UAS) could be of benefit for surveying wetlands, which often have spatially complex habitats that are challenging to navigate and assess at ground level. We used a small UAS to acquire aerial imagery and characterize land cover in a 128 ha wetland impoundment as part of a conservation study of the least bittern (Ixobrychus exilis). The method was successful in gathering sub-decimetre georeferenced imagery that clearly revealed the fine-scale water–vegetation interface and in which several types of vegetation could be distinguished and classified using spectral image analysis software. Simplified three-category land cover classifications obtained in this manner showed strong agreement with manual classification of random points in the imagery, as evidenced by a kappa coefficient of 87.19% (n = 600). Compared to cover estimates made during concurrent ground-based surveys in 30 sampling plots, UAS data yielded overall similar water–vegetation ratios, but proved more effectual for detecting small amounts of highly interspersed water. Significant differences (p = 0.004) in cover estimates of the dominant vegetation, cattail, were likely primarily due to limitations of ground-based surveys. Given the effective and convenient application of a UAS in this study, we recommend their further use in wetland-related research and management. Lien pérenne : DOI : 10.1139/juvs-2013-0014 Permalink : https://biblio.cbnpmp.fr/index.php?lvl=notice_display&id=151555
in Journal of unmanned vehicle systems > 1 (2013) . - 15-24Chabot, D., Bird, DM. 2013. Small unmanned aircraft: precise and convenient new tools for surveying wetlands. Journal of unmanned vehicle systems, 1: 15-24.Documents numériques
Consultable
Article (2013)URL