Détection simultanée de l’ombre et de la végétation sur des images aériennes couleur en haute résolution

Ngo, Tran-Thanh; Collet, Christophe; Mazet, Vincent

doi:10.3166/ts.32.311-333

Cited by 3 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The four raw channels of SPOT 6 used in this study were recorded in the R, G, B and NIR wavelengths, respectively. On the basis of the characteristics of the raw channels, neo-channels were calculated to highlight the particularity of certain land types in remote sensing [30,31] or complex objects such as urban infrastructures [32]. For example, NDVI [33] was used to highlight vegetation cover.…”

Section: Use Of Neo-channelsmentioning

confidence: 99%

Assessment of Deep Learning Techniques for Land Use Land Cover Classification in Southern New Caledonia

et al. 2021

View full text Add to dashboard Cite

Land use (LU) and land cover (LC) are two complementary pieces of cartographic information used for urban planning and environmental monitoring. In the context of New Caledonia, a biodiversity hotspot, the availability of up-to-date LULC maps is essential to monitor the impact of extreme events such as cyclones and human activities on the environment. With the democratization of satellite data and the development of high-performance deep learning techniques, it is possible to create these data automatically. This work aims at determining the best current deep learning configuration (pixel-wise vs semantic labelling architectures, data augmentation, image prepossessing, …), to perform LULC mapping in a complex, subtropical environment. For this purpose, a specific data set based on SPOT6 satellite data was created and made available for the scientific community as an LULC benchmark in a tropical, complex environment using five representative areas of New Caledonia labelled by a human operator: four used as training sets, and the fifth as a test set. Several architectures were trained and the resulting classification was compared with a state-of-the-art machine learning technique: XGboost. We also assessed the relevance of popular neo-channels derived from the raw observations in the context of deep learning. The deep learning approach showed comparable results to XGboost for LC detection and over-performed it on the LU detection task (61.45% vs. 51.56% of overall accuracy). Finally, adding LC classification output of the dedicated deep learning architecture to the raw channels input significantly improved the overall accuracy of the deep learning LU classification task (63.61% of overall accuracy). All the data used in this study are available on line for the remote sensing community and for assessing other LULC detection techniques.

show abstract

Section: Use Of Neo-channelsmentioning

confidence: 99%

Assessment of Deep Learning Techniques for Land Use Land Cover Classification in Southern New Caledonia

et al. 2021

View full text Add to dashboard Cite

show abstract

“…4). The shadow elimination procedure is based on Dempster-Shafer's evidence theory following a method presented in [12]. A final smoothing using the Iterated Conditional Modes (ICM) algorithm [13] is performed (Fig.…”

Section: A Datamentioning

confidence: 99%

“…The two methods have then been applied on the 4 cm resolution image (see Figure 8). Their results are compared in terms of precision and recall: recall = TP TP+FN (12) where TP stands for true positive i.e. number of correctly detected manhole covers; FN for false negative, i.e.…”

Section: E Merging the Approachesmentioning

confidence: 99%

Detection of Manhole Covers in High-Resolution Aerial Images of Urban Areas by Combining Two Methods

Pasquet

Desert

Bartoli

et al. 2016

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

International audienceMispositioning of buried utilities is an increasingly important problem both in industrialized and developing countries because of urban sprawl and technological advances. However, some of these networks have surface access traps, which may be visible on high-resolution airborne or satellite images and could serve as presence indicators. We put forward a methodology to detect manhole covers and grates on very high-resolution aerial and satellite images. Two methods are tested: the first is based on a geometrical circular filter, whereas the second one uses machine learning to retrieve some patterns. The results are compared and combined to benefit from the two approaches

show abstract

Use of satellite imagery to categorize vegetation on the French railway network (SNCF Réseau)

Onody,

Bah,

Boum

et al. 2023

Transportation Research Procedia

View full text Add to dashboard Cite

Détection simultanée de l’ombre et de la végétation sur des images aériennes couleur en haute résolution

Cited by 3 publications

References 42 publications

Assessment of Deep Learning Techniques for Land Use Land Cover Classification in Southern New Caledonia

Assessment of Deep Learning Techniques for Land Use Land Cover Classification in Southern New Caledonia

Detection of Manhole Covers in High-Resolution Aerial Images of Urban Areas by Combining Two Methods

Use of satellite imagery to categorize vegetation on the French railway network (SNCF Réseau)

Contact Info

Product

Resources

About