Mapping forest tree species in high resolution UAV-based RGB-imagery by means of convolutional neural networks

Schiefer, Felix; Kattenborn, Teja; Frick, Annett; Frey, Julian; Schall, Peter; Koch, Bárbara; Schmidtlein, Sebastian

doi:10.1016/j.isprsjprs.2020.10.015

Cited by 223 publications

(130 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…But it is difficult to separate the interference of the residential green space from the cooling effects of PGS. In recent years, with the advent of Unmanned Aerial Vehicle (UAV) remote sensing, the UAV-borne very-high spatial resolution, hyperspectral and thermal images (Zarco-Tejada et al, 2012;Feng and Li, 2019;Schiefer et al, 2020), such as those used for grapevine (Maimaitiyiming et al, 2020), can be employed to characterize the detailed, diurnal real-time canopy and thermal information of PGS in the future.…”

Section: Implications and Limitations For Urban Planningmentioning

confidence: 99%

Estimating the Cooling Effect of Pocket Green Space in High Density Urban Areas in Shanghai, China

Wang

et al. 2021

Front. Environ. Sci.

View full text Add to dashboard Cite

Recently, pocket green spaces (PGS), i.e., small green spaces, have attracted growing attention for their various ecological and social services. As a crucial part of urban green spaces in high-density urban areas, PGS facilitates recreation and relaxation for neighborhoods and thus improves the livability of cities at the local scale. However, whether and how the PGS cools the urban heat island effect is still unclear. This research was performed in the highly developed areas of the city of Shanghai during hot summer daytime. We applied a set of cooling effect indicators to estimate the cooling extent, cooling intensity, and cooling efficiency of PGS. We further examined whether and how landscape features within and surrounding the PGS influence its cooling effects. The results showed that 90% of PGS are cooler than their surroundings. Among the landscape features, the land surface temperature of PGS logarithmically decreased with its area, and the maximum local cool island intensity and maximum cooling area logarithmically increased with the area of PGS. The vegetation types and their composition within the PGS also influenced their surface temperature and the cooling effect. The PGS dominated by tree-shrub-grass showed the highest cooling efficiency. The surrounding landscape patterns, especially the patch density and the landscape shape index, influence the cooling effect of PGS at both class and landscape levels. These findings add new knowledge on factors influencing the cooling effect of PGS, and provide the biophysical theoretical basis for developing nature-based cooling strategies for urban landscape designers and planners.

show abstract

Section: Implications and Limitations For Urban Planningmentioning

confidence: 99%

Estimating the Cooling Effect of Pocket Green Space in High Density Urban Areas in Shanghai, China

Wang

et al. 2021

Front. Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…Forests play a vital role in the survival and development of human civilization. According to the report by the Food and Agriculture Organization (FAO) of the United Nations, forest ecosystems cover approximately one-third of the earth's land surface [1]. The composition and spatial distribution of forest tree species have a great impact on the forest ecological environment, biodiversity, resource utilization efficiency, production and carbon storage capacity, and nutrition cycle [2][3][4][5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Tree Species Classification of Forest Stands Using Multisource Remote Sensing Data

et al. 2021

View full text Add to dashboard Cite

The spatial distribution of forest stands is one of the fundamental properties of forests. Timely and accurately obtained stand distribution can help people better understand, manage, and utilize forests. The development of remote sensing technology has made it possible to map the distribution of tree species in a timely and accurate manner. At present, a large amount of remote sensing data have been accumulated, including high-spatial-resolution images, time-series images, light detection and ranging (LiDAR) data, etc. However, these data have not been fully utilized. To accurately identify the tree species of forest stands, various and complementary data need to be synthesized for classification. A curve matching based method called the fusion of spectral image and point data (FSP) algorithm was developed to fuse high-spatial-resolution images, time-series images, and LiDAR data for forest stand classification. In this method, the multispectral Sentinel-2 image and high-spatial-resolution aerial images were first fused. Then, the fused images were segmented to derive forest stands, which are the basic unit for classification. To extract features from forest stands, the gray histogram of each band was extracted from the aerial images. The average reflectance in each stand was calculated and stacked for the time-series images. The profile curve of forest structure was generated from the LiDAR data. Finally, the features of forest stands were compared with training samples using curve matching methods to derive the tree species. The developed method was tested in a forest farm to classify 11 tree species. The average accuracy of the FSP method for ten performances was between 0.900 and 0.913, and the maximum accuracy was 0.945. The experiments demonstrate that the FSP method is more accurate and stable than traditional machine learning classification methods.

show abstract

“…Certainly, the use of UAVs in forests and environmental monitoring is currently in an expansion phase [14][15][16][17][18][19][20][21][22], encouraged by the affordability of new systems and sensors [23]. Airborne multispectral [15,19,21,22,24], hyperspectral [16,17,20,25], and LiDAR (usually combined with optical sensors [14,18]) sensors represent the most recent and completed systems for species classification of natural habitats. The common point of such technologies is the production of very high resolution (VHR) data, which have introduced a new set of possibilities for classifying the Earth's surface at finer levels of spatial detail, allowing the description of small objects.…”

Section: Introductionmentioning

confidence: 99%

Mapping Riparian Habitats of Natura 2000 Network (91E0*, 3240) at Individual Tree Level Using UAV Multi-Temporal and Multi-Spectral Data

et al. 2021

View full text Add to dashboard Cite

Riparian habitats provide a series of ecological services vital for the balance of the environment, and are niches and resources for a wide variety of species. Monitoring riparian environments at the intra-habitat level is crucial for assessing and preserving their conservation status, although it is challenging due to their landscape complexity. Unmanned aerial vehicles (UAV) and multi-spectral optical sensors can be used for very high resolution (VHR) monitoring in terms of spectral, spatial, and temporal resolutions. In this contribution, the vegetation species of the riparian habitat (91E0*, 3240 of Natura 2000 network) of North-West Italy were mapped at individual tree (ITD) level using machine learning and a multi-temporal phenology-based approach. Three UAV flights were conducted at the phenological-relevant time of the year (epochs). The data were analyzed using a structure from motion (SfM) approach. The resulting orthomosaics were segmented and classified using a random forest (RF) algorithm. The training dataset was composed of field-collected data, and was oversampled to reduce the effects of unbalancing and size. Three-hundred features were computed considering spectral, textural, and geometric information. Finally, the RF model was cross-validated (leave-one-out). This model was applied to eight scenarios that differed in temporal resolution to assess the role of multi-temporality over the UAV’s VHR optical data. Results showed better performances in multi-epoch phenology-based classification than single-epochs ones, with 0.71 overall accuracy compared to 0.61. Some classes, such as Pinus sylvestris and Betula pendula, are remarkably influenced by the phenology-based multi-temporality: the F1-score increased by 0.3 points by considering three epochs instead of two.

show abstract

Mapping forest tree species in high resolution UAV-based RGB-imagery by means of convolutional neural networks

Cited by 223 publications

References 48 publications

Estimating the Cooling Effect of Pocket Green Space in High Density Urban Areas in Shanghai, China

Estimating the Cooling Effect of Pocket Green Space in High Density Urban Areas in Shanghai, China

Tree Species Classification of Forest Stands Using Multisource Remote Sensing Data

Mapping Riparian Habitats of Natura 2000 Network (91E0*, 3240) at Individual Tree Level Using UAV Multi-Temporal and Multi-Spectral Data

Contact Info

Product

Resources

About