Species-related single dead tree detection using multi-temporal ALS data and CIR imagery

Kamińska, Agnieszka; Lisiewicz, Maciej; Stereńczak, Krzysztof; Kraszewski, Bartłomiej; Sadkowski, Rafał

doi:10.1016/j.rse.2018.10.005

Cited by 55 publications

(30 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, Shi et al (2018) categorized five species, fusing ALS data with hyperspectral imagery (OA = 84%). Kamińska et al (2018) classified three tree species (spruce, pine, deciduous), each of them further categorized as "dead" or "alive". Their approach using an RF classifier and features generated from ALS data and color-infrared imagery reached an OA of 94%.…”

Section: Discussionmentioning

confidence: 99%

Classification of Tree Species and Standing Dead Trees by Fusing Uav-Based Lidar Data and Multispectral Imagery in the 3d Deep Neural Network Pointnet++

Briechle

Krzystek

Vosselman

2020

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Knowledge of tree species mapping and of dead wood in particular is fundamental to managing our forests. Although individual tree-based approaches using lidar can successfully distinguish between deciduous and coniferous trees, the classification of multiple tree species is still limited in accuracy. Moreover, the combined mapping of standing dead trees after pest infestation is becoming increasingly important. New deep learning methods outperform baseline machine learning approaches and promise a significant accuracy gain for tree mapping. In this study, we performed a classification of multiple tree species (pine, birch, alder) and standing dead trees with crowns using the 3D deep neural network (DNN) PointNet++ along with UAV-based lidar data and multispectral (MS) imagery. Aside from 3D geometry, we also integrated laser echo pulse width values and MS features into the classification process. In a preprocessing step, we generated the 3D segments of single trees using a 3D detection method. Our approach achieved an overall accuracy (OA) of 90.2% and was clearly superior to a baseline method using a random forest classifier and handcrafted features (OA = 85.3%). All in all, we demonstrate that the performance of the 3D DNN is highly promising for the classification of multiple tree species and standing dead trees in practice.

show abstract

Section: Discussionmentioning

confidence: 99%

Classification of Tree Species and Standing Dead Trees by Fusing Uav-Based Lidar Data and Multispectral Imagery in the 3d Deep Neural Network Pointnet++

Briechle

Krzystek

Vosselman

2020

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…ALS point cloud intensity has been recommended as important information for forest condition assessment [54]. The intensity values recorded by the ALS system correspond to the amount of energy reflected from the target to the laser sensor and relate to radiometric properties of the target.…”

Section: Als Intensity Normalizationmentioning

confidence: 99%

“…For each tree, 140 ALS indices, including height indices, intensity indices, point density indices, tree size and shape indices, were calculated (Table 2) from the ALS point cloud. The selection of indices was based on their known relevance for tree health assessment [26,29,30,54]. As there is high possibility that HSI pixels at the border of tree crown polygons were contaminated by background materials (e.g., impervious surfaces, shrubs and grass), the border pixels were removed before extracting tree crown specific pixels.…”

Section: Deriving Tree Crown Specific Als Indicesmentioning

confidence: 99%

“…The two important parameters for RF classification are the number of classification trees (ntree) and the number of features selected at each split in the tree building process (mtry). ntree was set at 500 and mtry was set at sqrt(M) (M being the number of input indices) based on previous work [26,54,105]. The classification procedure was conducted in Python using the scikit-learn library.…”

Section: Classification Proceduresmentioning

confidence: 99%

See 1 more Smart Citation

Urban Tree Health Classification Across Tree Species by Combining Airborne Laser Scanning and Imaging Spectroscopy

Chi

Degerickx

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Declining urban tree health can affect critical ecosystem services, such as air quality improvement, temperature moderation, carbon storage, and biodiversity conservation. The application of state-of-the-art remote sensing data to characterize tree health has been widely examined in forest ecosystems. However, such application to urban trees has not yet been fully explored—due to the presence of heterogeneous tree species and backgrounds, severely complicating the classification of tree health using remote sensing information. In this study, tree health was represented by a set of field-assessed tree health indicators (defoliation, discoloration, and a combination thereof), which were classified using airborne laser scanning (ALS) and hyperspectral imagery (HSI) with a Random Forest classifier. Different classification scenarios were established aiming at: (i) Comparing the performance of ALS data, HSI and their combination, and (ii) examining to what extent tree species mixtures affect classification accuracy. Our results show that although the predictive power of ALS and HSI indices varied between tree species and tree health indicators, overall ALS indices performed better. The combined use of both ALS and HSI indices results in the highest accuracy, with weighted kappa coefficients (Kc) ranging from 0.53 to 0.79 and overall accuracy ranging from 0.81 to 0.89. Overall, the most informative remote sensing indices indicating urban tree health are ALS indices related to point density, tree size, and shape, and HSI indices associated with chlorophyll absorption. Our results further indicate that a species-specific modelling approach is advisable (Kc points improved by 0.07 on average compared with a mixed species modelling approach). Our study constitutes a basis for future urban tree health monitoring, which will enable managers to guide early remediation management.

show abstract

“…The difference in OA values between the studies was caused in part by the different number of tree species classified, and more importantly the fact that the point clouds generated from ALS data had very different densities (22.0 vs. 3.50 pts m -2 ). Since ALS-based variables are fundamental to tree classification methods (Kaminska et al 2018), denser point clouds provide better descriptions of tree structure and significantly improve classification results. Voss & Sugumaran (2008) performed classification of seven tree species using two sets of hyperspectral data from the summer and fall season, combined with ALS data.…”

Section: Tree Speciesmentioning

confidence: 99%

Accuracy of determining specific parameters of the urban forest using remote sensing

Ciesielski¹,

Stereńczak²

2019

iForest

View full text Add to dashboard Cite

This paper reviews the current state of knowledge in the field of urban forest inventory and specific tree parameters derived by remote sensing. The paper discusses the possibilities and limitations of using remote sensing to determine the following characteristics of individual trees acquired during the inventory: position (coordinates), tree height, breast height diameter, tree crown parameters (crown span, height of tree crown basis, crown projection surface), health condition, and tree species. A total of 543 papers published in scientific databases (Scopus ® and ScienceDirect ® ) from the year 2000 to December 2017 have been analyzed; 86 of them were used for the review. The most important outcomes are: (a) the integration of many datasets, in particular spectral data (aerial images and satellite imageries) and structural data (LIDAR), allows the most complex use of remote sensing data and helps to improve the accuracy of parameter estimations as well as the correct identification of tree species; (b) the highest precision of measurement is characteristic of TLS, while ALS data has the largest operating system; (c) remote sensing data applications are associated with a large number of sophisticated processing on very large datasets using often proprietary elaborations; (d) the use of remote sensing data makes it possible to determine the characteristics of urban vegetation at various levels of detail and at different scales. Citation: Ciesielski M, Sterenczak K (2019). Accuracy of determining specific parameters of the urban forest using remote sensing. iForest 12:

show abstract

Species-related single dead tree detection using multi-temporal ALS data and CIR imagery

Cited by 55 publications

References 42 publications

Classification of Tree Species and Standing Dead Trees by Fusing Uav-Based Lidar Data and Multispectral Imagery in the 3d Deep Neural Network Pointnet++

Classification of Tree Species and Standing Dead Trees by Fusing Uav-Based Lidar Data and Multispectral Imagery in the 3d Deep Neural Network Pointnet++

Urban Tree Health Classification Across Tree Species by Combining Airborne Laser Scanning and Imaging Spectroscopy

Accuracy of determining specific parameters of the urban forest using remote sensing

Contact Info

Product

Resources

About