Swarm robot systems are an important application of autonomous unmanned surface vehicles on water surfaces.For monitoring natural environments and conducting security activities within a certain range using a surface ...Swarm robot systems are an important application of autonomous unmanned surface vehicles on water surfaces.For monitoring natural environments and conducting security activities within a certain range using a surface vehicle,the swarm robot system is more efficient than the operation of a single object as the former can reduce cost and save time.It is necessary to detect adjacent surface obstacles robustly to operate a cluster of unmanned surface vehicles.For this purpose,a LiDAR(light detection and ranging)sensor is used as it can simultaneously obtain 3D information for all directions,relatively robustly and accurately,irrespective of the surrounding environmental conditions.Although the GPS(global-positioning-system)error range exists,obtaining measurements of the surface-vessel position can still ensure stability during platoon maneuvering.In this study,a three-layer convolutional neural network is applied to classify types of surface vehicles.The aim of this approach is to redefine the sparse 3D point cloud data as 2D image data with a connotative meaning and subsequently utilize this transformed data for object classification purposes.Hence,we have proposed a descriptor that converts the 3D point cloud data into 2D image data.To use this descriptor effectively,it is necessary to perform a clustering operation that separates the point clouds for each object.We developed voxel-based clustering for the point cloud clustering.Furthermore,using the descriptor,3D point cloud data can be converted into a 2D feature image,and the converted 2D image is provided as an input value to the network.We intend to verify the validity of the proposed 3D point cloud feature descriptor by using experimental data in the simulator.Furthermore,we explore the feasibility of real-time object classification within this framework.展开更多
Background: Remote sensing-based mapping of forest Ecosystem Service(ES) indicators has become increasingly popular. The resulting maps may enable to spatially assess the provisioning potential of ESs and prioritize t...Background: Remote sensing-based mapping of forest Ecosystem Service(ES) indicators has become increasingly popular. The resulting maps may enable to spatially assess the provisioning potential of ESs and prioritize the land use in subsequent decision analyses. However, the mapping is often based on readily available data, such as land cover maps and other publicly available databases, and ignoring the related uncertainties.Methods: This study tested the potential to improve the robustness of the decisions by means of local model fitting and uncertainty analysis. The quality of forest land use prioritization was evaluated under two different decision support models: either using the developed models deterministically or in corporation with the uncertainties of the models.Results: Prediction models based on Airborne Laser Scanning(ALS) data explained the variation in proxies of the suitability of forest plots for maintaining biodiversity, producing timber, storing carbon, or providing recreational uses(berry picking and visual amenity) with RMSEs of 15%–30%, depending on the ES. The RMSEs of the ALS-based predictions were 47%–97%of those derived from forest resource maps with a similar resolution. Due to applying a similar field calibration step on both of the data sources, the difference can be attributed to the better ability of ALS to explain the variation in the ES proxies.Conclusions: Despite the different accuracies, proxy values predicted by both the data sources could be used for a pixel-based prioritization of land use at a resolution of 250 m~2, i.e., in a considerably more detailed scale than required by current operational forest management. The uncertainty analysis indicated that maps of the ES provisioning potential should be prepared separately based on expected and extreme outcomes of the ES proxy models to fully describe the production possibilities of the landscape under the uncertainties in the models.展开更多
This paper presents a method to reconstruct 3-D models of trees from terrestrial laser scan(TLS)point clouds.This method uses the weighted locally optimal projection(WLOP)and the AdTree method to reconstruct detailed ...This paper presents a method to reconstruct 3-D models of trees from terrestrial laser scan(TLS)point clouds.This method uses the weighted locally optimal projection(WLOP)and the AdTree method to reconstruct detailed 3-D tree models.To improve its representation accuracy,the WLOP algorithm is introduced to consolidate the point cloud.Its reconstruction accuracy is tested using a dataset of ten trees,and the one-sided Hausdorff distances between the input point clouds and the resulting 3-D models are measured.The experimental results show that the optimal projection modeling method has an average one-sided Hausdorff distance(mean)lower by 30.74%and 6.43%compared with AdTree and AdQSM methods,respectively.Furthermore,it has an average one-sided Hausdorff distance(RMS)lower by 29.95%and 12.28%compared with AdTree and AdQSM methods.Results show that the 3-D model generated fits closely to the input point cloud data and ensures a high geometrical accuracy.展开更多
With the development of sensors,the application of multi-source remote sensing data has been widely concerned.Since hyperspectral image(HSI)contains rich spectral information while light detection and ranging(LiDAR)da...With the development of sensors,the application of multi-source remote sensing data has been widely concerned.Since hyperspectral image(HSI)contains rich spectral information while light detection and ranging(LiDAR)data contains elevation information,joint use of them for ground object classification can yield positive results,especially by building deep networks.Fortu-nately,multi-scale deep networks allow to expand the receptive fields of convolution without causing the computational and training problems associated with simply adding more network layers.In this work,a multi-scale feature fusion network is proposed for the joint classification of HSI and LiDAR data.First,we design a multi-scale spatial feature extraction module with cross-channel connections,by which spatial information of HSI data and elevation information of LiDAR data are extracted and fused.In addition,a multi-scale spectral feature extraction module is employed to extract the multi-scale spectral features of HSI data.Finally,joint multi-scale features are obtained by weighting and concatenation operations and then fed into the classifier.To verify the effective-ness of the proposed network,experiments are carried out on the MUUFL Gulfport and Trento datasets.The experimental results demonstrate that the classification performance of the proposed method is superior to that of other state-of-the-art methods.展开更多
Background: The distribution of forest vegetation within urban environments is critically important as it influences urban environmental conditions and the energy exchange through the absorption of solar radiation and...Background: The distribution of forest vegetation within urban environments is critically important as it influences urban environmental conditions and the energy exchange through the absorption of solar radiation and modulation of evapotranspiration. It also plays an important role filtering urban water systems and reducing storm water runoff.Methods: We investigate the capacity of ALS data to individually detect, map and characterize large(taller than15 m) trees within the City of Vancouver. Large trees are critical for the function and character of Vancouver’s urban forest. We used an object-based approach for individual tree detection and segmentation to determine tree locations(position of the stem), to delineate the shape of the crowns and to categorize the latter either as coniferous or deciduous.Results: Results indicate a detection rate of 76.6% for trees > 15 m with a positioning error of 2.11 m(stem location). Extracted tree heights possessed a RMSE of 2.60 m and a bias of-1.87 m, whereas crown diameter was derived with a RMSE of 3.85 m and a bias of-2.06 m. Missed trees are principally a result of undetected treetops occurring in dense, overlapping canopies with more accurate detection and delineation of trees in open areas.Conclusion: By identifying key structural trees across Vancouver’s urban forests, we can better understand their role in providing ecosystem goods and services for city residents.展开更多
Background： Tree species recognition is the main bottleneck in remote sensing based inventories aiming to produce an input for species-specific growth and yield models. We hypothesized that a stratification of the ta...Background： Tree species recognition is the main bottleneck in remote sensing based inventories aiming to produce an input for species-specific growth and yield models. We hypothesized that a stratification of the target data according to the dominant species could improve the subsequent predictions of species-specific attributes in particular in study areas strongly dominated by certain species. Methods： We tested this hypothesis and an operational potential to improve the predictions of timber volumes, stratified to Scots pine, Norway spruce and deciduous trees, in a conifer forest dominated by the pine species. We derived predictor features from airborne laser scanning （ALS） data and used Most Similar Neighbor （MSN） and Seemingly Unrelated Regression （SUR） as examples of non-parametric and parametric prediction methods, respectively Results： The relationships between the ALS features and the volumes of the aforementioned species were considerably different depending on the dominant species. Incorporating the observed dominant species inthe predictions improved the root mean squared errors by 13.3-16.4 % and 12.6-28.9 % based on MSN and SUR, respectively, depending on the species. Predicting the dominant species based on a linear discriminant analysis had an overall accuracy of only 76 % at best, which degraded the accuracies of the predicted volumes. Consequently, the predictions that did not consider the dominant species were more accurate than those refined with the predicted species. The MSN method gave slightly better results than models fitted with SUR. Conclusions： According to our results, incorporating information on the dominant species has a clear potential to improve the subsequent predictions of species-specific forest attributes. Determining the dominant species based solely on ALS data is deemed challenging, but important in particular in areas where the species composition is otherwise seemingly homogeneous except being dominated by certain species.展开更多
Numerous studies have been performed to better understand the behavior of wake vortices with regards to aircraft characteristics and weather conditionsover the pastten years. These studies have led to the development ...Numerous studies have been performed to better understand the behavior of wake vortices with regards to aircraft characteristics and weather conditionsover the pastten years. These studies have led to the development of the aircraft RECATegorization(RECAT) programs in Europe and in USA. Its phase one focused on redefining distance separation matrix with six static aircraft wake turbulence categories instead of three with the current International Civil Aviation Organization(ICAO) regulations. In Europe, the RECAT-EU regulation is now entering under operational implementation atseveral key airports. As proven by several research projects in the past, LIght Detection And Ranging(LIDAR) sensors are considered as the ground truth wake vortex measurements for assessing the safety impact of a new wake turbulence regulation at an airport in quantifying the risks given the local specificities. LIDAR's can also be used to perform risk monitoring after the implementation. In this paper, the principle to measure wake vortices with scanning coherent Doppler LIDARs is described as well as its dedicated post-processing. Finally the use of WINDCUBELIDAR based solution for supporting the implementation of new wake turbulenceregulation is described along with satisfyingresults that have permitted the monitoring of the wake vortex encounter risk after the implementation of a new wake turbulence regulation.展开更多
The influence of laser beam divergence angle on the positioning accuracy of scanning airborne light detection and ranging （LIDAR） is analyzed and simulated. Based on the data process and positioning principle of air...The influence of laser beam divergence angle on the positioning accuracy of scanning airborne light detection and ranging （LIDAR） is analyzed and simulated. Based on the data process and positioning principle of airborne LIDAR, the errors from pulse broadening induced by laser beam di vergence angle are modeled and qualitatively analyzed for different terrain surfaces. Simulated results of positioning errors and suggestions to reduce them are given for the flat surface, the downhill of slope surface, and the uphill surface.展开更多
基金supported by the Future Challenge Program through the Agency for Defense Development funded by the Defense Acquisition Program Administration (No.UC200015RD)。
文摘Swarm robot systems are an important application of autonomous unmanned surface vehicles on water surfaces.For monitoring natural environments and conducting security activities within a certain range using a surface vehicle,the swarm robot system is more efficient than the operation of a single object as the former can reduce cost and save time.It is necessary to detect adjacent surface obstacles robustly to operate a cluster of unmanned surface vehicles.For this purpose,a LiDAR(light detection and ranging)sensor is used as it can simultaneously obtain 3D information for all directions,relatively robustly and accurately,irrespective of the surrounding environmental conditions.Although the GPS(global-positioning-system)error range exists,obtaining measurements of the surface-vessel position can still ensure stability during platoon maneuvering.In this study,a three-layer convolutional neural network is applied to classify types of surface vehicles.The aim of this approach is to redefine the sparse 3D point cloud data as 2D image data with a connotative meaning and subsequently utilize this transformed data for object classification purposes.Hence,we have proposed a descriptor that converts the 3D point cloud data into 2D image data.To use this descriptor effectively,it is necessary to perform a clustering operation that separates the point clouds for each object.We developed voxel-based clustering for the point cloud clustering.Furthermore,using the descriptor,3D point cloud data can be converted into a 2D feature image,and the converted 2D image is provided as an input value to the network.We intend to verify the validity of the proposed 3D point cloud feature descriptor by using experimental data in the simulator.Furthermore,we explore the feasibility of real-time object classification within this framework.
基金originally supported by the Research Funds of University of Helsinki
文摘Background: Remote sensing-based mapping of forest Ecosystem Service(ES) indicators has become increasingly popular. The resulting maps may enable to spatially assess the provisioning potential of ESs and prioritize the land use in subsequent decision analyses. However, the mapping is often based on readily available data, such as land cover maps and other publicly available databases, and ignoring the related uncertainties.Methods: This study tested the potential to improve the robustness of the decisions by means of local model fitting and uncertainty analysis. The quality of forest land use prioritization was evaluated under two different decision support models: either using the developed models deterministically or in corporation with the uncertainties of the models.Results: Prediction models based on Airborne Laser Scanning(ALS) data explained the variation in proxies of the suitability of forest plots for maintaining biodiversity, producing timber, storing carbon, or providing recreational uses(berry picking and visual amenity) with RMSEs of 15%–30%, depending on the ES. The RMSEs of the ALS-based predictions were 47%–97%of those derived from forest resource maps with a similar resolution. Due to applying a similar field calibration step on both of the data sources, the difference can be attributed to the better ability of ALS to explain the variation in the ES proxies.Conclusions: Despite the different accuracies, proxy values predicted by both the data sources could be used for a pixel-based prioritization of land use at a resolution of 250 m~2, i.e., in a considerably more detailed scale than required by current operational forest management. The uncertainty analysis indicated that maps of the ES provisioning potential should be prepared separately based on expected and extreme outcomes of the ES proxy models to fully describe the production possibilities of the landscape under the uncertainties in the models.
基金supported in part by the National Natural Science Foundation of China(Nos.42271343,42177387)the Fund of State Key Laboratory of Remote Sensing Information and Image Analysis Technology of Beijing Research Institute of Uranium Geology under(No.6142A010403)
文摘This paper presents a method to reconstruct 3-D models of trees from terrestrial laser scan(TLS)point clouds.This method uses the weighted locally optimal projection(WLOP)and the AdTree method to reconstruct detailed 3-D tree models.To improve its representation accuracy,the WLOP algorithm is introduced to consolidate the point cloud.Its reconstruction accuracy is tested using a dataset of ten trees,and the one-sided Hausdorff distances between the input point clouds and the resulting 3-D models are measured.The experimental results show that the optimal projection modeling method has an average one-sided Hausdorff distance(mean)lower by 30.74%and 6.43%compared with AdTree and AdQSM methods,respectively.Furthermore,it has an average one-sided Hausdorff distance(RMS)lower by 29.95%and 12.28%compared with AdTree and AdQSM methods.Results show that the 3-D model generated fits closely to the input point cloud data and ensures a high geometrical accuracy.
基金supported by the National Key Research and Development Project(No.2020YFC1512000)the General Projects of Key R&D Programs in Shaanxi Province(No.2020GY-060)Xi’an Science&Technology Project(No.2020KJRC 0126)。
文摘With the development of sensors,the application of multi-source remote sensing data has been widely concerned.Since hyperspectral image(HSI)contains rich spectral information while light detection and ranging(LiDAR)data contains elevation information,joint use of them for ground object classification can yield positive results,especially by building deep networks.Fortu-nately,multi-scale deep networks allow to expand the receptive fields of convolution without causing the computational and training problems associated with simply adding more network layers.In this work,a multi-scale feature fusion network is proposed for the joint classification of HSI and LiDAR data.First,we design a multi-scale spatial feature extraction module with cross-channel connections,by which spatial information of HSI data and elevation information of LiDAR data are extracted and fused.In addition,a multi-scale spectral feature extraction module is employed to extract the multi-scale spectral features of HSI data.Finally,joint multi-scale features are obtained by weighting and concatenation operations and then fed into the classifier.To verify the effective-ness of the proposed network,experiments are carried out on the MUUFL Gulfport and Trento datasets.The experimental results demonstrate that the classification performance of the proposed method is superior to that of other state-of-the-art methods.
文摘Background: The distribution of forest vegetation within urban environments is critically important as it influences urban environmental conditions and the energy exchange through the absorption of solar radiation and modulation of evapotranspiration. It also plays an important role filtering urban water systems and reducing storm water runoff.Methods: We investigate the capacity of ALS data to individually detect, map and characterize large(taller than15 m) trees within the City of Vancouver. Large trees are critical for the function and character of Vancouver’s urban forest. We used an object-based approach for individual tree detection and segmentation to determine tree locations(position of the stem), to delineate the shape of the crowns and to categorize the latter either as coniferous or deciduous.Results: Results indicate a detection rate of 76.6% for trees > 15 m with a positioning error of 2.11 m(stem location). Extracted tree heights possessed a RMSE of 2.60 m and a bias of-1.87 m, whereas crown diameter was derived with a RMSE of 3.85 m and a bias of-2.06 m. Missed trees are principally a result of undetected treetops occurring in dense, overlapping canopies with more accurate detection and delineation of trees in open areas.Conclusion: By identifying key structural trees across Vancouver’s urban forests, we can better understand their role in providing ecosystem goods and services for city residents.
基金financed by the Finnish Funding Agency for Innovation(Tekes) and its business and research partners
文摘Background： Tree species recognition is the main bottleneck in remote sensing based inventories aiming to produce an input for species-specific growth and yield models. We hypothesized that a stratification of the target data according to the dominant species could improve the subsequent predictions of species-specific attributes in particular in study areas strongly dominated by certain species. Methods： We tested this hypothesis and an operational potential to improve the predictions of timber volumes, stratified to Scots pine, Norway spruce and deciduous trees, in a conifer forest dominated by the pine species. We derived predictor features from airborne laser scanning （ALS） data and used Most Similar Neighbor （MSN） and Seemingly Unrelated Regression （SUR） as examples of non-parametric and parametric prediction methods, respectively Results： The relationships between the ALS features and the volumes of the aforementioned species were considerably different depending on the dominant species. Incorporating the observed dominant species inthe predictions improved the root mean squared errors by 13.3-16.4 % and 12.6-28.9 % based on MSN and SUR, respectively, depending on the species. Predicting the dominant species based on a linear discriminant analysis had an overall accuracy of only 76 % at best, which degraded the accuracies of the predicted volumes. Consequently, the predictions that did not consider the dominant species were more accurate than those refined with the predicted species. The MSN method gave slightly better results than models fitted with SUR. Conclusions： According to our results, incorporating information on the dominant species has a clear potential to improve the subsequent predictions of species-specific forest attributes. Determining the dominant species based solely on ALS data is deemed challenging, but important in particular in areas where the species composition is otherwise seemingly homogeneous except being dominated by certain species.
文摘Numerous studies have been performed to better understand the behavior of wake vortices with regards to aircraft characteristics and weather conditionsover the pastten years. These studies have led to the development of the aircraft RECATegorization(RECAT) programs in Europe and in USA. Its phase one focused on redefining distance separation matrix with six static aircraft wake turbulence categories instead of three with the current International Civil Aviation Organization(ICAO) regulations. In Europe, the RECAT-EU regulation is now entering under operational implementation atseveral key airports. As proven by several research projects in the past, LIght Detection And Ranging(LIDAR) sensors are considered as the ground truth wake vortex measurements for assessing the safety impact of a new wake turbulence regulation at an airport in quantifying the risks given the local specificities. LIDAR's can also be used to perform risk monitoring after the implementation. In this paper, the principle to measure wake vortices with scanning coherent Doppler LIDARs is described as well as its dedicated post-processing. Finally the use of WINDCUBELIDAR based solution for supporting the implementation of new wake turbulenceregulation is described along with satisfyingresults that have permitted the monitoring of the wake vortex encounter risk after the implementation of a new wake turbulence regulation.
基金Supported by the National Basic Research Program of China("973"Program)(2009CB72400401A)
文摘The influence of laser beam divergence angle on the positioning accuracy of scanning airborne light detection and ranging （LIDAR） is analyzed and simulated. Based on the data process and positioning principle of airborne LIDAR, the errors from pulse broadening induced by laser beam di vergence angle are modeled and qualitatively analyzed for different terrain surfaces. Simulated results of positioning errors and suggestions to reduce them are given for the flat surface, the downhill of slope surface, and the uphill surface.
