Classification of Land-Water Continuum Habitats Using Exclusively Airborne Topobathymetric Lidar Green Waveforms and Infrared Intensity Point Clouds

In this paper, we present the idea of Self Supervised learning on the Shape Completion and Classification of point clouds. Most 3D shape completion pipelines utilize autoencoders to extract features from point clouds used in downstream tasks such as Classification, Segmentation, Detection, and other related applications. Our idea is to add Contrastive Learning into Auto-Encoders to learn both global and local feature representations of point clouds. We use a combination of Triplet Loss and Chamfer distance to learn global and local feature representations. To evaluate the performance of embeddings for Classification, we utilize the PointNet classifier. We also extend the number of classes to evaluate our model from 4 to 10 to show the generalization ability of learned features. Based on our results, embedding generated from the Contrastive autoencoder enhances Shape Completion and Classification performance from 84.2% to 84.9% of point clouds achieving the state-of-the-art results with 10 classes.

Download Full-text

Land/Water Discrimination And Land Cover Classification Using Multispectral Airborne Lidar Data

10.32920/ryerson.14645793 ◽

2021 ◽

Author(s):

Salem Wagih Salem Morsy

Keyword(s):

Land Cover ◽

Urban Areas ◽

Region Growing ◽

Point Clouds ◽

Land Cover Classification ◽

Lidar Data ◽

Coastal Zones ◽

532 Nm ◽

Land Water

Multispectral airborne Light Detection And Ranging (LiDAR) systems are currently available. Optech Titan is an example of these systems, which acquires LiDAR point clouds at three independent wavelengths (1550, 1064 and 532 nm) from Earth’s surface. This dissertation aims to use the radiometric information (i.e., intensity) of the Optech Titan LiDAR data along with the geometric information (e.g., height) for land/water discrimination in coastal zones and land cover classification of urban areas. A set of point features based on elevation, intensity, and geometry was extracted and evaluated for land/water discrimination in coastal zones. In addition, an automated land/water discrimination approach based on seeded region growing algorithm was presented. Two data subsets were tested at Lake Ontario and Tobermory Harbour in Ontario, Canada. The elevation and geometry-based features achieved average overall accuracies of 72.8% - 83.3% and 69.9% -74.4%, respectively, while the intensity-based features achieved an average overall accuracy of 59.0% - 63.4%. The region growing method achieved an average overall accuracy of more than 99%, and the automation of this method is restricted by having double returns from water bodies at the 532 nm wavelength. A hierarchal point-based classification approach was presented for land cover classification of urban areas. The collected point clouds at the three wavelengths were first merged and three intensity values were estimated for each LiDAR point, followed by three-level classification approach. First, a ground filtering method was applied to separate non-ground from ground points. Second, three normalized difference vegetation indices (NDVIs) were computed, followed by NDVIs’ histograms construction. A multivariate Gaussian decomposition (MVGD) was then used to divide those histograms into buildings or trees from non-ground and roads or grass from ground points. Third, classes such as power lines, swimming pools and different types of trees were labeled based on their spectral characteristics. Three data subsets were tested representing different complexity of urban areas in Oshawa, Ontario, Canada. It is shown that the presented approach has achieved an overall accuracy up to 93.0%, which increased to more than 99% by considering the spatial coherence of the LiDAR point clouds.

Download Full-text

Land/Water Discrimination And Land Cover Classification Using Multispectral Airborne Lidar Data

10.32920/ryerson.14645793.v1 ◽

2021 ◽

Author(s):

Salem Wagih Salem Morsy

Keyword(s):

Land Cover ◽

Urban Areas ◽

Region Growing ◽

Point Clouds ◽

Land Cover Classification ◽

Lidar Data ◽

Coastal Zones ◽

532 Nm ◽

Land Water

Multispectral airborne Light Detection And Ranging (LiDAR) systems are currently available. Optech Titan is an example of these systems, which acquires LiDAR point clouds at three independent wavelengths (1550, 1064 and 532 nm) from Earth’s surface. This dissertation aims to use the radiometric information (i.e., intensity) of the Optech Titan LiDAR data along with the geometric information (e.g., height) for land/water discrimination in coastal zones and land cover classification of urban areas. A set of point features based on elevation, intensity, and geometry was extracted and evaluated for land/water discrimination in coastal zones. In addition, an automated land/water discrimination approach based on seeded region growing algorithm was presented. Two data subsets were tested at Lake Ontario and Tobermory Harbour in Ontario, Canada. The elevation and geometry-based features achieved average overall accuracies of 72.8% - 83.3% and 69.9% -74.4%, respectively, while the intensity-based features achieved an average overall accuracy of 59.0% - 63.4%. The region growing method achieved an average overall accuracy of more than 99%, and the automation of this method is restricted by having double returns from water bodies at the 532 nm wavelength. A hierarchal point-based classification approach was presented for land cover classification of urban areas. The collected point clouds at the three wavelengths were first merged and three intensity values were estimated for each LiDAR point, followed by three-level classification approach. First, a ground filtering method was applied to separate non-ground from ground points. Second, three normalized difference vegetation indices (NDVIs) were computed, followed by NDVIs’ histograms construction. A multivariate Gaussian decomposition (MVGD) was then used to divide those histograms into buildings or trees from non-ground and roads or grass from ground points. Third, classes such as power lines, swimming pools and different types of trees were labeled based on their spectral characteristics. Three data subsets were tested representing different complexity of urban areas in Oshawa, Ontario, Canada. It is shown that the presented approach has achieved an overall accuracy up to 93.0%, which increased to more than 99% by considering the spatial coherence of the LiDAR point clouds.

Download Full-text

Humans and the Environment

10.1093/oso/9780199590292.001.0001 ◽

2013 ◽

Keyword(s):

Spatial Scales ◽

Empirical Studies ◽

Human Action ◽

Cultural Practice ◽

Environmental Archaeology ◽

Archaeological Data ◽

Temporal And Spatial ◽

Global And Local ◽

The Relationship ◽

The Way

The environment has always been a central concept for archaeologists and, although it has been conceived in many ways, its role in archaeological explanation has fluctuated from a mere backdrop to human action, to a primary factor in the understanding of society and social change. Archaeology also has a unique position as its base of interest places it temporally between geological and ethnographic timescales, spatially between global and local dimensions, and epistemologically between empirical studies of environmental change and more heuristic studies of cultural practice. Drawing on data from across the globe at a variety of temporal and spatial scales, this volume resituates the way in which archaeologists use and apply the concept of the environment. Each chapter critically explores the potential for archaeological data and practice to contribute to modern environmental issues, including problems of climate change and environmental degradation. Overall the volume covers four basic themes: archaeological approaches to the way in which both scientists and locals conceive of the relationship between humans and their environment, applied environmental archaeology, the archaeology of disaster, and new interdisciplinary directions.The volume will be of interest to students and established archaeologists, as well as practitioners from a range of applied disciplines.

Download Full-text

Disturbance Analysis in the Classification of Objects Obtained from Urban LiDAR Point Clouds with Convolutional Neural Networks

Remote Sensing ◽

10.3390/rs13112135 ◽

2021 ◽

Vol 13 (11) ◽

pp. 2135

Author(s):

Jesús Balado ◽

Pedro Arias ◽

Henrique Lorenzo ◽

Adrián Meijide-Rodríguez

Keyword(s):

Laser Scanning ◽

Ambient Noise ◽

Point Clouds ◽

Density Variation ◽

Density Reduction ◽

Manual Intervention ◽

Point Density ◽

Disturbance Analysis ◽

Street Furniture

Mobile Laser Scanning (MLS) systems have proven their usefulness in the rapid and accurate acquisition of the urban environment. From the generated point clouds, street furniture can be extracted and classified without manual intervention. However, this process of acquisition and classification is not error-free, caused mainly by disturbances. This paper analyses the effect of three disturbances (point density variation, ambient noise, and occlusions) on the classification of urban objects in point clouds. From point clouds acquired in real case studies, synthetic disturbances are generated and added. The point density reduction is generated by downsampling in a voxel-wise distribution. The ambient noise is generated as random points within the bounding box of the object, and the occlusion is generated by eliminating points contained in a sphere. Samples with disturbances are classified by a pre-trained Convolutional Neural Network (CNN). The results showed different behaviours for each disturbance: density reduction affected objects depending on the object shape and dimensions, ambient noise depending on the volume of the object, while occlusions depended on their size and location. Finally, the CNN was re-trained with a percentage of synthetic samples with disturbances. An improvement in the performance of 10–40% was reported except for occlusions with a radius larger than 1 m.

Download Full-text

Semi-automated classification of colonial Microcystis by FlowCAM imaging flow cytometry in mesocosm experiment reveals high heterogeneity during seasonal bloom

Scientific Reports ◽

10.1038/s41598-021-88661-2 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Yersultan Mirasbekov ◽

Adina Zhumakhanova ◽

Almira Zhantuyakova ◽

Kuanysh Sarkytbayev ◽

Dmitry V. Malashenkov ◽

...

Keyword(s):

Machine Learning ◽

Flow Cytometry ◽

Spatial Resolution ◽

Mesocosm Experiment ◽

Imaging Flow Cytometry ◽

Leibler Divergence ◽

Temporal And Spatial ◽

High Level ◽

Training Sets

AbstractA machine learning approach was employed to detect and quantify Microcystis colonial morphospecies using FlowCAM-based imaging flow cytometry. The system was trained and tested using samples from a long-term mesocosm experiment (LMWE, Central Jutland, Denmark). The statistical validation of the classification approaches was performed using Hellinger distances, Bray–Curtis dissimilarity, and Kullback–Leibler divergence. The semi-automatic classification based on well-balanced training sets from Microcystis seasonal bloom provided a high level of intergeneric accuracy (96–100%) but relatively low intrageneric accuracy (67–78%). Our results provide a proof-of-concept of how machine learning approaches can be applied to analyze the colonial microalgae. This approach allowed to evaluate Microcystis seasonal bloom in individual mesocosms with high level of temporal and spatial resolution. The observation that some Microcystis morphotypes completely disappeared and re-appeared along the mesocosm experiment timeline supports the hypothesis of the main transition pathways of colonial Microcystis morphoforms. We demonstrated that significant changes in the training sets with colonial images required for accurate classification of Microcystis spp. from time points differed by only two weeks due to Microcystis high phenotypic heterogeneity during the bloom. We conclude that automatic methods not only allow a performance level of human taxonomist, and thus be a valuable time-saving tool in the routine-like identification of colonial phytoplankton taxa, but also can be applied to increase temporal and spatial resolution of the study.

Download Full-text

An Inverse Node Graph-Based Method for the Urban Scene Segmentation of 3D Point Clouds

Remote Sensing ◽

10.3390/rs13153021 ◽

2021 ◽

Vol 13 (15) ◽

pp. 3021

Author(s):

Bufan Zhao ◽

Xianghong Hua ◽

Kegen Yu ◽

Xiaoxing He ◽

Weixing Xue ◽

...

Keyword(s):

Semantic Segmentation ◽

Point Clouds ◽

Intelligent Vehicles ◽

Critical Data ◽

Multi Scale ◽

3D Point Clouds ◽

Cluster Optimization ◽

Urban Scene ◽

Processing Steps

Urban object segmentation and classification tasks are critical data processing steps in scene understanding, intelligent vehicles and 3D high-precision maps. Semantic segmentation of 3D point clouds is the foundational step in object recognition. To identify the intersecting objects and improve the accuracy of classification, this paper proposes a segment-based classification method for 3D point clouds. This method firstly divides points into multi-scale supervoxels and groups them by proposed inverse node graph (IN-Graph) construction, which does not need to define prior information about the node, it divides supervoxels by judging the connection state of edges between them. This method reaches minimum global energy by graph cutting, obtains the structural segments as completely as possible, and retains boundaries at the same time. Then, the random forest classifier is utilized for supervised classification. To deal with the mislabeling of scattered fragments, higher-order CRF with small-label cluster optimization is proposed to refine the classification results. Experiments were carried out on mobile laser scan (MLS) point dataset and terrestrial laser scan (TLS) points dataset, and the results show that overall accuracies of 97.57% and 96.39% were obtained in the two datasets. The boundaries of objects were retained well, and the method achieved a good result in the classification of cars and motorcycles. More experimental analyses have verified the advantages of the proposed method and proved the practicability and versatility of the method.

Download Full-text