Search

Convolutional neural networks (CNNs) are a powerful tool for pattern recognition and computer vision, but they do not scale well to higher-dimensional inputs, because of the associated memory demands for storing and manipulating high-dimensional tensors. This work starts from the observation that higher-dimensional data, like for example 3D voxel volumes, are sparsely populated. CNNs naturally lend themselves to densely sampled data, and sophisticated, massively parallel implementations are available. On the contrary, existing frameworks by and large lack the ability to efficiently process sparse data. Here, we introduce a suite of tools that exploit sparsity in both the feature maps and the filter weights of a CNN, and thereby allow for significantly lower memory footprints and computation times than the conventional dense framework, when processing data with a high degree of sparsity. Our scheme provides (i) an efficient GPU implementation of a convolution layer based on direct, sparse convolution, as well as sparse implementations of the ReLU and max-pooling layers; (ii) a filter step within the convolution layer, which we call attention, that prevents fill-in, i.e., the tendency of convolution to rapidly decrease sparsity, and guarantees an upper bound on the computational resources; and (iii) an adaptation of back-propagation that makes it possible to combine our approach with standard learning frameworks, while still benefitting from sparsity in the data as well as the model. [ABSTRACT FROM AUTHOR]

Wildfires often threaten natural and economic resources and human lives. Wildfire susceptibility assessments have become essential for efficient disaster management and increasing resilience. In this study, we assessed the forest fire susceptibility in Istanbul Province and Thrace Region, Türkiye using a well-known machine learning technique, Artificial Neural Networks (ANN). Benefiting from freely available Earth Observation datasets such as Sentinel-2 images, Tree Cover Density from European Union (EU) European Environment Agency (EEA) Copernicus Land Monitoring Service, Shuttle Radar Topography Mission (SRTM) data, etc., and a forest inventory with ignition locations recorded over a period of eight years, we utilized a total of 16 independent and one dependent variables. The variables can be categorized as anthropogenic, topographic, vegetation, and hydrological factors. A ratio of 1:2 was preferred for the fire/non-fire location samples. The results show that the ANN exhibited high prediction performance with Area Under the Receiver Operating Characteristic Curve (AUC) value and F-1 score of 0.94 and 0.80, respectively. Based on feature importance analyses, we found that a human-related factor, proximity to forest roads, was the most predictive input variable. The ANN model trained with openly available data (i.e., without forest database) also yielded a high F-1 score, but produced maps with fewer details. Our results confirm that data-driven machine learning methods are promising for regional forest fire susceptibility assessments and can be extended further for other regions by deriving similar parameters from freely available Earth Observation datasets. • Forest fire susceptibility map for Istanbul and Thrace Region, Türkiye was produced. • A data-driven approach was applied using a fire inventory between 2013 and 2021. • An overall accuracy of 88% obtained from high dimensional and quality features. • The use of local forest database is recommended for the modeling. • Human influence on fires was proven as forest roads was the most predictive variable. [ABSTRACT FROM AUTHOR]

This paper deals with semantic segmentation of high-resolution (aerial) images where a semantic class label is assigned to each pixel via supervised classification as a basis for automatic map generation. Recently, deep convolutional neural networks (CNNs) have shown impressive performance and have quickly become the de-facto standard for semantic segmentation, with the added benefit that task-specific feature design is no longer necessary. However, a major downside of deep learning methods is that they are extremely data hungry, thus aggravating the perennial bottleneck of supervised classification, to obtain enough annotated training data. On the other hand, it has been observed that they are rather robust against noise in the training labels. This opens up the intriguing possibility to avoid annotating huge amounts of training data, and instead train the classifier from existing legacy data or crowd-sourced maps that can exhibit high levels of noise. The question addressed in this paper is: can training with large-scale publicly available labels replace a substantial part of the manual labeling effort and still achieve sufficient performance? Such data will inevitably contain a significant portion of errors, but in return virtually unlimited quantities of it are available in larger parts of the world. We adapt a state-of-the-art CNN architecture for semantic segmentation of buildings and roads in aerial images, and compare its performance when using different training data sets, ranging from manually labeled pixel-accurate ground truth of the same city to automatic training data derived from OpenStreetMap data from distant locations. We report our results that indicate that satisfying performance can be obtained with significantly less manual annotation effort, by exploiting noisy large-scale training data. [ABSTRACT FROM PUBLISHER]

This paper presents a new 3D point cloud classification benchmark data set with over four billion manually labelled points, meant as input for data-hungry (deep) learning methods. We also discuss first submissions to the benchmark that use deep convolutional neural networks (CNNs) as a work horse, which already show remarkable performance improvements over state-of-the-art. CNNs have become the de-facto standard for many tasks in computer vision and machine learning like semantic segmentation or object detection in images, but have no yet led to a true breakthrough for 3D point cloud labelling tasks due to lack of training data. With the massive data set presented in this paper, we aim at closing this data gap to help unleash the full potential of deep learning methods for 3D labelling tasks. Our semantic3D.net data set consists of dense point clouds acquired with static terrestrial laser scanners. It contains 8 semantic classes and covers a wide range of urban outdoor scenes: churches, streets, railroad tracks, squares, villages, soccer fields and castles. We describe our labelling interface and show that our data set provides more dense and complete point clouds with much higher overall number of labelled points compared to those already available to the research community. We further provide baseline method descriptions and comparison between methods submitted to our online system. We hope semantic3D.net will pave the way for deep learning methods in 3D point cloud labelling to learn richer, more general 3D representations, and first submissions after only a few months indicate that this might indeed be the case. [ABSTRACT FROM AUTHOR]

Abstract: Research into the visual perception of human emotion has traditionally focused on the facial expression of emotions. Recently researchers have turned to the more challenging field of emotional body language, i.e. emotion expression through body pose and motion. In this work, we approach recognition of basic emotional categories from a computational perspective. In keeping with recent computational models of the visual cortex, we construct a biologically plausible hierarchy of neural detectors, which can discriminate seven basic emotional states from static views of associated body poses. The model is evaluated against human test subjects on a recent set of stimuli manufactured for research on emotional body language. [Copyright &y& Elsevier]

Sentinel-2 multi-spectral images collected over periods of several months were used to estimate vegetation height for Gabon and Switzerland. A deep convolutional neural network (CNN) was trained to extract suitable spectral and textural features from reflectance images and to regress per-pixel vegetation height. In Gabon, reference heights for training and validation were derived from airborne LiDAR measurements. In Switzerland, reference heights were taken from an existing canopy height model derived via photogrammetric surface reconstruction. The resulting maps have a mean absolute error (MAE) of 1.7 m in Switzerland and 4.3 m in Gabon (a root mean square error (RMSE) of 3.4 m and 5.6 m, respectively), and correctly estimate vegetation heights up to >50 m. They also show good qualitative agreement with existing vegetation height maps. Our work demonstrates that, given a moderate amount of reference data (i.e., 2000 km2 in Gabon and ≈5800 km2 in Switzerland), high-resolution vegetation height maps with 10 m ground sampling distance (GSD) can be derived at country scale from Sentinel-2 imagery. Unlabelled Image • Vegetation height at 10 m ground sampling distance is regressed from Sentinel-2 • Country-wide maps are computed for Switzerland and Gabon • Mean absolute error (MAE) of 1.7 m in Switzerland and 4.3 m in Gabon • The deep convolutional neural network correctly predicts vegetation heights up to 50 m [ABSTRACT FROM AUTHOR]

Up-to-date catalogs of the urban tree population are of importance for municipalities to monitor and improve quality of life in cities. Despite much research on automation of tree mapping, mainly relying on dedicated airborne LiDAR or hyperspectral campaigns, tree detection and species recognition is still mostly done manually in practice. We present a fully automated tree detection and species recognition pipeline that can process thousands of trees within a few hours using publicly available aerial and street view images of Google Maps TM . These data provide rich information from different viewpoints and at different scales from global tree shapes to bark textures. Our work-flow is built around a supervised classification that automatically learns the most discriminative features from thousands of trees and corresponding, publicly available tree inventory data. In addition, we introduce a change tracker that recognizes changes of individual trees at city-scale, which is essential to keep an urban tree inventory up-to-date. The system takes street-level images of the same tree location at two different times and classifies the type of change (e.g., tree has been removed). Drawing on recent advances in computer vision and machine learning, we apply convolutional neural networks (CNN) for all classification tasks. We propose the following pipeline: download all available panoramas and overhead images of an area of interest, detect trees per image and combine multi-view detections in a probabilistic framework, adding prior knowledge; recognize fine-grained species of detected trees. In a later, separate module, track trees over time, detect significant changes and classify the type of change. We believe this is the first work to exploit publicly available image data for city-scale street tree detection, species recognition and change tracking, exhaustively over several square kilometers, respectively many thousands of trees. Experiments in the city of Pasadena, California, USA show that we can detect >70% of the street trees, assign correct species to >80% for 40 different species, and correctly detect and classify changes in >90% of the cases. [ABSTRACT FROM AUTHOR]