Non-linear spectral unmixing of hyperspectral data using Modified PPNMM
Spectral unmixing is one of the unique advantages of hyperspectral images to map the type of species. Such images contain a high spectral resolution making it a classical problem of signal processing at each pixel, which is supposedly formed by the ...
Ankur Dixit, Shefali Agarwal
doaj +1 more source
PEDESTRIAN DETECTION AND TRACKING IN SPARSE MLS POINT CLOUDS USING A NEURAL NETWORK AND VOTING-BASED APPROACH [PDF]
This paper presents and extends an approach for the detection of pedestrians in unstructured point clouds resulting from single MLS (mobile laser scanning) scans. The approach is based on a neural network and a subsequent voting process.
B. Borgmann +4 more
doaj +1 more source
ReS2tAC—UAV-Borne Real-Time SGM Stereo Optimized for Embedded ARM and CUDA Devices
With the emergence of low-cost robotic systems, such as unmanned aerial vehicle, the importance of embedded high-performance image processing has increased.
Boitumelo Ruf +4 more
doaj +1 more source
Minimax Learning for Remote Prediction [PDF]
The classical problem of supervised learning is to infer an accurate predictor of a target variable $Y$ from a measured variable $X$ by using a finite number of labeled training samples. Motivated by the increasingly distributed nature of data and decision making, in this paper we consider a variation of this classical problem in which the prediction ...
Cheuk Ting Li +3 more
openaire +2 more sources
Despite high hopes that schools are institutions of integrity and are properly governed, very few have demonstrated this with distinction. With this article we argue that good governance depends on the partnership between schools and parents in times of ...
B.A. Ntuli, D.W. Mncube, G.M. Mkhasibe
doaj +1 more source
Understanding Education Workers’ Stressors after Lockdowns in Ontario, Canada: A Qualitative Study
Understanding the experiences and stressors of education workers is critical for making improvements and planning for future emergency situations. Province-specific studies offer valuable information to understand the stressors of returning to the ...
Frances Serrano +5 more
doaj +1 more source
TRACE: Instance-Level Open-Vocabulary Inventory Generation for 3D Forensic Evidence Reconstruction [PDF]
State of the art crime scene documentation not only relies on visually and geometrically faithful 3D reconstruction, but also structured access to potentially relevant evidentiary objects.
F. Eichinger +5 more
doaj +1 more source
The impact of students’ attitudes about distance learning on their creativity
Introduction. Since 2020, education systems around the world had to shift from traditional classroom-based methods of teaching and learning to different types of remote or distance learning.
Kateryna Glubochenko
doaj +1 more source
Unsupervised feature learning in remote sensing [PDF]
The need for labeled data is among the most common and well-known practical obstacles to deploying deep learning algorithms to solve real-world problems. The current generation of learning algorithms requires a large volume of data labeled according to a static and pre-defined schema.
Aaron A. Reite +5 more
openaire +2 more sources
The Potential of Copernicus Satellites for Disaster Response: Retrieving Building Damage from Sentinel-1 and Sentinel-2 [PDF]
Natural disasters demand rapid damage assessment to guide humanitarian response. Here, we investigate whether medium-resolution Earth observation images from the Copernicus program can support building damage assessment, complementing very-high ...
O. Dietrich +7 more
doaj +1 more source

