Related papers: An Orientation Selective Neural Network and its Ap…
We developed a method to characterize arbitrary superpositions of light orbital angular momentum (OAM) with high fidelity by using astigmatic tomography and machine learning processing. In order to define each superposition unequivocally,…
We apply convolutional neural networks (CNN) to the problem of image orientation detection in the context of determining the correct orientation (from 0, 90, 180, and 270 degrees) of a consumer photo. The problem is especially important for…
Many real-world problems, e.g. object detection, have outputs that are naturally expressed as sets of entities. This creates a challenge for traditional deep neural networks which naturally deal with structured outputs such as vectors,…
Semantic segmentation by convolutional neural networks (CNN) has advanced the state of the art in pixel-level classification of remote sensing images. However, processing large images typically requires analyzing the image in small patches,…
This paper explores the use of cosmic ray muons to image the contents of shielded containers and detect high-Z special nuclear materials inside them. Cosmic ray muons are a naturally occurring form of radiation, are highly penetrating and…
The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion. Existing approaches typically employ a single neural…
Recently, many Convolution Neural Networks (CNN) have been successfully employed in bitemporal SAR image change detection. However, most of the existing networks are too heavy and occupy a large volume of memory for storage and calculation.…
High-energy physics experiments require fast and efficient methods for reconstructing the tracks of charged particles. The commonly used algorithms are sequential, and the required CPU power increases rapidly with the number of tracks.…
Object detection and instance segmentation in remote sensing images is a fundamental and challenging task, due to the complexity of scenes and targets. The latest methods tried to take into account both the efficiency and the accuracy of…
The Hough transform is a popular and classical technique in computer vision for the detection of lines (or more general objects). It maps a pixel into a dual space -- the Hough space: each pixel is mapped to the set of lines through this…
External localization is an essential part for the indoor operation of small or cost-efficient robots, as they are used, for example, in swarm robotics. We introduce a two-stage localization and instance identification framework for…
Muon scattering tomography is a non-destructive technique used to image different materials by utilizing natural cosmic ray muons. Typically it requires position-sensitive detectors with a sub-millimeter resolution to effectively…
The analysis of weak variations in the energetic particle flux, as detected by neutron or muon monitors, can often be considerably improved by analysing data from monitor networks and thereby exploiting the spatial coherence of the flux. We…
A Convolutional Neural Network architecture was used to classify various isotopes of time-sequenced gamma-ray spectra, a typical output of a radiation detection system of a type commonly fielded for security or environmental measurement…
Spintronic devices offer a promising avenue for the development of nanoscale, energy-efficient artificial neurons for neuromorphic computing. It has previously been shown that with antiferromagnetic (AFM) oscillators, ultra-fast spiking…
We here propose a machine learning approach for monitoring particle detectors in real-time. The goal is to assess the compatibility of incoming experimental data with a reference dataset, characterising the data behaviour under normal…
Muon Tomography based on the measurement of multiple scattering of atmospheric cosmic ray muons in matter is a promising technique for detecting heavily shielded high-Z radioactive materials (U, Pu) in cargo or vehicles. The technique uses…
Accurate moving object segmentation is an essential task for autonomous driving. It can provide effective information for many downstream tasks, such as collision avoidance, path planning, and static map construction. How to effectively…
Significant progress has been made in ultrasonic guided wave (UGW) technology for pipe signal processing and defect imaging recently. However, developing a defect localization and imaging algorithm that requires fewer parameters, offers a…
Deep Convolutional Neural Networks (DCNN) have been proven to be effective for various computer vision problems. In this work, we demonstrate its effectiveness on a continuous object orientation estimation task, which requires prediction of…