Nima Sedaghat

Nima Sedaghat
University of Washington Seattle | UW · Department of Astronomy

Doctor of Philosophy

About

21
Publications
4,307
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
872
Citations
Introduction
I do research at the intersection of Deep Learning and Astronomy/Cosmology.
Additional affiliations
June 2019 - December 2021
European Southern Observatory
Position
  • AI Lead
April 2014 - October 2014
University of Freiburg
Position
  • Lecture Assistant
Description
  • 3D Image Analysis
January 2014 - January 2017
University of Freiburg
Position
  • Lecture Assistant
Description
  • Image Processing & Computer Graphics
Education
November 2005 - March 2008
Amirkabir University of Technology
Field of study
  • Electrical Engineering - Telecommunications
October 2001 - June 2005
Amirkabir University of Technology - Tehran Polytechnic
Field of study
  • Electrical Engineering - Telecommunications

Publications

Publications (21)
Article
Machine learning has been widely applied to clearly defined problems of astronomy and astrophysics. However, deep learning and its conceptual differences to classical machine learning have been largely overlooked in these fields. The broad hypothesis behind our work is that letting the abundant real astrophysical data speak for itself, with minimal...
Preprint
Full-text available
Machine learning has been widely applied to clearly defined problems of astronomy and astrophysics. However, deep learning and its conceptual differences to classical machine learning have been largely overlooked in these fields. The broad hypothesis behind our work is that letting the abundant real astrophysical data speak for itself, with minimal...
Article
The new generation of deep photometric surveys requires unprecedentedly precise shape and photometry measurements of billions of galaxies to achieve their main science goals. At such depths, one major limiting factor is the blending of galaxies due to line-of-sight projection, with an expected fraction of blended galaxies of up to 50 per cent. This...
Preprint
The new generation of deep photometric surveys requires unprecedentedly precise shape and photometry measurements of billions of galaxies to achieve their main science goals. At such depths, one major limiting factor is the blending of galaxies due to line-of-sight projection, with an expected fraction of blended galaxies of up to 50%. Current debl...
Article
Context. Open clusters (OCs) are popular tracers of the structure and evolutionary history of the Galactic disc. The OC population is often considered to be complete within 1.8 kpc of the Sun. The recent Gaia Data Release 2 (DR2) allows the latter claim to be challenged. Aims. We perform a systematic search for new OCs in the direction of Perseus u...
Article
Full-text available
The Zwicky Transient Facility is a large optical survey in multiple filters producing hundreds of thousands of transient alerts per night. We describe here various machine learning (ML) implementations and plans to make the maximal use of the large data set by taking advantage of the temporal nature of the data, and further combining it with other...
Preprint
Open clusters (OCs) are popular tracers of the structure and evolutionary history of the Galactic disk. The OC population is often considered to be complete within 1.8 kpc of the Sun. The recent Gaia Data Release 2 (DR2) allows the latter claim to be challenged. We perform a systematic search for new OCs in the direction of Perseus using precise an...
Article
Full-text available
Large sky surveys are increasingly relying on image subtraction pipelines for real-time (and archival) transient detection. In this process one has to contend with varying point-spread function (PSF) and small brightness variations in many sources, as well as artefacts resulting from saturated stars and, in general, matching errors. Very often the...
Article
Full-text available
Large sky surveys are increasingly relying on image subtraction pipelines for real-time (and archival) transient detection. In this process one has to contend with varying PSF, small brightness variations in many sources, as well as artifacts resulting from saturated stars, and, in general, matching errors. Very often the differencing is done with...
Article
Full-text available
CNN-based optical flow estimation has attracted attention recently, mainly due to its impressively high frame rates. These networks perform well on synthetic datasets, but they are still far behind the classical methods in real-world videos. This is because there is no ground truth optical flow for training these networks on real data. In this pape...
Article
Full-text available
General human action recognition requires understanding of various visual cues. In this paper, we propose a network architecture that computes and integrates the most important visual cues for action recognition: pose, motion, and the raw images. For the integration, we introduce a Markov chain model which adds cues successively. The resulting appr...
Article
CNN-based optical flow estimators have attracted attentions recently, mainly due to their impressive speed. As successful as they've been on synthetic datasets, they are still far behind the classical methods in real-world scenarios, mainly due to lack of flow ground-truth. In the current work, we seek to boost CNN-based flow estimation in real sce...
Article
Full-text available
Recent work has shown good recognition results in 3D data using 3D convolutional networks. In this paper, we argue that the object orientation plays an important role in 3D recognition. To this end, we approach the category-level classification task as a multi-task problem, in which the network is forced to predict the pose of the object in additio...
Article
Full-text available
Hough transform based object detectors divide an object into a number of patches and combine them using a shape model. For efficient combination of patches into the shape model, the individual patches are assumed to be independent of one another. Although this independence assumption is key for fast inference, it requires the individual patches to...
Conference Paper
Image-based License Plate Recognition (LPR) algorithms are the core modules of many Intelligent Transportation Systems (ITS). Different algorithms and approaches have been proposed so far. All of these methods have the following three steps in common: License Plate Localization, Character Segmentation & Character Recognition. There are many real-wo...
Article
Full-text available
Abstract—Ray tracing has been successfully usedin pred iction of wave propagation models in recent years. Although this method has its own obvious benefits, it suffers from a big problem: slow performance. In this paper, novel methods are proposed in which the main focus is on reducing the number,of ray-facet intersections. First a pre- processing...
Conference Paper
Ray Tracing has been successfully used in prediction of wave propagation models in recent years. Although this method has its own obvious benefits, it suffers from a big problem: slow performance. In this paper, a novel method is proposed in which the main focus is on reducing the number of ray-facet intersections. It includes a light-weight pre-pr...
Conference Paper
Full-text available
Ray tracing has been successfully used in prediction of wave propagation models in recent years. Although this method has its own obvious benefits, it suffers from a big problem: slow performance. In this paper, a novel method is proposed in which the main focus is on reducing the number of ray-facet intersections. It combines a volume bounding alg...

Network

Cited By

Projects

Projects (3)
Project
Deep Learning + Computer Vision for real-time transient detection.