The Digital Imaging and Remote Sensing (DIRS) Laboratory was formed over 30 years ago at the Rochester Institute of Technology (RIT) to serve as a focal point for remote sensing research and education at RIT. The DIRS Laboratory is one of the research laboratories within RIT's Chester F. Carlson Center for Imaging Science, an academic unit within the College of Science. DIRS focuses on the development of tools to extract information about the earth from aerial and satellite imaging systems with an emphasis on the application of science and engineering to solving end-to-end remote sensing problems using a systems engineering approach. This includes design and development of imaging instruments, developing algorithms to extract information from remotely sensed systems and measurement and modeling of the physical phenomena associated with the formation of remotely sensed images. DIRS currently has about 40 graduate students conducting advanced remote sensing research who are supported by 10 faculty and 10 full time research and administrative staff. DIRS has on-going research partnerships with multiple federal agencies, large and small companies, and other academic institutions.

News! Software developed by Aaron Gerace and Matt Montanaro, senior scientists in DIRS, improves the accuracy of NASA’s Landsat 8 Earth-sensing satellite, which was giving inaccurate readings due to defective optics in the thermal infrared sensor. Read more at RIT's University News:  http://www.rit.edu/news/story.php?id=58199&source=enewsletter

Mission Statement:

To educate students and conduct research in the science, engineering and application of physics-based quantitative remote sensing and digital imaging systems (source-to-information) to aid in the solution of real-world problems.

Vision Statement:

Be known as the university laboratory of choice for education and research related to the physics-based phenomenology, modeling, collection, calibration, and analysis of remote sensing and digital imagery.

Values Statement:

Our core values include integrity, dedication, respect, and commitment to excellence in our educational, research and professional activities.

Check out our Resources page for a listing of our equipment for image and ground reference data.

2015-16 DIRS Annual Report

DIRS Group Meeting Schedule Spring 2017. We meet Wednesdays at 10 am in CAR-3215.



1/25Mashad MahdaviRoof Damage Assessment Using Deep Learning Techniques
2/1Yihang SunProducts to Aid ORNL's High-throughput Image Registration

Don McKeown  & Tim Bauch

MX1 UAS Payload Overview
2/15Chi ZhangThe Usage of Recurrent Neural Network in Video/Image Understanding

John Kerekes

Validation of Abundance Map Reference Data for Imaging Spectroscopy Unmixing



Sanghui Han

Tania Kleyhans

Efficient Generation of Image Chips for Training Deep Learning Networks

Estimating Top-of-atmosphere Thermal Infrared Radiance Using MERRA2 Atmospheric Data


Di Bai


Tim Gibbs

A Pigment Analysis Tool for Hyperspectral Images of Cultural Heritage Artifacts

Contaminant Mass Estimation of Powder Contaminated Surfaces


Jie Yang

Runchen Zhao

FPN Pixel-Wise Linear Correction for Crime Scene Imaging CMOS Sensor

Improvements to an Earth Observing Statistical Performance Model


Nirmalan Jeganathan

Paul Sponagle

Characterizing the Temporal and Spatial Variability of Longwave Infrared Spectral Images of Targets and Backgrounds

Automatic Mission Planning Algorithms for Aerial Collection of Imaging-specific Tasks


Gefei Yang

Tyler Hayes & Nathan Cahill

Neural Network Applying for Reflectance Spectrum Classification

Piecewise Flat Embeddings for Hyperspectral Image Analysis


4/12 No meeting due to SPIE DCS
4/19Tim RuprightTBD
4/26Aneesh RangnekarVehicle Tracking Using Hyperspectral Imagery: Challenges and Solutions
5/10Cara Murphy

Novel Chemical Detection Approach Using Sparse Methods

DIRS Group Meeting Schedule Fall 2016. We meet Wednesdays at 11 am in CAR-3215.

9/7John KerekesOverview of DIRS Laboratory and Projects
9/14Zhaoyu CuiFuture Landsat Spatial-spectral Trade-off Study

Gefei Yang

Jared van Cor

Machine Learning and Statistical Analysis for Reflectance Spectrum Classification

Quantifying the Relevence of Earthshine in Exoatmospheric Imaging

9/28Adam GoodenoughDIRSIG 5.0

Mingming Wang

Ron Kemker

Validating DIRSIG 5 Via RAMI Scenes

Generating Labeled Data for Deep Semantic Segmentation in Remote Sensing Imagery


Emily Myers

Greg Badura

Predicting Above- and Below-ground Carbon Storage in Wetland Ecosystems

The Effect of Roughness on the Reflectance of Sediments


Runchen Zhao

Yue Wang

Improvements to an Earth Observing Statistical Performance Model with Applications to LWIR Spectral Variability

Stray Light Calibration for Landsat 8 TIRS


Ryan Ford

Paul Sponagle

Quantification of Cynobacteria Blooms Using UAS Imagery

Automated Flight Planning Tools for Imaging Purposes


Nirmalan Jeganathan

Tania Kleynhans

Introduction to the Spectral and Polarimetric Imagery Collection Experiment (SPICE) Data

Estimating Top-of-atmosphere Thermal Infrared Radiance using MERRA2 Atmospheric Data


McKay Williams

Emily Berkson

Validation of abundance map reference data: more than you ever wanted to know about the data you always assumed were true

Anomaly detection in hyperspectral imagery: statistical vs. graph-based methods


Utsav Gewali

Colin Axel

A Survey on Machine Learning Methods for Hyperspectral Data Analysis

Roadway Flooding Detection and Depth Estimation


Brittany Ambeau

Rehman Eon

The Characterization of a DIRSIG Simulation Environment to Support the Inter-calibration of Spaceborne Sensors

Calibration Studies for the SOLARIS Sensor


Maksims Zigunovs (special guest)

Applications of Neural Networks in Plant Recognition