1st Thermal Image Super Resolution Challenge <PBVS-TISR Challenge, CVPR 2020>

http://vcipl-okstate.org/pbvs/20/challenge.html

in conjuntion with the 16th IEEE Workshop on Perception Beyond the Visible Spectrum (PBVS 2020), CVPR 2020

http://vcipl-okstate.org/pbvs/20/

June 2020
Seattle, WA, USA

=====================================================

Important Dates
    Registration open & datase released: December 10, 2019
    Evaluation images distributed: February 21, 2020
    Deadline for challenge & result submitted: February 28, 2020
    Winner announcement: June 14, 2020

=====================================================

Objective & Scope

In general, thermal images have a poor resolution, which could be improved by using learning-based traditional super-resolution methods. These methods have been largely used in the visible spectral domain. They work by downsampling and adding noise and blur to the given image. These noisy and blurred poor quality images, together with the given images (which are used as the Ground Truths), are used in the learning process.

The approach mentioned above has been mostly used to tackle the super-resolution problem, however there are few contributions where the learning process is based on the usage of a pair of images (low and a high-resolution images) obtained from different cameras. For the current challenge, a novel thermal image dataset has been created, containing images with three different resolutions (low, mid, high) obtained with three different thermal cameras. The challenge consists in creating a solution capable of generating super-resolution images in x2, x3 and x4 scale from each resolution, in the case of x2 an additional evaluation will be performed by using a HR image obtained from another camera. The results from each team will be evaluated in two ways as detailed in the Challenge Web page:

http://vcipl-okstate.org/pbvs/20/challenge.html 

=====================================================
16th IEEE Workshop on Perception Beyond the Visible Spectrum (PBVS 2020), in Conjunction with CVPR 2020 http://vcipl-okstate.org/pbvs/20/)
June 2020
Seattle, WA, USA
=====================================================

Important Dates

• Paper Submission: March 13, 2020
• Author Notification: April 5, 2020
• Camera Ready: April 12, 2020
• PBVS Workshop: June 14, 2020

=====================================================

Objective & Scope

Download the CFP

The objective of this workshop is to highlight cutting edge advances and state-of-the-art work being made in the exponentially growing field of PBVS (previously “Object Tracking & Classification Beyond the Visible Spectrum” – OTCBVS) integrating sensor processing, algorithms, and applications. PBVS involves deep theoretical research in sub-areas of image processing, machine vision, pattern recognition, machine learning, robotics, and augmented reality within and beyond the visible spectrum. Advancing vision-based systems includes frameworks and methods featured in PBVS.

The computer vision community has typically focused mostly on the development of vision algorithms for object detection, tracking, and classification with visible range sensors in day and office-like environments. In the last decade, infrared (IR), depth, thermal and other non-visible imaging sensors were used only in special area like medicine and defense. The relatively lower interest level in those sensory areas in comparison to computer vision was due in part to their high cost, low resolutions, poor image quality, lack of widely available data sets, and/or lack of consideration of the potential advantages of the non-visible part of the spectrum. These objections are becoming overcome as sensory technology is advancing rapidly and the sensor cost is dropping dramatically. Image sensing devices with high dynamic range and IR sensitivity have started to appear in a growing number of applications ranging from defense and automotive domains to home and office security.

We encourage the submission of original papers that cover the topics of interest mentioned below. In order to develop robust and accurate vision-based systems that operate in and beyond the visible spectrum, not only existing methods and algorithms originally developed for the visible range should be improved and adapted, but also entirely new algorithms that consider the potential advantages of nonvisible ranges are certainly required. The fusion of visible and non-visible ranges, like radar and IR images, depth images or IMU information, or thermal and visible spectrum images as well as acoustic images, is another dimension to explore for higher performance of vision-based systems.

This 16th IEEE CVPR Workshop on Perception Beyond the Visible Spectrum (PBVS’2020) fosters connections between communities in the machine vision world ranging from public research institutes to private, defense, and federal laboratories. PBVS brings together academic pioneers, industrial and defense researchers and engineers in the field of computer vision, image analysis, pattern recognition, machine learning, signal processing, artificial intelligence, sensor exploitation, and HCI.

PBVS’2020 is accompanied by the first Thermal Image Super-Resolution (TISR’2020) challenge. For more information about the challenge, the dataset, the evaluation approach and measures as well as the deadline for participation, please visit the workshop website.

—————————————————————–

Topics of Interest

Sensing/Imaging Technologies

• IR/EO/RGBD imaging system
• Underwater sensing
• Multi-spectral/Satellite imaging
• Spectroscopy/Microscopy imaging
• LIDAR/LDV sensing
• Compressive sensing
• RADAR/SAR imaging
• Radiation sensing
• Active imaging; Cooperative Sensing

Applications and Systems

• Surveillance and reconnaissance systems
• Unmanned autonomous systems
• Vehicle, ship, object classification
• Robotic grasping
• Vision-aided navigation and SLAM
• Night/Shadow vision
• Sensing for agriculture and food safety
• Vision-based autonomous aerial vehicles
• Lifelong & Robust machine learning

Theory and Algorithm

• Deep Learning, Reinforcement Learning
• Imagery/Video exploitation
• Object/Target tracking and recognition
• Feature extraction and matching
• Activity/Pattern learning and recognition
• Multimodal/Multi-sensor/INT fusion
• Multimodal Geo-registration
• 3D Reconstruction and shape modeling
• Automatic caption generation; Data labeling