No content found

IMPORTANT DATES
2021
Call for Papers Deadlines
» Journal-first (JIST & JPI)
5 April
» Conference
30 April
Acceptance Notification
» Conference 30 June 
» Journal-first (JIST & JPI)
7 July 
Preliminary Program Released & Registration Opens mid-July
Final Manuscripts Due
» Journal-first by 12 July
» Conference
23 Aug
Early Registration Ends
TBD
Conference Begins
20 Sept
   

At-a-Glance

LIM 2021 will take place over 3 days, with the technical program held 20-21 September. The program will be comprised of keynote and invited talks, along with peer-reviewed oral and poster presentations. There will be an additional day for short courses/workshops. Details on courses/workshops will be released at a later date.

Technical presentations are currently being solicited. The Author/Submission tab provides detailed information on submitting work.

Plenary Talks


Soft-Prototyping Camera Designs for Autonomous Driving

Dr. Joyce E. Farrell, executive director
Stanford University Center for Image Systems Engineering (SCIEN)

Abstract: It is impractical to build different cameras and then acquire and label the necessary data for every potential camera design. Creating software simulations that can generate synthetic camera images captured in physically realistic 3D scenes (soft prototyping) is the only practical approach. We implemented soft-prototyping tools that can quantitatively simulate image radiance and camera designs to create synthetic camera images that are input to convolutional neural networks for car detection. We show that performance derived from training on physically-based multispectral simulations of camera images generalizes to real camera images with nearly the same performance level as training based on real camera image datasets. Using simulations, we can develop and test new metrics for quantifying the effect that different camera parameters have on CNN performance. As an example, we introduce a new metric based on the distance at which object detection reaches 50%. Our open-source and freely available prototyping tools, together with performance-based metrics, enable us to evaluate the effect that changes in scene and camera parameters have on CNN performance.


Camera Metrics for Autonomous Vision
(working title)
Dr. Robin Jenkin, principal image quality engineer
NVIDIA



Funding for the conference keynotes is supported by EPSRC.

Focal Talks


Image understanding for color constancy and viceversa
Simone Bianco, associate professor of Computer Science 
Università degli Studi di Milano-Bicocca
 


Title TBA
Valentina Donzella, associate professor, Intelligent Vehicles Group
University of Warwick



Title TBA
Ali Seyad, associate professor
Norwegian University of Science and Technology (NTNU)
 


Title TBA
Jonas Unger, professor
Linköping University
 

No content found

No content found

No content found

No content found