Nearly 150 members of the signal and image science community recently came together to discuss the latest advances in the field and connect with colleagues, friends and potential collaborators at the 28th annual Center for Advanced Image and Signal Science (CASIS) workshop.
Held at the University of California Livermore Collaboration Center (UCLCC) for the first time, the workshop achieved its highest attendance and greatest external participation in years. The event featured more than 50 technical contributions across six workshop tracks and a parallel tutorials session, including 40 talks and 23 posters that helped encourage discussions. This year's topics included remote and noninvasive sensing, non-destructive evaluation, signal and image science at NIF, machine learning/AI, quantum sensing and quantum computing and energy applications.
"The workshop has always been a great opportunity to network and find new collaboration partners across the Lab, or just learn what is happening in a nice cross-section of topics that rely on the signal and image sciences," said Ruben Glatt, CASIS director and Artificial Intelligence Research Group leader. "The increasing number of external participants as attendees and contributors also shows the growing interest of industry and academia in the research conducted at LLNL."
Centering the community
Signal and image sciences enable efficient and accurate processing, generation, analysis and interpretation of signals and images in fields such as telecommunications, medical imaging, computer vision and more. At the Lab, they are the backbone of NIF diagnostics, nondestructive evaluation and characterization, advanced sensing, AI/machine learning and various other critical mission roles.
"Signal and image science touches virtually everything we do, be it experimental work or computational work, and it's a growing element of the flow of information into AI/machine learning as well," said Rob Sharpe, Engineering deputy principal associate director for R&D. "This community is distributed across all areas of the Lab, so reconnecting and cross-fertilizing ideas is very exciting."
CASIS was founded in 1994, and its workshop is one of the Lab's longest continuously running events. Over the years, it has evolved from a technical workshop for Sandia and LLNL employees to a connection point for the signal and image sciences at the Lab and in the community.
The UCLCC courtyard - filled with native plants, open spaces and picnic tables, as well as eight meeting rooms and hoteling offices - served as the event's meeting place. More than 20 technical posters lined the space, which attendees could silently browse or use to start a discussion. During breaks and lunchtime, the tables were lively with conversation that ranged from large-group discussions with people of all career levels to individual chats for talking shop or catching up.
"It's great to reconnect with former colleagues, and the talks cover such a great breadth of topics," said Tyler Ralston, chief technology officer at microscopy company ONI and a former Lab employee. "[Without this event], people wouldn't be able to come together to discuss these topics."
Something for everyone
CASIS workshops cover a broad range of topics and draw a diverse group of attendees from students and interns like Gwindolyn Anderson - who wanted to learn more about machine learning - to senior researchers like physicist Stephen Libby, who wanted to "dip in" to learn what his younger colleagues are working on.
"When we do research, we normally focus on what we're doing on a day-to-day basis, but there's so many other things that are happening around the world," said Mohit Agarwal, a Google employee and former LLNL intern who gave a presentation on brain-computer interfaces. "The workshop gives a good context for that."
Glatt credits the UCLCC for helping facilitate the higher-than-usual attendance. Participation from academia doubled - particularly among University of California (UC) affiliates - in addition to contributions from Oak Ridge and Lawrence Berkeley national laboratories, Google, Oracle and Electronic Arts. It bodes well for Glatt's goal of making the workshop a public entry point to the Lab's signal and image science research.
"CASIS is uniquely positioned to provide this kind of overview of a large number of different areas connected by the multidisciplinary field," he said. "This makes the workshop a great opportunity to make the Lab more approachable by inviting the broader research community to interact with us and identify overlapping interests and collaboration opportunities."
The workshop was the result of months of hard work by the CASIS organization team, the program chairs, their partners at UCLCC, the Lab's technical information department web team and the local IEEE Signal Processing and Computer Society chapters, who are the event's long-time sponsors and important connections to the Bay Area technical community.
