Automating Underwater Mine Detection Using a Brain-Computer Interface

BCIIt may seem like science fiction, but we showed that it is possible to use sensors to monitor your brain waves and quickly detect underwater mines in sonar images. We combined techniques from computer vision with cutting edge classification of focal interest of human operators via electroencephalography (EEG) analysis, i.e., the recording of electrical activity along the scalp. This is the first approach for using EEG in this application.

These ideas are detailed in our upcoming journal paper, “A Brain-Computer Interface (BCI) for the Detection of Mine-Like Objects in Side Scan Sonar Imagery”, that has been accepted as a full article in the Journal of Oceanic Engineering. Congrats are in order to the authors: Christopher Barngrover, Alric Althoff, Paul DeGuzman, and Ryan Kastner. Special thanks to Neuromatters for the support with the EEG analysis tools and to Advanced Brain Monitoring for the use of the EEG sensors and hardware. The picture shows Dr. Chris Barngrover stylishly sporting the EEG cap at Neuromatters in New York City.

Ruku the Robot Kickstarter

rukuRuku – a robotic Rubik’s Cube solver – started a Kickstarter campaign. They are aiming to raise funding to develop their robotic platform as a way to motivate K-12 students to participate in science, technology, engineering, and math (STEM). The project was started by Daryl Stimm. He recruited Jonas Kabigting and Will Mutterspaugh to help him realize the project during Ryan’s CSE 145. They are aiming to raise $50,000 which will enable them to move this into larger production. We wish them the best of luck in their fundraising and future endeavors!

Ruku Robot Website
Kickstarter page
YouTube Video from CSE 145 Final Presentation
CSE 145 Webpage
UCSD Guardian Article

Cell Sorting Research Highlighted in IEEE Signal Processing Magazine

cell parametersOur work on high speed cell sorting was one of three research projects discussed in a “Looking at Machine Vision” article recently published in the IEEE Signal Processing Magazine. This work is building a hardware accelerated system to classify cells as they pass through a microfluidic device. The image processing must handle 10,000+ frames/second, while accurately detecting the type of cell. We originally developed the algorithms based upon work in Prof. Dino DiCarlo’s lab at UCLA. We are now working with the startup Cytovale to develop a commercial system based upon our initial technology.

Amazon’s Fall 2014 Graduate Research Symposium

janarbek-shadow_lakeJanarbek was selected to attend and present a poster at Amazon’s Graduate Research Symposium. The symposium brings together graduate students from around the country to Amazon headquarters in Seattle, WA. Janarbek will present his research on easing the design process for building hardware accelerated applications.

Kinect Fusion Accelerated Using FPGAs

The Kinect is a powerful tool for creating 3D models, and making a low power, real-time version has substantial impacts for robotics and virtual reality. Our recent work in this space used the new OpenCL API from Altera to implement portions of the algorithm on an FPGA. This is an important first step towards a mobile version of the Kinect Fusion 3D mapping algorithm. This research was accepted to the International
Conference on Field-Programmable Technology (FPT)
held in Shanghai, China in December. The work was authored by Quentin Gautier, Alexandria Shearer, Janarbek Matai, Dustin Richmond, Pingfan Meng, and Ryan Kastner.


The picture shows the 3D reconstruction of our messy shelves in the student offices at UCSD. The left part shows the “normal” camera input. The center images is the depth map, and the right images is the 3D model. This demo runs on an FPGA.

3rd Annual Kastner Research Group Retreat

group_animatedBefore the start of Fall Quarter, the group trekked up to Mammoth Lakes, CA (Eastern Sierras), home of endless scenery, breathtaking activities (not only due to 9000+ ft of elevation), and enlightening research talks. Each of us choose different activities during that day, ranging from hiking, mountain biking, fishing, and climbing, and came together in the evenings for discussions on past and future research directions. Add in a bit of bagpipe playing, pool shooting, card games and some beverages, and it was a great trip. Our group activity this year was a hike to the top of Lembert Dome in the Tuolumne Valley in Yosemite National Park, where we took in the amazing view and a research group picture. We invite you to find another research group with a better picture. We doubt you will be successful.

Advanced Survey Technology at Maya Site El Zotz

Kastner Group members Dustin Richmond, Perry Naughton, and Ryan Kastner were among a group of researchers documenting cultural heritage at the Maya site El Zotz in the Peten region of Guatemala. The team, which also included members from Engineers for Exploration and the Explorers Club, used ground lidar, imagery from unmanned aerial vehicles, and structure from motion to provide precise data of the temples, stelae, bowls, tunnels, and masks throughout the site from the Early Classic period. The site is named “Zotz” (the Maya name for “bat”) after the thousands of bats that emerge every night from a nearby cliff. Our team was also able to provide a 3D image of that cliff and determine the location of the bat cave. Additionally, we created 3D models of the excavated tunnels beneath two the main temples, El Diablo and M7-1.

After getting the blessing from the Guatemalan government, the results of these expeditions were written up by Calit2, put on the front page of the UCSD website and the Jacobs School website, picked up by, Gizmodo, and International Business Times.

Patent Issued on “Simulate and Eliminate” Research

patent-award-imageThe US Patent Office recently issued patent number US 8,812,285 B2 to our research group for work related to developing application specific processors. The patent was awarded to Dr. Ali Irturk and Ryan, and is licensable through the UCSD Technology Transfer Office. The patent covers material related to Ali’s PhD thesis, which took a general purpose processor, analyzed a set of applications that would run upon it, and removed unnecessary components in order to reduce the complexity, save power, and increase the performance.

Best Paper Award at FPL

20140902_090242The Kastner Group brought home another award from the International Conference on Field Programmable Logic and Applications (FPL). The odds were stacked in our favor as two of the three papers that we had accepted to FPL were nominated for the best paper award. Unfortunately, only one can win. 20140903_225108And that one was our paper called “Hardware Accelerated Novel Optical De Novo Assembly for Large-Scale Genomes” authored by Pingfan Meng, Matt Jacobsen, former visiting scholar Motoki Kimura, our collaborators at BioNano Genomics, Vladimir Dergachev, Thomas Anantharaman, Michael Requa, and Ryan Kastner.

Congratulations is also in order for the best paper nomination of the research titled “Improving FPGA Accelerated Tracking with Multiple Online Trained Classifiers” authored by Matt Jacobsen, former Kastner Group undergraduate Siddarth Sampangi (now a graduate student at UMass Amherst), Yoav Freund, and Ryan.

Last year we also had three FPL papers with one winning the Community Award (see previous post for more info). The bar has been set high for next year. Congrats again to all of the authors!