App Connects You to Nearby Friends
You’ve just emerged from a lecture in fluid mechanics with 90 minutes to spare before your next class. You’re also hungry, and wouldn’t mind some company while you chow down. So you whip out your smartphone, click on an app and tap on the names of two friends who the app shows are available and close by. Seconds after you send them a request—“[Your name] wants to hang out with you at 3:15 p.m. at The Fresh Food Co. at Marciano Commons.”—you receive
notification that one of the friends has accepted. Problem solved.
The app that’s enabling such connections,Downtyme, is the brainchild of Barron Roth and Luke Sorenson (both CE’16), who came up with the idea last November when deciding on a final project for
their Introduction to Software Engineering course. They subsequently turned it into a startup, Downtyme LLC, within three months. After releasing the app for beta testing to students at colleges and universities in Boston on March 31, Downtyme LLC aggregated nearly 500 downloads the first day.
The app’s immediate popularity is no surprise to Roth.
“It’s very difficult for college students to find opportunities to get together with friends, given the intricacies of our schedules,” he said. “Having access to a list of people you care about who are available and nearby makes life more social and enjoyable.” It also encourages you to spend less time on your smartphone and more time connecting offline.
Users identify their friends by linking the app to their Facebook account, and indicate t
heir availability by entering or importing their calendars. To bring up a list of nearby
Facebook friends, they may either press “Now” or “Later,” depending on when they want to get together. Users may also press “Hide me” to keep their schedules hidden until further notice, or “Bulletins” to post an open invitation to all their Downtyme friends to join them for activities ranging from study sessions to frat parties.
“Downtyme is a fantastic example of students taking a real-world need—scheduling free time—and translating that into a software application,” said Assistant Prof
essor Douglas Densmore (ECE, BME), the Introduction to Software Engineeringinstructor. “Its level of polish and presentation are on par with a professional-level startup, and the leadership of the project is committed to its success.”
Convinced that the idea had commercial potential after they and three other teammates completed a functioning version for Android mobile devices in December, Roth and Sorenson began laying the groundwork for a startup. Over the winter break, the co-founders brought in Nicholas Sorenson (SMG’14) for financial expertise, and recruited Timothy Chong (CE’16) and John Moore (CE’15) to help Luke develop the app for the iPhone and improve the server infrastructure. Roth focuse
d on branding, marketing and customizing the look and feel of Downtyme.
“It’s very rewarding working on a startup, where every decision you make has a big impact and can affect the future of your company,” said Roth, who is now working on Downtyme after hours while serving as a spring semester co-op at AMD in Austin, Texas. Taking advantage of his Austin location, Roth recently pitched the app to 500 technology enthusiasts at the city’s annual South by Southwest festival.
Downtyme plans to launch the app across the country in the fall, distributing it through campus representatives at Stanford University, University of California, Berkeley, and other colleges and universities. The company’s initial goal is to build a substantial user base for the free app, and then develop revenue-generating partnerships with academic institutions and industry.
Projects Automates Pothole Detection and Management
By Mark Dwortzan
The impact of a long and stormy winter continues to be felt on the roads. According to the Boston Globe, this year the City of Boston has already filled more than 8,800 potholes, primarily reported by drivers, including one in Cleveland Circle that sent a man to the hospital. Taking a more proactive approach could prevent vehicular damage, injuries and claims against the city while saving time and money for all concerned.
Now a vehicle mounted pothole detection system developed by Electrical Engineering seniors as part of their senior design project aims to do just that. Instead of relying on citizens to report potholes or paying crews to look for them, the system, known as AutoScan, could enable city vehicles to detect them automatically as they go about their daily routes. Coupled with tracking and scheduling software and incorporating a low-cost, embedded technology development platform called a Gizmo board, the system could provide a comprehensive and economical road repair solution.
“The low cost, achieved through the extensive use of open source solutions, made it compelling to the Gizmo community,” said Scott Hoot, president of GizmoSphere. “But the idea of how seamlessly this idea fit into the Internet of Things, made the BU project a winner. Clearly this is a project that takes close to real-time measurements in the physical world, and utilizes those measurements through the open standards available in the Internet.”
The AutoScan senior design team consists of Austen Schmidt (systems integration), Vinny DeGenova (image processing), Nandheesh Prasad (power engineering), Charlie Vincent (networking and GPS) and Stuart Minshull (Web application). The EE seniors developed their prototype under the supervision of ECE Adjunct Professor Babak Kia, who often assumed the role of prospective customer.
While there are several solutions available that can quickly measure potholes on a mobile platform, ranging from lasers to accelerometers, the EE team focused on a “time-of-flight” infrared camera that determines distance between the camera and various points in its field of view.
“Our system is basically an onboard computer that mounts to the bottom of a city vehicle, such as a bus,” said Schmidt. “As the bus goes along, it uses the infrared camera to scan the road for potholes and computes their depth, and sends the data collected on each pothole—volume, GPS coordinates, time and date—over a cellular network to a database hosted by a website. The website interprets data coming in from multiple scanners, displays it on a Google map and updates a Web-accessible road repair schedule.”
Exploiting the Gizmo board and open source software, the team has advanced a prototype of a system that promises to cost a few thousand dollars, far cheaper than alternatives that can range from $10,000 to $100,000. The only sacrifice is a bit of accuracy.
“Our system is a little less accurate than our competitors, because they focus on applications where you really need high-fidelity detection, such as airport tarmacs or bridges,” said Minshull. “We wanted a cheaper way for potholes to be detected without having to worry about tracking millimeter-line cracks in the road.”
To put AutoScan to the test, the team used cardboard boxes to create an elevated road surface with cutouts of different volumes representing potholes. Tests showed that the system accurately measured the volume of each cutout and successfully relayed collected data to the website. Next steps include conducting high-speed tests beyond the lab environment, and finding a way to protect the unit against vibration and adverse weather conditions.
Starting March 21 at 7 PM, students have 24 hours to “hack” a digital or physical product. Hackers will work on starting a website or mobile app from scratch, which could be useful for present applications.
“There have been various hackathons before run by BUILDS [an organization that strives on hacker ethic] and other student organizations but we believe this will be the largest, first to take place at EPIC, and includes a collaboration between multiple student organizations,” says team coordinator Connor McEwen (ECE ’14).
Boston University students are invited to get into groups of 2-4 people to learn new practical skills, meet other students interested in building things, having fun, and producing a project to show to potential employers or friends.
In addition, alumni interested in mentoring are welcomed to show up at 7 PM on Friday or 10 AM on Saturday, and those interested in judging should come at 5 PM on Saturday.
There are interesting categories students are being judged on, such as Most Fun Project, Best Noob Project (for those who have not competed or hacked before), Best Mobile Project, Best Web Project, and Best Hardware Project.
The most rewarding prize, however, will be the hands-on and educational experience.
For more information: http://make.bu.edu/
- Chelsea Hermond (SMG ’15)
Cultivating Excellence, Transforming Society
In 1963, the College of Industrial Technology (CIT) offered only three degree programs — in technology, aeronautics and management — and occupied a single, four-story building, but the former aviation school’s new dean, Arthur T. Thompson, was bullish about CIT’s future. He aspired to do no less than transform this dot on the Boston University map into an accredited engineering program, and to develop engineers with “the capacity for responsible and effective action as members of our society.”
Thompson began to work this transformation on February 27, 1964 — 50 years ago today — when CIT was officially renamed as the Boston University College of Engineering. Since then the College has grown to become one of the world’s finest training grounds for future engineers and platforms for innovation in synthetic biology, nanotechnology, photonics and other engineering fields, attracting record levels of student applications, research funding and philanthropic support.
Between 1964 and 2013, the number of degrees conferred annually has increased from zero to 281 bachelors, 184 masters and 53 PhDs; enrollment from around 100 to 1416 undergraduate, zero to 394 masters and zero to 349 PhDs; faculty from 10 to more than 120; advanced degree programs offered from zero to nine masters and six PhDs; and annual sponsored research dollars from zero to $52 million. Meanwhile, the College’s position in the annual US News & World Report’s annual survey of US engineering graduate programs has surged from unranked to the top 20 percent nationally.
At the same time, the College’s faculty, students and alumni have significantly advanced their fields and spearheaded major innovations in healthcare, energy, information and communication, transportation, security and other domains.
Building a World Class Institution
The infrastructure for the world class research and education taking place at today’s College of Engineering was built in stages.
During Thompson’s deanship from 1964 to 1974, the new Aerospace, Manufacturing and Systems Engineering departments received accreditation, with the Manufacturing Engineering program the ﬁrst of its kind to be accredited in the US. The College also instituted the nation’s first BS degree program in bioengineering and expanded to five BS and three MS programs in five fields. Between 1975 and 1985, when Louis Padulo was dean, the College’s student body grew from 250 to 2481; minority and female enrollments skyrocketed; degree offerings rose to 24 BS, MS and PhD programs in eight fields; full-time faculty increased to 67; and sponsored research exceeded $3 million.
When Professor Charles DeLisi (BME) became the new dean in 1990, he recruited many leading researchers in biomedical, manufacturing, aerospace, mechanical, photonics and other engineering fields, establishing a research infrastructure that ultimately propelled the College to its ranking in US News & World Report’s top 50 engineering graduate schools (realized in 2003). A case in point is the BME Department, which DeLisi turned into the world’s foremost biomolecular engineering research hub, paving the way for his successor, Professor David K. Campbell (Physics, ECE), to oversee the department’s receipt in 2001 of a $14 million Whitaker Foundation Leadership Award and discussions leading to additional support from the Wallace H. Coulter Foundation. Between 1990 and 2005, as the number of full-time faculty rose to 120, research centers to eight, and PhD programs to seven, the College’s external research funding surpassed $26 million.
When Professor Kenneth R. Lutchen (BME) took over as dean in 2006, he aligned the curriculum with undergraduates’ growing interest in impacting society, redefining the educational mission of the College to create Societal Engineers, who “use the grounded and creative skills of an engineer to improve the quality of life.”
Lutchen rolled out several programs to advance this agenda, ranging from the Technology Innovation Scholars Program, which sends ENG students to K-12 schools to show how engineering impacts society, to the new Engineering Product Innovation Center (EPIC), a unique, hands-on facility, that will educate all ENG students on product design-to-deployment-to-sustainability. He also ushered in a new era of multidisciplinary education and research collaboration by establishing the Systems Engineering and Materials Science & Engineering divisions along with several new minors and concentrations. Meanwhile, professional education opportunities surged on campus with the introduction of eight new Master of Engineering programs and four new certificate programs.
Moving On to the Next 50 Years
That said, what do the next 50 years hold for the College of Engineering? For starters, upcoming educational initiatives include increased integration of digital technologies in courses; new programs with the schools of Management, Education and Public Health; continued efforts to build the engineering pipeline through outreach to K-12 students; and the Summer Institute for Innovation and Technology Leadership, which recruits companies to host teams of ENG and SMG students to tackle targeted problems.
BU also plans to construct the Center for Integrated Life Sciences and Engineering Building — a seven-story, 150,000-square-foot facility that will include interdisciplinary research space for faculty and students in systems and synthetic biology (expanding the College’s recently launched Center of Synthetic Biology (CoSBi)) — within the next 10 years, as well as a 165,000-square-foot science and engineering research building. By 2016, ENG expects to add about 61,500 square feet of new lab and classroom space.
In its first half-century, the College of Engineering — through its students, faculty and alumni — has made its mark on several fields while improving the quality of life around the globe. If its rich history of high-impact education and innovation is any guide, the College can expect many more life-enhancing achievements in the coming 50 years.
As a master’s candidate studying Photonics at Boston University, Kevin Mader (ECE ’08, MS ’08) decided to become an Undergraduate Teaching Fellow, a position that allowed him to work with students and help them master difficult concepts.
“I felt like I could help students because I had just struggled with learning the concepts a year before and could relate well to what they were going through,” he said.
The experience made Mader realize he wanted to become a teacher and today, he is a lecturer at ETH Zürich in Switzerland, where he is hoping to inspire the next generation to get excited about engineering.
“I think that a lot of students lose interest in science and engineering early on because it becomes too technical before it gets interesting,” he said. “I hope to try and make it exciting without watering it down too much.”
Prior to living in Switzerland, Mader’s roots were in the United States, where he lived in California, Ohio, Oregon, and Massachusetts. Still, moving abroad wasn’t quite the challenge you might expect.
“For some things it is no adjustment at all – there are Starbucks and McDonald’s restaurants on nearly every street corner – but for other aspects getting used to a new language and a different culture can take some time,” he explained. “Luckily, students seem to be pretty similar all around the world and Zürich is a very international city so it’s never a problem finding interesting people and somewhere to fit in.”
As an undergraduate studying Electrical Engineering at BU, Mader worked closely with Senior Lecturer, Babak Kia, on his senior design project. Like in Switzerland, Mader never had any problems finding other researchers he could collaborate with effortlessly.
“He was a very effective team player, espousing a humble leadership style and patiently sharing his thoughts and ideas with his team,” said Kia, who served as Mader’s customer during senior design.
Mader’s team, Esplanade Runner, was tasked with enabling a robot to navigate a Google Maps route while avoiding obstacles in its path. Known as autonomous navigation, the project was assigned a few years before Google Street View cars were popularized.
Calling the research one of his “most valuable experiences at BU,” Mader said, “Our project was particularly cool since it was tangible: make a little car follow a route and avoid obstacles. It was also deceptively simple, and I learned how difficult it is to make timelines and get everything running on time. We spent a few nights in the lab banging our heads against the wall trying to synchronize our vehicle, compass, sensors, and GPS.”
The hard work ultimately paid off and their team won the ECE Day Best Presentation Award that year.
“Kevin could hardly contain his drive and enthusiasm throughout the project,” said Kia. “He has such a natural ability and curious mind for exploring the unknown that is just a joy to witness.”
After earning his bachelor’s degree, Mader decided to continue his studies by pursuing a master’s in Photonics at BU.
“Initially I was intrigued by Photonics because I had no idea what it really was and had studied in the building by that name for years,” said Mader. “After taking the introductory class I was surprised by how complicated imaging really is – iPhones make it so easy – and how much potential there was in the field.”
Mader had completed a summer internship at the Center for Biophotonics at the University of California, Davis, where he looked at how cellular spectroscopy and imaging could be used to detect cancer. Upon returning to BU, he decided to build upon what he learned by taking a course on imaging and microscopy with Professor Jerome Mertz (BME).
“What struck me about Professor Mertz from my first interaction with him was how much interest and passion he had for the science he was working on,” explained Mader. “He seemed like one of those people who would continue to do the exact same thing even after winning the lottery because he enjoyed it so much.”
Mader went on to work on his master’s thesis in Mertz’s laboratory, where he worked on improving bioluminescence imaging so that a small group of cells, like a tumor, could be detected without using lasers or X-rays.
“Kevin was great to work with – really creative,” said Mertz. “He could always look at things from different and unexpected perspectives that were really intriguing. I think he’ll make a great professor someday.”
Since completing his master’s, Mader has taken more steps toward eventually becoming a professor, including earning a Ph.D. in Electrical Engineering and Biomechanics from ETH Zürich.
He has also earned a Pioneer Fellowship from the university, which will allow him to work toward pairing microscopes, MRIs and CT-scanners with tools that will turn pictures into meaningful statistics.
“There seems to be sufficient industrial interest. The real challenge will be connecting with the right people at the right times,” he said.
As Mader balances research with teaching, he continues to give his all in both.
“I think one of the best ways to really understand a topic is to have to disseminate it to other people,” he said. “In particular, I enjoy trying to connect abstract concepts like parallel computing to everyday ones like card games with friends.”
Truly committed to being the best teacher he can be, Mader can often be found tweaking his lecture slides minutes before a talk, even though he’d finished preparing weeks before.
Said Kia: “I have no doubt, not even for a second, that he will become a highly effective professor and that his deep passion for research and discovery will be surpassed only by his immense passion for his students.”
Learn more about Mader’s new company, 4Quant.
-Rachel Harrington (firstname.lastname@example.org)
Mike Kasparian (ECE ’12, MS ’13)
As many of us try to stick to our New Year’s resolution of going to the gym more, we often find ourselves looking toward apps and equipment that can help us keep track of our progress.
Jawbone and Nike Fuel Band are just some of the wearable products on the market that allow you to keep track of this data, but what if these devices could be more customizable?
That’s the idea behind Atlas, the company founded by Mike Kasparian (ECE ’12, MS ’13) and his preschool friend, Peter Li.
Atlas tracks and identifies exercises, counts reps, calculates burned calories, and evaluates form. It also displays workouts live and is compatible with many popular fitness apps such as MapMyFitness.
Said Kasparian: “It’s one thing to come up with a great idea that will disrupt a technology, but it’s another thing to formulate the idea into a business and develop it into something that will one day not only generate revenue but also be in the hands of consumers.”
Li initially came up with the idea and contacted Kasparian to help with the hardware. Techstars, a startup accelerator in Austin, provided them office space, funding, and mentorship.
It was not an easy decision for Kasparian, who had a stable position at Philips Healthcare, to leave his day job. However, he took the risk and now holds the position of Chief Technology Officer (CTO) of the growing company.
The company gained funding through a campaign on indiegogo, a web platform that helps people raise money for new ideas and products. Atlas has surpassed its $125,000 fundraising goal, collecting over $450K.
Even though there is a lot of uncertainty associated with this venture, Kasparian feels that providing people with a personalized workout experience outweighs the risk.
Kasparian, who studied Electrical Engineering at Boston University, attributes the Department of Electrical & Computer Engineering’s senior design course as having a significant impact on his career. He said, “It was really the first time I was able to fully apply all of the technical skills from my coursework toward a legitimate project.”
As his advisor, Professor Bakak Kia gave Kasparian invaluable help and guidance during senior design. Kia is very proud of Mike, saying, “To reach this level, where he is competing with some of the most innovative companies in this field, speaks volumes about Mike’s vision, ability, and the value of the education he has received at BU.”
While working on the project, MINSensory, for senior design, Kasparian said he learned the importance of both collaboration and taking feedback. He did both well, too, winning the top team prize, the P. T. Hsu Memorial Award for Outstanding Senior Design Project, and an individual honor, the Michael F. Ruane Award for Excellence in Senior Capstone Design.
Later, his M.S. research project involved designing the hardware platform that would be used in the Atlas wristband. Professor Ajay Joshi (ECE) was Kasparian’s academic and research advisor, and he advised him during the platform design process. Joshi believes “the fitness band market is just picking up” and said he hopes “the Atlas wristband becomes the preferred choice of most fitness enthusiasts.”
Kasparian continues to remain close to the department, serving as one of the judges for senior design last year and graduating with his M.S. in December.
- Chelsea Hermond (SMG ’15)
Many engineers have great ideas for products, but unfortunately, they don’t often have a background in business that will allow them to bring their designs to market.
To help with this problem, two Boston University research teams recently participated in the National Science Foundation (NSF) Innovation Corps (I-Corps), a program that encourages scientists and engineers to broaden their focus beyond lab work through entrepreneurship training.
“We had been trying to bring some of our ideas to a commercial state when we heard about the program,” said David Freedman, a BU research associate in the Department of Electrical & Computer Engineering. “It seemed like a great fit for us.”
Freedman and postdoctoral associate, George Daaboul, had been working closely with Professor Selim Ünlü’s (ECE, BME, MSE) research group trying to determine how their technology, IRIS, used to detect viruses and pathogens, might be applied in doctors’ offices, hospitals, and emergency care centers. They soon decided that forming an I-Corps team would allow them to evaluate the commercial potential.
Teams receive $50K in grant money and consist of an Entrepreneurial Lead (Daaboul), a Principal Investigator (Freedman), and a business mentor. The researchers asked BU lecturer and entrepreneur, Rana Gupta (SMG), to take on the latter role.
Also participating from BU were Assistant Professor Douglas Densmore (ECE) and Research Assistant Professor Swapnil Bhatia (ECE). They pitched Lattice Automation, technology that will allow technology by the Cross-disciplinary Integration of Design Automation Research (CIDAR) group to transition into commercial products. Ultimately, they hope to create software that will help synthetic biologists work more efficiently.
“Our technology is building upon state-of-the-art techniques in computer science, electrical engineering, and bioengineering,” explained Densmore.
Over eight weeks in the fall, participants attended workshops in Atlanta, Ga., met with researchers from the 21 teams, followed an online curriculum, and spoke with up to 100 different potential consumers of their technology – a process known as “customer discovery.”
Through this experience, Freedman and Daaboul quickly learned that introducing a new technology to customers might not be the right approach for their research.
“We decided instead to focus on the pains customers had with existing technologies and hone in on how we could alleviate those,” said Freedman.
Added Daaboul: “Finding out what people really needed before developing a technology really allowed for a much different perspective than what I’m used to.”
Much of the knowledge gained through I-Corps will be used to advance science and engineering research. Some products tested during the workshops even show immediate market potential by the conclusion of the curriculum.
“I would recommend this program to anyone working in science or industry,” said Freedman. “Not only did this change how we think about our research, we also learned how to better tell our narrative.”
-Rachel Harrington (email@example.com)
It’s been a bitter winter in Boston, but that didn’t keep students and faculty from making their way toward the Photonics Building Colloquium Room on January 22. Anxious undergraduate students looking for research opportunities mingled among the 28 tables of Boston University researchers at the recent ECE Undergraduate Research and Lab Job Fair hoping to find opportunities to gain hands-on engineering experience.
The story of the research fair goes back four years ago when Dean Kenneth R. Lutchen spoke to matriculating freshman about the importance of research. While listening to the talk, Professor Mark Horenstein (ECE) realized that while entering students were being encouraged to engage in research, no one was telling them how.
In response, Horenstein started the annual ECE Undergraduate Research and Lab Job Fair as a way for undergraduates and faculty to explore mutual interests related to research and for students to ask about available research positions. The event also provides a public forum in which faculty can showcase what is happening in their laboratories. “This is a get-to-know-you meet-and-greet event,” says Horenstein.
Watching presentations and submitting resumes to BU faculty and graduate students, about 75 students attended this year. Two sophomores, Dean De Carli (EE ’16) and Matthew Owney (EE ’16), were scouting for summer and fall positions.
“Even though I didn’t get any research jobs, I was able to connect with the faculty,” said second-time attendee, De Carli. Owney added that he is looking for any opportunity since it’s his first time attending the fair.
Horenstein tells younger attendees, such as Alexandra Miller-Browne (CE ’17), that it’s important to “build up your skills as time goes on; don’t get discouraged.”
People on the other side of the table have a similar thought process. Dr. Traci Haddock, Executive Director of the Center for Synthetic Biology at BU, says, “Most students have no experience, but we will take anyone who is interested.” For example, she is looking for students to help develop the iGEM team’s website and build genetic devices this summer.
Third-time veteran, Associate Professor Robert Kotiuga, changes his presentation every year but remains steadfast in his belief that though people will always possess different areas of expertise, “it is important to be passionate about the project.”
Every year since the program’s initiation, the event has turned out eager attendees, and 2014 was no exception. Students continue to return each year, hoping to gain experience and take advantage of the department’s available opportunities.
-Chelsea Hermond (SMG ’15)
When a bug in Pentium processors was discovered that gave rise to incorrect solutions of scientific and mathematical calculations, the company was forced to take action. The result? Public outcry and the loss of $475 million worth of earnings.
It’s been almost two decades since the Pentium FDIV bug made headlines, but its discovery led to a new research thrust in computer science and engineering – one that Professor Sharad Malik, Chair of the Department of Electrical Engineering at Princeton University, knows quite well.
“It’s an instance of how real practical concerns have driven solutions to real, fundamental problems,” said Malik.
The incident brought the examination of Boolean Satisfiability or SAT, the challenge of determining if a logic formula will ever evaluate to true, to the forefront. In proving the correctness, this problem has a direct application to hardware and software and more specifically, avoiding costly bugs. SAT was already well known in computer science, but theoretical analysis deemed it to be too difficult to be applied in practice.
Malik is one of the nation’s experts on the topic, and his group has made several critical contributions to the field of SAT solvers that are now widely used in practice. On January 29, he visited Boston University to share his findings during the Department of Electrical & Computer Engineering Distinguished Lecture Series, which brings groundbreaking engineers to campus.
Currently, there is a strong motivation to discover useful SAT solvers thanks to all of the potential practical uses, such as in applications in artificial intelligence, circuit synthesis, and malware analysis.
“It’s already very widely used in hardware verification and we’re seeing an increasing use of the theory in software verification,” added Malik.
Though the SAT problem may be relatively unknown outside computer science and engineering, a very active community of researchers exists and can be found sharing their research and questions on the website, SAT Live!
Malik notes that the biggest change he’s noticed with SAT studies over the years is a revolution in how the topic is approached.
“There has been a significant shift from theoretical interest in SAT to how it can have a practical impact,” he said. What was once considered practically impossible due to its theoretical hardness is now within reach thanks to challenge-driven algorithmic and experimental research.
Malik’s talk was the first in the three-part Spring 2014 Distinguished Lecture Series. The next talk features Professor C. V. Hollot of University of Massachusetts, Amherst, who will speak on the topic, “Regulation of Cell Populations in Individuals Using Feedback-Based Drug-Dosing Protocols.” Hear him on March 5, 2014, at 4 p.m. in Room 211 of the Photonics Center, located at 8 Saint Mary’s St.
-Rachel Harrington (firstname.lastname@example.org)
After the Boston Marathon bombings last year, it took authorities just three days to sift through an abundance of footage and find their suspects – light speed compared to the weeks it took to find those responsible for the London bombings in 2005.
Still, can this happen faster? Professor Venkatesh Saligrama (ECE, SE) thinks so, and he’s working to making that vision a reality.
The Office of Naval Research awarded him $900K for his project, Video Search and Retrieval, which will focus on developing a visual search system. Think Google but for security videos.
“Our initial idea was to develop a system that could annotate web videos,” said Saligrama, who collaborated with Pierre-Marc Jodoin at the University of Sherbrooke on early stages of this research. “That project turned out to be extremely challenging so we started to focus on surveillance videos, where the footage is obtained in a controlled environment.”
Manually searching large archives of footage can be both time-consuming and monotonous. Saligrama and Ph.D. students, Greg Castanon (ECE) and Yuting Chen (SE), are now working closely with the U.S. Naval Research Laboratory to help change this.
Chen said she is looking forward to working on this project with Saligrama, who she first encountered while conducting her own research.
“I spent almost a year and a half working on an idea that employs correlating motion clues to calibrating camera networks,” she said. “When I came to BU Systems Engineering and browsed the research papers, I found the exact idea implemented by Venkatesh’s group. I was surprised and just a little bit bitter.”
From there, she knew that she wanted to study with Saligrama.
“He is an experienced researcher and just as passionate and curious as a young freshman,” she said. “I find that one sentence from him can help me through a problem that’s been troubling me for weeks.”
Chen, Castanon and Saligrama hope that together, they can make the process of searching through security footage more automated and responsive to user query video searches.
“Currently, for many YouTube videos, there are textual meta-tags that are used in the search process,” Saligrama explained. “For surveillance videos, we do not often have this so our searches need to be based purely on visual features and patterns.”
One of the challenges in video search is that activity patterns can be highly inconsistent and can occur for unpredictable amounts of time.
“Unlike image search though, videos have some temporal patterns we can exploit,” said Saligrama.
In the future, Saligrama hopes that the research will not only improve security but improve medical database searches as well.
For more information about the project, visit our Research Spotlight page.
-Rachel Harrington (email@example.com)