ANN ARBOR--Contrary to what you might see in police dramas, you don’t have to be Jason Bourne to shake off a computer tracking you through a video feed. Cross paths with someone who vaguely resembles you, and the computer is likely to swap your labels.
- Pedagogy - 09:00 Parents should be allowed to make informed choices over infant bed- sharing, says child sleep expert
- Medicine - 08:00 Largest- ever global survey of 1,273 women in 12 countries reveals women with advanced breast cancer feel left out of the breast cancer movement
- Mechanical Engineering - 07:30 Crash risk among young drivers linked to less sleep
- Social Sciences - 07:30 Big miners’ community engagement doing more harm than good?
- Medicine - May 20 Discovery of a novel medicine for the treatment of chronic wounds
- Medicine - May 20 Penn Medicine Study Raises Questions About Added Costs and Physician Resources
- Event - May 20 Salil Vadhan named Simons Investigator
- Medicine - May 20 Vigorous athletic activity is safe with implanted arrhythmia devices
- Literature - May 20 Sarah Thomas to lead Harvard Library
- Life Sciences - May 20 Amazon River exhales virtually all carbon taken up by rain forest
- Physics - May 20 Stanford physicists develop revolutionary low- power polariton laser
- Arts - May 20 The Golden Gate returns to Stanford May 30
- Medicine - May 20 New £23m research unit will use advances in genetics to help reduce risk of disease
- Study of Religions - May 20 South African crime- fiction wave hits Cambridge
- Business - May 20 Brazil ’still not a priority’ in the eyes of the media
- Life Sciences - May 20 Studying the unseen activity in bacteria chatter and a nation's bereavement
Bourne pursuit: Improving computer tracking of human activity
But researchers at the University of Michigan have found a way to improve a computer’s human-tracking accuracy by more than 30 percent by looking not only at where the targets are going, but also at what they’re doing.
"By creating software that understands which activity a person or a group of people is performing, we can obtain much more robust and stable tracking results," says Silvio Savarese, professor of electrical engineering and computer science. "This is a new way of solving the tracking problem and can potentially revolutionize the way researchers look at the tracking problem in general."
Savarese and doctoral student Wongun Choi conducted the research.
"Our method reduces the computational complexity and makes it possible to solve the problem of inferring what a person will do based on their activities as an individual, their interactions with other individuals and their behavior in larger groups "
In order to say anything useful about what its video feed sees, a computer needs to be able to track people and things moving through the scene. Already, computers can identify and track people who are standing or walking, but camera movements and obstacles that temporarily hide targets can throw them off. In order to make computer tracking more reliable, Savarese’s team taught the software to recognize interactions such as people walking together, standing in a line or crossing a street.
The motions of an individual give information about his or her interactions, and the interactions can predict future behavior of an individual. For instance, when two people appear to be walking and talking together, the computer can connect their tracks. If the pair then pass behind an obstacle with a third person, the computer now has the intuition to predict that when the individuals reappear, the two in conversation will probably still be together.
If such advanced software tries to follow the behaviors of targets with "brute force"--that is, by considering every possible interaction that could occur and deciding which is most likely--Savarese says that it could take years to give its tracking solution. Ideally, for applications like vehicle collision prevention, such software should run in real time.
To speed things up, the team taught their software to think more like a human. They fed it example videos with targets and behaviors labeled. That way, the computer could capitalize on the analytical strength of our brains: recognizing patterns based on previous experience.
"Our method reduces the computational complexity and makes it possible to solve the problem of inferring what a person will do based on their activities as an individual, their interactions with other individuals and their behavior in larger groups," Savarese says.
His research team will continue to speed up the process, and he reports that a simplified version of the tracking software is approaching real-time operation.
The problem of tracking targets is significant in many fields, from robot vision to observing animal herds in the wild and picking out suspicious activity in a crowd. The application Savarese has in mind would aid drivers, keeping an eye on the pedestrians and sounding an alarm or braking if one of them is about to take an unexpected step into the street.
Last job offers
- Computer Science - 21.5
PHD Candidate in Healthcare Innovation Management
- Computer Science - 15.5
Computer Scientist specialized in Mobile Devices
- Pedagogy - 15.5
Doktorandin oder Doktorand
- Environmental Sciences - 14.5
PhD Position Agent-Based Modelling (13 TV-L, 50%)
- Business - 14.5
Wissenschaftliche/r Mitarbeiter/in Steuern
- Business - 14.5
Assistenzprofessur für Betriebswirtschaftliche Steuerlehre und Internationales Steuerrecht
- Social Sciences - 20.5
Professor, Social Policy
- Pedagogy - 20.5
Senior Lecturer / associate Professor - Associate Director of Teaching and Learning
- Psychology - 17.5
Juniorprofessur (W1) für Sozialpsychologie
- Life Sciences - 17.5
Juniorprofessur für High Throughput Genomics
- Medicine - 20.5
Associate Professor / Lecturer in Biostatistics
- History - 17.5
Professor of Early Modern British History
- Medicine - 18.5
Assistant Professor, Health Policy 1
- Medicine - 18.5
Assistant Professor, Health Policy 2