New research from Binghamton University, State University of New York, could make it easier to track and process suspicious activity in surveillance footage.
Traditional surveillance cameras do not always detect suspicious activities or objects in a timely manner. To combat this issue, Binghamton University Associate Professor of Electrical and Computer Engineering Yu Chen and his team developed a hybrid lightweight tracking algorithm known as Kerman (Kernelized Kalman filter). The research uses single board computers (SBCs) mounted on surveillance cameras to process videos and extract features that focus on enhanced detection of people, tracking their movement and recognizing behaviors for increased surveillance coverage.
Kerman - Algorithm - Cameras - Edge - Source
"The Kerman algorithm enables the smart cameras at the edge (the source of data generation) to raise an alert as soon as something suspicious is detected in the incoming video streams," said Chen.
The research team introduced SBCs...
Wake Up To Breaking News!