scorecardresearch
Follow Us:
Friday, February 26, 2021

IISc researchers develop software platform for tracking missing persons, objects

Yogesh Simmhan, associate professor at the Department of Computational and Data Sciences (CDS), said such analysis would also be helpful for automated traffic control as well as other Smart City initiatives.

By: Express Web Desk | Bengaluru |
Updated: January 22, 2021 4:14:17 pm
The platform, researchers claim, enables apps and algorithms to “intelligently track and analyse” video feeds from cameras spread across cities. (Representational image)

Tracking missing persons or objects could soon get easier, thanks to a unique software platform developed by researchers at the Indian Institute of Science (IISc). The platform, researchers claim, enables apps and algorithms to “intelligently track and analyse” video feeds from cameras spread across cities.

Yogesh Simmhan, associate professor at the Department of Computational and Data Sciences (CDS), said such analysis would also be helpful for automated traffic control as well as other Smart City initiatives.

“There has been a lot of research on increasing the accuracy of these models, but sufficient attention hasn’t been paid to how you can make (the model) work as part of a larger operation,” Simmhan said. He added that ‘Anveshak’, the software platform, was developed to enable an efficient running of tracking models, plugging in advanced computer vision tools and intelligently adjusting different parameters, such as the search radius of a camera network, in real-time.

The team of researchers recently published its work to show how Anveshak could come in handy when it comes to tracking missing objects (such as a stolen car) across a 1,000-camera network. “A key feature of the platform is that it allows a tracking model or algorithm to focus only on feeds from certain cameras along an expected route and tune out other feeds. It can also automatically increase or decrease the search radius or “spotlight” based on the object’s last known position,” a member of the research team said.

Simmhan said that the platform also enables tracking to continue uninterrupted even if resources such as the type and number of computers that analyse the feeds are limited. “In the field, the amount of computing power you have is not really negotiable on the fly. The devices are static. You have to do the best you can with what is available. For example, if the search radius needs to be increased and the computer becomes overwhelmed, the platform will automatically start dropping the video quality to save on bandwidth, while continuing to track the object,” he said.

He said that existing platforms are usually cast in stone and do not offer much flexibility to modify the model as the situation changes, or test new models over the same camera network.

“Many cities worldwide have set up thousands of video cameras. Machine learning models can scour through the feeds from these cameras for a specific purpose. These models cannot work by themselves and instead run on a software platform or “environment” (somewhat similar to a computer’s operating system),” he said.

A statement released by IISc said the same team of researchers were behind the winning entry for the IEEE TCSC SCALE Challenge Award in 2019.

“Simmhan’s lab showed how Anveshak could potentially be used to control traffic signals and automatically open up “green routes” for ambulances to move faster. The platform used a machine learning model to track an ambulance on a simulated Bengaluru road network with about 4,000 cameras. It also employed a “spotlight tracking algorithm” to automatically restrict which feeds needed to be analysed based on where the ambulance was expected to go,” the statement read.

📣 The Indian Express is now on Telegram. Click here to join our channel (@indianexpress) and stay updated with the latest headlines

For all the latest Education News, download Indian Express App.

Advertisement
Advertisement
Advertisement
Advertisement