Using deep-learning techniques to locate potential human activities in videos

August 30, 2018, Agency for Science, Technology and Research (A*STAR), Singapore
Using deep-learning techniques to locate potential human activities in videos
The 'YoTube' detector helps makes AI more human-centered. Credit: iStock

When a police officer begins to raise a hand in traffic, human drivers realize that the officer is about to signal them to stop. But computers find it harder to work out people's next likely actions based on their current behavior. Now, a team of A*STAR researchers and colleagues has developed a detector that can successfully pick out where human actions will occur in videos, in almost real-time.

Image analysis technology will need to become better at understanding human intentions if it is to be employed in a wide range of applications, says Hongyuan Zhu, a computer scientist at A*STAR's Institute for Infocomm Research, who led the study. Driverless cars must be able to detect police officers and interpret their actions quickly and accurately, for safe driving, he explains. Autonomous systems could also be trained to identify suspicious activities such as fighting, theft, or dropping dangerous items, and alert security officers.

Computers are already extremely good at detecting objects in static images, thanks to deep learning techniques, which use to process complex image information. But videos with moving objects are more challenging. "Understanding human actions in videos is a necessary step to build smarter and friendlier machines," says Zhu.

Previous methods for locating potential human actions in videos did not use deep-learning frameworks and were slow and prone to error, says Zhu. To overcome this, the team's YoTube combines two types of in parallel: a static neural network, which has already proven to be accurate at processing still images, and a recurring neural network, typically used for processing changing data, for speech recognition. "Our method is the first to bring detection and tracking together in one pipeline," says Zhu.

The team tested YoTube on more than 3,000 videos routinely used in computer vision experiments. They report that it outperformed state-of-the-art detectors at correctly picking out potential human actions by approximately 20 per cent for videos showing general everyday activities and around 6 per cent for sports videos. The detector occasionally makes mistakes if the people in the are small, or if there are many people in the background. Nonetheless, Zhu says, "We've demonstrated that we can detect most potential human action regions in an almost real-time manner."

Explore further: Detecting 'deepfake' videos in the blink of an eye

More information: Hongyuan Zhu et al. YoTube: Searching Action Proposal Via Recurrent and Static Regression Networks, IEEE Transactions on Image Processing (2018). DOI: 10.1109/TIP.2018.2806279

Related Stories

Detecting 'deepfake' videos in the blink of an eye

August 29, 2018

A new form of misinformation is poised to spread through online communities as the 2018 midterm election campaigns heat up. Called "deepfakes" after the pseudonymous online account that popularized the technique – which ...

Computer program looks five minutes into the future

June 13, 2018

Computer scientists from the University of Bonn have developed software that can look a few minutes into the future. The program first learns the typical sequence of actions, such as cooking, from video sequences. Based on ...

Robots do kitchen duty with cooking video dataset

January 5, 2015

Now that we have robots that walk, gesture and talk, roboticists are interested in a next level: How can they learn more than they already know? The ability of these machines to learn actions from human demonstrations is ...

Recommended for you

Team breaks world record for fast, accurate AI training

November 7, 2018

Researchers at Hong Kong Baptist University (HKBU) have partnered with a team from Tencent Machine Learning to create a new technique for training artificial intelligence (AI) machines faster than ever before while maintaining ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.