Motion To Discover Objects in Videos

Researchers at Carnegie Mellon University's Robotics Institute have shown that computer vision systems can more easily detect objects in motion - like a car driving down the street or a person walking in a crosswalk - than stationary objects. Martial Hebert , dean of CMU's School of Computer Science and a professor in the Robotics Institute, and robotics Ph.D. candidate Zhipeng Bao collaborated on The research could help computers and robots better automatically detect objects in videos. Object recognition is fundamental to understanding real-world scenes, so developing motion-guided methods for discovering objects could improve autonomous driving. It could also prove useful for retail robotics, robotic manipulation and robots in the home. Working with colleagues from Toyota, the University of California, Berkeley, and the University of Illinois Urbana-Champaign, the CMU researchers developed a framework called MoTok that enables the computer to identify features of things it sees moving on its own. MoTok then uses these features to reconstruct the object, allowing the computer to discover the object in a way that enables it to find that same object again.