Researchers have adapted deep learning techniques in a multi-object tracking framework, overcoming short-term occlusion and achieving remarkable performance without sacrificing computational speed.

Quarterly of Applied Mathematics, Vol. 60, No. 4 (December 2002), pp. 737-771 (35 pages) We explore a coherent statistical/Bayesian framework for tracking rigid or non-rigid objects in highly ...

Tracking objects in 3D space and predicting their 6DoF pose is an essential task in computer vision. State-of-the-art approaches often rely on object texture to tackle this problem. However, while ...

Researchers at the University of Toronto Institute for Aerospace Studies (UTIAS) have introduced a pair of high-tech tools that could improve the safety and reliability of autonomous vehicles by ...

The latest version of ARCore, Google's augmented reality developer platform for Android phones, now includes a depth API. The API was released as a preview back in December, but now it's live for ...