Tracking-Learning-Detection (TLD)

TLD is an award-winning, real-time algorithm for tracking of unknown objects in video streams. The object of interest is defined by a bounding box in a single frame. TLD simultaneously tracks the object, learns its appearance and detects it whenever it appears in the video. The result is a real-time tracking that often improves over time.

TLD has been developed by Zdenek Kalal during his PhD thesis supervised by Krystian Mikolajczyk and Jiri Matas. The main contributions of TLD have been presented at international computer-vision conferences. For his work on TLD, Zdenek Kalal has been awarded the UK ICT Pioneers 2011.

Fast motion


Similar objects

Low-textured objects


TLD has been released under GPL v3.0. You can download the source code, read installation guide and participate in a discussion group.

Commercial Version

A license has to be purchased for using TLD in closed source projects. The licencing is managed the University of Surrey. Please contact the Technology Transfer Office at the University of Surrey for further information.

(c) 2013 Zdenek Kalal