Object Trackers: Approaches and Applications

Summit Track: 
Technical Insights I

Object tracking is a powerful algorithm component and one of the fundamental building blocks for many real-world computer vision applications. Object trackers provide two main benefits when incorporated into a localization module. First, trackers can reduce overall computation and power requirements by allowing a reduction in the frequency at which detections must be generated. Second, trackers can maintain the identity of an object across multiple frames, which is important for many applications. Recent advances in deep learning provide us with a unified method for designing detectors, but we still have many design choices for trackers. In this talk we will describe three basic tracker approaches and their use in video analytics applications including face recognition, people counting and action recognition. We will also provide insights on how recent advances in recurrent neural networks and reinforcement learning can be used for enhancing trackers.


Minje Park

Deep Learning R&D Engineer, Intel

Minje Park is a Computer Vision and Machine Learning engineer in Intel. His main focus is to develop algorithms for real-time video analytics such as face analysis and object localization. He holds Ph.D. in Computer Science from Korea Advanced Institute of Science and Technology (KAIST). Before joining Intel, he worked for Visual Effects and Computer Graphics research and development organizations.

See you at the Summit! May 20-23 in Santa Clara, California!
Register today and reserve your hotel room!