Realtime Affine-photometric KLT Feature Tracker on GPU in CUDA Framework

Junsik Kim, Myung Hwangbo, and Takeo Kanade
Workshop on Embedded Computer Vision (ECV), 2009 (held in conjunction with ICCV), October, 2009.


Download
  • Adobe portable document format (pdf) (4MB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
Feature tracking is one of fundamental steps in many computer vision algorithms and the KLT (Kanade-Lucas-Tomasi) method has been successfully used for optical flow estimation. There has been also much effort to implement KLT on GPUs to increase the speed with more features. Many implementations have chosen the translation model to describe a template motion because of its simplicity. However, a more complex model is demanded for appearance change especially in outdoor scenes or when camera undergoes roll motions. We implement the KLT tracker using an affine-photometric model on GPUs which has not been in a popular use due to its computational complexity. With careful attention to the parallel computing architecture of GPUs, up to 1024 feature points can be tracked simultaneously at a video rate under various 3D camera motions. Practical implementation issues will be discussed in the NVIDIA CUDA framework. We design different thread types and memory access patterns according to different computation requirements at each step of the KLT. We also suggest a CPU-GPU hybrid structure to overcome GPU limitations.

Notes

Text Reference
Junsik Kim, Myung Hwangbo, and Takeo Kanade, "Realtime Affine-photometric KLT Feature Tracker on GPU in CUDA Framework," Workshop on Embedded Computer Vision (ECV), 2009 (held in conjunction with ICCV), October, 2009.

BibTeX Reference
@inproceedings{Kim_2009_6535,
   author = "Junsik Kim and Myung Hwangbo and Takeo Kanade",
   title = "Realtime Affine-photometric KLT Feature Tracker on GPU in CUDA Framework",
   booktitle = "Workshop on Embedded Computer Vision (ECV), 2009 (held in conjunction with ICCV)",
   month = "October",
   year = "2009",
}