TY  - JOUR
AU  - Li, Jiaxi
AU  - Wang, Binbin
AU  - Ma, Huijun
AU  - Gao, Longfei
AU  - Fu, Heran
PY  - 2024
DA  - 2024/05/15
TI  - Visual Feature Extraction and Tracking Method Based on Corner Flow Detection
JO  - ICCK Transactions on Intelligent Systematics
T2  - ICCK Transactions on Intelligent Systematics
JF  - ICCK Transactions on Intelligent Systematics
VL  - 1
IS  - 1
SP  - 3
EP  - 9
DO  - 10.62762/TIS.2024.136895
UR  - https://www.icck.org/article/abs/TIS.2024.136895
KW  - computer vision
KW  - feature tracking
KW  - optical flow method
KW  - visual features
KW  - visual tracking
AB  - Front-end feature tracking based on vision is the process in which a robot captures images of its surrounding environment using a camera while in motion. Each frame of the image is then analyzed to extract feature points, which are subsequently matched between pairwise frames to estimate the robot’s pose changes by solving for the variations in these points. While feature matching methods that rely on descriptor-based approaches perform well in cases of significant lighting and texture variations, the addition of descriptors increases computational cost and introduces instability. Therefore, in this paper, a novel approach is proposed that combines sparse optical flow tracking with Shi-Tomasi corner detection, replacing the use of descriptors. This new method offers improved stability in situations of challenging lighting and texture variations while maintaining lower computational cost. Experimental results, validated using the OpenCV library on the Ubuntu operating system, demonstrate the algorithm's effectiveness and efficiency.
SN  - 3068-5079
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Li2024Visual,
  author = {Jiaxi Li and Binbin Wang and Huijun Ma and Longfei Gao and Heran Fu},
  title = {Visual Feature Extraction and Tracking Method Based on Corner Flow Detection},
  journal = {ICCK Transactions on Intelligent Systematics},
  year = {2024},
  volume = {1},
  number = {1},
  pages = {3-9},
  doi = {10.62762/TIS.2024.136895},
  url = {https://www.icck.org/article/abs/TIS.2024.136895},
  abstract = {Front-end feature tracking based on vision is the process in which a robot captures images of its surrounding environment using a camera while in motion. Each frame of the image is then analyzed to extract feature points, which are subsequently matched between pairwise frames to estimate the robot’s pose changes by solving for the variations in these points. While feature matching methods that rely on descriptor-based approaches perform well in cases of significant lighting and texture variations, the addition of descriptors increases computational cost and introduces instability. Therefore, in this paper, a novel approach is proposed that combines sparse optical flow tracking with Shi-Tomasi corner detection, replacing the use of descriptors. This new method offers improved stability in situations of challenging lighting and texture variations while maintaining lower computational cost. Experimental results, validated using the OpenCV library on the Ubuntu operating system, demonstrate the algorithm's effectiveness and efficiency.},
  keywords = {computer vision, feature tracking, optical flow method, visual features, visual tracking},
  issn = {3068-5079},
  publisher = {Institute of Central Computation and Knowledge}
}