TY - JOUR
T1 - Automatic detection and localization of markers in stereotactic neurosurgery
AU - Meng, Cai
AU - Yan, Haozheng
AU - Li, Yanjie
AU - Liu, Da
AU - Wang, Tianmiao
PY - 2013/3
Y1 - 2013/3
N2 - The techniques of image processing and computer vision were used to study the automatic detection and localization of the markers in stereotactic neurosurgery, and a method for markers' detection and localization was proposed as below: Firstly, design two kinds of markers with special texture, noted as 'A' and 'B', to improve the detection rate. Secondly, detect 'B' markers and 'A' markers and search for the lost 'A' markers based on the epipolar constraint. Finally, match the detected markers in the binocular camera images and calculate the coordinate of markers. The detection rate and localization accuracy of the approach were tested by the experiment. The results showed that the markers' false rate was 0. 08%, the markers' lost rate was zero, the average processing time per pair of images was less than 200ms, and the markers' average localization error was less than 0. 55mm. This approach can simplify the registration procedure of stereotactic neurosurgery and continuously update the registration data by tracking the markers attached to the head.
AB - The techniques of image processing and computer vision were used to study the automatic detection and localization of the markers in stereotactic neurosurgery, and a method for markers' detection and localization was proposed as below: Firstly, design two kinds of markers with special texture, noted as 'A' and 'B', to improve the detection rate. Secondly, detect 'B' markers and 'A' markers and search for the lost 'A' markers based on the epipolar constraint. Finally, match the detected markers in the binocular camera images and calculate the coordinate of markers. The detection rate and localization accuracy of the approach were tested by the experiment. The results showed that the markers' false rate was 0. 08%, the markers' lost rate was zero, the average processing time per pair of images was less than 200ms, and the markers' average localization error was less than 0. 55mm. This approach can simplify the registration procedure of stereotactic neurosurgery and continuously update the registration data by tracking the markers attached to the head.
KW - Artificial markers
KW - Epipolar constraint
KW - Image registration
KW - Stereotactic neurosurgery
UR - https://www.scopus.com/pages/publications/84877040372
U2 - 10.3772/j.issn.1002-0470.2013.03.008
DO - 10.3772/j.issn.1002-0470.2013.03.008
M3 - 文章
AN - SCOPUS:84877040372
SN - 1002-0470
VL - 23
SP - 270
EP - 276
JO - Gaojishu Tongxin/Chinese High Technology Letters
JF - Gaojishu Tongxin/Chinese High Technology Letters
IS - 3
ER -