DocumentCode :
3274110
Title :
Track fast-moving tiny flies by adaptive LBP feature and cascaded data association
Author :
Mingzhong Li ; Zhaozheng Yin ; Thimgan, Matthew S. ; Ruwen Qin
Author_Institution :
Dept. of Comput. Sci. & Syst. Eng., Missouri Univ. of Sci. & Technol., Rolla, MO, USA
fYear :
2013
fDate :
15-18 Sept. 2013
Firstpage :
1172
Lastpage :
1176
Abstract :
Studying the behavior of fruit flies that mimic normal animal motivations can inform us about the molecular mechanisms and biochemical pathways. We build a glass chamber to house flies and record their behaviors in video frame sequences. Due to the challenges of low image contrast, small object size and fast object motion, we propose an adaptive Local Binary Pattern (LBP) feature to detect flies and develop a cascaded data association approach with fine-to-coarse gating region control to track flies in the spatio-temporal domain. Our approach is validated on two long video sequences with very good performance, showing its potential to enable automated characterization of biological processes.
Keywords :
behavioural sciences computing; biology computing; feature extraction; image fusion; image motion analysis; image sequences; object tracking; video signal processing; zoology; adaptive LBP feature; adaptive local binary pattern feature; biochemical pathways; biological processes; cascaded data association approach; fast-moving tiny flies tracking; fine-to-coarse gating region control; flies detection; fruit flies behavior; glass chamber; house flies; image contrast; molecular mechanisms; normal animal motivations; object motion; object size; spatio-temporal domain; video frame sequences; Feature extraction; Glass; Object tracking; Support vector machines; Target tracking; Trajectory; Multiple object tracking; adaptive local binary pattern feature; cascaded data association;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2013 20th IEEE International Conference on
Conference_Location :
Melbourne, VIC
Type :
conf
DOI :
10.1109/ICIP.2013.6738242
Filename :
6738242
Link To Document :
بازگشت