Title :
An algorithm for single-pixel detection and tracking
Author :
Xiong, Yan ; PENG, JIA-XIONG ; Li, Qiang
Author_Institution :
Inst. of Image Recognition & Artificial Intelligence, Huazhong Univ. of Sci. & Technol., Wuhan, China
Abstract :
The paper presents a new method for detection and tracking of pixel-sized moving targets from a time sequence. It uses the pipeline continuity filter for preprocessing, and then tracks the target trajectories in the two projection planes x-t and y-t by a tree-searching algorithm. Experiments show the advantage of this method for the detection and tracking of arbitrary target trajectories in high noise environments without some constraints that most other algorithms require for similar tasks
Keywords :
array signal processing; filtering and prediction theory; image sequences; infrared imaging; motion estimation; parallel algorithms; parameter estimation; pipeline processing; search problems; signal detection; tracking; trees (mathematics); high noise environments; pipeline continuity filter; pixel-sized moving targets; preprocessing; single-pixel detection; target trajectories; time sequence; tracking; tree-searching algorithm; Filling; Filtering; Filters; Image sequences; Noise reduction; Object detection; Pipelines; Pixel; Target tracking; Trajectory;
Conference_Titel :
Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on
Print_ISBN :
0-7803-1865-X
DOI :
10.1109/SIPNN.1994.344965
