Small dim object tracking using frequency and spatial domain information

作者：

Highlights：

• A novel algorithm for detecting and tracking small dim targets in Infrared (IR) image sequences is presented.

• Using a Dual-Tree Complex Wavelet Transform, a CFAR detector is applied to find potential targets.

• A Support Vector Machine (SVM) classification is applied to refine potential targets.

• The combination of the frequency and spatial domain information can accurately provide moving object trajectories.

摘要

•A novel algorithm for detecting and tracking small dim targets in Infrared (IR) image sequences is presented.•Using a Dual-Tree Complex Wavelet Transform, a CFAR detector is applied to find potential targets.•A Support Vector Machine (SVM) classification is applied to refine potential targets.•The combination of the frequency and spatial domain information can accurately provide moving object trajectories.

论文关键词：Dim object tracking,Support Vector Machine (SVM),Dual-Tree Complex Wavelet Transform (DT-CWT),Constant False Alarm Rate (CFAR) Detection

论文评审过程：Received 2 July 2015, Revised 18 February 2016, Accepted 4 April 2016, Available online 12 April 2016, Version of Record 26 May 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.04.001