Abstract
According to the features of infrared dim point targets, this paper adopts the method of background suppression before high-pass filter in order to suppress the non linear distribution and then the threshold segmentation in order to separate the infrared point targets efficiently from low SNR and complex background. At the same time, the spot targets are detected by aggregating point targets that have been separated. This algorithm can not only reduce operation but also is applicable to some complex cases where the point targets and spot targets exist at one time.
Original language | English |
---|---|
Pages (from-to) | 40-41+60 |
Journal | Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics |
Volume | 23 |
Issue number | 8 |
Publication status | Published - Aug 2001 |
Keywords
- Background noise
- Image recognition
- Target detection