Design of multi-spectral images real-time segmentation system
| Autor: | Bo Zhai, Yameng Han, Youshan Qu, Jiang Zhou |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Segmentation-based object categorization
business.industry Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Scale-space segmentation Image processing Image segmentation Image texture Parallel processing (DSP implementation) Digital image processing Computer vision Segmentation Artificial intelligence business |
| Zdroj: | SPIE Proceedings. |
| ISSN: | 0277-786X |
| DOI: | 10.1117/12.2075966 |
| Popis: | In order to realize the real-time segmentation processing of multi-spectral images in practice, a real-time multi-spectral images segmentation system composed of four TMS320C6455 DSPs, two Virtex-4 aV4 XC4VLX80 aFPGAs and one Virtex-2 Pro a V2 Pro20 aFPGA is designed. Through the optimization of the cooperation processing of the multi-DSP and multi-FPGA, the parallel multi-task processing ability of the DSPs and the effective interf ace coordination ability of the FPGAs in the built system are used fully. In order to display the processing ability, the segmentation test experiments of 10 spectra visible images, with 1024×1024, segmented by the Multi-scale Image Segmentation Method, was done in the built multi-spectral images segment system. The experiment re sults prove that the multi-DSP and multi-FPGA multi-spectral images processing system designed in this paper satisfies the real-time processing requirement in engineering practice. Keywords: Multi-spectral Imagery, Image Segmentation, Multi-scale Image Segmentation Method, Multi-DSP, Multi-FPGA, Parallel Processing. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|