摘要
针对布匹瑕疵检测系统在工业应用中的实时性需求,在分析了小规模过完全字典布匹瑕疵检测算法的基础上,将该算法从VS平台移植至TMS320C6678平台,并提出了一种基于特征拆分的并行方案以充分利用各个内核资源,采用优化的内核间同步、通信方案,实现了高效的多核并行处理,大大减少了算法耗时。实验结果表明,该方法是可行、有效的,并且极大地提升了布匹瑕疵检测系统的实时处理能力,为以后工业应用打下了良好的基础。
Aiming at the real-time requirement of the fabric defect detection systems in industrial application,the fabric defects detection algorithm via small scale over-complete basis set were analyzed,and it was transformed from VS to TMS320C6678.Moreover,a parallel scheme based on features' split was proposed to make full use of each core's resources.Incorporating with optimized synchronization and communication method,it achieves efficient multicore parallel processing and reduces the time-consuming greatly.Experimental results show that the method is feasible and effective,and the real-time processing capability of fabric defect detection system based on TMS320C6678 has improved so much,making a solid foundation for future industrial applications.
出处
《科学技术与工程》
北大核心
2014年第30期202-205,213,共5页
Science Technology and Engineering
基金
国家自然科学基金项目(61072135)资助