Because of the advantages of simple construction, low cost of protection of unit length and wide detection range, the fiber perimeter intrusion detection has become a hot research field both at home and abroad. Positioning type vibration fiber detection machine outputs huge sensor array signals. The data volume is very large and needs high real-time processing requirement. Based on the locating optical fiber perimeter security system engineering project, NVIDIA's Compute Unified Device Architecture(CUDA) platform on Graphics Processing Unit(GPU) is utilized to accelerate preprocessing algorithm. The results show that the preprocessing algorithm can achieve a good acceleration on GPU, and improve the performance of the system obviously.
Reference
Related
Cited by
Get Citation
姜大闯,潘 鸣,俞旭辉,王 静,桂小刚,汪 瑞,江兆凤,於景暽.基于GPU的振动光纤入侵探测数据预处理算法[J]. Journal of Terahertz Science and Electronic Information Technology ,2019,17(5):898~903