由于成像算法复杂,而且雷达数据量大、速率高,方位预处理和转置存储器的实时实现具有很大的挑战性。
Due to the complexity of the image algorithm and the large amount and high-speed of the radar data transaction, it is a real challenge for real-time realization of azimuth preprocess and CTM.
讨论了复数矩阵的数据结构和共轭转置运算的算法实现,并给出该算法的时间复杂度。
The paper deals with the data structure of plural matrix and the achievement of method about associate operation, and gives its complex degree of time.
为了解决数据量庞大、高速数据存取的问题,本文采用了FPGA芯片和同步动态存储器(SDRAM)来实现矩阵转置运算。
For the problem of huge data storage, use SDRAM to store the data, and use FPGA to control SDRAM to complete the transpose.
相对于行列分解法,该算法节省了约一半的乘法次数,省略了数据的转置存储过程,而加法的运算复杂度基本维持不变。
Compared to Roll and Column Method (RCM), this new fast algorithm reduces half of multiplication times, eliminates transposition of data, and retains computational complexity of addition.
相对于行列分解法,该算法节省了约一半的乘法次数,省略了数据的转置存储过程,而加法的运算复杂度基本维持不变。
Compared to Roll and Column Method (RCM), this new fast algorithm reduces half of multiplication times, eliminates transposition of data, and retains computational complexity of addition.
应用推荐