改进证据融合次序的目标识别算法

Target Recognition Algorithm Based on Improved Evidence Fusion Order

为提高证据冲突情况下目标识别的准确性,提出了基于证据综合可信度改进证据融合次序的目标识别算法.新算法基于证据之间的差异性大小来确定度量冲突所用参数并给出了证据综合可信度计算公式,依此对证据融合次序进行优化及将冲突因子所含矛盾信息在相关焦元间进行加权再分配.算例和仿真实验结果表明,新算法能够有效处理不同类型冲突证据.特别是在证据高冲突情况下,与多维证据直接融合算法相比,新算法的正确目标识别概率高出0.15~0.24个点且其时间花费低于多维证据直接融合算法时间花费的1/10.因此,所提算法是一种具有较高稳定性和较低时间花费的目标识别算法.

In order to improve the accuracy of the target recognition under the condition of conflicting evidence, we propose a target recognition algorithm improving the order of the evidence fusion by using the comprehensive reliability of the evidence. The new algorithm determines the parameters of the conflict measurement based on the differences between every two pieces of evidence, and gives the formula for calculating the comprehensive reliability of evidence. On this basis, the order of evidence fusion is optimized, and the contradictory information contained in conflicting factors is redistributed by weight among relevant focal elements. The numerical examples and the simulation results show that the new algorithm can effectively deal with different types of conflicting evidence. Especially in the case of highly conflicting evidence, compared with the direct fusion algorithm of multi-dimensional evidence, the correct target recognition probability of the new algorithm is improved by 0.15 - 0.24 points, and the time spent is less than one-tenth of that of the direct fusion algorithm of multi-dimensional evidence. Therefore, the proposed algorithm is a target recognition algorithm with high stability and less time spent.