脉冲神经网络在运动目标检测中的应用  

Application of Pulse Neural Network in Moving Target Detection

作　　者：林梅燕[1] 吴庆祥[1] 蔡荣太[1] 郭红英[1] 

机构地区：[1]福建师范大学物理与光电信息科技学院,福建福州350007

出　　处：《现代电子技术》2010年第8期145-147,150,共4页Modern Electronics Technique

基　　金：福建自然科学基金资助项目:基于脉冲神经网络的运动目标识别算法研究(09J05141)

摘　　要：近几年,在智能监控系统中,广泛应用了基于生物视觉原理的运动目标检测与跟踪计算模型。这里提出一种基于神经轴突延迟机制,利用脉冲神经元网络模型对运动目标进行检测与跟踪的算法,该神经网络模型是利用轴突延迟脉冲神经网络模拟人类的视觉特性,从而提取运动目标,并具体分析脉冲神经元网络算法的实际意义。实验结果表明,该算法能够动态并行地进行运动目标提取,可通过硬件实现而应用于监控系统中。In recent years, the moving target detection and tracking computational models based on biological visual principle are widely used in intelligent surveillance systems. An algorithm for moving object detection and tracking by means of the pulse neuroid model based on the principle of axonal delay is proposed. The neural network model simulates the visual characteristics of the human visual system by axons delay pulse neural network in order to extract the moving target and anlyse the actual significance of pulse neuroid algorithm. The results show that the algorithm can dynamically extract moving objects in a parallel architecture, and can be applied in surveillance systems to extract the moving objects if it is implemented in hardware.

关 键 词：脉冲神经网络 轴突延迟 运动检测 生物视觉 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391[自动化与计算机技术—控制科学与工程]