基于深度卷积神经网络的运动目标光流检测方法

The optical flow detection method of moving target using deep convolution neural network

运动目标检测是物体检测领域的一个重要研究方向,在目标识别中有着至关重要的作用。针对传统运动检测方法精度不高、无法对运动目标进行检测,本文将深度卷积神经网络引入到运动目标光流检测中,将前后帧图像及目标光流场图像作为网络的输入,自适应地学习运动目标光流,并通过对网络放大架构的优化及网络的精简,同时采用数据增广等技术,设计出精度与实时性兼顾的目标物体光流检测网络。实验结果表明,本文方法在运动目标的光流场检测中有更好的表现,SS-sp和CS-sp网络相比原网络在检测精度上均提高了约5.0%,同时大幅减少了网络的运行时间,基本满足实时检测的要求。

Moving target detection is an important research direction of object detection,and it plays an important role in target recognition.The accuracy of traditional motion detection methods is low,which are unable to only detect the required moving target.In this study,deep convolutional neural network is introduced into the optical flow detection of moving target.In this method,a pair of images and optical flow fields of target are used as inputs of the network to adaptively study the target optical flow.Furthermore,through optimization of the expanding part of the network and the simplification of the network,and combined with many data augmentation technologies,the optical flow detection network of target object with both accuracy and real-time is designed.Experimental results show that the proposed method has better performance in the optical flow detection of moving target.SS-sp and CS-sp network are improved by about 5.0%compared to the original network on the precision and the runtime of the network is significantly reduced,which meet the requirements of real-time detection.