基于卷积神经网络的可见光和红外跟踪算法

Object Tracking Algorithm Based on Convolutional Neural Network for Visible and Infrared Video Sequences

针对目标遮挡、运动模糊和复杂背景等问题,提出一种可见光和红外视频融合的有效卷积神经网络的相关目标跟踪算法,以提高跟踪性能。两层的卷积神经网络通过使用卷积滤波器,提取可见光和红外视频的稀疏特征。其中的卷积滤波器包含两种类型,目标滤波器和相关滤波器。在第一帧中,算法使用一组归一化融合局部图像作为目标滤波器。在其它帧,算法使用相关模型,生成相关滤波器,将前景和背景信息相结合,构建精确的表观模型。实验表明,上述无需训练的轻量级跟踪算法,与传统的目标跟踪算法相比,显著的提升了目标跟踪性能。

To address the problems such as occlusion,motion blur and complex backgrounds,a novel relative object tracking algorithm using a convolutional neural network is proposed aiming to boost the tracking performance.A two-layer convolutional neural network extracts sparse feature representation of visible and infrared sequences via convolutional filters.The convolutional filters contain two types,object filter,and relative filters.In the first frame,we employed a set of normalized fusion patches as the object filters.Moreover,a relative model was explored to generate relative filters,which integrated information from both foreground and background to build accurate appearance model.This algorithm without training is robust and efficient.Quantitative and qualitative evaluations demonstrate that the performance of this algorithm improves significantly the performance of target tracking.