王军,,
胡磊,
田畅,
曾明勇,
杜麟
中国人民解放军陆军工程大学通信工程学院 ??南京 ??210007
详细信息
作者简介:吴泽民:男,1973年生,副教授,硕士生导师,研究方向为图像分析、数据融合
王军:男,1995年生,硕士生,研究方向为深度学习、图像与视频的显著度研究
胡磊:男,1987年生,博士,研究方向为目标跟踪与识别、数据融合
田畅:男,1963年生,教授,博士生导师,研究方向为数据链技术、图像视频处理
曾明勇:男,1988年生,博士生,研究方向为目标检测与识别
杜麟:男,1990年生,博士生,研究方向为视频编码与视频传输保障
通讯作者:王军 wangjun_ice@126.com
中图分类号:TP391.41计量
文章访问数:1865
HTML全文浏览量:533
PDF下载量:79
被引次数:0
出版历程
收稿日期:2018-03-16
修回日期:2018-08-22
网络出版日期:2018-08-31
刊出日期:2018-12-01
Co-saliency Detection Based on Convolutional Neural Network and Global Optimization
Zemin WU,Jun WANG,,
Lei HU,
Chang TIAN,
Mingyong ZENG,
Lin DU
College of Communications Engineering, Army Engineering University of PLA, Nanjing 210007, China
摘要
摘要:针对目前协同显著性检测问题中存在的协同性较差、误匹配和复杂场景下检测效果不佳等问题,该文提出一种基于卷积神经网络与全局优化的协同显著性检测算法。首先基于VGG16Net构建了全卷积结构的显著性检测网络,该网络能够模拟人类视觉注意机制,从高级语义层次提取一幅图像中的显著性区域;然后在传统单幅图像显著性优化模型的基础上构造了全局协同显著性优化模型。该模型通过超像素匹配机制,实现当前超像素块显著值在图像内与图像间的传播与共享,使得优化后的显著图相对于初始显著图具有更好的协同性与一致性。最后,该文创新性地引入图像间显著性传播约束因子来克服超像素误匹配带来的影响。在公开测试数据集上的实验结果表明,所提算法在检测精度和检测效率上优于目前的主流算法,并具有较强的鲁棒性。
关键词:协同显著性/
深度学习/
卷积神经网络/
协同优化
Abstract:To solve the problems in current co-saliency detection algorithms, a novel co-saliency detection algorithm is proposed which applies fully convolution neural network and global optimization model. First, a fully convolution saliency detection network is built based on VGG16Net. The network can simulate the human visual attention mechanism and extract the saliency region in an image from the semantic level. Second, based on the traditional saliency optimization model, the global co-saliency optimization model is constructed, which realizes the transmission and sharing of the current superpixel saliency value in inter-images and intra-image through superpixel matching, making the final saliency map has better co-saliency value. Third, the inter-image saliency value propagation constraint parameter is innovatively introduced to overcome the disadvantages of superpixel mismatching. Experimental results on public test datasets show that the proposed algorithm is superior over current state-of-the-art methods in terms of detection accuracy and detection efficiency, and has strong robustness.
Key words:Co-saliency/
Deep Learning/
Convolutional Neural Network/
Global Optimization
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=f3152ef5-e4fe-4dad-b5b3-1f1e36352ffe