基于眼动点视觉先验与边缘优化的显著性检测  

Saliency Detection Based on Eye Fixation Prediction and Boundary Optimization

作　　者：刘翔宇 蹇木伟 鲁祥伟 何为凯 李晓峰[3] 尹义龙 LIU Xiang-yu;JIAN Mu-wei;LU Xiang-wei;HE Wei-kai;LI Xiao-feng;YIN Yi-long(School of Computer Science and Technology,Shandong University of Finance and Economics,Jinan 250014,China;School of Aeronautics,Shandong Jiaotong University,Jinan 250357,China;School of Computer Science and Technology,Shandong Jianzhu University,Jinan 250000,China)

机构地区：[1]山东财经大学计算机科学与技术学院,济南250014 [2]山东交通学院航空学院,济南250357 [3]山东建筑大学计算机科学与技术学院,济南250000

出　　处：《计算机科学》2021年第S01期107-112,共6页Computer Science

基　　金：国家自然科学基金(61976123);山东省泰山青年学者计划;山东省基础研究重点发展计划(ZR2020ZD44)。

摘　　要：图像显著性检测是计算机视觉中的基础研究课题之一。当前基于深度学习的方法虽然能够有效提高显著性检测结果的准确性,但是在显著性目标的物体边缘细节提取方面还不能令人满意。为此,提出了一种基于眼动点预测先验的边缘细化网络用于显著性目标提取。首先,对输入图像进行眼动点预测,将生成的特征图像作为后续显著性检测的视觉先验;其次,利用多注意力机制VGG16网络进行显著性目标特征提取;最后,对特征图像进行质量优化处理,进一步提升图像显著图的质量。实验结果表明,在3个公开数据集(DUTS,ECSSD,HKU-IS)上,所提方法与其他6个主流方法相比,取得了更好的显著性检测效果。Saliency detection is one of the most fundamental challenges in computer vision.Although the rapid development of deep learning has greatly improved the accuracy of saliency-detection results,the extraction of details of salient object is still unsatisfactory.Therefore,this paper proposes an edge refinement network based on eye-fixation prediction priori for salient object detection.Firstly,eye-fixation extraction is carried out on the original image and the extracted feature image is used as the visual priori of subsequent saliency detection.Secondly,the multi-attention mechanism of VGG16 network is used for feature extraction,and finally the feature image is refined to improve the quality of the saliency image.Experimental results show that,compared with other 6 state-of-the-art methods,the proposed method achieves better results in 3 open-accessed data sets(i.e.DUTS,ECSSD,HKU-IS).

关 键 词：显著性检测 注意力机制 眼动点预测 边缘优化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]