激光与光电子学进展, 2018, 55 (10): 101502, 网络出版: 2018-10-14   

基于全部卷积特征融合的显著性检测 下载: 792次

Salient Detection Based on All Convolutional Feature Combination
作者单位
江南大学物联网工程学院, 江苏 无锡 214122
摘要
如何充分利用各级卷积特征是当前显著性检测研究的关键问题。就此提出一种基于融合全部卷积层特征的全卷积神经网络显著性检测方法。首先, 将全部卷积特征映射到内部的多个尺度中, 在每个尺度上联合各级卷积特征预测显著图; 然后, 融合各尺度的显著图, 得到融合显著图; 最后, 通过全连接条件随机场平滑显著图和优化显著边界。实验结果表明, 该方法在ECSSD和SED2数据库上具有较高的准确率、召回率和较低的平均绝对误差, 可为目标识别、机器视觉等应用提供更可靠的预处理结果。
Abstract
In the current saliency detections based on deep learning, how to make full use of the convolution features at all levels is the key issue. In order to solve this problem, we propose a saliency detection method based on full convolution neural network, which is a fusion of all convolutional features. Firstly, all the convolution features are mapped to multiple internal scales, and the saliency maps are predicted by combining the convolutional features of each level on each scale. Then the fused saliency maps are obtained by fusing the saliency maps of each scale. Finally, smooth saliency maps and optimized salient boundaries are obtained through full connected conditional random fields. Experimental results show that the proposed method has higher accuracy, recall rate and lower average absolute error in ECSSD database and SED2 database, and provides more reliable pretreatment results for target recognition, machine vision and other applications.

张松龙, 谢林柏. 基于全部卷积特征融合的显著性检测[J]. 激光与光电子学进展, 2018, 55(10): 101502. Zhang Songlong, Xie Linbo. Salient Detection Based on All Convolutional Feature Combination[J]. Laser & Optoelectronics Progress, 2018, 55(10): 101502.

本文已被 5 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!