李鑫, 陈雷霆, 蔡洪斌, 李建平, 杨帆. 基于双层多尺度神经网络的显著性对象检测算法[J]. 微电子学与计算机, 2018, 35(11): 1-7.
引用本文: 李鑫, 陈雷霆, 蔡洪斌, 李建平, 杨帆. 基于双层多尺度神经网络的显著性对象检测算法[J]. 微电子学与计算机, 2018, 35(11): 1-7.
LI Xin, CHEN Lei-ting, CAI Hong-bing, LI Jian-ping, YANG Fan. Salient Object Detection Algorithm Based on Dual-Layer Multi-Scale Neural Network[J]. Microelectronics & Computer, 2018, 35(11): 1-7.
Citation: LI Xin, CHEN Lei-ting, CAI Hong-bing, LI Jian-ping, YANG Fan. Salient Object Detection Algorithm Based on Dual-Layer Multi-Scale Neural Network[J]. Microelectronics & Computer, 2018, 35(11): 1-7.

基于双层多尺度神经网络的显著性对象检测算法

Salient Object Detection Algorithm Based on Dual-Layer Multi-Scale Neural Network

  • 摘要: 为了提高显著性对象检测的准确率, 本文提出一种基于双层多尺度神经网络的深度模型.不同于现有的深度神经网络模型.首先, 该模型以由精到粗的方式进行深度特征学习, 并且定位显著性对象的初始位置; 然后, 以由粗到精的方式整合多尺度上下文语义信息, 从而精确检测整个显著性对象区域, 输出相应的显著性图; 最后, 为了进一步提高检测结果的准确率, 利用全连接条件随机场对输出的显著性图进行优化, 得到最终的显著性对象检测结果.在多个显著性对象检测公共数据集的验证结果表明, 本文算法在运行效率和准确率上均优于当前传统显著性对象检测算法以及现有的基于深度学习的显著性对象检测算法.

     

    Abstract: To further improve the accuracy of salient object detection, a novel Dual-Layer Multi-Scale Neural Network (DLMSNN) was proposed in this work. Different from existing deep model, the proposed deep model first learned deep features in a fine-to-coarse manner, and roughly located the salient object regions. Then, the model integrated multi-scale contextual information in a coarse-to-fine manner to precisely detect the entire salient object regions, and generated accurate saliency map of the input image. Finally, to further improve the performance, the dense conditional random field algorithm was used to refine the saliency map and produce the final result. The experimental results on several public benchmarks showed that the proposed algorithm outperformed traditional salient object detection methods and existing deep learning-based algorithms.

     

/

返回文章
返回