基于堆叠边缘感知模块的显著性目标检测

现有显著性目标检测算法对边缘感知的效果不理想.因此,为了有效利用高层语义信息及低层纹理信息,文中提出基于堆叠边缘感知模块的显著性目标检测算法.采用多尺度骨干网络(Res2Net)作为主干网络提取图像的多尺度、多目标的显著性特征.堆叠边缘感知模块以非对称性方式融合图像高低层信息,增强显著性目标区域.网络输出显著性目标的检测结果.在5个公开数据集上的实验表明,文中算法检测结果较优,同时,在客观评估指标和主观视觉效果上也较优.

Salient Object Detection Based on Stack Edge-Aware Module

To improve the poor performance of the existing salient object detection algorithms in edge perception, a salient object detection algorithm based on stack edge-aware module is proposed to utilize high-level semantic information and low-level texture information effectively. Multi-scale backbone network is utilized as the backbone network to extract the multi-scale and multi-target salient features. In stacked edge-aware module, the high-level information and low-level information of the image are combined in an asymmetric manner to enhance the area of the salient object. The network outputs salient object detection results. The experiments on five public datasets indicate that the proposed algorithm produces better detection results and better performance in objective evaluation indicators and subjective visual effects.