显著性目标检测轮廓增强技术研究

Refinement-Based Approach of Saliency Detection

摘要: 显著性区域检测即针对一张图像，找出其中最显著的目标。传统方法大多基于先验知识以及根据人工提取的特征来计算对比度，继而得到显著性目标。这普遍存在适应性差的问题，即对于某些场景效果比较好，对于别的场景效果则差很多。近年来深度学习算法的兴起开始应用于显著性检测，优点在于只要数据集覆盖比较全面，对于各种场景，都可以得到优于传统方法的结果。本文在原有模型的基础上，结合粗提取到细精炼两个过程，提出了新的深度学习模型。粗提取过程由两个子网络组合，以原图像作为输入，第一个子网络以超像素为单位，结合局部上下文关系得到的特征与第二个子网络在VGG中提取的高层次特征串联得到原图的显著性粗略预测。细精炼过程由一系列循环卷积层组成的，从粗糙尺度到精细尺度精炼这个粗糙的预测，最终端对端输出精度高的显著性目标区域。

Abstract: The aim of saliency detection is to find out significant regions of an image. Traditional salient ob-ject detection methods often use various prior knowledge and hand-crafted features to formulate contrast to get the saliency object, which have poor adaptability. Recently, deep learning is more and more popular in saliency detection. With a comprehensive learning set, the result will be much better than the traditional methods, especially for complex scenes. In this paper, a new deep learning model is proposed with a coarse-extracting process and fine-refining process. The coarse-extracting process contains two subnetworks. The first subnetwork’s output feature map with the local context of superpixels cascade to the second subnetwork’s high feature map extracted by VGG, then generating a coarse saliency prediction map. The fine-refining process composed of a series of recurrent convolution layers refining the coarse prediction map from coarse scales to fine scales, finally generating a fine saliency map.