arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1812.02122cs.CV
收藏

学习吸引场表示的鲁棒线段检测

Learning Attraction Field Representation for Robust Line Segment Detection

Wuhan University(武汉大学);University of Oxford(牛津大学);NC State University(北卡罗来纳州立大学)

Nan Xue, Song Bai, Fudong Wang, Gui-Song Xia, Tianfu Wu, Liangpei Zhang

摘要:

本文提出了一种基于区域划分的线段地图吸引场对偶表示,从而将线段检测问题转化为区域着色问题。然后通过学习深度卷积神经网络(ConvNets)来解决后者的准确性、鲁棒性和效率。对于2D线段图,我们的对偶表示由三个部分组成:(i)区域分区图,其中每个像素被分配给一个且仅一个线段;(ii)吸引场图,其中分区区域中的每个像素由其2D投影向量w.r.t.相关联的线段;以及(iii)挤压模块,其将吸引场挤压成几乎完美地恢复输入场的线段图。通过利用二元性,我们学习ConvNets以端到端的方式计算原始输入图像的吸引场图,然后是LSD的挤压模块。我们的方法严格解决了LSD中的几个挑战,如局部模糊性和类不平衡。我们的方法还利用了基于ConvNets的语义分割方法中开发的最佳实践,例如编码器-解码器架构和a-trous卷积。在实验中,我们的方法在WireFrame数据集和YorkUrban数据集上进行了测试,获得了最先进的性能。特别是,我们将WireFrame数据集的性能提高了4.5个百分点。我们的方法也是快速的6.6~10.4 FPS,优于大多数现有的线段检测器。

英文摘要:

This paper presents a region-partition based attraction field dual representation for line segment maps, and thus poses the problem of line segment detection (LSD) as the region coloring problem. The latter is then addressed by learning deep convolutional neural networks (ConvNets) for accuracy, robustness and efficiency. For a 2D line segment map, our dual representation consists of three components: (i) A region-partition map in which every pixel is assigned to one and only one line segment; (ii) An attraction field map in which every pixel in a partition region is encoded by its 2D projection vector w.r.t. the associated line segment; and (iii) A squeeze module which squashes the attraction field to a line segment map that almost perfectly recovers the input one. By leveraging the duality, we learn ConvNets to compute the attraction field maps for raw in-put images, followed by the squeeze module for LSD, in an end-to-end manner. Our method rigorously addresses several challenges in LSD such as local ambiguity and class imbalance. Our method also harnesses the best practices developed in ConvNets based semantic segmentation methods such as the encoder-decoder architecture and the a-trous convolution. In experiments, our method is tested on the WireFrame dataset and the YorkUrban dataset with state-of-the-art performance obtained. Especially, we advance the performance by 4.5 percents on the WireFrame dataset. Our method is also fast with 6.6~10.4 FPS, outperforming most of existing line segment detectors.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑