Edge Detection Network with Multi-Depth Feature Enhancement and Top-Level Information Guidance

被引：0
|
作者：
Zhu W. [1 ]
Cen K. [1 ]
Xu X. [1 ]
He D. [1 ]
机构：
[1] College of Information Engineering, Zhejiang University of Technology, Hangzhou
来源：
| 1705年 / Institute of Computing Technology卷 / 33期
关键词：
Edge detection network; Feature enhancement; Multi-depth feature; Top-level information guidance; UNet++;
D O I：
10.3724/SP.J.1089.2021.18752
中图分类号：
学科分类号：
摘要：
The existing edge detection networks still have problems such as missing edges and excessive noise in complex natural scenes. Therefore, an edge detection network with multi-depth feature enhancement and top-level information guidance is proposed. First, UNet++ is used as the backbone network to extract features of different depths, and the edges of different scales are made more complete by feature superposition. Then, a feature enhancement module is added after the side output of each convolution layer to increase the receptive field and enhance the multi-scale information by introducing the dilated convolution. Finally, a top-level information guidance module is designed to enhance the edge detection effect by introducing top-level semantic features into jump connection. The experimental results show that training on the three datasets of BSDS500, NYUDv2 and Multicue has achieved good results. On the BSDS500 dataset, the ODS, OIS and AP of this network reach 0.821, 0.839 and 0.869 respectively, which is generally higher than the existing edge detection networks. Moreover, the result has less noise and the subjective effect is closer to the ground truth. © 2021, Beijing China Science Journal Publishing Co. Ltd. All right reserved.
引用
收藏
页码：1705 / 1714
页数：9
相关论文
共 31 条
  • [1] Arbelaez P, Maire M, Fowlkes C, Et al., Contour detection and hierarchical image segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 33, 5, pp. 898-916, (2011)
  • [2] Ferrari V, Fevrier L, Jurie F, Et al., Groups of adjacent contour segments for object detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 30, 1, pp. 36-51, (2008)
  • [3] Girshick R, Donahue J, Darrell T, Et al., Rich feature hierarchies for accurate object detection and semantic segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, (2014)
  • [4] Sobel I E., Camera models and machine perception, (1970)
  • [5] Canny J., A computational approach to edge detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 8, 6, pp. 679-698, (1986)
  • [6] Dollar P, Zitnick C L., Fast edge detection using structured forests, IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 8, pp. 1558-1570, (2015)
  • [7] Konishi S, Yuille A L, Coughlan J M, Et al., Statistical edge detection: learning and evaluating edge cues, IEEE Transactions on Pattern Analysis and Machine Intelligence, 25, 1, pp. 57-74, (2003)
  • [8] Martin D R, Fowlkes C C, Malik J., Learning to detect natural Image boundaries using local brightness, color, and texture cues, IEEE Transactions on Pattern Analysis and Machine Intelligence, 26, 5, pp. 530-549, (2004)
  • [9] Ganin Y, Lempitsky V., N<sup>4</sup>-Fields: neural network nearest neighbor fields for image transforms, Proceedings of Asian Conference on Computer Vision, pp. 536-551, (2014)
  • [10] Bertasius G, Shi J B, Torresani L., DeepEdge: a multi-scale bifurcated deep network for top-down contour detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4380-4389, (2015)
1234