Abstract:Aiming at the problems such as chaotic and fuzzy edge lines caused by current deep learning based edge detection technology, an end-to-end Cross-layer Fusion Feature for edge detection (CFF) model based on RCF (Richer Convolutional Features) was proposed. In this model, RCF was used as a baseline, the CBAM (Convolutional Block Attention Module) was added to the backbone network, translation-invariant downsampling technology was adopted, and some downsampling operations in the backbone network were removed in order to preserve the image details information, dilated convolution technique was used to increase the model receptive field at the same time. In addition, the method of cross-layer fusion of feature maps was adopted to enable high-level and low-level features to be fully fused together. In order to balance the relationship between the loss in each stage and the fusion loss, and to avoid the phenomenon of excessive loss of low-level details after multi-scale feature fusion, the weight parameters were added to the losses. The model was trained on Berkeley Segmentation Data Set (BSDS500) and PASCAL VOL Context dataset, and the image pyramid technology was used in testing to improve the quality of edge images. Experimental results show that the contour extracted by CFF model is clearer than that extracted by the baseline network and can solve the edge blurring problem. The evaluation performed on the BSDS500 benchmark shows that, the Optimal Dataset Scale (ODS) and the Optimal Image Scale (OIS) are improved to 0.818 and 0.839 respectively by this model.
宋杰, 于裕, 骆起峰. 基于RCF的跨层融合特征的边缘检测[J]. 计算机应用, 2020, 40(7): 2053-2058.
SONG Jie, YU Yu, LUO Qifeng. Cross-layer fusion feature based on richer convolutional features for edge detection. Journal of Computer Applications, 2020, 40(7): 2053-2058.
[1] CHENG M,HOU Q,ZHANG S,et al. Intelligent visual media processing:when graphics meets vision[J]. Journal of Computer Science and Technology,2017,32(1):110-121. [2] HU S,CHEN T,XU K,et al. Internet visual media processing:a survey with graphics and vision applications[J]. The Visual Computer,2013,29(5):393-405. [3] FERRARI V,FEVRIER L,JURIE F,et al. Groups of adjacent contour segments for object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(1):36-51. [4] ZITNICK C L,DOLLÁR P. Edge boxes:locating object proposals from edges[C]//Proceedings of the 13th European Conference on Computer Vision,LNCS 8693. Cham:Springer,2014:391-405. [5] ARBELÁEZ P,PONT-TUSET J,BARRON J,et al. Multiscale combinatorial grouping[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2014:328-335. [6] FELDMAN J A,FELDMAN G M,FALK G,et al. The Stanford hand-eye project[C]//Proceedings of the 1st International Joint Conference on Artificial Intelligence. San Francisco, CA:Morgan Kaufmann Publishers Inc.,1969:521-526,526a. [7] CANNY J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986, PAMI-8(6):679-698. [8] MARTIN D R,FOWLKES C C,MALIK J. Learning to detect natural image boundaries using local brightness,color,and texture cues[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(5):530-549. [9] DOLLÁR P,ZITNICK C L. Fast edge detection using structured forests[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(8):1558-1570. [10] GANIN Y,LEMPITSKY V. N4-fields:neural network nearest neighbor fields for image transforms[C]//Proceedings of the 12th Asian Conference on Computer Vision, LNCS 9004. Cham:Springer,2014:536-551. [11] XIE S,TU Z. Holistically-nested edge detection[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway:IEEE,2015:1395-1403. [12] LONG J,SHELHAMER E,DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2015:3431-3440. [13] SIMONYAN K,ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2019-03-02]. https://arxiv.org/pdf/1409.1556.pdf. [14] LIU Y,CHENG M,HU X,et al. Richer convolutional features for edge detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:5872-5881. [15] WOO S,PARK J,LEE J Y,et al. CBAM:convolutional block attention module[C]//Proceedings of the 15th European Conference on Computer Vision,LNCS 11211. Cham:Springer,2018:3-19. [16] ZHANG R. Making convolutional networks shift-invariant again[C]//Proceedings of the 36th International Conference on Machine Learning. New York:International Machine Learning Society, 2019:7324-7334. [17] YU F,KOLTUN V. Multi-scale context aggregation by dilated convolutions[EB/OL].[2019-03-02]. https://arxiv.org/pdf/1511.07122.pdf. [18] LIN T Y,DOLLÁR P,GIRSHICK R,et al. Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2017:936-944. [19] MARTIN D,FOWLKES C,TAL D,et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C]//Proceedings of the 8th IEEE International Conference on Computer Vision. Piscataway:IEEE,2001:416-423. [20] MOTTAGHI R,CHEN X,LIU X,et al. The role of context for object detection and semantic segmentation in the wild[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2014:891-898. [21] HU J,SHEN L,SUN G. Squeeze-and-excitation networks[C]//. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2018:7132-7141. [22] HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:770-778. [23] ARBELÁEZ P,MAIRE M,FOWLKES C,et al. Contour detection and hierarchical image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(5):898-916. [24] BERTASIUS G,SHI J,TORRESANI L. DeepEdge:a multi-scale bifurcated deep network for top-down contour detection[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2015:4380-4389. [25] SHEN W,WANG X,WANG Y,et al. DeepContour:a deep convolutional feature learned by positive-sharing loss for contour detection[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2015:3982-3991.