Edge detection is the basis of many computer vision tasks. Current techniques mainly rely on deep learning, but most models improve the accuracy of predicted edges using Non-Maximum Suppression in the evaluation stage. These models only focus on the accuracy of predicted edges without considering the coarseness and fineness of the edges. To address this issue, this paper proposes a new feature fusion strategy based on the dense extreme inception network. This strategy incorporates top-down multi-scale fusion edge detection with spatial co-location rule and retains the multi-network structure based on the traditional deep learning edge detection side output. The proposed strategy can better integrate the high semantic characteristic of high-layer information with the high-resolution texture characteristic of low-layer information, thereby suppressing pixel confusions in backgrounds and lines that are predicted incorrectly in edge detection. In the feature connection, Concat block is used to replace the single operation of Concat, to better fuse semantic information in different scales. Lastly, a simple attention fusion block is used to fuse outputs of multiple networks. Also, different output prediction maps at different scales are deeply supervised combining the tracing loss. This model is independent of Non-Maximum Suppression. By fully utilizing the multi-scale and multi-level information of the target image, this model improves the accuracy of prediction along with improving images’ edges. The experimental results show that without the morphological Non-Maximum Suppression, on the BIPED data set, the proposed model on ODS, OIS, and AP are 0.891, 0.895, 0.900, respectively; with the morphological Non-Maximum Suppression, the proposed model on ODS, OIS, and AP are 0.894、0.899、0.931, respectively, which is superior to all comparison algorithms involved in this article. Also, on the MDBD data set, optimal results were also achieved.
RADENOVIĆF, TOLIASG, CHUMO. Deep shape matching[M]//Computer Vision-ECCV 2018. Cham:Springer International Publishing, 2018: 774-791.
[2]
SUY Q, LIUY H, CUANB N, et al. Contour guided hierarchical model for shape matching[C]//2015 IEEE International Conference on Computer Vision (ICCV).Santiago,Chile.IEEE,2015:1609-1617.
[3]
CHENC, LIS, WANGY G, et al. Video saliency detection via spatial-temporal fusion and low-rank coherency diffusion[J].IEEE Transactions on Image Processing, 2017, 26(7): 3156-3170.
[4]
WANGX H, LIS, CHENC,et al .Data-level recombination and lightweight fusion scheme for RGB-D salient object detection[J].IEEE Transactions on Image Processing,2021,30:458-471.
[5]
CHENGM, LIUY, HOUQ, et al. HFS: hierarchical feature selection for efficient image segmentation[C]//Computer Vision-ECCV 2016. Amsterdam, the Netherlands: Springer, 2016:867-882.
[6]
WEIY C, LIANGX D, CHENY P,et al .STC:a simple to complex framework for weakly-supervised semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(11): 2314-2320.
[7]
HUNTSBERGERT L, DESCALZIM F .Color edge detection[J].Pattern Recognition Letters,1985,3(3): 205-209.
[8]
HUANGJ S, TSENGD H .Statistical theory of edge detection[J].Computer Vision,Graphics,and Image Processing,1988, 43(3):337-346.
[9]
TORREV, POGGIOT A .On edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,PAMI-8(2):147-163.
[10]
ZHANGJ Y, CHENY, HUANGX X .Edge detection of images based on improved Sobel operator and genetic algorithms[C]//2009 International Conference on Image Analysis and Signal Processing.Linhai,China. IEEE,2009:31-35.
[11]
CANNYJ .A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,PAMI-8(6):679-698.
[12]
DOLLARP, TUZ W, BELONGIES .Supervised learning of edges and object boundaries[C]//2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).New York,NY,USA. IEEE,2006:1964-1971.
[13]
RENX F. Multi-scale improves boundary detection in natural images[C]//ECCV'08: Proceedings of the 10th European Conference on Computer Vision: Part III. Marseille, France: Springer, 2008: 533-545.
[14]
DOLLARP, ZITNICKC L .Fast edge detection using structured forests[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(8):1558-1570.
[15]
ISOLAP, ZORAND, KRISHNAND, et al. Crisp boundary detection using pointwise mutual information[C]// Computer Vision-ECCV 2014 . Zurich, Switzerland: Springer, 2014:799-814.
[16]
SHIJ B, MALIKJ .Normalized cuts and image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000, 22(8): 888-905.
[17]
GANINY, LEMPITSKYV . N4-fields:neural network nearest neighbor fields for image transforms[M]//Computer Vision-ACCV 2014.Cham:Springer International Publishing,2015:536-551.
[18]
BERTASIUSG, SHIJ B, TORRESANIL .DeepEdge:a multi-scale bifurcated deep network for top-down contour detection[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Boston,MA,USA. IEEE,2015:4380-4389.
[19]
LONGJ, SHELHAMERE, DARRELLT .Fully convolutional networks for semantic segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Boston,MA,USA. IEEE,2015:3431-3440.
[20]
KRIZHEVSKYA, SUTSKEVERI, HINTONG E .ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
[21]
SIMONYANK, ZISSERMANA .Very deep convolutional networks for large-scale image recognition[EB/OL].
[22]
HEK M, ZHANGX Y, RENS Q,et al .Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas,NV,USA. IEEE,2016:770-778.
[23]
CHOLLETF .Xception:deep learning with depthwise separable convolutions[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu,HI,USA. IEEE, 2017:1800-1807.
[24]
HUANGG, LIUZ, VAN DER MAATENL,et al .Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu,HI,USA. IEEE,2017:2261-2269.
[25]
XIES N, TUZ W .Holistically-nested edge detection[J].International Journal of Computer Vision,2017,125(1):3-18.
[26]
LIUY, CHENGM M, HUX W,et al .Richer convolutional features for edge detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu,HI,USA. IEEE,2017:5872-5881.
[27]
LIUY, CHENGM M, HUX W,et al .Richer convolutional features for edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,41(8):1939-1946.
[28]
SORIAX, RIBAE, SAPPAA .Dense extreme inception network:towards a robust CNN model for edge detection[C]//2020 IEEE Winter Conference on Applications of Computer Vision (WACV).Snowmass,CO,USA. IEEE,2020:1912-1921.
[29]
MÉLYD A, KIMJ, MCGILLM,et al .A systematic comparison between visual cues for boundary detection[J].Vision Research,2016,120:93-107.
[30]
WANGY P, ZHAOX, HUANGK Q .Deep crisp boundaries[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu,HI,USA. IEEE,2017:1724-1732.
[31]
HEJ Z, ZHANGS L, YANGM,et al .BDCN:Bi-directional cascade network for perceptual edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,44(1):100-113.
[32]
HUANL X, XUEN, ZHENGX W,et al .Unmixing convolutional features for crisp edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,44(10):6602-6609.
[33]
SUZ, LIUW Z, YUZ T,et al .Pixel difference networks for efficient edge detection[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV).Montreal,QC,Canada. IEEE,2021:5097-5107.
[34]
YUF, KOLTUNV .Multi-scale context aggregation by dilated convolutions[EB/OL].
[35]
CHENL C, ZHUY K, PAPANDREOUG,et al .Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//European Conference on Computer Vision.Cham:Springer,2018:833-851.
基金资助
国家自然科学基金资助项目(62067006)
国家自然科学基金资助项目(62367005)
National Natural ScienceFoundation of China(62067006)
National Natural ScienceFoundation of China(62367005)