首页 > 论文 > 激光与光电子学进展 > 55卷 > 10期(pp:101502--1)

基于全部卷积特征融合的显著性检测

Salient Detection Based on All Convolutional Feature Combination

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

如何充分利用各级卷积特征是当前显著性检测研究的关键问题。就此提出一种基于融合全部卷积层特征的全卷积神经网络显著性检测方法。首先, 将全部卷积特征映射到内部的多个尺度中, 在每个尺度上联合各级卷积特征预测显著图; 然后, 融合各尺度的显著图, 得到融合显著图; 最后, 通过全连接条件随机场平滑显著图和优化显著边界。实验结果表明, 该方法在ECSSD和SED2数据库上具有较高的准确率、召回率和较低的平均绝对误差, 可为目标识别、机器视觉等应用提供更可靠的预处理结果。

Abstract

In the current saliency detections based on deep learning, how to make full use of the convolution features at all levels is the key issue. In order to solve this problem, we propose a saliency detection method based on full convolution neural network, which is a fusion of all convolutional features. Firstly, all the convolution features are mapped to multiple internal scales, and the saliency maps are predicted by combining the convolutional features of each level on each scale. Then the fused saliency maps are obtained by fusing the saliency maps of each scale. Finally, smooth saliency maps and optimized salient boundaries are obtained through full connected conditional random fields. Experimental results show that the proposed method has higher accuracy, recall rate and lower average absolute error in ECSSD database and SED2 database, and provides more reliable pretreatment results for target recognition, machine vision and other applications.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.41

DOI:10.3788/lop55.101502

所属栏目:机器视觉

基金项目:国家自然科学基金(61374047, 60973095)

收稿日期:2018-03-19

修改稿日期:2018-04-16

网络出版日期:2018-04-23

作者单位    点击查看

张松龙:江南大学物联网工程学院, 江苏 无锡 214122
谢林柏:江南大学物联网工程学院, 江苏 无锡 214122

联系人作者:谢林柏(xielb@126.com)

【1】Fang Y M, Chen Z Z, Lin W S, et al. Saliency detection in the compressed domain for adaptive image retargeting[J]. IEEE Transactions on Image Processing, 2012, 21(9): 3888-3901.

【2】Gao R, Tu Q, Xu J, et al. Visual saliency detection based on mutual information in compressed domain[C]. Visual Communications and Image Processing (VCIP), 2015: 1-4.

【3】Ren Z X, Gao S H, Chia L T, et al. Region-based saliency detection and its application in object recognition[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2014, 24(5): 769-779.

【4】Sharma G, Jurie F, Schmid C. Discriminative spatial saliency for image classification[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2012: 3506-3513.

【5】Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259.

【6】Tong N, Lu H, Ruan X, et al. Salient object detection via bootstrap learning[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 1884-1892.

【7】Qin Y, Lu H, Xu Y, et al. Saliency detection via cellular automata[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 110-119.

【8】Liu F, Shen T S, Lou S L, et al. Deep network saliency detection based on global model and local optimization[J]. Acta Optica Sinica, 2017, 37(12): 1215005.
刘峰, 沈同圣, 娄树理, 等. 全局模型和局部优化的深度网络显著性检测[J]. 光学学报, 2017, 37(12): 1215005.

【9】Zhu W, Liang S, Wei Y, et al. Saliency optimization from robust background detection[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014: 2814-2821.

【10】Yang C, Zhang L, Lu H, et al. Saliency detection via graph-based manifold ranking[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013: 3166-3173.

【11】Dai J, He K, Li Y, et al. Instance-sensitive fully convolutional networks[C]∥European Conference on Computer Vision, 2016: 534-549.

【12】Bi L H, Liu Y C. Plant leaf image recognition based on improved neural network algorithm[J]. Laser & Optoelectronics Progress, 2017, 54(12): 121102
毕立恒, 刘云潺. 基于改进神经网络算法的植物叶片图像识别研究[J]. 激光与光电子学进展, 2017, 54(12): 121102.

【13】Liu Y, Cheng M M, Hu X, et al. Richer convolutional features for edge detection[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 5872-5881.

【14】Wang L, Lu H, Ruan X, et al. Deep networks for saliency detection via local estimation and global search[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 3183-3192.

【15】Zhao R, Ouyang W, Li H, et al. Saliency detection by multi-context deep learning[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 1265-1274.

【16】Li G, Yu Y. Visual saliency based on multiscale deep features[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 5455-5463.

【17】Wang L, Wang L, Lu H, et al. Saliency detection with recurrent fully convolutional networks[C]. European Conference on Computer Vision, 2016: 825-841.

【18】Mahendran A, Vedaldi A. Understanding deep image representations by inverting them[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 5188-5196.

【19】Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv: 1409. 1556, 2014.

【20】Zhang P, Wang D, Lu H, et al. Learning uncertain convolutional features for accurate saliency detection[C]∥Proceedings of the IEEE International Conference on Computer Vision, 2017: 212-221.

【21】Krhenbühl P, Koltun V. Efficient inference in fully connected CRFs with Gaussian edge potentials[C]∥Advances in Neural Information Processing Systems, 2011: 109-117.

【22】Jia Y, Shelhamer E, Donahue J, et al. Caffe: convolutional architecture for fast feature embedding[C]∥Proceedings of the 22nd ACM International Conference on Multimedia, 2014: 675-678.

【23】Perazzi F, Krhenbühl P, Pritch Y, et al. Saliency filters: contrast based filtering for salient region detection[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2012: 733-740.

【24】Wei Y, Wen F, Zhu W, et al. Geodesic saliency using background priors[C]. European Conference on Computer Vision, 2012: 29-42.

【25】Fang Z M, Cui R Y, Jin J X, et al. Static saliency region detection in traffic scenes[J]. Laser & Optoelectronics Progress, 2017, 54(5): 051501.
方志明, 崔荣一, 金璟璇. 交通场景静态显著性区域检测[J]. 激光与光电子学进展, 2017, 54(5): 051501.

【26】Hou Q, Cheng M M, Hu X, et al. Deeply supervised salient object detection with short connections[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 5300-5309.

引用该论文

Zhang Songlong,Xie Linbo. Salient Detection Based on All Convolutional Feature Combination[J]. Laser & Optoelectronics Progress, 2018, 55(10): 101502

张松龙,谢林柏. 基于全部卷积特征融合的显著性检测[J]. 激光与光电子学进展, 2018, 55(10): 101502

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF