显著性引导的低光照人脸检测

doi:10.13700/j.bh.1001-5965.2020.0469

北京航空航天大学学报 ›› 2021, Vol. 47 ›› Issue (3): 572-584.doi: 10.13700/j.bh.1001-5965.2020.0469

显著性引导的低光照人脸检测

李可夫¹, 钟汇才^2,3, 高兴宇², 翁超群², 陈振宇^2,4, 李勇周², 王师峥^2,3

1. 中国科学院大学微电子学院, 北京 100049;
2. 中国科学院微电子研究所, 北京 100029;
3. 中国科学院物联网研究发展中心, 无锡 214000;
4. 国家电网有限公司大数据中心, 北京 100031

收稿日期:2020-08-27 发布日期:2021-04-08
通讯作者: 高兴宇 E-mail:gaoxingyu@ime.ac.cn
作者简介:李可夫,男,硕士研究生。主要研究方向:人工智能、计算机视觉;钟汇才,男,博士,研究员。主要研究方向:人工智能;高兴宇,男,博士,研究员。主要研究方向:人工智能。
基金资助:
国家自然科学基金（61702491，61802390）；北京市自然科学基金（4194095）；茂名市科技计划（2020028）

Saliency guided low-light face detection

LI Kefu¹, ZHONG Huicai^2,3, GAO Xingyu², WENG Chaoqun², CHEN Zhenyu^2,4, LI Yongzhou², WANG Shizheng^2,3

1. School of Microelectronics, University of Chinese Academy of Sciences, Beijing 100049, China;
2. Institute of Microelectronics of Chinese Academy of Sciences, Beijing 100029, China;
3. Chinese Academy of Sciences R&D Center for Internet of Things, Wuxi 214000, China;
4. Big Data Center of State Grid Corporation of China, Beijing 100031, China

Received:2020-08-27 Published:2021-04-08
Supported by:
National Natural Science Foundation of China (61702491,61802390);Beijing Natural Science Foundation (4194095);Maoming Science and Technology Plan (2020028)

摘要/Abstract

摘要： 针对卷积神经网络难以对低光照环境拍摄的图像进行人脸检测的问题。提出了一种将图像显著性检测算法和深度学习相结合的算法，并应用于低光照人脸检测。所提算法将图像的显著性信息与图像原始RGB通道融合，用于神经网络训练。在低光照人脸数据集DARK FACE上进行了充分的实验，结果表明：所提方法在DARK FACE数据集上获得了比当前主流人脸检测算法更好的检测精度，进而验证了所提算法的有效性。

关键词: 人脸检测, 显著性引导, 深度神经网络, 低光照, 计算机视觉

Abstract: To deal with the problem that it is hard for convolution neural network to do face detection in low light environment, we propose a method combining image saliency and deep learning and apply it to low-light face detection, which integrates saliency and the original RGB channels of the image into neural network training. Sufficient experiments are implemented on DARK FACE, a low-light face dataset, and the results show that the proposed low-light face detection method achieves better detection accuracy than the existing mainstream face detection algorithms on DARK FACE, thus confirming the validity of the proposed method.

Key words: face detection, saliency guided, deep neural network, low light, computer vision

中图分类号:

TP391

李可夫, 钟汇才, 高兴宇, 翁超群, 陈振宇, 李勇周, 王师峥. 显著性引导的低光照人脸检测[J]. 北京航空航天大学学报, 2021, 47(3): 572-584.

LI Kefu, ZHONG Huicai, GAO Xingyu, WENG Chaoqun, CHEN Zhenyu, LI Yongzhou, WANG Shizheng. Saliency guided low-light face detection[J]. Journal of Beijing University of Aeronautics and Astronautics, 2021, 47(3): 572-584.

参考文献

[1] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Reocgnition.Piscataway:IEEE Press,2014:580-587.
[2] GIRSHICK R.Fast RCNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision.Piscataway:IEEE Press,2015:10-15.
[3] REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1147.
[4] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unifified,real-time object detection[C].In Proceedings of the IEEE Computer Vision & Pattern Recognition.Piscataway:IEEE Press,2016:779-788.
[5] LI J,WANG Y,WANG C,et al.DSFD:Dual shot face detector[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2020:5060-5069.
[6] TANG X,DU D K,HE Z Q,et al.PyramidBox:A context-assisted single shot face detector[EB/OL].(2018-08-17)[2020-09-12].https:arxiv.orglabs/1803.07737?context=cs.
[7] JAIN V,LEARNED-MILLER E G.FDDB:A benchmark for face detection in unconstrained settings[EB/OL].[2020-09-12].http://works.bepress.com/erik_learned_miller/55/.
[8] YANG S,LUO P,LOY C C,et al.WIDER FACE:A face detection benchmark[C]//Proceedings of the 2016 IEEE Conference on Computer Version and Pattern Recognition.Piscataway:IEEE Press,2016:5525-5533.
[9] YE Y,YANG W H,REN W Q,et al.UG²⁺ Track 2:A collective benchmark effort for evaluating and advancing[EB/OL].[2020-03-31].http://arxiv.org/abs/1904.04474v4.
[10] JOBSON D J,RAHMAN Z,WOODELL G.A multiscale retinex for bridging the gap between color images and the human observation of scenes[J].IEEE Transactions on Image Processing,1997,6(7):965-976.
[11] LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shot multibox detector[C]//European Conference on Computer Version.Berlin:Springer,2016:21-37.
[12] LI Z H,TANG X,HAN J Y,et al.PyramidBox++:High performance detector for finding tiny face[EB/OL].[2020-09-12].https://arxiv.org/abs/1904.00386.
[13] LIU S,HUANG D,WANG Y H.Receptive field block net for accurate and fast object detection[C]//European Conference on Computer Vision.Berlin:Springer,2018:404-419.
[14] LAND E H.The Retinex theory of color vision[J].Scientific American,1977,237(6):108.
[15] JOBSON D J,RAHMAN Z,WOODELL G A.Properties and performance of a center/surround Retinex[J].IEEE Transactions on Image Processing,1997,6(3):451-462.
[16] RAHMAN Z U,JOBSON D J,WOODELL G A.Multi-scale Retinex for color image enhancement[C]//Proceedings of 3rd International Conference on Image Processing. Piscataway:IEEE Press,1996:1003-1006.
[17] GUO X J,LI Y,LING H B.LIME:Low-light image enhancement via illumination map estimation[J]. IEEE Transactions on Image Processing,2017,26(2):982-993.
[18] YUN Z,MUBARAK S.Visual attention detection in video sequences using spatiotemporal cues[C]//Proceedings of the 14th ACM International Conference on Multimedia.New York:ACM Press,2006:815-824.
[19] CHENG M M,ZHANG G X,MITRA N J.Global contrast based salient region detection[C]//Proceedings of the 2011 IEEE Conference on omputer Vision and Pattern Recognition.Piscataway:IEEE Press,2011:569-582.
[20] ACHANTA R,ESTRADA F,WILS P,et al.Salient region detection and segmentation[C]//Proceedings of the 6th International Conference on Computer Version Systems.Berlin:Springer,2008.
[21] 张冬明,靳国庆,代锋,等.基于深度融合的显著性目标检测算法[J].计算机学报,2019,42(9):2076-2086.ZHANG D M,JIN G Q,DAI F,et al.Salient object detection based on deep fusion of hand-crafted features[J].Chinese Journal of Computers,2019,42(9):2076-2086(in Chinese).
[22] JIAN M W,LAM K M,DONG J Y,et al.Visual-patch-attention-aware saliency detection[J].IEEE Transactions on Cybernetics,2015,45(8):1575-1586.
[23] TSUNG-YI L,PRIYA G,ROSS B G,et al.Focal loss for dense object detection[C]//Proceedings of the 2017 IEEE International Conference on Computer Version.Piscataway:IEEE Press,2017:2999-3007.
[24] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Version and Pattern Recognition.Piscataway:IEEE Press,2016:770-778.
[25] LIN T Y,DOLLA P,CIRSHICK R,et al.Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Version and Pattern Recognition.Piscataway:IEEE Press,2017:936-944.
[26] LIN T Y,MAIRE M,BELONGIE S,et al.Microsoft COCO:Common objects in context[C]//European Conference on Computer Version.Berlin:Springer,2014:740-755.
[27] REDMON J,FARHADI A.YOLO9000:Better,faster,stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2017:6517-6525.
[28] FU C Y,LIU W A,RANGA A.et al.DSSD:Deconvolutional single shot detector[EB/OL].[2019-09-12].http://arxiv.org/abs/170.06659.
[29] FAEN Z,FAN X Y, AI G, et al.Accurate face detection for high performance[EB/OL].(2019-05-24)[2020-09-12].http://arxiv.org/abs/1905.01585.
[30] HOU X D,HAREL J, KOCH C.Image signature:Highlighting sparse salient regions[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(1):194-201.
[31] NAJIBI M,SAMANGOUEI P,CHELLAPPA R,et al.SSH:Single stage headless face detector[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision.Piscataway:IEEE Press,2017:4875-4884.
[32] YING Z Q,LI G,GAO W.A bio-inspired multi-exposure fusion framework for low-light image enhancement[EB/OL].[2020-09-12].https://arxiv.org/abs/1711.00591.
[33] DONG X,WANG G,PANG Y,et al.Fast efficient algorithm for enhancement of low lighting video[C]//Proceedings of the 2011 IEEE International Conference on Multimedia and Expo.Piscataway:IEEE Press,2011:1-6.
[34] FU X Y,ZENG D,HUANG Y H,et al.A fusion-based enhancing method for weakly illuminated images[J].Signal Processing,2016,129:82-96.
[35] REN X D,LI M D,CHENG W H,et al.Joint enhancement and denoising method via sequential decomposition[C]//2018 IEEE International Symposium on Circuits and Systems (ISCAS).Piscataway:IEEE Press,2018:1-5.
[36] WEI C,WANG W,YANG W,et al.Deep Retinex decomposition for low-light enhancement[C]//Proceedings of British Machine Vision Conference,2018:155.
[37] YANG W H,YUAN Y,REN W Q,et al.Advancing image understanding in poor visibility environments:A collective benchmark study[J].IEEE Transanctions on Processing,2020,29:5737-5752.

显著性引导的低光照人脸检测

Saliency guided low-light face detection

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	练连荣, 项欣光. 基于噪声柯西分布的社交图像标签优化与标注[J]. 北京航空航天大学学报, 2021, 47(3): 632-640.
[2]	马腾宇, 李孜, 刘日升, 樊鑫, 罗钟铉. 基于无监督学习的多模态可变形配准[J]. 北京航空航天大学学报, 2021, 47(3): 658-664.
[3]	李承昊, 茹乐, 何林远, 迟文升. 一种可变锚框候选区域网络的目标检测方法[J]. 北京航空航天大学学报, 2020, 46(8): 1610-1617.
[4]	赵国, 秦世引. PMMWI与VI优势互补的人体隐蔽违禁物检测与定位[J]. 北京航空航天大学学报, 2019, 45(10): 2011-2025.
[5]	郭琳, 秦世引. 遥感图像飞机目标高效搜检深度学习优化算法[J]. 北京航空航天大学学报, 2019, 45(1): 159-173.
[6]	汪溁鹤, 陈裕雄, 马世龙, 吕江花. 实时鲁棒的频域空间目标跟踪方法[J]. 北京航空航天大学学报, 2017, 43(12): 2457-2465.
[7]	潘炜深, 金连文, 冯子勇. 基于多尺度梯度及深度神经网络的汉字识别[J]. 北京航空航天大学学报, 2015, 41(4): 751-756.
[8]	郑海超, 毛峡, 梁晓庚. 基于边缘信息的灰度目标跟踪算法[J]. 北京航空航天大学学报, 2015, 41(12): 2240-2249.
[9]	赵龙, 肖军波. 一种改进的运动目标抗遮挡跟踪算法[J]. 北京航空航天大学学报, 2013, 39(4): 517-520.
[10]	段海滨, 张奇夫, 范彦铭, 李昊. 基于计算机视觉的UAV自主空中加油半物理仿真[J]. 北京航空航天大学学报, 2013, 39(11): 1491-1496.
[11]	徐国艳, 王传荣, 高峰, 王江峰. 车辆视频检测感兴趣区域确定算法[J]. 北京航空航天大学学报, 2010, 36(7): 781-784.
[12]	吴华, 秦世引. 基于增量式路标表观学习的移动机器人定位[J]. 北京航空航天大学学报, 2010, 36(6): 708-712.
[13]	陈磊,陈宗基. 基于视觉的无人作战飞机跑道障碍物检测方案[J]. 北京航空航天大学学报, 2007, 33(11): 1313-1316.
[14]	李超,李运华,王国栋,李临生. 一种基于嵌入式图像处理的工程车辆导向装置[J]. 北京航空航天大学学报, 2007, 33(10): 1212-1215.
[15]	王晓剑, 潘顺良, 宋子善, 沈为群. 无人直升机自主着舰的计算机视觉技术[J]. 北京航空航天大学学报, 2007, 33(06): 686-689.