[1]王照国,张红云,苗夺谦.基于F1值的非极大值抑制阈值自动选取方法[J].智能系统学报,2020,15(5):1006-1012.[doi:10.11992/tis.202006056]
 WANG Zhaoguo,ZHANG Hongyun,MIAO Duoqian.Automatic selection method of non-maximum suppression threshold based on F1 score[J].CAAI Transactions on Intelligent Systems,2020,15(5):1006-1012.[doi:10.11992/tis.202006056]
点击复制

基于F1值的非极大值抑制阈值自动选取方法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第15卷
期数:
2020年5期
页码:
1006-1012
栏目:
吴文俊人工智能科学技术奖论坛
出版日期:
2020-10-31

文章信息/Info

Title:
Automatic selection method of non-maximum suppression threshold based on F1 score
作者:
王照国1 张红云2 苗夺谦2
1. 同济大学 电子与信息工程学院,上海 201804;
2. 同济大学 嵌入式系统与服务计算教育部重点实验室,上海 201804
Author(s):
WANG Zhaoguo1 ZHANG Hongyun2 MIAO Duoqian2
1. College of Computer Science and Technology, Tongji University, Shanghai 201804, China;
2. Key Laboratory of Embedded System and Service Computing of Ministry of Education, Tongji University, Shanghai 201804, China
关键词:
计算机视觉目标检测非极大值抑制算法卷积神经网络深度学习检测框F1值自适应算法
Keywords:
computer visionobject detectionnon-maximum suppression algorithmconvolutional neural networkdeep learningdetection boxesF1 valueself-adaptive algorithm
分类号:
TP391
DOI:
10.11992/tis.202006056
文献标志码:
A
摘要:
传统的NMS算法的过滤阈值是人为设定的,由于阈值的选取不当可能会造成漏检和误检。在应用NMS算法时,所有图像的最佳阈值不是完全相同的,根据图像自身信息的不同而发生变化。针对上述问题,提出基于F1值的非极大值抑制阈值自动选取方法,综合考虑检测算法的准确率与召回率,选取使F1值最高的最佳过滤阈值,构建映射关系。测试阶段,利用映射关系和图像信息自动选取对应的过滤阈值。实验结果表明,本文提出的改进版本NMS算法将检测精度mAP值提高了1.1%。与现有的先进算法做对比,证明了本文算法的有效性。
Abstract:
The filtering threshold of the traditional non-maximum suppression (NMS) algorithm is artificially set. However, the improper selection of the threshold may result in leak and error detection. When applying the NMS algorithm, the optimal threshold for all images differs because the information obtained from the image itself changes. Given the aforementioned problems, we propose an automatic selection method of the NMS threshold based on the F1 score, which comprehensively considers the accuracy and recall rates of the detection algorithm and selects the best filtering threshold based on the highest F1 score to establish a relationship map. Experimental results show that the improved version of the NMS algorithm proposed in this study enhances the detection accuracy mAP value by 1.1%. Compared with the existing advanced algorithms, the proposed algorithm has been proven to be more effective.

参考文献/References:

[1] FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al. Object detection with discriminatively trained part-based models[J]. IEEE transactions on pattern analysis and machine intelligence, 2010, 32(9): 1627-1645.
[2] HAN Junwei, ZHANG Dingwen, CHENG Gong, et al. Advanced deep-learning techniques for salient and category-specific object detection: a survey[J]. IEEE signal processing magazine, 2018, 35(1): 84-100.
[3] XIE Cihang, WANG Jianyu, ZHANG Zhishuai, et al. Adversarial examples for semantic segmentation and object detection[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 1369-1378.
[4] BORJI A, CHENG Mingming, JIANG Huaizu, et al. Salient object detection: a benchmark[J]. IEEE transactions on image processing, 2015, 24(12): 5706-5722.
[5] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 779-788.
[6] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, the Netherlands, 2016: 21-37.
[7] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv preprint arXiv: 1804.02767, 2018.
[8] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA, 2014: 580-587.
[9] GIRSHICK R. Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, USA, 2015: 1440-1448.
[10] REN Shaoqing, HE Kaiming, 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): 1137-1149.
[11] ROSENFELD A, THURSTON M. Edge and curve detection for visual scene analysis[J]. IEEE transactions on computers, 1971, C-20(5): 562-569.
[12] BODLA N, SINGH B, CHELLAPPA R, et al. Soft-NMS—improving object detection with one line of code[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 5561-5569.
[13] HE Yihui, ZHU Chenchen, WANG Jianren, et al. Bounding box regression with uncertainty for accurate object detection[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA, 2019: 2888-2897.
[14] 侯志强, 刘晓义, 余旺盛, 等. 基于双阈值-非极大值抑制的Faster R-CNN改进算法[J]. 光电工程, 2019, 46(12): 190159
HOU Zhiqiang, LIU Xiaoyi, YU Wangsheng, et al. Improved algorithm of Faster R-CNN based on double threshold-non-maximum suppression[J]. Opto-electronic engineering, 2019, 46(12): 190159
[15] 赵文清, 严海, 邵绪强. 改进的非极大值抑制算法的目标检测[J]. 中国图象图形学报, 2018, 23(11): 1676-1685
ZHAO Wenqing, YAN Hai, SHAO Xuqiang. Object detection based on improved non-maximum suppression algorithm[J]. Journal of image and graphics, 2018, 23(11): 1676-1685
[16] LIU Yuliang, JIN Lianwen, ZHANG Shuaitao, et al. Detecting curve text in the wild: new dataset and new solution[J]. arXiv preprint arXiv: 1712.02170, 2017.
[17] JIANG Borui, LUO Ruixuan, MAO Jiayuan, et al. Acquisition of localization confidence for accurate object detection[C]//Proceedings of the 15th European Conference on Computer Vision. Munich, Germany, 2018: 784-799.
[18] HOSANG J, BENENSON R, SCHIELE B. A Convnet for Non-maximum Suppression[C]//Proceedings of the 38th German Conference on Pattern Recognition. Hannover, Germany, 2016: 192-204.
[19] LIU Songtao, HUANG Di, WANG Yunhong. Adaptive NMS: refining pedestrian detection in a crowd[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA, 2019: 6459-6468.
[20] EVERINGHAM M, VAN GOOL L, WILLIAMS C K I, et al. The PASCAL visual object classes (VOC) challenge[J]. International journal of computer vision, 2010, 88(2): 303-338.
[21] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland, 2014: 740-755.

相似文献/References:

[1]夏 凡,王 宏.基于局部异常行为检测的欺骗识别研究[J].智能系统学报,2007,2(05):12.
 XIA Fan,WANG Hong.Methodologies for deception detection based on abnormal b ehavior[J].CAAI Transactions on Intelligent Systems,2007,2(5):12.
[2]杨 戈,刘 宏.视觉跟踪算法综述[J].智能系统学报,2010,5(02):95.
 YANG Ge,LIU Hong.Survey of visual tracking algorithms[J].CAAI Transactions on Intelligent Systems,2010,5(5):95.
[3]刘宏,李哲媛,许超.视错觉现象的分类和研究进展[J].智能系统学报,2011,6(01):1.
 LIU Hong,LI Zheyuan,XU Chao.The categories and research advances of visual illusions[J].CAAI Transactions on Intelligent Systems,2011,6(5):1.
[4]叶果,程洪,赵洋.电影中吸烟活动识别[J].智能系统学报,2011,6(05):440.
 YE Guo,CHENG Hong,ZHAO Yang.moking recognition in movies[J].CAAI Transactions on Intelligent Systems,2011,6(5):440.
[5]胡光龙,秦世引.动态成像条件下基于SURF和Mean shift的运动目标高精度检测[J].智能系统学报,2012,7(01):61.
 HU Guanglong,QIN Shiyin.High precision detection of a mobile object under dynamic imaging based on SURF and Mean shift[J].CAAI Transactions on Intelligent Systems,2012,7(5):61.
[6]史晓鹏,何为,韩力群.采用Hough变换的道路边界检测算法[J].智能系统学报,2012,7(01):81.
 SHI Xiaopeng,HE Wei,HAN Liqun.A road edge detection algorithm based on the Hough transform[J].CAAI Transactions on Intelligent Systems,2012,7(5):81.
[7]韩峥,刘华平,黄文炳,等.基于Kinect的机械臂目标抓取[J].智能系统学报,2013,8(02):149.[doi:10.3969/j.issn.1673-4785.201212038]
 HAN Zheng,LIU Huaping,HUANG Wenbing,et al.Kinect-based object grasping by manipulator[J].CAAI Transactions on Intelligent Systems,2013,8(5):149.[doi:10.3969/j.issn.1673-4785.201212038]
[8]顾照鹏,刘宏.单目视觉同步定位与地图创建方法综述[J].智能系统学报,2015,10(04):499.[doi:10.3969/j.issn.1673-4785.201503003]
 GU Zhaopeng,LIU Hong.A survey of monocular simultaneous localization and mapping[J].CAAI Transactions on Intelligent Systems,2015,10(5):499.[doi:10.3969/j.issn.1673-4785.201503003]
[9]赵军,於俊,汪增福.基于改进逆向运动学的人体运动跟踪[J].智能系统学报,2015,10(04):548.[doi:10.3969/j.issn.1673-4785.201403032]
 ZHAO Jun,YU Jun,WANG Zengfu.Human motion tracking based on an improved inverse kinematics[J].CAAI Transactions on Intelligent Systems,2015,10(5):548.[doi:10.3969/j.issn.1673-4785.201403032]
[10]韩延彬,郭晓鹏,魏延文,等.RGB和HSI颜色空间的一种改进的阴影消除算法[J].智能系统学报,2015,10(5):769.[doi:10.11992/tis.201410010]
 HAN Yanbin,GUO Xiaopeng,WEI Yanwen,et al.An improved shadow removal algorithm based on RGB and HSI color spaces[J].CAAI Transactions on Intelligent Systems,2015,10(5):769.[doi:10.11992/tis.201410010]
[11]张新钰,邹镇洪,李志伟,等.面向自动驾驶目标检测的深度多模态融合技术[J].智能系统学报,2020,15(4):758.[doi:10.11992/tis.202002010]
 ZHANG Xinyu,ZOU Zhenhong,LI Zhiwei,et al.Deep multi-modal fusion in object detection for autonomous driving[J].CAAI Transactions on Intelligent Systems,2020,15(5):758.[doi:10.11992/tis.202002010]

备注/Memo

备注/Memo:
收稿日期:2020-06-30。
基金项目:国家自然科学基金项目(61573255,61976158,61673301);国家重点研发计划项目(213)
作者简介:王照国,硕士研究生,主要研究方向为目标检测、深度学习、粒计算;张红云,副教授,博士生导师,博士,主要研究方向为主曲线算法、粒计算、模糊集。发表学术论文近50篇;苗夺谦,教授,博士生导师,博士,主要研究方向为人工智能、机器学习、大数据分析、粒计算。授权专利9项,发表学术论文180余篇,出版教材和学术著作9部
通讯作者:张红云.E-mail:zhanghongyun@tongji.edu.cn
更新日期/Last Update: 2021-01-15