张永军
发布时间: 2021-12-10 | 查看数:6202
个人基本情况介绍:
张永军,博士,民建会员,硕士生导师/副教授,英国卡迪夫大学访问学者,贵州大学人工智能研究院执行院长,贵州省遥感大数据创新中心主任,贵州大学遥感大数据工程中心主任,贵州省民建科教委副主任。全国高等学校计算机教育研究会理事、贵州省创新方法二级导师、IEEE member,中国计算机学会(CCF)会员、中国人工智能学会会员、中国安防协会会员,中国安防协会专家咨询委专家组成员、中国测试学会大数据与人工智能工作委员会委员,国家技术标准创新基地城市综合视频图像大数据专业委员会核心专家、欧洲人工智能会议(ECAI 2020)程序委员会委员;人工智能与机器人国际会议(ISAIR2020 )程序委员会委员;图像、视觉和智能系统国际会议(ICIVIS 2023,2024 Workshop chair);图像、视觉和计算国际会议(ICIVC Technical Program Committee)。以第一作者/通讯作者在计算机顶级会议/期刊CVPR,ACCV,IEEE汇刊等发表计算机视觉方面论文50余篇,其中CVPR2023论文选为 Highlight(亮点论文,入选率为2.5%),为贵州首篇论文,申请发明专利15项。指导的硕士研究生毕业均发表一篇以上的高质量SCI期刊论文,每届硕士毕业生平均2人以上综合排名专业前三,并获得国家奖学金。
研究领域与方向:
智能视频分析,图像处理(包括:双目立体匹配,目标检测识别,图像增强等),遥感图像处理及工程应用等。
团队双目视觉立体匹配算法方面的研究成果目前处于国际前列,开发的双目视觉立体匹配算法EAI-Stereo和DLNR从2022年6月起在全球双目视觉算法权威排行榜Middlebury Evaluation位居第一长达一年半,目前DLNR仍排名第二,相关研究成果被ACCV2023和CVPR2023接收;MoCha-Stereo算法从2023年5月起在全球双目视觉算法权威排行榜KITTI2015和KITTI2012 Reflective处于榜单第一,相关研究成果被CVPR2024接收。
欢迎有一定编程基础,在人工智能计算机视觉方向有科研梦想、有抱负的同学加入我们研究团队!(想躺平混毕业的同学不用和我们联系)
希望在我们团队的学习经历能够成为你今后的人生财富,为你未来走得更高打下坚实的基础!
科研课题(近十年以来主要承担的科研项目):
(1) 教育部科技发“天诚汇智”创新促教基金, 2018A03020, 基于近红外图像的夜间行人检测算法研究, 2019-04 至 2020-03, 20万元, 结题, 主持
(2) 贵州省科学技术基金项目,汽车主动安全防撞预警系统关键技术的研究,NO. 黔科合LH字[2014]7635,2014.12—2016.12,8万,已结题,主持。
(3) 贵州大学人才引进基金课题,(2016)49号,基于姿态模型的汽车主动安全行人检测算法研究, 2017/01-2018/12,3.5万元,已结题,主持。
(4) 珠海欧比特宇航科技股份有限公司横向课题,基于机器学习原理的遥感图像处理及应用关键技术研究与开发实现,2018.06—2019.06,50万元,结题,主持。
(5) 贵阳网顺大数据科技有限公司,水族语言同声传译系统语音识别关键技术研究与实现,2019.11.01-2020.10.31,50万元,结题,主持。
(6) 贵州天禧机电设备有限公司,天禧机电科技创新能力提升关键技术研究与实现,2023.5-2025.5,16万元,在研,主持。
(7) 观山湖区核酸采样点查询系统,贵州君为科技有限公司,2022.9-2022.12,5万元,结题,主持。
(8) 贵州长通电气有限公司,基于i语音的GEPI机制砂智能制造关键技术研究,2022.5-2023.5,5万元,结题,主持。
(9) 贵州省应用基础研究计划重大科技项目,黔科合JZ字[2014]2005, 贵州复杂构造区页岩气赋存与渗透机制研究, 2015.01-2017.12,260万,已结题,参与。
(10) 国家自然科学基金项目,61540050,基于算法机制设计和平坦化技术的调度算法研究, 2015.12-2016.12,10万,已结题,参与。
(11) 国家自然科学基金委员会, 地区科学基金项目, 62062023, 扩散磁共振张量成像的医学图像鲁棒水印算法研究, 2021-01-01 至 2024-12-31, 35万元, 在研, 参与
(12) 深圳市战略新兴产业发展专项资金项目,基于智能占位检测的中央空调节能控制系统的关键技术研究及产业化, NO. CXZZ20120618142922197, 2012/11-2014/04,737.00万元,已结题,主要参与人。
(13) 香港特区政府创新科技署及香港汽车零部件研发中心的研发项目,新一代高级汽车辅助驾驶系统,NO.ITP/015/13AI,2013/11-2015/11,280.00万元,已结题,主要参与人。
学术论著(以第一作者/通讯作者发表的部分论文、专著):
[1] Chen Z, Long W, Yao H, Zhang Y*, et al. MoCha-Stereo: Motif Channel Attention Network for Stereo Matching[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). 2024. (CCF-A类会议)(通讯作者)
[2] Zhang X, Zhang Y*, Wang Z, et al. Sparse representation scheme with enhanced medium pixel intensity for face recognition[J]. CAAI Transactions on Intelligence Technology, 2024. (SCI二区)(通讯作者)
[3] Yang Y, Zhang Y, Cui Z, et al. Single image deraining using scale constraint iterative update network[J]. Expert Systems with Applications, 2024, 236: 121339. (SCI一区TOP)(通讯作者)
[4] Jian H, Zhang Y*, Gao W, et al. Dual-branch feature fusion dehazing network via multispectral channel attention[J]. International Journal of Machine Learning and Cybernetics, 2024: 1-17. (SCI三区)(通讯作者)
[5] Ouyang T, Zhang Y*, Zhao H, et al. A multi-color and multistage collaborative network guided by refined transmission prior for underwater image enhancement[J]. The Visual Computer, 2024: 1-19. (SCI三区)(通讯作者)
[6] Zhang X, Zhang Y*, Wang Z, et al. Sparse representation scheme with enhanced medium pixel intensity for face recognition[J]. CAAI Transactions on Intelligence Technology, 2024. ((SCI二区)(通讯作者)
[7] Zhao H, Zhou H, Zhang Y*, et al. High-Frequency Stereo Matching Network[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). 2023: 1327-1336. (CCF-A类会议,获CVPR2023 HighLight论文,入选率2.5%) (通讯作者)
[8] Yao H, Zhang Y*, Jian H, et al. Nighttime pedestrian detection based on Fore-Background contrast learning[J]. Knowledge-Based Systems, 2023: 110719. (SCI一区TOP)(通讯作者)
[9] Long W, Zhang Y*, Cui Z, et al. Threshold Attention Network for Semantic Segmentation of Remote Sensing Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023. (SCI一区TOP)(通讯作者)
[10] Yang H L, Zhang Y* J, Cui Z W, et al. DGRN: Image super-resolution with dual gradient regression guidance[J]. Computers & Graphics, 2023, 110: 141-150. (SCI三区)(通讯作者)
[11] Janneh L L, Zhang Y*, Cui Z, et al. Multi-level feature re-weighted fusion for the semantic segmentation of crops and weeds[J]. Journal of King Saud University-Computer and Information Sciences, 2023: 101545. (SCI三区)(通讯作者)
[12] Wang X, Zhang Y*, Xu Y, et al. Multi-feature fusion network for person reidentification [J]. Journal of Electronic Imaging, 2023, 32(2): 023044-023044. (SCI四区)(通讯作者)
[13] Yao H, Zhang Y*, Jian H, et al. Nighttime pedestrian detection based on Fore-Background contrast learning[J]. Knowledge-Based Systems, 2023: 110719. (SCI一区TOP)(通讯作者)
[14] Gao W, Zhang Y*, Jian H. A novel attention-based network for single image dehazing[J]. The Visual Computer, 2023: 1-13. (SCI三区)(通讯作者)
[15] Gao W, Zhang Y*, Jian H. Multispectral attention-based network for single image deraining[J]. Signal, Image and Video Processing, 2023: 1-11. (SCI四区)(通讯作者)
[16] Gao W, Zhang Y*, Long W, et al. A deraining with detail-recovery network via context aggregation[J]. Multimedia Systems, 2023: 1-11. (SCI三区)(通讯作者)
[17] XueXue Z, WeiHao G, He Yao, Yongjun Z*, et al. Face Recognition Based on SRCS Algorithm and Score of Exponential Weighting[C]//Proceedings of The 4th International Conference on Image, Vision and Intelligent Systems(ICIVIS 2023),2023. (EI收录,获大会最佳学生论文)
[18] Zhang Y, Liu W, Fan H, et al. Dictionary learning and face recognition based on sample expansion[J]. Applied Intelligence, 2022: 1-15. (SCI二区)(第一作者)
[19] Zou Y, Zhang Y*, Yan J, et al. License plate detection and recognition based on YOLOv3 and ILPRNET[J]. Signal, Image and Video Processing, 2022, 16(2): 473-480. (SCI四区)(通讯作者)
[20] Pan C, Zhang Y*, Wang Z, et al. Improved Multiple Vector Representations of Images and Robust Dictionary Learning[J]. Electronics, 2022, 11(6): 847. (SCI三区)(通讯作者)
[21] Wang Z, Zhang Y*, Pan C, et al. MMPCANet: An improved PCANet for occluded face recognition[J]. Applied Sciences, 2022, 12(6): 3144. (SCI三区)(通讯作者)
[22] Zhang Y, Wang Z, Zhang X, et al. Application of improved virtual sample and sparse representation in face recognition[J]. CAAI Transactions on Intelligence Technology, 2023, 8(4): 1391-1402. (SCI二区)(第一作者)
[23] 牛梦佳, 张永军*, 李智,等.基于自适应多尺度与轮廓梯度的遥感图像分割网络[J]. 激光与光电子学进展, 2023, 60(2):10. (核心期刊)(通讯作者)
[24] Yang Y, Zhang Y*, Cui Z, et al. Single image deraining using multi‐stage and multi‐scale joint channel coordinate attention fusion network[J]. International Journal of Intelligent Systems, 2022, 37(11): 9750-9773. (SCI一区TOP(通讯作者)
[25] Haoliang Zhao, Zhang Yongjun*,EAI-Stereo: Error Aware Iterative Network for Stereo Matching, The 16th Asian Conference on Computer Vision, Dec. 4-8, ACCV2022. (CCF-C类会议) (通讯作者)
[26] Xu Y J, Zhang Y* J, Li Z, et al. Multi-scale dehazing network via high-frequency feature fusion[J]. Computers & Graphics, 2022, 107: 50-59. (SCI三区)(通讯作者)
[27] 刘竣文, 张永军*, 李智,等. 基于RDM-YOLOv3的头部检测[J]. 激光与光电子学进展, 2022, 59(8):10. (核心期刊)(通讯作者)
[28] Zhang Y, Zheng S, Zhang X, et al. Multi-resolution dictionary learning method based on sample expansion and its application in face recognition[J]. Signal, Image and Video Processing, 2021, 15: 307-313. (SCI四区)(第一作者)
[29] Liu J, Zhang Y*, Xie J, et al. Head detection based on dr feature extraction network and mixed dilated convolution module[J]. Electronics, 2021, 10(13): 1565. (SCI三区)(通讯作者)
[30] Zhang Y, Zou Y, Fan H, et al. Pedestrian detection based on I-HOG feature[C]//International Symposium on Artificial Intelligence and Robotics 2021. SPIE, 2021, 11884: 624-635. (EI收录)(第一作者)
[31] Niu M, Zhang Y*, Yang G, et al. Semantic segmentation for remote sensing images via dense feature extraction and companion loss neural network[J]. International Journal of Remote Sensing, 2021, 42(22): 8640-8660. (SCI三区)(通讯作者)
[32] Zhao Y, Cui Z, Zhang Y, et al. Fast pedestrian detection method based on BING[J]. The Journal of Engineering, 2020, 2020(13): 653-658. (EI收录)(通讯作者)
[33] Liu W, Zhang Y*Fan H, et al. Detection of Late Blight in Potato Leaves Based on Multi-Feature and SVM Classifier[C]//Journal of Physics: Conference Series. IOP Publishing, 2020, 1518(1): 012045. (EI 收录源刊)
[34] Zheng S, Zhang Y*, Liu W, et al. Improved image representation and sparse representation for image classification[J]. Applied Intelligence, 2020, 50: 1687-1698. (SCI二区)(通讯作者)
[35] Zheng S, Zhang Y*, Liu W, et al. A dictionary learning algorithm based on dictionary reconstruction and its application in face recognition[J]. Mathematical Problems in Engineering, 2020, 2020: 1-10. (SCI四区)(通讯作者)
[36] Wenjie Liu, Yongjun Zhang*, Haisheng Fan, Yongjie Zou, Zhongwei Cui:
A New Multi-Channel Deep Convolutional Neural Network for Semantic Segmentation of Remote Sensing Image. IEEE Access 8: 131814-131825 (2020) (SCI二区)(通讯作者)
[37] Yongjie Zou, Yongjun Zhang, Jun Yan, Xiaoxu Jiang, Tengjie Huang, Haisheng Fan, Zhongwei Cui:A Robust License Plate Recognition Model Based on Bi-LSTM. IEEE Access 8: 211630-211641 (2020) (SCI二区)(通讯作者)
[38] Qian Wang, Yongjun Zhang*, Ling Xiao and Yuewei Li, Extension of Sample Dimension and Sparse Representation Based Classification of Low-Dimension Data, Genetic and Evolutionary Computing, 2019.pp:633-639. (EI收录)(通讯作者)
[39] Li Y, Zhang Y* , Wang Q , et al. A Noise Resistant Method by Setting Thresholds for Use With Face Recognition[C]// ICAIP 2019: 2019 3rd International Conference on Advances in Image Processing. 2019. (EI收录)(通讯作者)
[40] 程如中,张永军*,李晶晶,汪国平,雷凯,赵勇,应用于行人检测的HLBP与CHLBP纹理特征,北京大学学报(自然科学版),第54卷,第5期,2018,pp935-945。(核心期刊)(通讯作者)
[41] Ling, Xiao, Yongjun Zhang*, et al. Combining HWEBING and HOG-MLBP features for pedestrian detection[C]. the 7th Asian Conference on Artificial Intelligence Technology(ACAIT ), vol 16, 2018, pp. 1421-1426.(EI收录,获第二届亚洲人工智能技术大会最佳学生论文)
[42] Yongjun ZHANG, Yong ZHAO,Guoliang LI,Daimeng WEI and Ruzhong CHENG, Efficient and Real-time Pedestrian Detection at Night-time Environments[J], International Journal of Innovative Computing, Information and Control, 2015, Vol. 11, No.2,pp.599-613. (EI收录)(第一作者)
[43] Zhao Y, Zhang Y, Cheng R, et al. An enhanced histogram of oriented gradients for pedestrian detection[J]. IEEE Intelligent Transportation Systems Magazine, 2015, 7(3): 29-38. (SCI二区)(通讯作者)
发明专利及获奖情况(近十年):
(1) 指导研究生获亚洲人工智能技术大会(ACAIT2018)最佳论文
(2) 指导研究生获图像、视觉和智能系统国际会议(ICIVIS 2023)最佳论文
(3) 曲彦桥; 张永军; 高维豪 ; 一种基于多光谱注意力的单图像去雨方法及装置, 2023-10-27, 中国,CN117474799A( 发明专利)
(4) 程如中; 张永军; 姚和 ; 一种基于前背景对比注意力的单光谱夜间行人检测方法及系统, 2023-5-12,中国, CN117115726A ( 发明专利)
(5) 滕亦皓; 龙伟; 张永军; 欧阳婷; 曲彦桥; 黄贵圣 ; 一种基于阈值注意力的遥感图像语义分割网络及分割方法, 2023-04-07, 中国, ZL 2022 1 0876357.0( 发明专利)
(6) 张永军; 赵浩良; 陈子扬; 杨亦童; 赵勇 ; 一种立体匹配方法、装置、设备及计算机可读存储介质,2023-03-28, 中国, CN202310309495.5( 发明专利)
(7) 李智; 张永军; 徐毓杰; 杨亦童; 欧阳婷; 杨和亮; 王西禾; 赵浩良 ; 一种基于图像高频信息融合的多尺度特征去雾网络及方法, 2021-12-13, 中国, CN114202481A ( 发明专利)
(8) 张永军; 李智; 杨亦童; 徐毓杰; 王西禾; 赵浩良; 欧阳婷; 杨和亮 ; 一种基于多阶段和多尺度注意力融合网络及图像去雨方法, 2021-12-13, 中国, CN114187275A ( 发明专利)
(9) 张永军; 杨刚; 牛梦佳; 唐浩; 曾骏; 陈添 ; 一种准确率高的遥感图像语义分割方法, 2021-7-2, 中国, CN113298817A( 发明专利)
(10) 颜军; 张永军; 刘文杰; 邓剑文; 吴明朗; 郑忠良; 郝梦 ; 基于加权损失融合网络的遥感图像分割方法、装置及介质, 2020-10-14, 中国, CN112364699A ( 发明专利)
(11) 张永军; 秦永彬; 许尽染; 肖伶 ; 快速高效的行人检测方法, 2018-8-28, 中国, ZL 2018 10986642.1( 发明专利)
(12) 张永军; 秦永彬; 许尽染; 赵勇 ; 图像纹理提取方法, 2016-01-10, 中国, ZL 2016 1 0001687.X ( 发明专利)
学术兼职及荣誉称号:
(1) 全国高等学校计算机教育研究会理事
(2) 贵州省创新方法二级导师
(3) IEEE member
(4) 中国人工智能学会会员
(5) 中国安防协会会员
(6) 中国安防协会专家咨询委专家组成员
(7) 中国测试学会大数据与人工智能工作委员会委员
(8) 国家技术标准创新基地城市综合视频图像大数据专业委员会核心专家
(9) 欧洲人工智能会议(ECAI 2020)程序委员会委员
(10) 人工智能与机器人国际会议(ISAIR2020 )程序委员会委员;
(11) 图像、视觉和智能系统国际会议(ICIVIS 2023,2024)Workshop chair;
(12) 图像、视觉和计算国际会议(ICIVC)Technical Program Committee
(13) 担任国际顶级期刊及会议《IEEE Transactions on Circuits and Systems for Video Technology》、《IEEE Transactions on Geoscience and Remote Sensing》、《IEEE Intelligent Transportation Systems Magazine》、《Knowledge-Based Systems》、《Expert Systems with Applications》,ACCV,ECAI等的审稿人
教学格言:
没有教不会的学生,只有教不好的老师!
电子邮件:
zyj6667@126.com