邹文斌,1981年出生,博士,副教授,博士生导师。广东省教育厅智能视觉感知与理解创新团队负责人,深圳市深大爱培科智能驾驶技术研发中心理事长,深圳大学图像处理与机器学习理论及应用交叉学科创新团队副组长。于2010年获得北京大学软件工程专业硕士学位,2014年获得法国国立应用科学院信号与图像处理专业博士学位。2014-2015年在巴黎高科--国立路桥大学任研究员。2015年7月至今,任职于深圳大学信息工程学院。先后获评深圳市“孔雀计划” 海外高层次人才、深圳市南山区领航人才、深圳大学“荔园优青”学者。主持国家自然科学基金项目2项,各级项目累计经费1000余万元。长期从事计算机视觉和深度学习方面的研究工作。在IEEE Transactions on Image Processing、IEEE International Conference on Computer Vision (ICCV) 等期刊和会议上发表SCI/EI学术论文80余篇,担任IEEE Transactions on Image Processing、IEEE Transactions on Circuits and Systems for Video Technology等多家SCI期刊的审稿人。
研究兴趣:复杂动态场景语义感知、高精度定位与构图、自主无人系统适应性视觉导航
招生方向:计算机视觉(博士后)、信息与通信工程(博士、学硕)、电子与通信工程(专硕)
教授课程:《计算机视觉算法及其应用》《图像处理》《Python程序设计》《C程序设计》《面向对象程序设计》
最新动态:
1.本团队项目“Sensing AI--视障者的生活助手”荣获2019广东“众创杯”创新创业大赛金奖,赛事介绍:http://www.gddpf.org.cn/gzdt/201909/t20190923_1014631.htm
2.本团队论文《PR Product: A Substitute for Inner Product in Neural Networks》被顶级国际会议2019 ICCV论文,并将受邀在韩国首尔的主会议现场作口头报告,录取率4.3%。
3.本团队获得国际挑战赛ECCV 2018 ApolloScape: Vision-based Navigation for Autonomous Driving 第一名,比赛结果链接:http://apolloscape.auto/ECCV/carboard.html
4.本团队获得国际挑战赛CVPR 2018 WAD Video Segmentation Challenge 第三名,比赛结果链接:https://www.kaggle.com/c/cvpr-2018-autonomous-driving/leaderboard
近五年主持科研项目清单:
1. 国家自然科学基金面上项目,批准号:61771321,时空约束的协同视觉显著性检测与目标跟踪,2018/01-2021/12, 62万元(直接经费)。
2. 国家自然科学基金青年项目,批准号:61401287, 联合显著性检测和对象分割的算法研究,2015/01-2017/12, 21万元。
3. 广东省创新团队,批准号:2018KCXTD027,智能视觉感知与理解,2019/07-2022/06,40万元。
4. 广东省自然科学基金--面上项目,批准号:2020A1515010959,基于视频显著性检测引导的目标跟踪算法研究,2019/10-2022/09,10万元。
5. 深圳市残疾人综合服务中心--康复辅助器具项目,批准号:F02,便于盲人出行的无障碍导盲系统,2020/06-2021/04,50万元。
6. 深圳市海外高层次人才创新创业专项资金技术创新项目,批准号:KQJSCX20170327151357330,海量视频的协同显著性检测与目标跟踪关键算法研究,2017/07-2020/06,100万元。
7. 深圳市新引进高端人才科研启动项目,面向无人机的运动目标检测、识别与跟踪算法的研究,2016/07-2019/06, 270万元。
8. 深圳市科创委基础研究项目,面向视频大数据的快速视觉显著性检测及目标分割算法,2016/07-2018/06,35万元。
9. 企业横向,智能驾驶技术研发, 100万
部分代表性期刊论文:
[1] W. Zou* et al. “Unsupervised Joint Salient Region Detection and Object Segmentation”, IEEE Transactions on Image Processing, (23) 3858 – 3873,2015(顶级期刊,中科院大类二区,IF=4.828)
[2] W. Zou* et al. “Online Glocal Transfer for Automatic Figure-ground Segmentation”, IEEE Transactions on Image Processing, (23) 3858 – 3873,2014(顶级期刊,中科院大类二区,IF=4.828)
[3] Y. Chen, W. Zou* et al. "SCOM: Spatiotemporal Constrained Optimization for Salient Object Detection", IEEE Transactions on Image Processing, vol. 27, no. 7, pp. 3345-3357, July 2018. (顶级期刊,中科院大类二区,影响因子4.828)
[4] Z. Liu#, W. Zou# et al. “Saliency Tree: A Novel Saliency Detection Framework”, IEEE Transactions on Image Processing, (5) 1937 – 1952,2014(中科院大类二区,IF=4.828)
[5] Y. Yuan#, W. Zou# et al. “A Robust and Efficient Approach to License Plate Detection”, IEEE Transactions on Image Processing, 2017 (3) 1102 - 1114(顶级期刊,中科院大类二区,IF=4.828)
[6] W. Zou*et al. “Automatic Foreground Extraction via joint CRF and Online Learning”, Electronics Letter, 49 (18), 1140-1142, 2013(中科院大类四区,IF=1.155)
[7] Y. Tang, W. Zou* et al. " Weakly Supervised Salient Object Detection with Spatiotemporal Cascade Neural Networks", IEEE Transactions on Circuits and Systems for Video Technology,, doi: 10.1109/TCSVT.2018.2859773. 中科院大类二区,IF=3.599)
[8] Z. Jin, T. Tillo, W. Zou* et al. “Robust Plane Detection using Depth Information from a Consumer Depth Camera”, IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2017.2780181(中科院大类二区,IF=3.599)
[9] B. Lei, W. Hou, W. Zou* et al. "Longitudinal score prediction for Alzheimer’s disease based on ensemble correntropy and spatial–temporal constraint", Brain Imaging and Behavior, DOI: 10.1007/s11682-018-9834-z (中科院大类JCR二区,IF=3.985)
[10] S. Jiao, W. Zou* “High-resolution parallel phase-shifting digital holography using a low-resolution phase-shifting array device based on image inpainting”, Optics Letters, (42) 482-485,2017(顶级期刊,中科院大类二区,IF=3.341)
[11] S. Jiao, Z. Zhuang, W. Zou* “Fast computer generated hologram calculation with a mini look-up table incorporated with radial symmetric interpolation”, Optics Express, (25) 112-123,2017(顶级期刊,中科院大类二区,IF=3.307)
[12] S. Jiao, P. Tsang, T. Poon, J. Liu, W. Zou et al. “Enhanced Autofocusing in Optical Scanning Holography Based on Hologram Decomposition”, IEEE Transactions on Industrial Informatics, (13) 2455-2463, 2017.(顶级期刊,中科院大类一区,IF=6.764)
[13] C. Xiang, L. Zhang, W. Zou* et al. “MS-CapsNet: A Novel Multi-Scale Capsule Network”, IEEE Signal Processing Letters, DOI: 10.1109/LSP.2018.2873892, 2018(中科院大类三区,IF=2.813)
[14] S. Jiao, C. Zhou, Y. Shi, W. Zou, Xia Li, “Review on optical image hiding and watermarking techniques”, Optics & Laser Technology, Volume 109, 2019, Pages 370-380(中科院大类三区,IF=2.503)
[15] S. Jiao, W. Zou* et al. “QR code based noise-free optical encryption and decryption of a gray scale image”, Optics Communications, (387) 235-240,2017(中科院大类三区,IF=1.588)
[16] S. Jiao, C. Zhou, W. Zou*et al. “Shift, rotation and scale invariant optical information authentication with binary digital holography”, Optics Communications, (405)53-59,2017(中科院大类三区,IF=1.588)
[17] Z. Zhuang, S. Jiao, W. Zou*et al. “Embedding intensity image into a binary hologram with strong noise resistant capability”, Optics Communications, (11)245-251, 2017(中科院大类三区,IF=1.588)
[18] S. Jiao, Z. Zhuang, C. Zhou, W. Zou*, X. Li, “Security enhancement of double random phase encryption with a hidden key against ciphertext only attack”, Optics Communications, 418, 106-114, 2018(中科院大类三区,IF=1.588)
[19] S. Jiao, G. Li, C. Zhou, W. Zou*et al. “Special ciphertext only attack to double random phase encryption by plaintext shifting with speckle correlation”, Journal of the Optical Society of America A: Optics, Image Science & Vision, (35) A1-A6, 2018(中科院大类三区,IF=1.621)
[20] S. Jiao, Z. Jin, C. Zhou, W. Zou*et al. “Is QR code an optimal choice of data container in optical encryption from an error correction coding perspective?”, Journal of the Optical Society of America A: Optics, Image Science & Vision, (35) A23-A29, 2018(中科院大类三区,IF=1.621)
[21] S. Jiao, C. Zhou, W. Zou*, X. Li, “Non-destructive ghost authentication for single-pixel imaging in mass user environment”, Laser Physics 28 (9), 2018(中科院大类四区,IF=1.158)
[22] H. Lei, H. Xie, W. Zou*et al. “Hierarchical Saliency Detection via Probabilistic Object Boundaries”, International Journal of Pattern Recognition and Artificial Intelligence, (6)1-23, 2017(中科院大类四区,IF=0.915)
部分代表性会议论文:
[1] W. Zou* et al. “HARF: Hierarchy-associated Rich Features for Salient Object Detection”, IEEE International Conference on Computer Vision, 2015
[2] W. Zou* et al. “Segmentation Driven Low-rank Matrix Recovery for Saliency Detection”, British Machine Vision Conference, 2013
[3] W. Zou* et al. “Semantic image segmentation using region bank”, International Conference on Pattern Recognition, 2012
[4] W. Zou* et al. “Semantic Segmentation via Sparse Coding over Hierarchical Regions”, IEEE International Conference on Image Processing, 2012
[5] D. Wu, W. Zou* et al. “Kernalised Multi-resolution Convnet for Visual Tracking”, IEEE Conference on Computer Vision and Pattern Recognition, 2017
[6] Y. Tang, W. Zou* et al. "Multi-Scale Spatiotemporal Conv-LSTM Network for Video Saliency Detection", ACM International Conference on Multimedia Retrieval , 2018
[7] Y. Chen, W. Zou* et al. "Video Salient Object Detection via MultipleTime-scale Analysis", IEEE International Conference on Image Processing, 2018
[8] Y. Tang, W. Zou* et al. “Multi-modal Metric Learning for Vehicle Re-identification in Traffic Surveillance Environment”, IEEE International Conference on Image Processing, 2017
[9] Z. Jin, W. Zou* et al. “A CNN Cascade for Quality Enhancement of Compressed Depth images”, IEEE International Conference on Visual Communication and Image Processing, 2017
专利:
(1) 一种基于二元分割树的区域特征描述方法及系统,申请号:201510924918.X
(2) 基于多目标函数深度学习的车辆重识别方法及装置,申请号:201710015898.3
(3) 一种基于时空约束的视频显著性检测方法及系统,申请号:201710437947.2
(4) 一种基于时空约束的视频显著性检测方法及系统,申请号:PCT/CN2017/087709
(5) 一种灰度图像编码隐藏方法及装置、解码方法及装置,申请号:201710451885.0
(6) 一种基于多分辨率神经网络的目标跟踪方法及系统,申请号:201710570207.6
(7) 基于光学加密和解密技术的图像加密和解密方法及装置,申请号:PCT/CN2016/105931
(8) 基于光学加密和解密技术的图像加密和解密方法及装置,申请号:201611036562.7
(9) 基于全卷积神经网络的压缩双目图像质量增强方法及装置,申请号:201710600916.4
(10) 基于全卷积神经网络的压缩深度图质量增强方法及装置,申请号:201710602293.4
(11) 一种鲁棒的基于深度信息的平面检测方法及系统,申请号:201710866367.5
(12) 一种鲁棒的基于深度信息的平面检测方法及系统,申请号:PCT/CN2017/102947
(13) 图像信息的隐藏方法及装置、解密方法及装置,申请号:201810792079.4
(14) 图像信息的隐藏方法及装置、解密方法及装置,申请号:PCT/CN2018/096149
(15) 轨迹预测方法及装置,申请号:PCT/CN2018/095144
(16) 轨迹预测方法及装置,申请号:201810752554.5
(17) 基于弱监督时空级联神经网络的显著目标检测方法及系统,申请号:PCT/CN2018/071902
(18) 基于弱监督时空级联神经网络的显著目标检测方法及系统,申请号:2018100186723
(19) 一种加/解密方法、加/解密端及双随机相位加解密系统,申请号:PCT/CN2017/113261
(20) 一种加/解密方法、加/解密端及双随机相位加解密系统,申请号:201711213115.9
办公室:信息工程学院N925
E-mail:wzou@szu.edu.cn