智能多媒体实验室

苏松志


副教授

博士,厦门大学副教授
苏松志,男,福建泉州人,博士,硕士生导师,副教授2005年毕业于山东大学计算机科学与技术学院获工学学士,2008年和2011年毕业于厦门大学信息科学与技术学院,分别获计算机科学工学硕士和人工智能基础理学博士。目前是IEEE Image Processing, NeuroComputing, IET Image Processing, Mutltimedia Tools and Application, 计算机学报等期刊的审稿人。主持和参与多项国家自然科学基金和横向课题,发表SCI论文30多篇。 研究方向: 计算机视觉、机器学习及其应用、人脸识别与行人检测、无人驾驶中的智能视觉技术、三维场景的感知与理解和航拍图片分析

所属部门: 智能科学与技术系
联系电话: +86-15980939316
电子邮件: ssz @ xmu.edu.cn
主讲课程: 程序设计语言原理(本科生课程);机器学习(本科生课程);机器学习(硕博生课程) ;计算机视觉(博士生课程)
主持项目
[1]低空航拍下基于隐式姿态模型的平躺人体检测方法研究, 国家青年基金项目(61202143), 2013/01~2015/12, 项目主持人
[2]基于低空航拍图像的灾害环境下平躺人体检测方法研究,福建省青年基金(2013J05100) ,  2013/01~2015/12, 项目主持人
[3]基于视觉的车载行人检测辅助驾驶平台开发及应用,厦门*****汽车工业有限公司,2015/04~2016/05,项目主持人
[4]漫画UGC创作中的关键技术研发, 横向课题, 2013/12~2014/06,项目主持人
发表论文:
1. Luo, Zhiming; Jodoin, Pierre-Marc; Su, Song-Zhi(苏松志); Li, Shao-Zi; Larochelle, Hugo. Traffic Analytics With Low-Frame-Rate Videos, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,1051-8215 ,2018-04.
2. Cai, Guorong; Su, Songzhi(苏松志); Leng, Chengcai; Wu, Yundong; Lu, Feng. A Robust Transform Estimator Based on Residual Analysis and Its Application on UAV Aerial Images, REMOTE SENSING,2072-4292 ,2018-02.
3. Zhang, Jia (1, 2); Li, Candong (3); Cao, Donglin (1, 2); Lin, Yaojin (4); Su, Songzhi (1, 2)(苏松志); Dai, Liang (1, 2); Li, Shaozi (1, 2) . Multi-label learning with label-specific features by resolving label correlations, Knowledge-Based Systems,0950-7051 ,2018.
4. Huang, Min(1,2); Cai, Guo-Rong(3); Zhang, Hong-Bo(4); Yu, Sheng(1,2); Gong, Dong-Ying(1,2); Cao, Dong-Lin(1,2); Li, Shaozi(1,2); Su, Song-Zhi(1,2)(苏松志). Discriminative parts learning for 3D human action recognition, Neurocomputing,0925-2312 ,2018.
5. Wang, Tao(1); He, Xuming(2); Su, Songzhi(3)(苏松志); Guan, Yin(4). Efficient Scene Layout Aware Object Detection for Traffic Surveillance, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops,2160-7508 ,2017-08-22.
6. He, Wenli(1); Cai, Guorong(2); Zhong, Zhun(1); Su, Songzhi(1)(苏松志). Feature++: Cross dimension feature fusion for road detection, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings,1520-6149 ,2017-06-16.
7. Huang, Min(1,2); Su, Song-Zhi(1,2)(苏松志); Cai, Guo-Rong(3); Zhang, Hong-Bo(4); Cao, Donglin(1,2); Li, Shao-Zi(1,2). Meta-action descriptor for action recognition in RGBD video, IET Computer Vision,1751-9632 ,2017-06-01.
8. Duh, D.-J.(1); Huang, J.-C.(2); Chen, S.-Y.(2); Su, S.(3)(苏松志); Zhang, H.(4); Li, S.(3). Facial expression recognition based on spatio-temporal interest points for depth sequences, Imaging Science Journal,1368-2199 ,2016-10-02.
9. 苏松志*,李绍滋,蔡国榕.《行人检测:原理与应用》,厦大出版社-南强丛书,2016-3.
10.Su, Songzhi(苏松志); Wu, Sin-Sian; Chen, Shu-Yuan; Duh, Der-Jyh; Li, Shaozi. Multi-view fall detection based on spatio-temporal interest points. Multimedia Tools and Applications, v 75, n 14, p 8469-8492, July 2016. (JCR4区, SCI/EI)
11. Song-Zhi Su(苏松志), Zhi-Hui Liu, Su-Ping Xu, Shao-Zi Li, Rongrong Ji. Depth image feature learning based on sparse auto-encoder for human detection, Signal Processing, 2015, 112:43-52. (SCI, JCR 3)
12. Song-Zhi Su(苏松志), Zong-Yu Lan, Shao-Zi Li, Shu-Yuan Chen, Category-specific scene categorization, Journal of the Chinese Institute of Engineers, 2015, 38(1):128-137. (SCI, JCR 4)
13. Song-Zhi Su(苏松志)*, Shu-Yuan Chen. Analysis of feature fusion based on HIK SVM and its application for pedestrian detection. Abstract and Applied Analysis. 2013. (SCI)Volume 2013, page: 1-11, http://dx.doi.org/10.1155/2013/436062.
14. 苏松志*, 李绍滋, 陈淑媛, 蔡国榕, 吴云东. 行人检测技术综述[J]. 电子学报. 2012, 40(4): 814-820. (EI)
15. Guo-Rong Cai,Pierre-Marc Jodoin,Shao-Zi Li,Yun-Dong Wu,Song-Zhi Su(苏松志)(*),Zhen-Kun Huang,Perspective-SIFT: An efficient tool for low-altitude remote sensing image registration,Signal Processing,2013.11.01,93(11):3088~3110
16.Li-Chuan Geng,Pierre-Marc Jodoin,Song-Zhi Su(苏松志)(*),Shao-Zi Li,CBDF: Compressed Binary Discriminative Feature,Neurocomputing,2016.04.05,2016(184):43~54
17. Yi Wang,Sébastien Piérard,Song-Zhi Su(苏松志)(*),Pierre-Marc Jodoin,Improving pedestrian detection using motion-guided filtering,Pattern Recognition Letters,2016.12.29,000(2016):1~7
18. Zhi-Ming Luo,Pierre-Marc Jodoin,Song-Zhi Su(苏松志)(*),Shao-Zi Li,Hugo Larochelle,Traffic analytics with low frame rate videos,IEEE Transactions on Circuits and Systems for Video Technology,2016.11.24,2016(99):1~9
19. De-Dong Yuan,Jie Dong,Song-Zhi Su(苏松志)(*),Shao-Zi Li,Rong-Rong Ji,Pursuing detector efficiency for simple scene pedestrian detection,International Conference on MultiMedia Modeling (MMM),Dublin, Ireland,2014.1.6-2014.1.10
20. Dao-Xun Xia,Song-Zhi Su(苏松志)(*),Shao-Zi Li,Pierre-Mar Jodoin,Lying-Pose Detection with Training Dataset Expansion,IEEE International Conference on Image Processing (ICIP),France,2014.10.27-2014.10.30
21. Wen-Li He,Guo-Rong Cai,Zhun Zhong,Song-Zhi Su(苏松志)(*),Feature++: Cross dimension feature fusion for road detection,IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),美国,2017.03.05-2017.03.06
22. Bing Shuai,Song-Zhi Su(苏松志)(*),Shao-Zi Li,Yun Cheng,Rong-Rong Ji,Decomposed human localization in personal photo albums,International Conference on Visual Communications and Image Processing (VCIP),Malaysia,2013.12.7-2013.12.10