杨聪

发布时间:2025-07-11浏览次数:4491

研究领域

人工智能,计算机视觉,机器学习(含深度学习),智能驾驶


在研课题

1. 舱驾一体关键技术研究


(1)研究内容

基于国产大算力芯片智能驾驶(自动驾驶、智能座舱、智能泊车)关键技术研发与生态拓展:

1. 基于国产大算力芯片的舱内外视觉融合感知

2. 基于视觉的4D标注框架及关键算法

3. 面向J/X系列芯片的智能驾驶生态拓展,包括教材撰写、参考算法开发等


(2)代表论文(* 通讯作者)

[1] 杨聪 等编著,《智能座舱开发与实践》,机械工业出版社,2022. (2023年全国十佳汽车图书)

[2] 杨聪 等编著,《智能驾驶与机器视觉》,机械工业出版社,2024.(2024年1月份出版发行)

[3] Cong Yang, Zhenyu Yang, Weiyu Li and John See, FatigueView: A Multi-Camera Video Dataset for Vision-based Drowsiness Detection, IEEE Transactions on Intelligent Transportation Systems, pp 233-246, 2022. (中科院一区, IF=9.551)

[4] Cong Yang, Wenfeng Wang, Yunhui Zhang, Zhikai Zhang, Lina Shen, Yipeng Li and John See, MLife: a lite framework for machine learning lifecycle initialization, Machine Learning, pp 1-21, 2021. (CCF B, IF=5.414)

[5] Ruohong Mei, Wei Sui, Jiaxin Zhang, Xue Qin, Gang Wang, Tao Peng and Cong Yang(*), RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation, IEEE Transactions on Intelligent Vehicles, pp 1-11, 2024. (中科院二区,IF=8.2)


(3)代表专利

[1] Cong Yang; Zhenyu Yang; Weiyu Li,Fatigue state detection method and apparatus, medium, and electronic device,US11580757B2(美国专利),2023/2/14

[2] Cong Yang; Yunhui Zhang; Zhikai Zhang,Machine Model Update Method and Apparatus, Medium, and Device,US20220198331A1(美国专利),2022/6/23

[3] Yunhui Zhang; Zhikai Zhang; Cong Yang,Behavior Recognition Method and Apparatus, Medium, and Electornic Device,US20220188537A1(美国专利),2022/6/16

[4] 杨聪; 杨振宇; 李威宇,疲劳状态检测方法、装置、介质及电子设备,CN112528792A(中国专利),2021/3/19

[5] 杨聪; 张运辉; 张致恺,机器模型的更新方法、装置、介质及设备,CN112541447A(中国专利),2021/3/23


(4)媒体报道(摘选与本成果相关)

1. 长江日报:http://cjrb.cjn.cn/html/2024-04/16/node_8.htm

2. 汽车评价:https://mp.weixin.qq.com/s/_uc1Zvahmh1t7Lkaem68nA

3. 汽车之心:https://mp.weixin.qq.com/s/izy7IIROdsWtzQ2zeSukYw

4. 亿欧网:https://mp.weixin.qq.com/s/yCD6jiBseBf1jhoTzL1mgw


2. 面向零售场景的视觉感知关键技术研究


(1)研究内容

零售场景中的视觉感知关键技术包括:

1. 超宽视距下的高精度图像拼接算法(Wide Parallax Image Stitching)

2. 大规模细粒度商品检测与分类算法(Large-Scale Fine-grained SKU Recognition)

3. 图像质量检测与恢复算法(Image Quality Evaluation and Restoration)


(2)代表论文(*通讯作者)

[1] Cong Yang, Bipin Indurkhya, John See, Bo Gao, Yan Ke, Zeyd Boukhers, Zhenyu Yang and Marcin Grzegorzek, Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks, International Journal of Computer Vision (IJCV), pp 1-23, 2023. (CCF A, IF=19.5)

[2] Cong Yang, Zhenyu Yang, Yan Ke, Tao Chen, Marcin Grzegorzek and John See, Doing More with Moiré Pattern Detection in Digital Photos, IEEE Transactions on Image Processing, pp 694-708, 2023. (中科院一区,CCF A,IF=11.041)

[3] Cong Yang, Bipin Indurkhya, John See and Marcin Grzegorzek, Towards Automatic Skeleton Extraction with Skeleton Grafting, IEEE Transactions on Visualization and Computer Graphics, pp 4520-4532, 2021. (中科院一区,CCF A, IF= 5.226)

[4] Cong Yang, Oliver Tiebe, Kimiaki Shirahama and Marcin Grzegorzek, Object matching with hierarchical skeletons, Pattern Recognition, pp 183-197, 2016. (中科院一区,IF=8.0)

[5] Zhiming Chen, Kean Chen, Weiyao Lin, John See, Hui Yu, Yan Ke and Cong Yang(*), PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments, European Conference on Computer Vision (ECCV 2020), pp 1-17, 2020. (CCF B)


(3)代表专利

[1] 杨聪; 柯严,模型训练用图像的快速扩充方法、系统、设备及存储介质,CN108647553B(中国专利),2022/1/25

[2] 杨聪; 柯严,商品与标签的自动关联方法、系统、设备及存储介质,CN108416403B(中国专利),2021/5/4

[3] 杨聪; 唐健; 柯严; 严治庆,图像识别模型的训练方法、系统、设备和存储介质,CN111027621A(中国专利),2020/4/17

[4] 杨聪; 姚阳; 桑亮; 刘鸣洲; 柯严; 严治庆,带有摩尔纹的图片生成方法、系统、设备和存储介质,CN110992244A(中国专利),2020/4/10

[5] 杨聪; 王家豪; 李福辉; 柯严; 严治庆,货架空缺位置商品信息获取方法、系统、设备及存储介质,CN110516628A(中国专利),2019/11/29


(4)媒体报道(摘选与本成果相关)

1. 上海市信息服务业行业协会:https://mp.weixin.qq.com/s/-R4q9GgN_4qtB7CNbOSLgQ

2. 36氪:https://mp.weixin.qq.com/s/pxTLgOJounIpff-uZ_hNmw

3. 长宁区江苏社区发布:https://mp.weixin.qq.com/s/5UriubalfZCb_LYg9rPMfg


3. 基于空地协同的智能风电“巡检修”关键技术研究


(1)研究内容

智能风电“巡检修”关键技术包括:

1. 高空强干扰条件下全自动目标巡检数据采集技术

2. 数智化风电设备运维管理平台系统

3. 智能异形检修机器人多功能集成技术


(2)代表论文(* 通讯作者)

[1] Cong Yang, Xun Liu, Hua Zhou, Yan Ke and John See, Towards Accurate Image Stitching for Drone-based Wind Turbine Blade Inspection, Renewable Energy, pp 267-279, 2023. (中科院一区,IF=8.634).

[2] Cong Yang, Hua Zhou, Xun Liu, Yan Ke, Tao Chen and John See, BladeView: Towards Automatic Wind Turbine Inspection with Unmanned Aerial Vehicle, IEEE Transactions on Automation Science and Engineering (T-ASE), pp 1-12, 2023. (中科院一区, IF=5.6)

[3] Yulu Zhang, Liang Sang, Marcin Grzegorzek, John See and Cong Yang(*), BlumNet: Graph Component Detection for Object Skeleton Extraction, ACM Multimedia, pp 5528-5536, 2022. (CCF A)

[4] Imad Gohar, Abderrahim Halimi, John See, Weng Kean Yew and Cong Yang. Slice-Aided Defect Detection in Ultra High-Resolution Wind Turbine Blade Images Machines 11, no. 10: 953, 2023.

[5] Yuxi Li, Weiyao Lin, John See, Ning Xu, Shugong Xu, Ke Yan and Cong Yang, CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization, European Conference on Computer Vision (ECCV 2020), pp 1-17, 2020.


(3)媒体报道(摘选与本成果相关)

1. 中国工业报/新华社客户端:https://h.xinhuaxmt.com/vh512/share/10684496?channel=weixin

2. 36氪:https://36kr.com/newsflashes/2073194043292800?channel=wechat

3. 极客公园:https://mp.weixin.qq.com/s/LYyTDpnwvg0fgBffO-q1_Q

4. 长宁区工商联:https://mp.weixin.qq.com/s/VAzHFBhmJ6lmf12ZxPCiyA

5. 环球网:https://m.huanqiu.com/article/48AAKRlvxJs