陈世峰  男  博导  中国科学院深圳先进技术研究院
电子邮件: shifeng.chen@siat.ac.cn
通信地址: 深圳市南山区西丽深圳大学城学苑大道1068号
邮政编码: 518055

研究领域

计算机视觉,嵌入式人工智能

部分研究简介

  • 计算机视觉与深度学习模型研究:围绕计算机视觉核心应用算法以及深度学习模型的理论分析与研究,包括图像识别、检测、分类、检索、重建等各种视觉信息感知与理解方法,研究对象包括人、物、场景、行为、事件等。

机器视觉主要研究方向


  • 深度神经网络模型压缩与量化:针对深度神经网络规模大、运算资源依赖强的问题,对神经网络模型结构进行压缩,并对参数进行低比特位量化,从而提升深度神经网络的运行效率以及降低部署资源依赖。

联合通道网络剪枝方法及其性能


基于误差补偿的神经网络量化方法收敛性与精度对比


  • 嵌入式AI:软硬一体AI方案、基于各种嵌入式芯片平台(ARM CPU、MCU、VPU、嵌入式GPU、各类NPU)的AI系统等。

嵌入式人脸识别智能门控系统


  • 智能交通:交通相关的智能视频分析,包括车牌识别、车辆违停、行人闯入、抛洒物、路障、拥堵、火灾等一系列人车物相关的交通事件检测。(获国际著名智能交通比赛AICity 2021 Track4冠军

交通事件检测与分析


  • 工业场景应用:视觉在工业场景中的应用,包括缺陷检测、工件识别、位姿估计、工况理解、动态分拣等。

工业环境下的6D位姿估计


基于6D位姿分析的动态规划与分拣系统。


  • 视觉的医学应用:人工智能和AI技术在医学中的应用,包括CT图像、X射线图像、组织切片图像等分析。

腺体组织切片分析


基于CT图像的脊柱分割


  • 低层视觉(Low Level Vision:图像增强、去雾、超分辨、去噪、和谐化等。

图像去雾


图像和谐化


招生信息

人工智能,计算机视觉,图像视频处理,模式识别,机器学习

发明专利

[1] 基于Retinex理论的对抗神经网络的单图像去雾方法. CN202111558227.4.

[2] 混合结构的视频识别方法. CN202111545930.1.

[3] 基于对称感知的六自由度物体姿态估计方法及系统. CN202111542551.7.

[4] 一种视频标注方法、装置、设备及计算机可读存储介质. PCT/CN2021/137580.

[5] 一种6D姿态估计方法. CN202110582277.X.

[6] 一种基于图像识别的开关柜状态检测方法及其系统. CN202110606268.X.

[7] 一种目标检测方法、装置、终端设备和存储介质. CN202110360031.8.

[8] 一种视频标注方法、装置、设备及计算机可读存储介质. CN202110185443.2.

[9] 基于混合2D卷积和伪3D卷积的立体匹配方法. PCT/CN2020/139400.

[10]     容量瓶容积的校准方法、装置、终端设备及存储介质. PCT/CN2020/129528.

[11]     数据处理方法、装置、设备及计算机可读存储介质. CN202010680761.1.

[12]     一种视频分类的方法、装置及存储介质. CN202010251105.X.

[13]     基于混合2D卷积和伪3D卷积的立体匹配方法. CN202011436492.0.

[14]     视频分类方法及相关装置. CN202010203123.0.

[15]     基于生成对抗网络GAN的图像处理方法、装置、以及电子设备、存储介质. CN201911287816.6.

[16]     医学图像识别方法、医学图像识别装置、终端设备及介质. CN201910790660.7.

[17]     容量瓶容积的校准方法、装置、终端设备及存储介质. CN201911128691.2.

[18]     深度图像的处理方法及装置. CN2016100419936.

[19]     视频切割的方法及装置. CN201610046722X.

[20]     基于视频的物体切割方法及装置. CN2016100417112.

[21]     用于处理人脸特征数据的方法和装置. CN2014108427429.

[22]      一种基于特征融合的图像检索方法. CN2014108057629.

[23]     一种图像压缩、解压的方法、装置及图像系统. CN2013107053946.

[24]     一种标定模板、模板检测方法、装置及终端. CN2015101401051.

[25]     一种图像检索排序的方法及装置. CN2013106905050.

[26]     确定数据点的相似度的方法. CN2014108059056.

[27]     图像检索方法和装置. CN2012105723718.

[28]     图像共显著物体的检测方法. CN2014108431693.

[29]     一种图像显著性物体检测方法和装置. CN2013106869302.

[30]     数据重排序方法和系统. CN2012105722749.

[31]     图像检索的方法和系统. CN2012105727278.

[32]     图像超分辨方法及系统. CN201110283921X.

[33]     视频处理方法及系统. CN2011102839099.

[34]     视频播放中的广告插播方法和设备. CN2013104970888.

[35] 一种基于人脸属性的人群分析方法及装置. CN2014108552560.

发表论文

[1]    Hanyu Peng, Jiaxiang Wu, Zhiwei Zhang, Shifeng Chen, and Hai-Tao Zhang: “Deep Network Quantization via Error Compensation,” IEEE Trans. on Neural Networks and Learning Systems, 2021.

[2]    Yuxiang Zhao, Wenhao Wu, Yue He, Yingying Li, Xiao Tan, Shifeng Chen: “Good Practices and a Strong Baseline for Traffic Anomaly Detection,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 3993-4001, 2021.

[3]    Chunbi Jiang, Dongxiao Zhang, and Shifeng Chen: “Lithology identification from well log curves via neural networks with additional geological constraint,” Geophysics, 86 (5), pages: IM85–IM100, 202.

[4]    Ming Zhang, Xuefei Zhe, Shifeng Chen, Hong Yan: “Deep center-based dual-constrained hashing for discriminative face image retrieval,” Pattern Recognition, 117: 107976, 2021.

[5]    Hao Xu, Yongjin Hou, Jia-Wei Luo, Tianyu Wu, Yue Wu, Shifeng Chen, Xianglei Li, and Hai-Tao Zhang: “Cooperative Manipulation in Unknown Environment with Distributed Control,” Proceeding in Chinese Control Conference, 2021.

[6]    Ming Zhang, Xuefei Zhe, Le Ou-Yang, Shifeng Chen, and Hong Yan: “Semantic Hierarchy Preserving Deep Hashing for Large-Scale Image Retrieval,” Proceeding in International Conference on Machine Vision and Applications (MVA), 2021.

[7]    Zhiyue Wang, Wei Zhou, Junlin Li, Zhiyong Chen, Shifeng Chen, and Hai-Tao Zhang: “A Reweighted ℓ1-Minimization Algorithm for Joint Topology and Line Parameter Identification in Electric Grid”, Proceeding in Chinese Control Conference, 2021.

[8]    Hongren Wang and Shifeng Chen: “Research on Two-stage Object Detection Method Based on Key Point Detection,” Journal of Integration Technology, 10(5):34-42, 2021.

[9]    Gui-Ping Ren, Ziheng Yu, Yue Wu, Shifeng Chen, Xianglei Li, and Hai-Tao Zhang: “The analysis of similarities and differences between ADRC and PID controller for AMB system,” Proceeding in Chinese Control Conference, 2021.

[10] Jiayu Xu, Shifeng Chen, Like Zhang, Junle Wang, Chong Zhang, Yanqing Jing, Zhenhuan Wang, Xinqi Zhu: “Lineup Mining and Balance Analysis of Auto Battler,” Proceedings of the 2020 International Conference on Aviation Safety and Information Technology (ICASIT), Pages 169–176, 2020.

[11] Zhiwei Zhang, Shifeng Chen, Lei Sun: “P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection,” IJCAI, pp. 3237-3243, 2020.

[12] Wenhao Wu, Dongliang He, Xiao Tan, Shifeng Chen, Yi Yang, Shilei Wen: “Dynamic Inference: A New Approach Toward Efficient Video Action Recognition,” CVPR workshop, pp. 2890-2898, 2020.

[13] Xufei Zhe, Shifeng Chen, Hong Yan: “Deep Class-Wise Hashing: Semantics-Preserving Hashing via Class-wise Loss,” IEEE Transactions on Neural Networks and Learning Systems, 31(5): 1681 - 1695, 2020.

[14] Huijun Ding, Zhanpeng Pan, Qian Cen, Yang Li, Shifeng Chen: “Multi-scale fully convolutional network for gland segmentation using three-class classification,” Neurocomputing, 380: 150-161, 2020

[15] Yu Dong, Yihao Liu, He Zhang, Shifeng Chen, Yu Qiao: “FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing,” In Proc. AAAI Conference on Artificial Intelligence (AAAI), pp. 10729-10736, 2020.

[16] Weizhong Jiang, Haiming Yu, and Shifeng Chen: “Person Re-identification Method Based on Correlation Between Features,” Journal of Integration Technology, 9(4):68-78, 2020.

[17] Xuefei Zhe, Shifeng Chen, Hong Yan: “Directional statistics-based deep metric learning for image classification and retrieval,” Pattern Recognition, 93: 113-123, 2019.

[18] Hanyu Peng, Shifeng Chen: “BDNN: Binary convolution neural networks for fast object detection,” Pattern Recognition Letters, 125: 91-97, 2019.

[19] Hanyu Peng; Junjun He; Shifeng Chen; Yali Wang; Yu Qiao: “Dual-supervised attention network for deep cross-modal hashing,” Pattern Recognition Letters, 128: 333-339, 2019.

[20] Hanyu Peng, Jiaxiang Wu, Shifeng Chen, Junzhou Huang: “Collaborative Channel Pruning for Deep Networks,” In Proc. Int'l Conf. Machine Learning (ICML), pp. 5113-5122, 2019.

[21] Wenhao Wu, Dongliang He, Xiao Tan, Shifeng Chen, Shilei Wen: “Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition,” In Proc. Int'l Conf. Computer Vision (ICCV), pp. 6221-6230, 2019.

[22] Sunping Wang and Shifeng Chen: “Depth-Aware Convolutional Neural Networks for Semantic Segmentation,” Journal of Integration Technology, 7(5):58-66, 2018.

[23] Zhexiao Guo, Minmin Shen, Le Duan, Yongjin Zhou, Jianghuai Xiang, Huijun Ding, Shifeng Chen, Oliver Deussen, Guo Dan: “Deep assessment process: Objective assessment process for unilateral peripheral facial paralysis via deep convolutional neural network,” 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI): 135-138, 2017.

[24] Hao Lv and Shifeng Chen: “Strong Edge-Aware Depth Image Completion with Multi-Direction Filtering,” Journal of Integration Technology, 5(6):36-45, 2016.

[25] Changqing Zou, Shifeng Chen, Hongbo Fu, Jianzhuang Liu: “Progressive 3D reconstruction of planar-faced manifold objects with DRF-based line drawing decomposition,” IEEE Transactions on Visualization and Computer Graphics, 21(2): 252-263, 2015.

[26] Shuze Du, Shifeng Chen: “Detecting Co-Salient Objects in Large Image Sets,” IEEE Signal Processing Letters (SPL), 22(2): 145-148, 2015.

[27] Changqing Zou, Xiaojiang Peng, Hao Lv, Shifeng Chen, Hongbo Fu, Jianzhuang Liu: “Sketch-based 3-D modeling for piecewise planar objects in single images,” Computer and Graphics, 46: 130–137, 2015.

[28] Shuze Du, Shifeng Chen, “Salient Object Detection via Random Forest,” IEEE Signal Processing Letters (SPL), Volume 21, Issue 1, Pages 51-54, 2014.

[29] Shifeng Chen, Qiang Zhou, Huijun Ding: “Learning Boundary and Appearance for Video Object Cutout,” IEEE Signal Processing Letters (SPL), Volume 21, Issue 1, Pages 101-104, 2014.

[30] Shuze Du, Wei Zhang, Shifeng Chen, Yafei Wen: “Learning Flexible Binary Code for Linear Projection Based Hashing with Random Forest,” Proc. Int'l Conf. Pattern Recognition (ICPR), pp. 2685-2690, 2014.

[31] Yafei Wen, Changqing Zou, Jianzhuang Liu, Shuze Du, Shifeng Chen: “Sketch-Based 3D Model Retrieval via Multi-feature Fusion,” Proc. Int'l Conf. Pattern Recognition (ICPR), pp. 4570-4575, 2014.

[32] Chao Dong, Shifeng Chen, Xiaoou Tang: “AdVisual: A Visual-based Advertising System,” Proc. ACM Multimedia (ACM-MM Demo), pp. 433-434, 2013.

[33] Xianbiao Qi, Yi Lu, Shifeng Chen, Chun-Guang Li, Jun Guo: “Spatial Co-occurrence of Local Intensity Order for Face Recognition,” ICME MIS-MEDIA Workshop, pp. 1-6, 2013.

[34] Wei Zhang, Chen Cao, Shifeng Chen, Jiangzhuang Liu, and Xiaoou Tang: “Style Transfer via Image Component Analysis,” IEEE Trans. on Multimedia (TMM), Volume 15, Issue 7, Pages 1594-1601, 2013.

[35] Shifeng Chen, Ming Liu, Wei Zhang, Jianzhuang Liu: “Edge Preserving Image Denoising with a Closed Form Solution,” Pattern Recognition (PR), Volume 46, Issue 3, Pages 976–988, March 2013.

[36] Chen Cao, Shifeng Chen, Yuhong Li, Jianzhuang Liu: “Online Non-feedback Image Re-ranking via Dominant Data Selection,” Proc. ACM Multimedia (ACM-MM), pp. 889-892, 2012.

[37] Chen Cao, Shifeng Chen, Changqing Zou, Jianzhuang Liu: “Locating High-density Clusters with Noisy Queries,” Proc. Int'l Conf. Pattern Recognition (ICPR), pp. 3537-3540, 2012.

[38] Qian Li, Shifeng Chen, Beiwei Zhang: “Predictive Video Saliency Detection,” Proc. Chinese Conference on Pattern Recognition (CCPR), pp. 178-185, 2012.

[39] Qiang Zhou, Shifeng Chen, Jianzhuang Liu, Xiaoou Tang: “Edge-Preserving Single Image Super-Resolution,” ACM Multimedia (ACM-MM), pp. 1037-1040, 2011.

[40] Chen Cao, Shifeng Chen, Wei Zhang, Xiaoou Tang: “Automatic Motion-Guided Video Stylization and Personalization,” ACM Multimedia (ACM-MM), pp. 1041-1044, 2011.

[41] Shifeng Chen, Yu Qiao, “Image Segmentation via Multi-Scaled Belief Propagation,” ICIA, 2011.

[42] Wei Zhang, Yu Qiao, Chunjing Xu, and Shifeng Chen, “Robust Non-Rigid 3D Tracking for Face Recognition in Real-world Videos,” ICIA, 2011.

[43] X. Wang and S. Chen, “Semantic Object Segmentation,” in the book of “Image/Video Segmentation,” edited by King N. Ngan and Hongliang Li, published by Springer, 2011. (专著章节)

[44] S. Chen, “Labeling Problems with Smoothness-Based Priors in Computer Vision,” LAP Lambert Academic Publishing, 2010. (专著)

[45] Shifeng Chen, Liangliang Cao, Yueming Wang, Jianzhuang Liu, Xiaoou Tang: “Image Segmentation by MAP-ML Estimations,” IEEE Trans. on Image Processing (TIP), vol. 19, no. 9, pp. 2254-2264, 2010.

[46] Jiayao Hu, Shifeng Chen, Jianzhuang Liu, Xiaoou Tang: “Fast Image Rearrangement via Multi-Scale Patch Copying,” Proc. ACM Multimedia (ACM-MM), pp. 691-694, 2010.

[47] Ming Liu, Shifeng Chen, Jianzhuang Liu: “Continuous MRF Based Image Denoising with a Closed Form Solution,” Proc. IEEE Int’l Conf. Image Processing (ICIP), pp. 1137-1140, 2010.

[48] Ming Liu, Shifeng Chen, Jianzhuang Liu: “Video Completion via Motion Guided Spatial-Temporal Global Optimization,” ACM Multimedia (ACM-MM), pp. 537-540, 2009

[49] Shifeng Chen, Yuandong Tian, Fang Wen, Ying-Qing Xu, Xiaoou Tang: “EasyToon: an Easy and Quick Tool to Personalize a Cartoon Storyboard Using Family Photo Album,” ACM Multimedia (ACM-MM), pp. 499-508, 2008.

[50] Fang Wen, Shifeng Chen, Xiaoou Tang: “Easytoon: Cartoon Personalization Using Face Photos,” ACM Multimedia (ACM-MM Demo), pp. 1021-1022, 2008.

[51] Ming Liu, Shifeng Chen, Jianzhuang Liu: “Precise Object Cutout from Images,” ACM Multimedia (ACM-MM), pp. 623-626, 2008.

[52] Shifeng Chen, Liangliang Cao, Jianzhuang Liu, Xiaoou Tang:  “Iterative MAP and ML Estimations for Image Segmentation,” IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2007.

[53] Shifeng Chen, Zhenguo Li, Jianzhuang Liu, Xiaoou Tang: “Image Matting Using Linear Optimization,” ACM Multimedia (ACM-MM), pp. 321-324, 2007.

[54] Huang Ting, Shifeng Chen, Jianzhuang Liu, Xiaoou Tang: “Image Inpainting by Global Structure and Texture Propagation,” ACM Multimedia (ACM-MM), pp. 517-520, 2007.

[55] Zhenguo Li, Jianzhuang Liu, Shifeng Chen, Xiaoou Tang: “Noise Robust Spectral Clustering,” IEEE Int. Conf. Computer Vision (ICCV), pp. 1-8, 2007.

[56] Shifeng Chen, Liangliang Cao, Jianzhuang Liu, Xiaoou Tang: “Automatic Segmentation of Lung Fields from Radiographic Images of SARS Patients Using a New Graph Cuts Algorithm,” Proc. Int. Conf. Pattern Recognition (ICPR), pp. 271-274, 2006.

[57] S-Y Yuen, H-S Lam, C-K Fong, S Chen, C-K Chow, “A Robust Iterative Hypothesis Testing Design of the Repeated Genetic Algorithm,” Image and Vision Computing, Vol. 23, pp. 972–980, 2005.