副教授 深港微电子学院
安丰伟博士于2019年加入南方科技大学,2013年在日本广岛大学获得工学博士学位。现在担任南方科技大学深港微电子学院副教授。在此之前担任过日本松下半导体公司的主管工程师及日本广岛大学副教授,其专长是图像识别与机器学习的大规模数字集成电路设计。积累了十年以上图像处理、图像识别、机器学习的电路设计和系统集成(SoC)等经验,具有丰富的学术界和工业界的背景。安教授在松下半导体公司开发的产品和在广岛大学的研究成果等的目标应用是高级辅助驾驶系统(ADAS)和自动驾驶。团队目前继续从事面向自动驾驶的动态目标追踪专用芯片的研究。
个人简介
个人简介
研究领域
安丰伟博士的主要研究领域是基于计算机视觉的低功耗边缘人工智能芯片设计,具体包括图像处理、图像识别、机器学习的超大规模数字集成电路设计和系统集成,并有在工业界的研究开发经验。
教学
片上系统集成电路设计
学术成果 查看更多
2023:
Journal paper:
- Yangyi Zhang; Xianglong Wang; Gang Shi; Zizhao Peng; Lei Chen; Fengwei An*, Anti-Aliasing and Anti-Color-Artifact Demosaicing for High-Resolution CMOS Image Sensor, IEEE Transactions on Circuits and Systems I: Regular Papers,2023,70(12),pp.4928-4937
- Gang Shi; Xianglong Wang; Yichen Ouyang; Ruoheng Yao; Zhuoyu Chen; Wei Zhang; Lei Chen; Fengwei An*, A Spatio-Temporal Video Denoising Co-Processor With Adaptive Codec, IEEE Transactions on Circuits and Systems I: Regular Papers,2023,70(11), pp.4223-4234
- Xiao,Lanxiang; Chen,Lei; An,Fengwei*, An 11.6aF/kPa Mechanical Stress Sensor with 0.808% Temperature-drift Oscillator for Flip-chip Packaging, IEEE Transactions on Circuits and Systems II: Express Briefs, 2023, 70(2), pp.391-395
- Tan,Yonghao; Deng,Huanshihong; Sun,Mengying; Zhou,Minghao; Chen,Yifei; Chen,Lei; Wang,Chao; An,Fengwei*, A Reconfigurable Coprocessor for Simultaneous Localization and Mapping Algorithms in FPGA, IEEE Transactions on Circuits and Systems II: Express Briefs, 2023, 70 (1), pp.286-290
Conference paper:
- Zhiyue Gao; Fengwei An*; Lei Chen, A Non-Local Means Denoising Co-Processor with Data Reuse Scheme and Dual-Clock Domain for High Resolution Image Sensor, 2023 IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA), Oct. 2023, pp.146-147
- Jipeng Wang; Jianhui Song; Bingqiang Liu; Zixuan Shen; Yu Jiang; Fengwei An*; Chao Wang; Jiang Tang, An Energy-Efficient, Resource-Efficient and High Frame-Rate End-to-End Pedestrian Detector Using HOG-SVM for Intelligent Edge Devices, IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society, Oct. 2023, pp.1-6
- Ouyang, Yichen;Wang, Xianglong; Shi, Gang; Chen, Lei; An, Fengwei*, A Dynamic Codec with Adaptive Quantization for Convolution Neural Network, 15th IEEE International Conference on ASIC, ASICON 2023, 2023, pp.1-4
- Wei Zhang;Junfeng Chang; Zizhao Peng; Lei Chen; Fengwei An*, A 1920×1080 129fps 4.3pJ/pixel Stereo-Matching Processor for Pico Aerial Vehicles, 2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS), Jun. 2023, pp.1-2
- Dong, Pingcheng; Chen, Zhuoyu; Li, Ke; Chen, Lei; Cheng, Kwang-Ting; An, Fengwei*, Live Demonstration: Supervised-learning-based Visual Quantification for Image Enhancement, IEEE 49th European Solid-State Circuits Conference (ESSCIRC), SEP. 2023, pp.345-348
2022:
Journal paper:
- Ma, Y.; Fang, X.; Guan, X.; Li, K.; Chen, L.; An, F*. Five-Direction Occlusion Filling with Five Layer Parallel Two-Stage Pipeline for Stereo Matching with Sub-Pixel Disparity Map Estimation. Sensors, 2022, 22, 8605. pp.1-17, https://doi.org/10.3390/s22228605
- Tan, Y.; Sun, M.; Deng, H.;Wu, H.; Zhou, M.; Chen, Y.; Yu, Z.; Zeng, Q.; Li, P.; Chen, L.; An, F*. A Reconfigurable Visual–Inertial Odometry Accelerated Core with High Area and Energy Efficiency for Autonomous Mobile Robots. Sensors, 2022, 22, 7669. 1-17, https://doi.org/10.3390/s22197669
- Dong, P., Chen, Z., Li, Z., …Wang, C., An, F.*, Configurable Image Rectification and Disparity Refinement for Stereo Vision, IEEE Transactions on Circuits and Systems II: Express Briefs, 2022, 69(10), pp. 3973–3977
- Yao, R., Chen, L., Dong, P., Chen, Z., An, F.*, A Compact Hardware Architecture for Bilateral Filter with the Combination of Approximate Computing and Look-Up Table, IEEE Transactions on Circuits and Systems II: Express Briefs, 2022, 69(7), pp. 3324–3328
- Yao,Ruoheng;Deng,Huanshihong; Zhang,Wengyue; Chen,Lei; An,Fengwei*, Asynchronous Double-Frame-Exposure Binocular-Camera With Pixel-Level Pipeline Architecture for High-Speed Motion Tracking, IEEE Transactions on Circuits and Systems II: Express Briefs, 2022, 69(6), pp.2967-2971
- Luo, Y., Li, P., Shi, G., …Chen, L., An, F.*, Lane Departure Assessment via Enhanced Single Lane-Marking, Sensors, 2022, 22(5), 2024
- Lyu, H., An, F., Zhao, S., Mao, W., Yu, H., A 703.4-GOPs/W Binary SegNet Processor with Computing-Near-Memory Architecture for Road Detection, IEEE Design and Test, 2022, 39(2), pp. 74–83
- Dong, P., Chen, Z., Li, Z., …Chen, L., An, F.*, A 4.29nJ/pixel Stereo Depth Coprocessor with Pixel Level Pipeline and Region Optimized Semi-Global Matching for IoT Application, IEEE Transactions on Circuits and Systems I: Regular Papers, 2022, 69(1), pp. 334–346
Conference paper:
- Yichen Ouyang;Xianglong Wang; Gang Shi; Lei Chen; Fengwei An*, A Dynamic JPEG CODEC with Adaptive Quantization Table for Frame Storage Compression, 2022 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), Nov. 2022, pp.119-122
- Yunhao Ma;Xiwei Fang; Pingcheng Dong; Xinyu Guan; Ke Li; Lei Chen;Fengwei An*, Subpixel Interpolation Disparity Refinement for Semi-Global Matching, 2022 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), Nov. 2022, pp.105-109
- Ke Li;Xinyu Guan; Pingcheng Dong; Zhuoyu Chen; Lei Chen; Fengwei An*, A 320 FPS Pixel-Level Pipelined Stereo Vision Accelerator with Regional Optimization and Multi-direction Hole Filling, 2022 IEEE Asia Pacific Conference on Postgraduate Research in Microelectronics and Electronics (PrimeAsia), Nov. 2022, pp.85-88
- Lanxiang Xiao;Lei Chen; Fengwei An*, A 14.39ppm/kPa Stress Sensor with Low Temperature-drift and High Linearity for turbulence Stress, 2022 IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA), Oct. 2022, pp.66-67
- Yunhao Ma;Xiwei Fang; Pingcheng Dong; Xinyu Guan; Ke Li; Lei Chen; Fengwei An*, Post-Processing Refinement for Semi-Global Matching Algorithm Based on Real-Time FPGA, 35th IEEE International System-on-Chip Conference (SOCC), Sept. 2022, pp.1-5
- Liang, Z., Chen, L., An, F.*,3D Vehicle Surround View Algorithm for Embedded Platform, Journal of Physics: Conference Series, 2022, 2253(1), 012026
2021:
- Liu, F., Wang, J., Liu, B., …An, F., Wang, C., Low computation and high efficiency sobel edge detector for robot vision, 2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021, 2021, pp. 684–689
- Chen, Z., Dong, P., Li, Z., …Chen, L., An, F.*, Real-Time FPGA-Based Binocular Stereo Vision System with Semi-Global Matching Algorithm, International System on Chip Conference, 2021, 2021-September, pp. 158–163
- Zhang, Y., Peng, Z., Yao, R., …Chen, L., An, F.*, Efficient VLSI Architecture for Edge Sensing Anti-Aliasing Demosaicing, 2021 IEEE International Conference on Integrated Circuits, Technologies and Applications, ICTA 2021, 2021, pp. 105–106
- Yao, R., Deng, H., Zhang, W., …Chen, L., An, F.*, A Pseudo 943 million Frames per Rate High-Speed Camera with Asynchronous Double-Frame Exposure for Motion Estimation, 2021 IEEE International Conference on Integrated Circuits, Technologies and Applications, ICTA 2021, 2021, pp. 103–104
- Wang,Jipeng;Zhan,Yi; Wang,Zhaoxu; Peng,Zixuan; Xu,Jiarui; Liu,Bingqiang; Yu,Guoyi; An,Fengwei; Wang,Chao; Zou,Xuecheng, A Reconfigurable Matrix Multiplication Coprocessor with High Area and Energy Efficiency for Visual Intelligent and Autonomous Mobile Robots, Proceedings – A-SSCC 2021: IEEE Asian Solid-State Circuits Conference, 2021
- Dong, P., Li, Z., Chen, Z., …Wang, C., An, F.*, A 139 fps pixel-level pipelined binocular stereo vision accelerator with region-optimized semi-global matching, Proceedings – A-SSCC 2021: IEEE Asian Solid-State Circuits Conference, 2021
专利:
- 一种高速低资源消耗的视差优化方法、装置及终端,中国发明专利,2021-12-1
- 基于raw数据进行边缘检测的去马赛克方法及电路,中国发明专利,2021-12-06
- 一种双边滤波器的硬件架构系统及其权重优化方法,中国发明专利,2021-11-30
- 一种适用于混合精度神经网络的定点乘加运算单元及方法,中国发明专利,2021-02-09
- 一种低功耗立体匹配系统及获取深度信息的方法,PCT,2021-03-29
- 一种适用于混合精度神经网络的定点乘加运算单元及方法,PCT,2021-11-19
2020:
Journal paper:
- Xu, C., Peng, Z., Hu, X., …Chen, L., An, F.*, FPGA-Based Low-Visibility Enhancement Accelerator for Video Sequence by Adaptive Histogram Equalization with Dynamic Clip-Threshold, IEEE Transactions on Circuits and Systems I: Regular Papers, 2020, 67(11), pp. 3954–3964, 9151314
- Xu, P., Xiao, Z., Wang, X., …Wang, C., An, F.*, A multi-core object detection coprocessor for multi-scale/type classification applicable to iot devices, Sensors (Switzerland), 2020, 20(21), pp. 1–13, 6239
- Xiao, Z., Xu, P., Wang, X., Chen, L., An, F.*, A Multi-Class Objects Detection Coprocessor with Dual Feature Space and Weighted Softmax, IEEE Transactions on Circuits and Systems II: Express Briefs, 2020, 67(9), pp. 1629–1633, 9144541
Conference paper:
- Deng, H., Dong, P., Li, Z., …Luo, Y., An, F.*, Robot navigation based on pseudo-binocular stereo vision and linear fitting, Proceedings of 2020 IEEE International Conference on Integrated Circuits, Technologies and Applications, ICTA 2020, 2020, pp. 174–175, 9332014
- Zhan,Yi;Wang,Zihao; Xu,Jiarui; Yu,Guoyi; An,Fengwei; Chi,Wenzheng; Wang,Chao, Fast CORDIC based Generalized-Voronoi-Diagram Hardware Accelerator for Efficient Robotic Exploration, 2020 5th International Conference on Robotics and Automation Engineering, ICRAE 2020, 2020, pp. 100–105, 9310864
- Mao, W., Xiao, Z., Xu, P., …An, F., Yu, H., Energy-efficient machine learning accelerator for binary neural networks, Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI, 2020, pp. 77–82
专利:
- 面向运动估计的跨帧超高速相机设计方法及运动估计方法,中国发明专利,2020-11-26
- 一种运动阻碍型疾病诊断装置,中国发明专利,2020-10-19
- 一种低功耗立体匹配系统及获取深度信息的方法,中国发明专利,2020-07-31
- 一种相机标定方法、车道偏离预警方法及系统,中国发明专利,2020-06-15
- 一种脊柱侧弯检测模型的生成方法和计算机设备,中国发明专利,2020-03-12
- 一种脊柱侧弯检测模型的生成方法和计算机设备,PCT,2020-03-12
on/before2019:
论文:
- Zhao, S., An, F., Yu, H., A 307-fps 351.7-GOPs/W Deep Learning FPGA Accelerator for Real-Time Scene Text Recognition, Proceedings – 2019 International Conference on Field-Programmable Technology, ICFPT 2019, 2019, 2019-December, pp. 263–266, 8977892
- An, F., Xu, P., Xiao, Z., Wang, C., FPGA-based object detection processor with HOG feature and SVM classifier, International System on Chip Conference, 2019, 2019-September, pp. 187–190, 9087991
- Guan, J., An, F., Zhang, X., Chen, L., Mattausch, H.J., Energy-efficient hardware implementation of road-lane detection based on Hough transform with parallelized voting procedure and local maximum algorithm, IEICE Transactions on Information and Systems, 2019, E102D(6), pp. 1171–1182
- Luo, A., An, F., Zhang, X., Mattausch, H.J., A Hardware-Efficient Recognition Accelerator Using Haar-Like Feature and SVM Classifier, IEEE Access, 2019, 7, pp. 14472–14487, 8621001
- An, F., Multi-port SRAM with Multi-bank for Self-organizing Maps Neural Network (Invited paper), 2018 14th IEEE International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2018 – Proceedings, 2018, 8564839
- Zhang, X., An, F., Chen, L., Ishii, I., Mattausch, H.J., A Modular and Reconfigurable Pipeline Architecture for Learning Vector Quantization, IEEE Transactions on Circuits and Systems I: Regular Papers, 2018, 65(10), pp. 3312–3325, 8301524
- An, F., Zhang, X., Luo, A., Chen, L., Mattausch, H.J., A Hardware Architecture for Cell-Based Feature-Extraction and Classification Using Dual-Feature Space, IEEE Transactions on Circuits and Systems for Video Technology, 2018, 28(10), pp. 3086–3098, 7979565
- Luo, A., An, F., Zhang, X., …Huang, Z., Mattausch, H.J., Flexible feature-space-construction architecture and its VLSI implementation for multi-scale object detection, Japanese Journal of Applied Physics, 2018, 57(4), 04FF04
- Luo, A., An, F., Zhang, X., Chen, L., Mattausch, H.J., Resource-Efficient Object-Recognition Coprocessor with Parallel Processing of Multiple Scan Windows in 65-nm CMOS, IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2017, 26(3), pp. 431–444
- Huang, Z., Zhang, X., Chen, L., …Wang, H., Feng, S., A hardware-efficient vector quantizer based on self-organizing map for high-speed image compression, Applied Sciences (Switzerland), 2017, 7(11), 1106
- Huang, Z., Zhang, X., Chen, L., …Wang, H., Feng, S., A vector-quantization compression circuit with on-chip learning ability for high-speed image sensor, IEEE Access, 2017, 5, pp. 22132–22143, 8070449
- An, F., Zhang, X., Chen, L., Mattausch, H.J., Parallel-elementary-stream architecture for nearest-neighbor-search-based self-organizing map, 2016 13th IEEE International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2016 – Proceedings, 2017, pp. 606–609, 7998991
- Guan, J., An, F., Zhang, X., Chen, L., Mattausch, H.J., Parallelization of Hough transform for high-speed straight-line detection in XGA-size videos, 2017 IEEE International Conference on Consumer Electronics – Taiwan, ICCE-TW 2017, 2017, pp. 313–314, 7991121
- An, F., Zhang, X., Chen, L., Ishii, I., Object-recognition VLSI for pedestrian detection in automotive applications, Proceedings of International Conference on ASIC, 2017, 2017-October, pp. 651–653
- Luo, A., An, F., Fujita, Y., …Chen, L., Mattausch, H.J., Low-power coprocessor for Haar-like feature extraction with pixel-based pipelined architecture, Japanese Journal of Applied Physics, 2017, 56(4), 04CF06
- Zhang, X., An, F., Nakashima, I., …Ishii, I., Mattausch, H.J., A hardware-oriented histogram of oriented gradients algorithm and its VLSI implementation, Japanese Journal of Applied Physics, 2017, 56(4), 04CF01
- Guan, J., An, F., Zhang, X., Chen, L., Mattausch, H.J., Real-time straight-line detection for XGA-size videos by hough transform with parallelized voting procedures, Sensors (Switzerland), 2017, 17(2), 270
- Fujita, Y., An, F., Luo, A., …Chen, L., Mattausch, H.J., Pixel-based pipeline hardware architecture for high-performance Haar-like feature extraction, 2016 IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2016, 2017, pp. 611–612, 7804044
- Pang, W., Huang, H., An, F., Yu, H., Low-power and real-Time computer vision on-chip, ISOCC 2016 – International SoC Design Conference: Smart SoC for Intelligent Things, 2016, pp. 43–44, 7799731
- An, F., Zhang, X., Chen, L., Mattausch, H.J., A Memory-Based Modular Architecture for SOM and LVQ with Dynamic Configuration, IEEE Transactions on Multi-Scale Computing Systems, 2016, 2(4), pp. 234–241, 7604135
- An, F., Mihara, K., Yamasaki, S., Chen, L., Mattausch, H.J., K-nearest neighbor associative memory with reconfigurable word-parallel architecture, Journal of Semiconductor Technology and Science, 2016, 16(4), pp. 405–414
- An, F., Zhang, X., Chen, L., Mattausch, H.J., Dynamically reconfigurable system for LVQ-based on-chip learning and recognition, Proceedings – IEEE International Symposium on Circuits and Systems, 2016, 2016-July, pp. 1338–1341, 7527496
- Zhang, X., An, F., Chen, L., Mattausch, H.J., Reconfigurable VLSI implementation for learning vector quantization with on-chip learning circuit, Japanese Journal of Applied Physics, 2016, 55(4), 04EF02
- An, F., Mihara, K., Yamasaki, S., Chen, L., Mattausch, H.J., Highly flexible nearest-neighbor-search associative memory with integrated k nearest neighbor classifier, configurable parallelism and dual-storage space, Japanese Journal of Applied Physics, 2016, 55(4), 04EF10
- An, F., Chen, L., Akazawa, T., Yamasaki, S., Mattausch, H.J., k nearest neighbor classification coprocessor with weighted clock-mapping-based searching, IEICE Transactions on Electronics, 2016, E99C(3), pp. 397–403
- An, F., Mihara, K., Yamasaki, S., Chen, L., Mattausch, H.J., Word-parallel associative memory for k-nearest-neighbor with configurable storage space of reference vectors, 2015 IEEE Asian Solid-State Circuits Conference, A-SSCC 2015 – Proceedings, 2016, 7387456
- An, F., Akazawa, T., Yamasaki, S., Chen, L., Mattausch, H.J., VLSI realization of learning vector quantization with hardware/software co-design for different applications, Japanese Journal of Applied Physics, 2015, 54(4), 04DE05
- An, F., Akazawa, T., Yamazaki, S., Chen, L., Mattausch, H.J., LVQ neural network SoC adaptable to different on-chip learning and recognition applications, IEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS, 2015, 2015-February(February), pp. 623–626, 7032858
- An, F., Akazawa, T., Yamazaki, S., Chen, L., Mattausch, H.J., A coprocessor for clock-mapping-based nearest Euclidean distance search with feature vector dimension adaptability, Proceedings of the IEEE 2014 Custom Integrated Circuits Conference, CICC 2014, 2014, 6946096
- Wicaksono, I.B., An, F., Mattausch, H.J., Memory-based hardware-accelerated system for high-speed human detection, Advanced Robotics, 2014, 28(5), pp. 317–327
- An, F., Chen, L., Mattausch, H.J., A SoPC architecture for nearest-neighbor based learning and recognition, 2014 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2014, 2014, pp. 147–152, 7024442
- Wicaksono, I.B., An, F., Mattausch, H.J., A Hardware-Accelerated Reduced Dimensionality Multi-Prototype Learning and Recognition System with complementary classifiers, Proceedings of the 2013 IEEE Conference on Cybernetics and Intelligent Systems, CIS 2013, 2013, pp. 1–6, 6751569
- An, F., Mattausch, H.J., K-means clustering algorithm for multimedia applications with flexible HW/SW co-design, Journal of Systems Architecture, 2013, 59(3), pp. 155–164
- An, F., Mattausch, H.J., Cluster-based prototype learning system for multiple applications with flexible HW/SW codesign, Parallel and Distributed Computing, Applications and Technologies, PDCAT Proceedings, 2012, pp. 416–419, 6589314
- Wicaksono, I.B., An, F., Mattausch, H.J., Human recognition with a hardware-accelerated multi-prototype learning and classification system, 2012 IEEE International Conference on Robotics and Biomimetics, ROBIO 2012 – Conference Digest, 2012, pp. 1507–1512, 6491182
- An, F., Koide, T., Mattausch, H.J., A K-means-based multi-prototype high-speed learning system with FPGA-implemented coprocessor for 1-NN searching, IEICE Transactions on Information and Systems, 2012, E95-D(9), pp. 2327–2338
- An, F., Mattausch, H.J., Koide, T., Real-time hybrid learning and recognition system with software-hardware cooperation, 2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011, 2011, pp. 2505–2510, 6181681
专利:
- 识别系统,日本,2017-08-10
- LVQ神经网络,日本,2019-7-14