電機系館5樓92510室
蔡家齊 助理教授
學經歷
學歷
2020
國立交通大學電子所博士
2015
國立交通大學電子系學士
經歷
2021~present
國立成功大學電機工程學系助理教授
2020~2021
聯發科技資深工程師
2015~2020
聯發科技工程師
研究領域
- AI 模型架構與壓縮(AI Model Architectrue and Compression)
- AI 加速器(AI Accelerator)
- AI 影像/聲音應用(AI-based Vision/Audio Application)
- 機器學習(Machine Learning)
- 嵌入式系統(Embedded System)
- 電腦視覺(Computer Vision)
- 數位訊號處理(Digital Signal Processing)
- 軟硬體整合設計(SW/HW Co-design)
著作
期刊論文( Journal )
more
less
- C. -C. Tsai and J. -I. Guo, "IVS-Caffe--Hardware-Oriented Neural Network Model Development," in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2021.3072145. (IF=11.6)
- C.-C. Tsai, C.-Y. Lin, and J.-I. Guo, "Dark channel prior based video dehazing algorithm with sky preservation and its embedded system realization for ADAS applications," Optics express, vol. 27, no. 9, pp. 11877-11901, 2019. (IF=3.6)
- J.-I. Guo, C.-C. Tsai, J.-L. Zeng, S.-W. Peng, and E.-C. Chang, "Hybrid Fixed Point/Binary Deep Neural Network Design Methodology for Low Power Object Detection," in IEEE Journal on Emerging and Selected Topics in Circuits and Systems. (IF =3.4)
會議論文( Conference )
more
less
- C.-C. Tsai, C.-K. Tseng, H.-C. Tang, and J.-I. Guo, "Vehicle detection and classification based on deep neural network for intelligent transportation applications," in 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2018: IEEE, pp. 1605-1608.
- C.-C. Tsai, Y.-T. Lai, Y.-F. Li, and J.-I. Guo, "A vision radar system for car safety driving applications," in 2017 International Symposium on VLSI Design, Automation and Test (VLSI-DAT), 2017: IEEE, pp. 1-4.
- C.-C. Tsai et al., "The 2020 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries," in 2020 IEEE International Conference on Multimedia & Expo (ICME), 2020.
專利
more
less
其他
more
less
研究計劃
- Project Executor, AI環境聲音偵測技術開發, 奇景光電
- Project Executor, 前瞻顯示科技與跨領域應用教學聯盟計畫, 教育部
- Project Executor, 智慧製造之多站點全流程優化, 科技部, 友達光電
- Project Executor, 以視覺應用為主之超低耗電穿戴式裝置晶片系統與軟體研究, 科技部
- Project Executor, 影像式內視鏡即時除霧技術開發, 科技部
- Project Executor, 多重感測訊號融合之障礙物辨識技術與系統實現, 科技部
- Project Executor, Auto-STR,從感知到反應:自動駕駛車應用之各式物件即時認知與駕駛反應技術及系統研發計畫-總計畫暨子計畫一:Auto-STR 應用之視覺深度學習物件行為辨識技術與駕駛反應技術, 科技部
- Project Executor, 結合深度學習與多重感測訊號融合之障礙物辨識技術, 科技部
- Project Executor, 應用於ADAS/特殊用途無人載具之嵌入式AI深度學習技術, 科技部
- Project Executor, 科管局研發精進計畫: 應用於智慧車載影像之光場影像記錄裝置與影像處理技術開發計畫, 中強光電
- Project Executor, 自動緊急剎車應用之物件偵測技術, 聯發科技
- Project Executor, BSD技術開發, 和碩聯合科技
- Project Executor, 深度學習之車輛偵測與車型辨識, 鐵雲科技
- Project Executor, 科管局研發精進計畫-大視角暨高動態光場取像裝置於物件辨識與偵測技術, 中強光電
- Project Executor, Field try experiments on ADAS Technology for Rear view obstacle detection/BSD/LDWS/FCWS/PD applications, 聯發科技
- Project Executor, 道路標線偵測模組委託開發, 工研院
- Project Executor, 行人偵測技術, 光寶科技
- Project Executor, 深度學習道路標線偵測模組, 工研院
- Project Executor, Key technology development/evaluation for autonomous driving applications, 聯發科技
- Project Executor, 打造工業物聯網WISE-PaaS教材設計, 研華
- Project Executor, 車流型態深度學習解析技術, 資策會
- Project Executor, Embedded Sensor Fusion Technology and Data Collection for ADAS/Self-driving Applications, 聯發科技
- Project Executor,Embedded camera/radar sensor fusion for object detection/tracking in 5G enabled applications, 鴻海精密
- Project Executor,Heterogeneous 9-ch camera/77GHz radar/lidar (32-bin) data collection and sensor fusion algorithm derivation for ADAS/Self-driving applications, Qualcomm
- Project Executor,Embedded camera/radar sensor fusion for object detection/tracking in 5G enabled applications, 鴻海精密
開授課程
2021 Fall
2022 Spring
2022 Fall
2023 Spring
2023 Fall
2024 Spring
指導學生
本學年度 實驗室成員
博士班
郭原宏
王士逢
陳柏翰
鄭惠文
羅祥睿
張峻豪
碩士班
高自在
吳振瑋
洪翊珈
蔡旻佑
盧正謀
黃瀞儀
黃姵瑄
湯詠涵
吳昀鴻
蔡承達
柯秉鈞
羅宇宸
游景翔
金稟鈞
許丞翔
林泳陞
許峻祐
曾柏硯
吳柄葳
郭君瑋
張茹涵
林芷萱
楊宗軒
林趺菩
施宇庭
陳品潔
黃啟維
已畢業學生
碩士班
111
王柏鈞   翁子浩   呂科進
112
陳閔祥   李政憲   林明賜
特殊榮譽
- 2020年 參加第二十屆旺宏金矽獎半導體設計與應用大賽,"混合卷積神經網路硬體加速器系統設計與其模型訓練分析工具Hybrid CNN Accelerator System Design and the Associated Model Training/Analyzing Tools" 榮獲 評審團銀獎。
- 2017年 參加第十七屆旺宏金矽獎半導體設計與應用大賽,"Stand By You-基於深度學習之駕駛學習輔助系統Driving Learning Assistance System Based on Deep Learning" 榮獲 優勝獎。