Annual Report 2014–15

資料庫過千組不同光暗、表情及拍攝 角度的照片中，識別容貌的準確度 高達99.15%，超越人類肉眼識別的 97.53%準確度。 透過深度學習模型強大的計算和學習 能力，中大的人面識別技術能在極 複雜環境下辨認大量目標，而傳統的 視頻監控只可在簡單環境中監測少量 目標。執法部門及保安單位利用此 項新技術，可輕易從數以萬計的人群 中找出目標人物。 提升液流電池能量密度 工程學院機械與自動化工程學系盧怡 君教授及其研究團隊採用高濃度硫碳 複合物，研發出創新的液流電池陰 極材料，大幅提高陰極的容積量、電 池的能量密度、生命周期、庫侖效率 及能量效率。該陰極材料實現容積量 高達294安時─每升(Ah L -1 )，是目前 文獻紀錄中最高的液流電池陰極容積 量。他們將此創新的硫碳複合液流陰 極與鋰陽極結合，實現鋰液流電池能 量密度高達645瓦時─每升(Wh L -1 )， 是目前文獻紀錄中最高的鋰液流電 池能量密度之一。 液流電池可用於儲存可再生能源（如 太陽能及風能）產生的電力，但過去 由於液流電池的能量密度低，嚴重限 制了它的應用。是次成果有助推進 高能量密度液流電池的發展。這項 研究成果在2015年1月刊登於《自然 通訊》。 With Deep Learning, the system significantly improves the accuracy of face recognition. Traditional video surveillance can only focus on a small number of objects in a very simple environment. With this new system, users can target thousands of objects in very complex environments, making it a powerful tool for law enforcement and security agencies to seek out individuals among a crowd of thousands. High-energy-density Redox Flow Batteries Prof. Lu Yi-chun at the Department of Mechanical and Automation Engineering and her research team created a flow cathode that exploits highly concentrated sulphur-impregnated carbon composite to achieve high catholyte volumetric capacity, battery energy density, cycle life, columbic efficiency and energy efficiency. Their approach achieved the highest catholyte volumetric capacity (294 ampere-hour per litre) reported to date. Combining the sulphur flow catholyte with a lithium anode, they achieved energy density as high as 654 watt- hour per litre, which is one of the highest energy densities reported for lithium flow batteries. Redox flow batteries (RFBs) are promising technologies for large- scale electricity storage for renewable energy sources. However, RFBs are plagued by the problem of low energy density, which significantly limits their applications. This research can facilitate the development of high-energy-density RFBs. The findings were published in Nature Communications in January 2015. 盧怡君教授（左）及其研究團隊在手套箱內組裝鋰硫碳 複合液流電池 Prof. Lu Yi-chun ( left ) and her research team are assembling a lithium sulphur-impregnated carbon composite flow battery in a glove box 液流電池原型 Flow battery prototype 香港中文大學年報 CUHK Annual Report 2014 – 2015 25