人工智能及智能化影像之技術(shù)與應(yīng)用

張樹武

【摘? ?要】 結(jié)合我國(guó)新一代人工智能發(fā)展規(guī)劃，簡(jiǎn)要剖析人工智能的內(nèi)涵和發(fā)展現(xiàn)狀，并解析智能化影像技術(shù)的主要應(yīng)用 方向。

【關(guān)鍵詞】 人工智能;智能化影像;技術(shù);應(yīng)用

文章編號(hào)： 10.3969/j.issn.1674-8239.2018.09.003

近年來(lái)，人工智能已成為信息技術(shù)及應(yīng)用領(lǐng)域最熱門的名詞。那么，如何定義人工智能？作為文化領(lǐng)域智能化技術(shù)的主要代表——智能化影像又有哪些特征？筆者將結(jié)合我國(guó)新一代人工智能發(fā)展規(guī)劃，簡(jiǎn)要剖析人工智能的內(nèi)涵和發(fā)展現(xiàn)狀，并解析智能化影像技術(shù)的主要應(yīng)用方向。

1? 人工智能國(guó)家發(fā)展戰(zhàn)略

2017年7月8日，經(jīng)中央政治局常委會(huì)、國(guó)務(wù)院常務(wù)會(huì)議審議通過(guò)，國(guó)務(wù)院印發(fā)《新一代人工智能發(fā)展規(guī)劃》（國(guó)發(fā)〔2017〕35 號(hào)）。《規(guī)劃》指出：“當(dāng)前，世界主要發(fā)達(dá)國(guó)家把發(fā)展人工智能作為提升國(guó)家競(jìng)爭(zhēng)力、維護(hù)國(guó)家安全的重大戰(zhàn)略，人工智能作為新一輪產(chǎn)業(yè)變革的核心驅(qū)動(dòng)力，已經(jīng)成為國(guó)際科技競(jìng)爭(zhēng)的新焦點(diǎn)，是未來(lái)經(jīng)濟(jì)發(fā)展的新引擎”。

《規(guī)劃》描繪了未來(lái)十幾年我國(guó)人工智能發(fā)展的藍(lán)圖，確立了“三步走”目標(biāo)：到2020年人工智能總體技術(shù)和應(yīng)用與世界先進(jìn)水平同步;到2025年人工智能基礎(chǔ)理論實(shí)現(xiàn)重大突破、技術(shù)與應(yīng)用部分達(dá)到世界領(lǐng)先水平;到2030年人工智能理論、技術(shù)與應(yīng)用總體達(dá)到世界領(lǐng)先水平，成為世界主要人工智能創(chuàng)新中心。

《規(guī)劃》提出6個(gè)方面重點(diǎn)任務(wù)：一是構(gòu)建開放協(xié)同的人工智能科技創(chuàng)新體系，從前沿基礎(chǔ)理論、關(guān)鍵共性技術(shù)、創(chuàng)新平臺(tái)、高端人才隊(duì)伍等方面強(qiáng)化部署;二是培育高端高效的智能經(jīng)濟(jì)，發(fā)展人工智能新興產(chǎn)業(yè)，推進(jìn)產(chǎn)業(yè)智能化升級(jí)，打造人工智能創(chuàng)新高地;三是建設(shè)安全便捷的智能社會(huì)，發(fā)展高效智能服務(wù)，提高社會(huì)治理智能化水平，利用人工智能提升公共安全保障能力，促進(jìn)社會(huì)交往的共享互信;四是加強(qiáng)人工智能領(lǐng)域軍民融合，促進(jìn)人工智能技術(shù)軍民雙向轉(zhuǎn)化、軍民創(chuàng)新資源共建共享;五是構(gòu)建泛在安全高效的智能化基礎(chǔ)設(shè)施體系，加強(qiáng)網(wǎng)絡(luò)、大數(shù)據(jù)、高效能計(jì)算等基礎(chǔ)設(shè)施的建設(shè)升級(jí);六是前瞻布局重大科技項(xiàng)目，針對(duì)新一代人工智能特有的重大基礎(chǔ)理論和共性關(guān)鍵技術(shù)瓶頸，加強(qiáng)整體統(tǒng)籌，形成以新一代人工智能重大科技項(xiàng)目為核心、統(tǒng)籌當(dāng)前和未來(lái)研發(fā)任務(wù)布局的人工智能項(xiàng)目群。

圍繞《規(guī)劃》的總體部署，各部門和地方正在加緊貫徹落實(shí)相關(guān)政策措施，加快部署相關(guān)方向發(fā)展計(jì)劃，搶占人工智能發(fā)展的先機(jī)和制高點(diǎn)。

2? 理解人工智能內(nèi)涵

所謂人工智能，就是使機(jī)器能夠模擬、延伸和擴(kuò)展類人智能的理論、方法、技術(shù)及應(yīng)用系統(tǒng)。歸納下來(lái)，它主要包括三方面的內(nèi)容。首先是對(duì)人及動(dòng)物組織機(jī)理的研究，主要剖析活體動(dòng)物的大腦功能組織機(jī)制及肢體運(yùn)動(dòng)結(jié)構(gòu)。二是認(rèn)知智能，即分析腦及肢體活動(dòng)內(nèi)在規(guī)律及物理原理，建立類腦的思維組織與理解模型及肢體運(yùn)動(dòng)仿生模型，這包括了思維科學(xué)、認(rèn)知學(xué)、語(yǔ)言學(xué)、心理學(xué)及仿生學(xué)等多個(gè)門類及跨學(xué)科的研究。三是感知智能，與認(rèn)知智能相對(duì)應(yīng)，感知智能主要從腦及肢體活動(dòng)外在表現(xiàn)來(lái)識(shí)別、計(jì)算和模擬仿真人類的智能，主要采用的是統(tǒng)計(jì)和模式學(xué)習(xí)的計(jì)算方法，并不要求一定具有物理意義上的原理解釋。

隨著計(jì)算機(jī)處理能力的快速增長(zhǎng)和感知智能技術(shù)的重大突破，機(jī)器與人類比較，在計(jì)算和分析處理海量數(shù)據(jù)的效率優(yōu)勢(shì)日益明顯，在某些方面超越了類人智能，逐步形成了特有的機(jī)器智能。人工智能的外延逐步擴(kuò)大，從單一的模擬類人智能延伸、擴(kuò)展，形成了人機(jī)混合智能。另一方面，從腦思維活動(dòng)和肢體運(yùn)動(dòng)兩種不同的智能模擬形態(tài)也衍生形成了智能計(jì)算和智能機(jī)器人兩個(gè)學(xué)術(shù)研究門類。

因此，綜合來(lái)講，所謂的“智能”就是使機(jī)器有實(shí)時(shí)識(shí)別和判斷的能力，有自適應(yīng)決策和行動(dòng)的機(jī)制（圖1）。

3? 人工智能發(fā)展現(xiàn)狀與趨勢(shì)

自1956年“人工智能”概念提出以來(lái)，人工智能發(fā)展經(jīng)歷了60余年的曲折發(fā)展歷程。到目前其發(fā)展?fàn)顩r可以概括為如下四點(diǎn)。

3.1? 腦功能組織機(jī)理研究尚處于理論探索階段

腦神經(jīng)組織機(jī)理研究是利用各種成像技術(shù)及電生理技術(shù)在宏觀、介觀及微觀尺度上建立人腦和動(dòng)物腦的腦區(qū)、神經(jīng)元群或神經(jīng)元之間的連接圖（腦網(wǎng)絡(luò)），在此基礎(chǔ)上研究腦網(wǎng)絡(luò)拓?fù)浣Y(jié)構(gòu)、腦網(wǎng)絡(luò)的動(dòng)力學(xué)屬性、腦功能及功能異常的腦網(wǎng)絡(luò)表征、腦網(wǎng)絡(luò)的遺傳基礎(chǔ)，并對(duì)腦網(wǎng)絡(luò)進(jìn)行建模和仿真，以及實(shí)現(xiàn)這些目標(biāo)所要的超級(jí)計(jì)算平臺(tái)（圖2）。

3.2? 認(rèn)知智能逐步被發(fā)現(xiàn)和應(yīng)用

從人類的語(yǔ)言組織、視聽認(rèn)知及表達(dá)、思維推理及記憶等方面，研究自然語(yǔ)言結(jié)構(gòu)化分析、人的視覺注意機(jī)制、聽覺及發(fā)音機(jī)理、自主學(xué)習(xí)記憶及知識(shí)推理等理論與方法，構(gòu)建以自主學(xué)習(xí)為核心的多腦區(qū)協(xié)同認(rèn)知腦計(jì)算模型，使機(jī)器具備人腦的多種認(rèn)知能力及其協(xié)同機(jī)制（圖3）。

同時(shí)，模擬人及動(dòng)物運(yùn)動(dòng)機(jī)理的仿生運(yùn)動(dòng)學(xué)研究取得一定突破，智能機(jī)器人成為仿生運(yùn)動(dòng)學(xué)研究及應(yīng)用的重要載體。國(guó)內(nèi)外科學(xué)家都在探索不同于螺旋槳推進(jìn)的其他高效率、機(jī)動(dòng)靈活的水下推進(jìn)方式?！胺律鷻C(jī)器魚”（圖4）作為魚類推進(jìn)機(jī)理和機(jī)器人技術(shù)的結(jié)合點(diǎn)，為研制新型的水下航行器提供了一種新思路。

日本的機(jī)械臂（圖5）采用了“生物混合（biohybrid）”設(shè)計(jì)，模擬人類手指的結(jié)構(gòu)和功能，用兩組大鼠肌肉來(lái)控制機(jī)械臂關(guān)節(jié)。而且，這個(gè)使用了活體肌肉的機(jī)械指，還能相互協(xié)作，提起重量更大的東西。

3.3? 以統(tǒng)計(jì)模式學(xué)習(xí)為代表的感知智能取得重要突破，成為人工智能應(yīng)用創(chuàng)新的理論基礎(chǔ)

統(tǒng)計(jì)模式學(xué)習(xí)通過(guò)基于海量計(jì)算的數(shù)值模擬逼近、概率判定和自適應(yīng)學(xué)習(xí)不斷修正和改善感知智能模型，隨著深度神經(jīng)網(wǎng)絡(luò)學(xué)習(xí)算法的重要突破，其對(duì)視音頻及語(yǔ)言的識(shí)別與認(rèn)識(shí)性能取得大幅提高，不斷逼近到類人的感知程度，而被產(chǎn)業(yè)界逐步認(rèn)可、接受和應(yīng)用。

深度神經(jīng)網(wǎng)絡(luò)與強(qiáng)化學(xué)習(xí)的結(jié)合，能夠使得AlphaGo超過(guò)人類頂尖棋手，進(jìn)一步通過(guò)強(qiáng)化學(xué)習(xí)，AlphaZero可以不依賴人類知識(shí)無(wú)師自通，使機(jī)器自主智能超越單純的類人智能。

生成對(duì)抗學(xué)習(xí)（GAN）基本思想源自博弈論的二人零和博弈，分別構(gòu)建模式識(shí)別生成器和判別器，通過(guò)相互博弈優(yōu)化生成器和判別器，通過(guò)對(duì)抗式訓(xùn)練增強(qiáng)了協(xié)同判別能力。

3.4? 類腦與計(jì)算感知混合的機(jī)器自主智能將成為未來(lái)“智慧社會(huì)”的主要源泉

借助信息技術(shù)的飛速發(fā)展，人類社會(huì)已從單純的現(xiàn)實(shí)社會(huì)過(guò)渡為數(shù)字化社會(huì)，進(jìn)而發(fā)展到現(xiàn)在的信息化社會(huì)。隨著類腦與計(jì)算感知混合的機(jī)器自主智能的飛速發(fā)展，AI向社會(huì)各行各業(yè)快速滲透融合，進(jìn)而重塑整個(gè)社會(huì)的發(fā)展。人類社會(huì)在不久的將來(lái)將進(jìn)入超越人類智慧的人機(jī)混合和虛實(shí)結(jié)合的“智慧化社會(huì)”。

事實(shí)上，AI熱的再次興起與以云計(jì)算、大數(shù)據(jù)、物聯(lián)網(wǎng)、5G為代表的現(xiàn)代信息技術(shù)快速發(fā)展密不可分，它是未來(lái)信息技術(shù)發(fā)展的核心突破點(diǎn)?？梢哉f(shuō)，“新一代人工智能”是以現(xiàn)代信息技術(shù)為基礎(chǔ)，面向未來(lái)智慧化社會(huì)構(gòu)建的技術(shù)應(yīng)用綜合集成體（圖6）。

總體來(lái)講，當(dāng)前人工智能理論與技術(shù)發(fā)展迅猛，無(wú)論是基礎(chǔ)理論創(chuàng)新、關(guān)鍵技術(shù)突破，還是規(guī)模產(chǎn)業(yè)應(yīng)用，都取得了豐碩的成果。人工智能因其廣闊的應(yīng)用前景和重大的戰(zhàn)略意義，近年來(lái)日益得到社會(huì)各界的高度關(guān)注。但真正的理論突破尚未到來(lái)，產(chǎn)業(yè)應(yīng)用尚處在初級(jí)階段，仍存在諸多瓶頸、盲區(qū)和局限。路漫漫其修遠(yuǎn)兮！

4? 解析智能化影像

這里所講的智能化影像（Visual Entertainment）是指將計(jì)算機(jī)圖形學(xué)、計(jì)算視覺、虛擬現(xiàn)實(shí)、三維數(shù)字化、媒體大數(shù)據(jù)等具有變革性的人工智能新技術(shù)綜合應(yīng)用于影視、演藝等文化娛樂(lè)領(lǐng)域，為新時(shí)期文化創(chuàng)新發(fā)展提供源泉和動(dòng)力，提升文化的創(chuàng)作力、表現(xiàn)力、感染力和傳播力。事實(shí)上，文化娛樂(lè)是當(dāng)前人工智能技術(shù)最具代表性的應(yīng)用領(lǐng)域之一。智能化影像涉及到人工智能諸多應(yīng)用技術(shù)，結(jié)合文化娛樂(lè)實(shí)際應(yīng)用場(chǎng)景，智能化影像具體表現(xiàn)可歸納為創(chuàng)作流程可視化、內(nèi)容展現(xiàn)沉浸化、網(wǎng)絡(luò)傳播透明化和技術(shù)裝備智能化四個(gè)方面。

4.1? 創(chuàng)作流程可視化

智能化技術(shù)使文化娛樂(lè)產(chǎn)品的創(chuàng)作和制作流程發(fā)生了革命性變革，通過(guò)可視化交互技術(shù)，大大提高了文化創(chuàng)作的效率和質(zhì)量、降低了制作成本（圖7）。

《鼠膽英雄》電影全篇預(yù)演

北京電影學(xué)院未來(lái)影像高精尖創(chuàng)新中心（AICFVE）采用大規(guī)模、大范圍外景的快速獲取與資產(chǎn)生成、多人VR協(xié)同創(chuàng)意環(huán)境與交互、多人光混動(dòng)捕混合現(xiàn)實(shí)、數(shù)字排演、演出場(chǎng)景建模與設(shè)備參數(shù)仿真等智能化虛擬預(yù)演技術(shù)為電影《鼠膽英雄》進(jìn)行了全篇預(yù)演（圖8），提升了電影制作的效率和質(zhì)量。

2018 平昌冬奧會(huì)“北京8分鐘”

北京電影學(xué)院和北京理工大學(xué)團(tuán)隊(duì)合作承擔(dān)2018平昌冬奧會(huì)“北京8分鐘”彩排技術(shù)支持工作，在參與表演創(chuàng)意設(shè)計(jì)和彩排的8個(gè)多月的過(guò)程中，針對(duì)“8分鐘”表演參演要素多、創(chuàng)意過(guò)程復(fù)雜、排練關(guān)聯(lián)度高的特點(diǎn)，利用影視虛擬制作技術(shù)和數(shù)字表演與仿真技術(shù)，專門研發(fā)了《創(chuàng)意設(shè)計(jì)全景虛擬仿真系統(tǒng)》和《訓(xùn)練彩排與數(shù)字驗(yàn)證系統(tǒng)》，保證了前期創(chuàng)意設(shè)計(jì)與現(xiàn)場(chǎng)排練工作的順利進(jìn)行（圖9）。

歌劇《馬克·波羅》

“絲綢之路國(guó)際劇院聯(lián)盟”原創(chuàng)歌劇《馬可·波羅》，主要用到了預(yù)演和自動(dòng)跟蹤兩大功能（圖10），可以在預(yù)演里進(jìn)行虛擬與實(shí)際舞臺(tái)1：1比例搭建和舞臺(tái)整體效果演示，同時(shí)可以根據(jù)劇本進(jìn)行場(chǎng)景變化預(yù)覽走位、素材視覺預(yù)覽編排、流程走臺(tái)編排、實(shí)時(shí)預(yù)覽編程等，極大地方便了國(guó)際合作團(tuán)隊(duì)的異地工作，加深了國(guó)際藝術(shù)交流和技術(shù)合作;也簡(jiǎn)化了舞臺(tái)上的工作，縮短了裝臺(tái)合成時(shí)間，提高了舞臺(tái)利用率和整體工作效率。

4.2? 內(nèi)容展現(xiàn)沉浸化

鄧麗君全息真人秀

日本綜藝《金sma》去年的一期節(jié)目中，利用3D投影技術(shù)“復(fù)活”了鄧麗君，并獻(xiàn)唱了一首《我只在乎你》的日文版《時(shí)の流れに身をまかせ》。一首歌結(jié)束后，“鄧麗君”消失。盡管在電視播出中增加了后期編輯合成技術(shù)處理，但其不同角度的逼真效果仍為人稱道（圖11）。

MSG Sphere 未來(lái)體驗(yàn)中心

MSG Sphere作為麥迪遜廣場(chǎng)花園的增強(qiáng)型沉浸式體驗(yàn)中心，正在試圖打造成為下一代演出場(chǎng)館。其最大的特色是擁有一塊約15 000 m2的球形LED，能夠提供極為沉浸的視聽體驗(yàn)。從外表來(lái)看，它采用球體設(shè)計(jì)，球體外表面擁有LED屏幕，能夠在不同的場(chǎng)景活動(dòng)中顯示不同的畫面。而在其內(nèi)部則擁有一塊約15 793 m2的LED屏幕。據(jù)介紹，MSG 計(jì)劃采用10臺(tái)8K攝像機(jī)來(lái)捕獲360°全景視頻，以此獲得更高清的畫面。Sphere內(nèi)部還采用了一套自適應(yīng)聲學(xué)系統(tǒng)，其特點(diǎn)是能夠把聲音傳遞至指定的區(qū)域，并且也能夠?qū)⒙曇粢跃鶆虻囊袅繌奈枧_(tái)擴(kuò)展出去，不會(huì)受到場(chǎng)館內(nèi)人員的影響，人們總是能夠聽到更清晰的、高保真的聲音。此外，場(chǎng)館內(nèi)部還具有基于氣味的嗅覺系統(tǒng)和具有物理觸覺的地板反饋系統(tǒng)，以此來(lái)進(jìn)一步提升沉浸感（圖12）。

上海迪士尼 4D 影像超感官互動(dòng)體驗(yàn) （圖13）

4.3? 網(wǎng)絡(luò)傳播透明化

侵權(quán)盜版是影響文化內(nèi)容產(chǎn)品網(wǎng)絡(luò)化傳播的最嚴(yán)重問(wèn)題之一。數(shù)字版權(quán)水印標(biāo)識(shí)技術(shù)可實(shí)現(xiàn)文化內(nèi)容作品網(wǎng)絡(luò)化傳播全過(guò)程透明化追蹤，媒體指紋技術(shù)和版權(quán)大數(shù)據(jù)分析有助于網(wǎng)絡(luò)侵權(quán)的鑒別和取證。中國(guó)科學(xué)院自動(dòng)化研究所開發(fā)的全媒體版權(quán)監(jiān)測(cè)平臺(tái)可實(shí)現(xiàn)包括音、視、圖、文等媒體類型作品在各類網(wǎng)絡(luò)平臺(tái)上的多維度全時(shí)段監(jiān)測(cè)（圖14），可保障內(nèi)容作品在授權(quán)、使用、傳播各途徑的版權(quán)價(jià)值最大化。該平臺(tái)已應(yīng)用于騰訊企鵝號(hào)以及國(guó)內(nèi)多家地方衛(wèi)視和影視公司的熱門綜藝視頻版權(quán)監(jiān)測(cè)。

4.4? 技術(shù)裝備智能化

歌劇《馬克.波羅》

歌劇《馬可·波羅》的舞美設(shè)計(jì)方案出自于英國(guó)“設(shè)計(jì)大?！北R克·霍爾斯，最大的設(shè)計(jì)亮點(diǎn)就是旋轉(zhuǎn)舞臺(tái)（圖15），他表示旋轉(zhuǎn)的舞臺(tái)象征著“文明的進(jìn)程”與“文化的交融”。該劇將視頻技術(shù)與機(jī)械運(yùn)動(dòng)有機(jī)結(jié)合，這個(gè)系統(tǒng)的特點(diǎn)就是能同時(shí)控制燈光、投影畫面、舞臺(tái)轉(zhuǎn)盤等多個(gè)技術(shù)模塊。

燈光追蹤（ClayPaky）

在 2018 德國(guó)法蘭克福國(guó)際舞臺(tái)燈光及音響技術(shù)展覽會(huì)上，ClayPaky 展出了一款 ZAC-EYE 離線追光燈產(chǎn)品。Zac-Eye的3D傳感器可以檢測(cè)舞臺(tái)上的多個(gè)人形，并將其區(qū)分開（圖16）。演員可以在場(chǎng)景中自由移動(dòng)，并被3D傳感器檢測(cè)到，連接的燈具進(jìn)行實(shí)時(shí)跟蹤，可以完全替代追光師的手工操作。視覺跟蹤是計(jì)算視覺領(lǐng)域的一項(xiàng)基礎(chǔ)研究，已經(jīng)具有了較成熟的算法，但在舞臺(tái)智能化裝備中還是剛剛開始應(yīng)用。相信未來(lái)會(huì)有更多的智能化技術(shù)應(yīng)用在舞臺(tái)裝備中，提升舞臺(tái)裝備的自動(dòng)化和智能化水平。

此外，還有像生物特征識(shí)別、語(yǔ)音控制、語(yǔ)言分析、智能機(jī)器人等諸多較成熟的模式識(shí)別與機(jī)器視覺智能化技術(shù)可以應(yīng)用在智能化影像中，“智能+影像”將會(huì)成為文化應(yīng)用領(lǐng)域的核心技術(shù)支撐（圖17）。

4.5? 部分前瞻性技術(shù)探索

基于浸入變換的三維物體重建（AICFVE-SIGGRAPH2017）

利用物體排水體積等于物體體積這一簡(jiǎn)單觀測(cè)巧妙地將表面重建問(wèn)題轉(zhuǎn)換為體積問(wèn)題。通過(guò)液體技術(shù)重建出來(lái)的模型與原始的三維模型幾乎一模一樣，由此開啟了非光學(xué)三維形狀獲取技術(shù)的新世界的大門。《Dip Transform for 3D Shape Reconstruction》入選 SIGGRAPH2017 大會(huì)，并被大會(huì)官方選為重點(diǎn)推薦的六篇論文之一，獲得了全球媒體的廣泛轉(zhuǎn)載。

基于渦流解算流體模擬（Xinxin Zhang etal，SIGGRAPH-Asia 2014）

張心欣等提出的基于渦流解算流體模擬（IVOCK）算法可以近似仿真模擬煙霧、海嘯等流體動(dòng)力學(xué)運(yùn)動(dòng)軌跡，在美國(guó)主流特效論壇CG Channel上，將張心欣與奧斯卡技術(shù)獎(jiǎng)獲得者Robert Bridson共同研發(fā)的IVOCK模擬算法評(píng)為2015 年計(jì)算機(jī)圖形圖像年會(huì)（SIGGRAPH）的高亮。

場(chǎng)景燈光自適應(yīng)變換（Relighting）

照明是攝制過(guò)程中非常重要的一環(huán)，攝影就是用光進(jìn)行造型的藝術(shù)，照明的效率與效果直接影響著最終的攝制質(zhì)量。AICFVE 中心的研究人員正在嘗試研究高效的軟硬件燈光自適應(yīng)匹配技術(shù)。

5? 結(jié)語(yǔ)

人工智能讓社會(huì)充滿智慧！智能化影像讓文化炫麗多彩！

注：本報(bào)告部分圖片和內(nèi)容取自中科院自動(dòng)化所、譚鐵牛院士、北京電影學(xué)院未來(lái)影像高精尖創(chuàng)新中心及公共網(wǎng)絡(luò)相關(guān)研究報(bào)告。謹(jǐn)此致謝！

Artificial Intelligence and Smart Images

- Technology and Application

ZHANG Shu-wu

（Institute of Automation， Chinese Academy of Sciences， Beijing 100190， China）

【Abstract】Taking the development plan for China's new generation of artificial intelligence into consideration， this report will briefly analyze the connotation and status quo of artificial intelligence， and analyze the main applications of visual entertainment technology.

【Key Words】artificial intelligence; smart images; technology; application

In recent years， artificial intelligence has become the hottest term in the field of information technology and its application. So how do we define artificial intelligence？ What are the characteristics of visual entertainment， the main representative of intelligent technology in the cultural field？ Taking the development plan for China's new generation of artificial intelligence into consideration， this report will briefly analyze the connotation and status quo of artificial intelligence， and analyze the main applications of visual entertainment technology.

1? National Development Strategy for Artificial Intelligence

On July 8， 2017， the State Council issued the Development Plan for a New Generation of Artificial Intelligence （[2017] No. 35）， which was reviewed and approved by the Standing Committee of the Political Bureau of the CPC Central Committee and the Executive Meeting of the State Council. The plan pointed out that "currently， the world's major developed countries regard the development of artificial intelligence as a major strategy to enhance national competitiveness and safeguard national security. Artificial intelligence， as the core driving force of a new round of industrial transformation， has become a new focus of international science and technology competition. It is the new engine for future economic development."

The plan draws the blueprint for the development of artificial intelligence in China in the next decade， and establishes the "three-step" goal： by 2020， the overall technology and application of artificial intelligence will be synchronized with the world's advanced level. By 2025， a major breakthrough will be achieved in the basic theory of artificial intelligence， and the country will lead the world in terms of its technology and application. By 2030， China will be a world leader in the theory， technology and application of artificial intelligence and become a major artificial intelligence innovation center in the world.

The plan proposes six key tasks： the first one is to build an open and collaborative artificial intelligence technology innovation system. The second one is to cultivate a high-end and efficient intelligent economy. The third one is to build a safe and convenient intelligent society. The fourth one is to strengthen the integration of military and civilian in the field of artificial intelligence. The fifth one is to build a ubiquitous and efficient intelligent infrastructure system. The sixth one is to arrange major scientific and technological projects with foresight.

2? Understanding the meaning of artificial intelligence

The so-called artificial intelligence is the theory， method， technology and application system that enables machines to simulate， extend and expand humanoid intelligence. In summary， it mainly includes three aspects. The first one is the study of the mechanism of human and animal tissues， which mainly analyzes the brain function organization mechanism and limb movement structure of living animals. The second one is cognitive intelligence， which analyzes the internal laws and physical principles of brain activities and limb movements， and establishes brain-like thinking organization and understanding models and bionic limb movement models. It involves several categories of researches and interdisciplinary ones， like thinking science， cognitive science， linguistics， psychology and bionics. The third one is perceptual intelligence， which is the counterpart of cognitive intelligence. Perceptual intelligence mainly recognizes， calculates and simulates human intelligence by the external manifestations of brain activities and limb movements. It mainly uses statistical and pattern learning calculation methods， and does not necessarily require a theoretical explanation in the physical terms.

With the rapid growth of computer processing capability and major breakthroughs in perceptual intelligence technology， machines have an increasingly obvious advantage in calculating， processing and analyzing massive data over humans. In some respects， they have surpassed humanoid intelligence and gradually formed unique machine intelligence. The extension of artificial intelligence has gradually expanded from the simple simulation of humanoid intelligence to a hybrid of human and machine intelligence. On the other hand， two academic research categories， intelligent computing and intelligent robots， have developed from the two different intelligent simulation forms of brain thinking activities and limb movements.

Therefore， in general， the so-called "intelligence" is to endow the machine with real-time recognition and judgment abilities and the mechanism of adaptive decision-making and action.

3? Status quo and trends of artificial intelligence development

Since the concept of “artificial intelligence” was put forward in 1956， the development of artificial intelligence has experienced a winding development process of more than 60 years. Up to now， its development status can be summarized into the following four points.

3.1? Research on brain function organization mechanism is still at the stage of theoretical exploration

3.2? Cognitive intelligence is gradually discovered and applied

3.3? Important breakthroughs have been made in perceptual intelligence represented by statistical pattern learning， which has become the theoretical basis for innovation in artificial intelligence applications

3.4? Autonomous machine intelligence with brain-like and computational perception will become the main source of the future "smart society"

As information technology develops rapidly， human society has transitioned from a simple real society to a digital society， and has developed into the current information society. With the rapid development of autonomous machine intelligence that features a mixture of brain-like and computational perception， AI rapidly penetrates and integrates into all walks of life in society and reshapes the development of society as a whole. In the near future， human society will become a "smart society" of man-machine hybrids and a combination of virtual and real worlds， which go beyond human wisdom.

In fact， the resurgence of AI fever is inseparable from the rapid development of modern information technology represented by cloud computing， big data， Internet of Things， and 5G. It is the core breakthrough point for the development of information technology in the future. It can be said that "a new generation of artificial intelligence" is an integration of technology applications based on modern information technology and built for the future intelligent society.

Generally speaking， the current theories and technologies of artificial intelligence are booming. Whether in terms of basic theoretical innovation， key technology breakthroughs or sizeable industry applications， it has achieved fruitful results. Due to its broad application prospects and significant strategic significance， artificial intelligence has received increasing attention from all walks of life in recent years. However， the real theoretical breakthrough has not yet been made， and the industrial applications are still at the initial stage. There are still many bottlenecks， blind spots and limitations. There is still a long way to go！

4? Analysis of visual entertainment

Visual entertainment discussed here refers to the comprehensive application of new innovative AI technologies such as computer graphics， computational vision， virtual reality， three-dimensional digitization and media big data in the cultural and entertainment fields such as film and television， performing arts， and so on. It provides the source and power for the cultural innovation and development in the new era and enhances the creativity， expressiveness， appeal and communication of culture. In fact， cultural entertainment is one of the most representative applications of artificial intelligence technology. Visual entertainment involves many application technologies of artificial intelligence. Combined with the real application scenarios of cultural entertainment， the specific elements of visual entertainment can be summarized into four aspects： visualized creation process， immersed content presentation， transparent network communication and intelligent technical equipment.

4.1? Visualized creation process

The intelligent technology has revolutionized the creation and production process of cultural and entertainment products. Through visual interaction technology， the efficiency and quality of cultural creation has been greatly improved， and the production cost has been reduced.

4.2? Immersed content presentation

4.3? Transparent network communication

Infringement and piracy are among the most serious problems that affect the networked dissemination of cultural content products. Digital copyright watermarking technology can transparently track the whole process of the network transmission of cultural content products. Media fingerprint technology and copyright big data analysis are helpful for the identification and evidence obtainment of network infringement. The all-media copyright monitoring platform developed by the Institute of Automation of the Chinese Academy of Sciences can realize multi-dimensional and full-time monitoring of several media types including audio， video， graphics and text works on various network platforms， which can guarantee the maximization of copyright value in the authorization， use and dissemination of content works. The platform has been applied to Tencent QQ and the monitoring of popular variety video rights of many local satellite TV and film companies.

4.4? Intelligent technical equipment

In addition， many more mature pattern recognition and machine vision intelligence technologies such as biometrics， voice control， language analysis and intelligent robots can be applied to visual entertainment. “Intelligence + imaging” will become the core technical support for cultural applications.

4.5? Exploration of some forward-looking technologies

Dip Transform for 3D Shape reconstruction （AICFVE-SIGGRAPH2017）

The simple observation that the object's drainage volume is equal to the volume of the object helps transform the surface reconstruction problem into a volume problem. The model reconstructed by liquid technology is almost identical to the original three-dimensional model， thus opening the door to a new world of non-optical three-dimensional shape acquisition technology.

Fluid simulation based on vortex calculation （Xinxin Zhang et al， SIGGRAPH-Asia 2014）

The vortex-based fluid simulation （IVOCK， Integrated Vorticity of Convective Kinematics） algorithm proposed by Zhang Xinxin et al. can simulate the hydrodynamic motion trajectories such as smoke and tsunami.

Adaptive transformation of scene lighting （Relighting）

Lighting is a very important part of the filming process. Photography is the art of modeling with light. The efficiency and effect of lighting directly affect the final filming quality. Researchers at the AICFVE Center are researching on efficient adaptive hardware and software lighting matching techniques.

5? Conclusion

Artificial intelligence makes society full of wisdom！ Visual entertainment makes culture dazzling and colorful！