標題: 智慧型行車安全紀錄系統晶片之關鍵性技術研發-子計畫二:支援全景視訊合成與視訊認證功能之H.264編碼器設計
H.264 video encoder design supporting panoramic video synthesis and video authentication
作者: 郭峻因
GUO JIUN-IN
國立交通大學電子工程學系及電子研究所
關鍵字: 全景視訊;平行化視訊編碼器;視訊浮水印認證;行人偵測;二輪車偵測;行進間車牌辨識;Panoramic video stitching;Parallel video encoding;Video watermarking;Video tampering detection;Pedestrian detection;Two-wheels vehicle detection;Car license plate detection
公開日期: 2013
摘要: 多媒體視訊處理技術的蓬勃發展衍生出各式各樣有趣的應用,提升人們日常生活品質,也增 添了許多生活樂趣,從個人應用如數位相機、手機電視、數位攝影機、手持式多媒體播放器等, 蓬勃發展到家庭應用如DVD、數位電視、網路視訊與安全監控系統等。而目前這股應用熱潮也進 入了車用電子的領域,從已經普及之汽車多媒體應用如車用電視、數位影音、GPS 3D導航、倒車 攝影系統等,逐漸發展到日漸流行的行車紀錄器及研發中之智慧汽車中的各項駕駛安全影像輔助 系統如智慧型後視鏡、全周影像輔助系統、防碰撞煞車系統、自動停車系統等。由目前全球先進 車廠在智慧汽車技術之研發趨勢與國內車廠所研發推出之標榜智慧汽車產品(LUXGEN品牌汽車) 的熱銷情形來看,未來具多媒體影像輔助之各式車用電子系統產品將持續蓬勃發展,代表著智慧 汽車中所追求的各項車用電子系統技術不再只是高級汽車品牌車輛的選用配備而已,將有機會成 為各式平價汽車可負擔的標準配備,可以有效提高行車安全性與便利性,降低車禍發生率,保障 用路人之生命安全。然而,此技術發展趨勢也同時衍生了嚴峻的車用電子系統之設計技術挑戰, 包含更高的計算複雜度、更大的記憶體儲存容量、更大的記憶體資料存取頻寬與更大的操作功率 消耗等。 為因應此技術發展趨勢,本計畫搭配總計畫所提出之全新的車用電子系統應用整合計畫:「智 慧型行車安全紀錄系統晶片之關鍵性技術研發」,進行子計畫二的研究,題目為「支援全景視訊 合成與視訊認證功能之H.264編碼器設計」。希望於此整合型計畫目標「智慧型行車安全紀錄系 統」之架構下(如圖11-1所示),實現支援全景視訊合成與視訊認證功能之新式H.264視訊編碼器設 計,讓本計畫所提出之智慧型行車安全紀錄系統應用概念能夠逐步落實其技術可行性,因此衍生 各種創新之車用電子系統應用。同時我們也希望藉由此計畫,逐年完成數項具前瞻性之創新車用 電子系統應用技術,以提昇國內學術界創新技術之研發能量。 搭配總計畫之設計目標,本計畫在三年規劃中預計將可產出 (1) 全景視訊合成器技術與晶片設計; (2) 支援 H.264 視訊編碼之視訊認證技術; (3) 支援全景視訊合成與視訊認證功能之 H.264 視訊編碼器設計。
The technology evolution of multimedia video processing has induced various interesting applications, which has promoted the quality of people’s life and introduced lots of fun in everyday life. The technology development starts from the personal portable applications like digital cameras, mobile TVs, digital CAM coders, and portable multimedia players, to the high complexity home entertainment applications like DVD players, digital TVs, 3-D TVs, network videos, and video surveillance. Currently, the multimedia technology has been applied in the car electronics area from the popular applications like mobile TVs, digital video/audio media, 3-D GPS navigation, and rear-view surveillance video, and evolved to the applications of car driving black-box, and some interesting technologies for intelligent cars like intelligent rear-view mirror, surround-view camera system, anti-collision breaking system, and auto-parking system, and so on. Observing the technology development trend in the topic of intelligent cars from the major players in the world and the hot selling phenomenon of the first intelligent domestic car (LUXGEN) in Taiwan, it is clear that there will be more and more progress in technology development on intelligent car driving supporting systems from now on, which will achieve the goal that the intelligent car technology will be equipped in every car in default in the near future, which would further improve the safety in driving and reduce the car accident events. However, this technology development trend also induces great design challenges in this area in the aspects of high design complexity, much data storage requirement, high memory bandwidth, and high processing power. Following this technology trend, this project is the sub-project 2 of the main project entitled “ISDRS: Intelligent Safety Driving Recording System and its key technology development” for bringing brand new applications for 4C area in the coming future. The title of this sub-project 2 is “H.264 video encoder design supporting panoramic video synthesis and video authentication”. Under the design concept of the main project, as shown in Fig. 11-1, this sub-project will develop the algorithms and architectures of panoramic video synthesis and H.264 video encoding with watermarking first and then develop a brand new H.264 video encoder IP supporting panoramic video synthesis and video authentication. The goal of this sub-project 2 is to enable the possibility of innovative intelligent safety driving recording system processing techniques into mass production so as to induce lots of brand new 4C related applications in the near future. Moreover, we will develop some advanced video processing technology in this project to enhance the research capability of Taiwan in this area. To support the main project, this sub-project 2 will deliver the following key technology in three years: (1) Panoramic video synthesis algorithm and architecture design; (2) Video authentication algorithm supporting H.264 video coding; (3) H.264 video encoder IP supporting panoramic video synthesis and video authentication.
官方說明文件#: NSC100-2221-E009-151-MY3
URI: http://hdl.handle.net/11536/91909
https://www.grb.gov.tw/search/planDetail?id=2855075&docId=404860
顯示於類別:研究計畫