透過您的圖書館登入
IP:18.117.196.184
  • 期刊

行動裝置拍攝影片之街景圖建構與索引

Street View Image Generation by Mobile Devices with Indexing

摘要


隨著數位生活技術與應用的快速發展,智慧型手機、數位相機、行車記錄器、穿戴式攝影機等行動數位攝像裝置日漸普及。其中「行車記錄器」為近年來新興之行動攝影裝置,其主要用途是當事故發生之時,可以作為釐清肇事責任之有效證據,故逐漸成為車輛必備裝置。此外,駕駛過程中路途上所遭遇的各種人事物亦將記錄於影片之中,所以當有危安事件發生之時,警政單位常會需要收集事發當日有經過該路段附近之行車記錄器影片以進行調查。然而,因資料量龐大,如未經整理,將需耗費大量人力與時間去檢視每部影片,以找出相關片段。因此,本論文提出一研究架構並實作一快速索引系統, 利用分析行車記錄器所拍攝之影片建構出沿途所經過之街景圖,並與影片內容建立連結索引,如此一來,不須看完整部影片,使用者即可迅速地瀏覽街景圖,從中選取所要檢視的片段。相信這套系統將可以有效加速影片審視與危安事件調查之速度。另一方面,相較於原始行車記錄器影片,街景圖的檔案資料量相當精簡,因此可以大幅降低對影像資料進行初部篩選時所需之傳輸量。

並列摘要


With the rapid advancement of Mobile Digital Life techniques, digital video/image capturing devices, such as smart phones, digital cameras, driving video recorders, and wearable cameras, have become ubiquitous. Driving video recorders begin to gain widespread popularity in recent years. What is seen and what happens along the way can thus be recorded in videos. However, searching for a specific scene or event among such video collections is laborious. In this paper, we propose a speed-adaptive street view image generation method for the videos recorded by front-mounted car camcorders, requiring no additional devices deployed. Visual summaries of the street scenes along the way can be provided, allowing users to retrieve a video clip corresponding to a specific road section much efficiently.

並列關鍵字

無資料

延伸閱讀