基於語意縮放之車輛偵測器資料視覺化

Abstract

車輛偵測器資料的分析在交通控制、運輸政策規畫及路況服務等扮演重要的角色。因此，探討交通資料的視覺化變成為了一個重要的課題。過去相關研究多半集中在討論global positioning system(GPS)軌跡資料的視覺化，而vehicle detector(VD)資料雖然無法觀測各別車輛的狀態，卻比GPS資料更良好的描述整體的交通概況。VD資料每隔一段時間可以提供定點量測的流量、速度以及占量等資訊。我們使用的資料為台灣國道上的VD，時間長度為三年。在本篇論文中，我們提出了sonic glyph由左到右描述隨時間推進的個別VD資料，並以時間為橫軸，VD在國道的里程數為縱軸排列每個sonic glyph來提供巨觀的觀測。另外，在我們的系統中提供了semantic zoom連續的改變在不同的尺度下sonic glyph的顯示方式，輔助使用者在巨觀以及微觀上的分析。我們的方法除了提供使用者研究微觀的交通現象，更可以進一步的展示巨觀下的交通狀態。視覺化系統的驗證方面，我們訪問了國道高速公路局主管以及運輸研究所的研究人員。使用者回饋說明了我們的VD資料視覺化系統在交通控制以及運輸政策上可以帶來幫助。

The visualization of vehicle detector (VD) data is essential because the data play an important role in traffic control, policy development, and road situation report. Most previous works focus on visualizing trajectories obtained from global positioning system (GPS), which are detailed but less representative. In contrast, VD data report the statistic traffic information at each sensing site during a period of time, including speed, flow, and occupancy of each lane, which contain thorough traffic information for analysis. In this work, we visualize three-year VD data of freeways in Taiwan. The visualization depicts the traffic situation at a site over time using a sonic glyph that extends from left to right as time goes. The glyphs are vertically stacked and horizontally aligned according to VD's mileage and data time, respectively, to provide global insight. Our system also allows the semantic zoom, which changes the glyph appearance in a continuous manner, to enable overview and detailed visualizations. Analysts can explore events that expand an area with different sizes and that persist a period of time with various lengths. To evaluate the feasibility of our technique, we conducted a user study with experts who work in the freeway bureau and the institute of traffic and transportation. The feedback shows that our VD data visualization is helpful to traffic control and policy development.