應用於駕駛輔助情境之第一人稱視覺分享系統

Making in-Front-of Cars Transparent: Sharing First-Person-Views via Dashcam

陳少祁(Shao-Chi Chen)

指導教授 ： 陳炳宇

國立臺灣大學/管理學院/資訊管理學研究所/碩士(2014年)

https://doi.org/10.6342/NTU.2014.11240

摘要

因前方車輛所造成的視線遮擋問題是威脅行車安全的重要因素之一，解決這個問題的其中一個可能方式，是將前方車輛以第一人稱視角所看到的景象分享給後方車輛，使其視野中被前方車輛遮擋住的區域能夠經由適當的修補而還原出，去除障礙物後的景象。然而，不同車輛間的攝影機鏡頭在幾何空間上的不一致，使得車對車的視覺分享與生成變得非常具有挑戰性。在本篇論文中，我們提出了一個能夠產生第一人稱視角的影像生成演算法來解決這類的問題。首先，我們先標記出後車視野中未被遮擋的部分作為我們的參考區域，接著迭帶地從前車影像中，估計出區域單應性轉換及進行視角適應性變形，我們即可對前車影像做區域性的形變，使其視角及輪廓邊緣能夠與後車被遮擋的部份對應，並能無縫地接合在一起，讓使用者看起來似乎是前方車輛變得半透明了。我們的系統改善了駕駛者的可見度，也因此降低了駕駛過程中的負擔，進而提昇駕駛舒適度。我們以幾組在實際駕駛情境中所拍攝的具挑戰性之測試資料來展示本系統的實用性及穩定性。

關鍵字

視覺分享 ； 隨區域而調整之影像變形 ； 影像接合 ； 視角適應化

並列摘要

Visual obstruction caused by a preceding vehicle is one of the key factors threatening driving safety. One possible solution is to share the first-person-view of the preceding vehicle to unveil the blocked field-of-view of the following vehicle. However, the geometric inconsistency caused by the camera-eye discrepancy renders view sharing between different cars a very challenging task. In this paper, we present a first-person-perspective image rendering algorithm to solve this problem. Firstly, we contour unobstructed view as the transferred region, then by iteratively estimating local homography transformations and performing perspective-adaptive warping using the estimated transformations, we are able to locally adjust the shape of the unobstructed view so that its perspective and boundary could be matched to that of the occluded region. Thus, the composited view is seamless in both the perceived perspective and photometric appearance. It creates an impression as if the preceding vehicle is transparent. Our system improves the driver’s visibility and thus relieving the burden on the driver, which in turn increases comfort. We demonstrate the usability and stability of our system by performing its evaluation with several challenging data sets collected from real-world driving scenarios.

並列關鍵字

view sharing ； spatial-varying image warping ； image stitching ； perspective adaptation

參考文獻

[1] A. Agarwalaa, C. Zheng, C. Pal, M. Agrawala, M. Cohen, B. Curless, D. Salesin, and R. Szelisk. Panoramic video textures. ACM Trans. Graphics, 24(3):821–827, 2005.

[2] H. Bay, T. Tuytelaars, and L. V. Gool. Surf: Speeded up robust features. In Proc. European Conf. Computer Vision, pages 404–417, 2006.

[3] M. Brown and D. G. Lowe. Recognising panoramas. In Proc. IEEE Intl. Conf. Computer Vision, pages 1218–1225 vol.2, 2003.

[4] M. Brown and D. G. Lowe. Automatic panoramaic image stitching using invariant features. ACM Trans. Graphics, 74(1):59–73, 2007.

[5] T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. In Proc. European Conf. Computer Vision, volume 3024 of Lecture Note in Computer Science, pages 25–36. Springer, May 2004.