Detecting Dominant Vanishing Points in Natural Scenes with Application to Composition-Sensitive Image Retrieval
This addresses automated linear perspective understanding for applications like aesthetics assessment and image retrieval, particularly for amateur photographers, but it is incremental as it builds on existing vanishing point detection techniques.
The paper tackles the problem of detecting dominant vanishing points in natural landscape photos, which is challenging due to insufficient converging edges, by proposing a novel method that uses contour detection to exploit global structures, and it significantly outperforms state-of-the-art methods on a public dataset.
Linear perspective is widely used in landscape photography to create the impression of depth on a 2D photo. Automated understanding of linear perspective in landscape photography has several real-world applications, including aesthetics assessment, image retrieval, and on-site feedback for photo composition, yet adequate automated understanding has been elusive. We address this problem by detecting the dominant vanishing point and the associated line structures in a photo. However, natural landscape scenes pose great technical challenges because often the inadequate number of strong edges converging to the dominant vanishing point is inadequate. To overcome this difficulty, we propose a novel vanishing point detection method that exploits global structures in the scene via contour detection. We show that our method significantly outperforms state-of-the-art methods on a public ground truth landscape image dataset that we have created. Based on the detection results, we further demonstrate how our approach to linear perspective understanding provides on-site guidance to amateur photographers on their work through a novel viewpoint-specific image retrieval system.