Detecting Ground Shadows in Outdoor Consumer Photographs
Detecting Ground Shadows in Outdoor Consumer Photographs
复制标题
DOI：
10.1007/978-3-642-15552-9_24
复制
发表时间：
2010-09
期刊：
影响因子：
--
通讯作者：
Jean-François Lalonde;Alexei A. Efros;S. Narasimhan
中科院分区：
文献类型：
--
作者：
Jean-François Lalonde;Alexei A. Efros;S. Narasimhan
从图像中检测阴影可以显著提高物体检测和跟踪等视觉任务的性能。最近的方法主要是使用光照不变量，当图像质量不是很好时，这可能会严重失败，就像大多数消费级照片的情况一样，比如谷歌或Flickr上的照片。我们提出了一种实用的算法，从一张消费者照片中自动检测物体投射到地面上的阴影。我们的关键假设是，室外场景中构成地面的材料类型相对有限，最常见的包括沥青、砖、石头、泥浆、草、混凝土等。因此，地面上阴影的外观不像一般阴影那样变化很大，因此可以从一组标记的图像中学习。我们的检测器由一个三层过程组成，包括(a)在每个图像边缘周围计算的一组阴影敏感特征上训练决策树分类器，(b)基于crf的优化，对检测到的阴影边缘进行分组，以生成连贯的阴影轮廓，以及(c)结合任何现有的专门训练用于检测图像中的地面的分类器。我们的结果表明，在几个具有挑战性的图像上，检测精度很高（85%）。由于大多数视觉应用感兴趣的对象（如行人，车辆，标志）都附着在地面上，我们相信我们的检测器可以找到广泛的适用性。
Detecting shadows from images can significantly improve the performance of several vision tasks such as object detection and tracking. Recent approaches have mainly used illumination invariants which can fail severely when the qualities of the images are not very good, as is the case for most consumer-grade photographs, like those on Google or Flickr. We present a practical algorithm to automatically detect shadows cast by objects onto the ground, from a single consumer photograph. Our key hypothesis is that the types of materials constituting the ground in outdoor scenes is relatively limited, most commonly including asphalt, brick, stone, mud, grass, concrete, etc. As a result, the appearances of shadows on the ground are not as widely varying as general shadows and thus, can be learned from a labelled set of images. Our detector consists of a three-tier process including (a) training a decision tree classifier on a set of shadow sensitive features computed around each image edge, (b) a CRF-based optimization to group detected shadow edges to generate coherent shadow contours, and (c) incorporating any existing classifier that is specifically trained to detect grounds in images. Our results demonstrate good detection accuracy (85%) on several challenging images. Since most objects of interest to vision applications (like pedestrians, vehicles, signs) are attached to the ground, we believe that our detector can find wide applicability.