Explicit Occlusion Reasoning for 3D Object Detection
Explicit Occlusion Reasoning for 3D Object Detection
复制标题
3D 对象检测的显式遮挡推理
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
B. Schiele
中科院分区：
文献类型：
--
作者：
D. Meger;C. Wojek;J. Little;B. Schiele
考虑识别图像中被部分遮挡的对象的问题。可见部分很可能匹配对象的学习外观模型，但隐藏部分不会。（假设的）理想系统将仅考虑可见对象信息，正确地忽略所有遮挡区域。在纯2D识别中，这需要推断存在的遮挡，这是一个重大挑战，因为可能的遮挡掩模的数量原则上是指数的。我们简化了问题，只考虑最可能的遮挡的一小部分（上、下、左、右半部分），并注意到一些不匹配是可以容忍的。我们训练的部分对象检测器完全适合这几种情况。此外，我们推理3D中的对象，并将感测到的几何形状（如从RGB深度相机）与视觉图像一起沿着。这允许为每个对象假设构造明确的遮挡掩模。遮罩根据其与可见对象区域的重叠来指定信任每个部分模板的程度。只有可见的证据有助于我们的客体推理。
Consider the problem of recognizing an object that is partially occluded in an image. The visible portions are likely to match learned appearance models for the object, but hidden portions will not. The (hypothetical) ideal system would consider only the visible object information, correctly ignoring all occluded regions. In purely 2D recognition, this requires inferring the occlusion present, which is a significant challenge since the number of possible occlusion masks is, in principle, exponential. We simplify the problem, considering only a small subset of the most likely occlusions (top, bottom, left, and right halves) and noting that some mismatch is tolerable. We train partial-object detectors tailored exactly to each of these few cases. In addition, we reason about objects in 3D and incorporate sensed geometry, as from an RGB-depth camera, along with visual imagery. This allows explicit occlusion masks to be constructed for each object hypothesis. The masks specify how much to trust each partial template, based on their overlap with visible object regions. Only the visible evidence contributes to our object reasoning.