From Images to Shape Models for Object Detection
From Images to Shape Models for Object Detection
复制标题
DOI：
10.1007/s11263-009-0270-9
复制
发表时间：
2010-05-01
影响因子：
19.5
通讯作者：
Schmid, Cordelia
中科院分区：
文献类型：
--
作者：
Ferrari, Vittorio;Jurie, Frederic;Schmid, Cordelia
我们提出了一种目标类检测方法，该方法充分融合了形状匹配器的互补优势。就像对象检测器一样，它可以直接从图像中学习类模型，并可以在存在类内变化、杂乱和比例变化的情况下定位新的实例。就像形状匹配器一样，它可以找到对象的边界，而不仅仅是它们的边界框。这是通过一种用于学习给定实例图像的对象类的形状模型的新技术来实现的。此外，我们还将霍夫式投票与非刚体点匹配算法相结合，以实现模型在杂波图像中的定位。广泛的评估表明，该方法能够准确定位目标边界，并且不需要分割样本进行训练(只需要包围盒)。
We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models directly from images, and can localize novel instances in the presence of intra-class variations, clutter, and scale changes. Like a shape matcher, it finds the boundaries of objects, rather than just their bounding-boxes. This is achieved by a novel technique for learning a shape model of an object class given images of example instances. Furthermore, we also integrate Hough-style voting with a non-rigid point matching algorithm to localize the model in cluttered images. As demonstrated by an extensive evaluation, our method can localize object boundaries accurately and does not need segmented examples for training (only bounding-boxes).