Sub-linear Indexing for Large Scale Object Recognition
Sub-linear Indexing for Large Scale Object Recognition
复制标题
用于大规模物体识别的次线性索引
DOI：
--
复制
发表时间：
2005
期刊：
影响因子：
--
通讯作者：
Jiri Matas
中科院分区：
文献类型：
--
作者：
Stepán Obdrzálek;Jiri Matas
现实的方法来大规模的对象识别，即检测和定位的数百个或更多的对象，必须支持次线性时间索引。在本文中，我们提出了一种方法，能够识别一个N个对象在log（N）时间。“视觉记忆”被组织成一棵二叉决策树，它的构建是为了最大限度地减少决策的平均时间。树的叶子表示一些局部图像区域，并且每个非终端节点与“弱分类器”相关联。在识别阶段，一个单一的不变的测量决定在哪个子树中寻找相应的图像区域。该方法保留了局部仿射区域方法的所有优点-对背景杂波，遮挡和大的视点变化的鲁棒性。实验表明，它支持近实时识别数百个对象与国家的最先进的识别率。在测试图像被处理之后（在当前的PC上在一秒内），通过索引到视觉记忆中的识别需要毫秒。
Realistic approaches to large scale object recognition, i.e. for detection and localisation of hundreds or more objects, must support sub-linear time indexing. In the paper, we propose a method capable of recognising one of N objects in log(N) time. The ”visual memory” is organised as a binary decision tree that is built to minimise average time to decision. Leaves of the tree represent a few local image areas, and each non-terminal node is associated with a ’weak classifier’. In the recognition phase, a single invariant measurement decides in which subtree a corresponding image area is sought. The method preserves all the strengths of local affine region methods – robustness to background clutter, occlusion, and large changes of viewpoints. Experimentally we show that it supports near real-time recognition of hundreds of objects with state-of-the-art recognition rates. After the test image is processed (in a second on a current PCs), the recognition via indexing into the visual memory requires milliseconds.