Multiple-window Bag of Features for Road Environment Recognition
Multiple-window Bag of Features for Road Environment Recognition
复制标题
DOI：
10.2991/jrnal.2014.1.2.13
复制
发表时间：
2014-09
期刊：
影响因子：
--
通讯作者：
S. Morita;J. Tan;Hyoungseop Kim;S. Ishikawa
中科院分区：
文献类型：
--
作者：
S. Morita;J. Tan;Hyoungseop Kim;S. Ishikawa
特征袋（Bag of Features，BoF）的概念最近常被用于一般物体识别。但是，由于它没有考虑检测到的特征的位置关系，识别率仍然不是很高的实际使用。本文提出了一种用考虑特征位置信息的BoF表示来描述物体特征的方法。虽然原始的BoF表示应用于整个图像，但所提出的方法在图像上采用多个窗口。BoF表示应用于每个窗口以表示图像中对识别感兴趣的对象。实验结果表明，所提出的方法的性能。
The idea of Bag of Features (BoF) is recently often employed for general object recognition. But, as it does not take positional relations of detected features into account, the recognition rate is still not very high for practical use. This paper proposes a method of describing the feature of an object by the BoF representation which considers positional information of the features. Although the original BoF representation is applied to an entire image, the proposed method employs multiple windows on an image. The BoF representation is applied to each of the windows to represent an object in the image interested for recognition. The performance of the proposed method is shown experimentally.