摘要：Robot localization is an important task for mobile robot navigation. There are many methods focused on this issue. Some methods are implemented in indoor and outdoor environments. However, robot localization in textureless environments is still a challenging task. This is because in these environments, the scene appears the same in almost every position. In this work, we propose a method that can localize robots in textureless environments. We use Histogram of Oriented Gradients (HOG) and Speeded Up Robust Feature (SURF) descriptors together with Depth information to form a Depth-HOG-SURF multifeature descriptor, which is later used for image matching. K-means clustering is applied to partition the whole feature into groups that are collectively called visual vocabulary. All the images in the database are encoded using the vocabulary. The experimental results show a good performance of the proposed method.
