Visual Navigation Method for Indoor Mobile Robot Based on Extended BoW Model
This paper proposes a new navigation method for mobile robots based on an extended BoW (Bag of Words) model for general object recognition in indoor environments.The SIFT (Scale-invariant Feature Transform) detection algorithm with the GPU (Graphic Processing Unit) acceleration technology is used to describe feature vectors in this model.Firstly,in order to add some redundant image information,statistical information of the spatial relationships of all the feature points in an image,i.e.,relative distances and angles,is used to extend the feature vectors in the original BoW model.Then,the unsupervised SVM (Support Vector Machine) classifier is used to classify objects.Also,in order to navigate conveniently in unknown and dynamic indoor environments,a type of human-robot interaction method based on a hand-drawn semantic map is considered.The experimental results show that this new navigation technology for indoor mobile robots is very robust and highly effective.
general object recognition Bag of Words model mobile robot visual navigation
Xianghui Li Xinde Li Mohammad Omar Khyam Chaomin Luo Yingzi Tan
Key Laboratory of Measurement and Control of CSE (Ministry of Education), School of Automation, Sout Department of Electrical and Computer Engineering, Faculty of Engineering, National University of Si Department of Electrical and Computer Engineering,University of Detroit Mercy, Michigan, USA
国内会议
哈尔滨
英文
631-638
2017-10-01（万方平台首次上网日期，不代表论文的发表时间）