Semantic Place Labeling Using a Probabilistic Decision List of AdaBoost Classifiers
Symone Gomes Soares Alcalá, Rui Alexandre M. Araújo · 2014
The success of mobile robots relies on the ability to extract from the environment additional information beyond simple spatial relations. In particular, mobile robots need to have semantic information about the entities in the environment such as the type or the name of places or objects. This work addresses the problem of classifying places (room, corridor or doorway) using mobile robots equipped with a laser range scan- ner. This paper compares the results of several AdaBoost algo- rithms (Viola-Jones AdaBoost, Gentle AdaBoost, Modest Ad- aBoost and Generalized AdaBoost for the place categorization) to train a set of classifiers and discusses these solutions. Since the problem is multi-class and these AdaBoosts provide only binary outputs, the AdaBoosts are arranged into Probabilistic Decision Lists (PDL), where each AdaBoost of the list gives a confidence value of each class. Then, Probabilistic Relaxation Labeling (PRL) is performed to smooth the classification re- sults. Moreover, heuristics for removing incorrect regions are proposed to reduce the classification error. Experimental re- sults suggest that PDL can be extended to several binary classi- fiers and show that PRL improves significantly the classification rates of the classifiers.