Supervised approach for object identification using speeded up robust features

Abstract

This paper proposes a vision based novel approach for real-time object counting. The proposed approach uses the textural information for object counting. Speeded up robust features (SURF) are used to extract the textural information from the image. Firstly, the approach selects stable SURF features from prototype image, i.e., object of interest. These features are matched with the SURF features of scene image captured using vision interface. Feature grid vectors (FGVs) and feature grid clusters (FGCs) are formed for matched SURF features in the scene to indicate the presence of object. Support vector machine (SVM) learning is used to identify true instances of the object. A parameter tuning approach is used to find optimised heuristics for more accuracy and less computation. The proposed approach performs well irrespective of illumination, rotation and scale. A run time environment of the proposed approach is also developed to get real-time status of the object count.