Detection of Free-Form Objects using Appearance-based Local Features

M.A. Vicente, C. Fernandez, L. Paya, and A. Gil (Spain)


Computer vision, object recognition, appearance-based re cognition, PCA.


An appearance based object detection system is presen ted, whose main goal is the detection of free-form ob jects in non structured environments. A multichannel and multiscale approach is used. Two different feature extrac tion methods are combined to generate a model for each object: Principal Component Analysis (PCA) and Non negative Matrix Factorization with Sparsity Constraints (NMFSC). An object-dependant adjustment of channel weighting allows to detect different objects with high accu racy. The detection threshold is also automatically adjusted depending on the object to be detected.

Important Links:

Go Back