Multi-sensor joint kernel sparse representation for personnel detection

In this paper, we propose a novel nonlinear technique for multi-sensor classification, which relies on sparsely representing a test sample in terms of all the training samples in a feature space induced by a kernel function. Our approach simultaneously takes into account the correlations as well as the complementary information between the homogeneous/heterogeneous sensors, while also considering the joint sparsity within each sensor's multiple observations in the feature space. This approach can be seen as a generalized model for representing a multi-task and multivariate Lasso in the feature space, where the data from all the sensors representing the same physical events are jointly represented by a sparse linear combination of the training data. Extensive experiments are conducted on real data sets and the results are compared with the conventional discriminative classifiers to verify the effectiveness of the proposed method in the application of automatic border patrol, where it is required to discriminate between human and animal footsteps.