IMPROVING MULTI-CAMERA ACTIVITY RECOGNITION BY EMPLOYING NEURAL NETWORK BASED READJUSTMENT

In this paper, we propose a method to enhance activity recognition in complex environments, where problems like occlusions, outliers and illumination changes occur. In order to address the problems induced by the dependency on the camera's viewpoint, multiple cameras are used in an endeavor to exploit redundancies. We initially examine the effectiveness of various information stream fusion approaches based on hidden Markov models, including Student's t-endowed models for tolerance to outliers. Following, we introduce a neural network-based readjustment mechanism that fits these fusion schemes and aims at dynamically correcting erroneous classification results for image sequences, thus improving the overall recognition rates. The proposed approaches are evaluated under complex real life activity recognition scenarios, and the acquired results are compared and discussed.