Parametric improvement of lateral interaction in accumulative computation in motion-based segmentation

Lateral inhibition in accumulative computation and fuzzy sets for human fall pattern recognition in colour and infrared imagery

Fall detection is an emergent problem in pattern recognition. In this paper, a novel approach which enables to identify a type of a fall and reconstruct its characteristics is presented. The features detected include the position previous to a fall, the direction and velocity of a fall, and the postfall inactivity. Video sequences containing a possible fall are analysed image by image using the lateral inhibition in accumulative computation method. With this aim, the region of interest of human figures is examined in each image, and geometrical and kinematic characteristics for the sequence are calculated. The approach is valid in colour and in infrared video.

Real-time accumulative computation motion detectors

The neurally inspired accumulative computation (AC) method and its application to motion detection have been introduced in the past years. This paper revisits the fact that many researchers have explored the relationship between neural networks and finite state machines. Indeed, finite state machines constitute the best characterized computational model, whereas artificial neural networks have become a very successful tool for modeling and problem solving. The article shows how to reach real-time performance after using a model described as a finite state machine. This paper introduces two steps towards that direction: (a) A simplification of the general AC method is performed by formally transforming it into a finite state machine. (b) A hardware implementation in FPGA of such a designed AC module, as well as an 8-AC motion detector, providing promising performance results. We also offer two case studies of the use of AC motion detectors in surveillance applications, namely infrared-based people segmentation and color-based people tracking, respectively.