Modeling a parallel L4 neuron array of the fly (Musca domestica) vision system with a sequential processor

At RMBS 2001 Olson presented a novel approach to image edge detection based on the vision system of the common house fly, Musca domestica [1]. Biologically based vision systems are inherently parallel and the vision related cells form a self-contained cartridge, ommatidium, which is duplicated across the surface of the fly's eye. Histological evidence provides the interconnection both within the vision cartridge and the connections to adjacent cartridges. Due to the parallel nature of biologically inspired vision systems, they outperform computer based digital vision systems in speed performance and memory requirements. Olson provided a model of the cartridge with its intra- and inter-connections. This model, rendered in MATLAB and Excel, demonstrated the feasibility of edge detection in the first several synaptic cellular connections within the cartridge. His results demonstrated how edge detection and object movements are easily obtained using a biologically based vision model. He demonstrated the model using simple rectangular and circular objects. We term this work Olson's Algorithm. We have extended Olson's Algorithm into a high-resolution model using a standard off-the-shelf frame grabber. Although, the frame grabber is a digitally based instrument, its image planes are used to model the photoreceptor layer (R1-R6), the L1, L2 monopolar cell layer, and also the monopolar L4 cell layer. The connections between these cells are programmed in "C". The high-resolution model demonstrates the feasibility of using a biologically based vision system in a real world application. Furthermore, it allows object segmentation, movement, and tracking to be modeled prior to implementation in parallel analog hardware.