Realising emergent image preprocessing tasks in cellular-automaton-alike massively parallel hardware

Abstract

In this paper, we present an emergent computing architecture scheme, denoted as marching pixels (MPs), which is well-suited for massively-parallel embedded systems based realising smart optical sensors. Smart in this context refers to sensors in which signal capturing and signal processing is combined either in one chip or in a compact 3D chip stack. MPs are life-like agents, which are crawling within a pixel field in such a chip in order to find centre points and other attributes of objects in binary images. MPs fulfill these tasks only by utilising local interaction and stigmertic communication. Principal ideas, the architecture and first results are described in this paper along with a comparison to both conventional and other unconventional computing approaches.

Evaluating the evolvability of emergent agents with different numbers of states

“…Using more agents as well as using more states normally costs more hardware resources. In the case of massively-parallel fine-grained models like Cellular Automata, analogic Cellular Neural Networks [8], or Marching Pixels [4], implementing more agents that work simultaneously is no problem but rather a feature, On the other hand, it is expensive to make the single cells more powerful. If it is cheap to have more agents, the search for emergent agent rules with the right global behavior becomes the main the problem.…”

Emergent algorithms for centroid and orientation detection in high-performance embedded cameras

“…Due to the key importance of center points and orientation of objects to industrial vision systems we focused on the detection of that information as task for our MPs. We have already found solutions [7] for center point detection in convex objects. In this paper, we present a new solution which allows determination of the center point in non-convex objects, too.…”

An Optimized FPGA Implementation for a Parallel Path Planning Algorithm Based on Marching Pixels

“…MPs are very simple units but together they can tackle complex tasks. MPs can be modeled with Cellular Automata (CA) and could be used for parallel centroid detection of multiple objects [13], complete image transformations like scaling or mirroring [14] and also path planning [4]. The algorithm we presented in [4] combines a skeletonization operation [15] with the MP concept.…”