Bio-Inspired Human Action Recognition using Hybrid Max-Product Neuro-Fuzzy Classifier and Quantum-Behaved PSO

TL;DR

This paper introduces a novel bio-inspired human action recognition model combining form and motion pathways, utilizing a hybrid neuro-fuzzy classifier and quantum-behaved PSO, achieving promising accuracy on standard datasets.

Contribution

It proposes a new biologically inspired model with a form feature extractor and a synergetic neural network optimized by QPSO, integrating pathways via fuzzy inference for improved recognition.

Findings

Achieved high accuracy on KTH and Weizmann datasets.

Demonstrated effectiveness of hybrid neuro-fuzzy classifier with QPSO.

Validated the model's robustness across different action representations.

Abstract

Studies on computational neuroscience through functional magnetic resonance imaging (fMRI) and following biological inspired system stated that human action recognition in the brain of mammalian leads two distinct pathways in the model, which are specialized for analysis of motion (optic flow) and form information. Principally, we have defined a novel and robust form features applying active basis model as form extractor in form pathway in the biological inspired model. An unbalanced synergetic neural net-work classifies shapes and structures of human objects along with tuning its attention parameter by quantum particle swarm optimization (QPSO) via initiation of Centroidal Voronoi Tessellations. These tools utilized and justified as strong tools for following biological system model in form pathway. But the final decision has done by combination of ultimate outcomes of both pathways via fuzzy inference which increases novality of proposed model. Combination of these two brain pathways is done by considering each feature sets in Gaussian membership functions with fuzzy product inference method. Two configurations have been proposed for form pathway: applying multi-prototype human action templates using two time synergetic neural network for obtaining uniform template regarding each actions, and second scenario that it uses abstracting human action in four key-frames. Experimental results showed promising accuracy performance on different datasets (KTH and Weizmann).