MirrorNet: Bio-Inspired Camouflaged Object Segmentation

Bio-inspired Motion-Based Object Segmentation

Although motion extraction requires high computational resources and normally produces very noisy patterns in real sequences, it provides useful cues to achieve an efficient segmentation of independent moving objects. Our goal is to employ basic knowledge about biological vision systems to address this problem. We use the Reichardt motion detectors as first extraction primitive to characterize ...

Bio-Inspired NMF Object Perception

The paper describes Neural Modeling Fields (NMF) for object perception, a bio-inspired paradigm. I discuss previous difficulties in object detection and recognition, and describe how NMF overcomes this difficulties. Neural and mathematical mechanisms are described and future research directions outlined. I. PAST DIFFICULTIES, COMPLEXITY AND LOGIC Biological object perception involves signals fr...

Bio-Inspired Algorithms for Color Image Segmentation

Effective image segmentation remains a challenging process as it constitutes a critical step to higher level image processing applications such as pattern recognition. In this paper,we present bio-inspired formulationto perform unsupervised image segmentation. Specifically,we used the Quantum PSO, the hybrid Gravitational PSO algorithm, a cooperative gravitational approach and the bees approach...

Modelling active bio-inspired object recognition in autonomous mobile agents

Bio-Inspired Vision Processor for Ultra-Fast Object Categorization

We present a scalable hardware architecture to implement large-scale bio-inspired synthetic vision systems. The system is a fully digital implementation of a modular vision engine that can perform real-time detection, recognition and segmentation of mega-pixel images. We present performance comparisons between software versions of the vision system executing on CPU and GPU machines, and show th...