PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 12628607

On motion detection through a multi-layer neural network architecture.

Antonio Fernández-Caballero·José Mira·Miguel A Fernández·Ana E Delgado
View original source ↗Export metadata ↓

Abstract

A neural network model called lateral interaction in accumulative computation for detection of non-rigid objects from motion of any of their parts in indefinite sequences of images is presented. Some biological evidences inspire the model. After introducing the model, the complete multi-layer neural architecture is offered in this paper. The architecture consists of four layers that perform segmentation by gray level bands, accumulative charge computation, charge redistribution by gray level bands and moving object fusion. The lateral interaction in accumulative computation associated learning algorithm is also introduced. Some examples that explain the usefulness of the system we propose are shown at the end of this article.

Explore related subjects

Motion PerceptionNeural Networks, ComputerPortraits as TopicJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Antonio Fernández-Caballero, José Mira, Miguel A Fernández, Ana E Delgado. 2003. On motion detection through a multi-layer neural network architecture.. https://doi.org/10.1016/s0893-6080(02)00233-2

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed1997

Movement, activity and action: the role of knowledge in the perception of motion.

This paper presents several approaches to the machine perception of motion and discusses the role and levels of knowledge in each. In particular, different techniques of motion understanding as focusing on one of movement, activity or action are described. Movements are the most atomic primitives, requiring no contextual or sequence knowledge to be recognized; movement is often addressed using either view-invariant or view-specific geometric techniques. Activity refers to sequences of movements or states, where the only real knowledge required is the statistics of the sequence; much of the recent work in gesture understanding falls within this category of motion perception. Finally, actions are larger-scale events, which typically include interaction with the environment and causal relationships; action understanding straddles the grey division between perception and cognition, computer vision and artificial intelligence. These levels are illustrated with examples drawn mostly from the group's work in understanding motion in video imagery. It is argued that the utility of such a division is that it makes explicit the representational competencies and manipulations necessary for perception.

Motion Perception↗
PubMed1997

Reciprocal interactions between occlusion and motion computations.

The "aperture problem" refers to the inherent ambiguity of the motion generated by an untextured contour moving within an aperture. The limited spatial extent of the receptive fields of neurons in cortical areas like V1 and MT render them susceptible to this problem. Most psychophysical experiments have probed how the visual system overcomes the aperture problem by presenting moving contours behind one or more simulated apertures. The assumption has been that the computational ambiguities that arise in resolving these displays are equivalent to the computational problems created by receptive fields that sample a small region of visual space. Evidence is presented here that challenges this view. We demonstrate that a fundamental computational difference in the interpretation of contour terminators arises in these two variants of the aperture problem. When the aperture is a receptive field, and a moving contour extends beyond its boundaries, the contour "terminators" delimit the boundaries of the receptive field, not the ends of the contour. In contrast, when a moving contour is viewed through a simulated aperture, the contour terminators are generated by the occluding edges of the aperture. In a series of experiments, we show that reciprocal interactions arise between computations of occlusion and those of motion direction and integration. Our results demonstrate that the visual system solves the aperture problem by decomposing moving contours into moving segments, and unpaired terminators that arise from the accretion and deletion of contours behind occluding edges, generating both coherent motion and illusory occluding surfaces.

Motion Perception↗