Object Location in Colour Images Using Fuzzy-Tuned Scanpaths and a Neural Network

Allen, Michael J.; Mehdi, Qasim; Griffiths, Ian; Gough, N.E.; Coulson, I. M.

doi:10.1007/978-1-4471-0745-3_20

Cited by 2 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These results from the automated process compare favourably with those reported previously using a man-ual procedure with competitive and radial basis ANNs (Allen et al 1999 andAllen et al 2001). The automated procedure endeavours to select the optimum size of sub-region and length of scanpath whereas the system designer predetermined these parameters for the manual technique.…”

Section: Resultssupporting

confidence: 88%

“…As described above, because processing resources are limited, the human visual system employs an active process to filter the vast amount of visual data generated from a scene and to focus on ROI. The FTSS procedure [4,5] is used to analyse the images contained within a frame sequence and to establish where ROI are located within a scene by processing historical data and expert knowledge (knowledge about the environment). The historical data is collated from examinations of the previous frames in the sequence and the expert knowledge is currently provided by the operator.…”

Section: Fuzzy Tuned Stochastic Scanpathsmentioning

confidence: 99%

“…The attention metric is a cumulative quantity that determines the possibilities within the saccade map for those sub-regions that are not local to a ROI. The function aims to promote a systematic scan of pixels in areas of low interest in order to identify new objects [4]. The plot in Fig.…”

Section: Fuzzy Inference Systemmentioning

confidence: 99%

“…The technique was proposed as a means of determining the physical position of a camera when scanning a scene. The operation of (FTSSs) has been further developed by Allen et al [4,5] as a means of scanning frames in an image sequence. In Allen et al [4] the technique was applied to real image data and multiple objects in a constrained environment.…”

Section: Introductionmentioning

confidence: 99%

“…The operation of (FTSSs) has been further developed by Allen et al [4,5] as a means of scanning frames in an image sequence. In Allen et al [4] the technique was applied to real image data and multiple objects in a constrained environment. A competitive network was used for object classification based on an object's colour.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Fuzzy processing for active vision

Allen

Marín

Garcìa-Lagos

et al. 2003

ICA

View full text Add to dashboard Cite

Humans employ an active visual system to gather visual data from the surrounding environment. In addition to continually re-focusing the lens and adjusting the iris to control the exposure of light on to the retina, the eye constantly moves so that specific information can be focused on to the fovea-the part of the retina capable of defining fine detail. The target location when the eye moves is determined by the attention of the viewer. The attention of the viewer is drawn towards regions within the environment that are interesting or salient, i.e.they contain visual or semantic information. A mobile robot traversing within its environment has to identify and locate landmarks and other mobile entities as part of its navigational processes. The ability to efficiently analyze visual data captured from the environment and relate this to information from its internal map is very important. In this work a technique is described that uses semantic data to direct attention towards regions of interest within a simple environment and systematically search other areas of the environment. A fuzzy system lies at the heart of the technique that reasons with historical and environmental data in order to influence the search patterns. A Kohonen self-organizing map is used for object classification. Experimental data will be provided to illustrate the success and efficiency of the technique and conclusions will be drawn that discuss future work.

show abstract

Section: Resultssupporting

confidence: 88%

Section: Fuzzy Tuned Stochastic Scanpathsmentioning

confidence: 99%

Section: Fuzzy Inference Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations