Object detection from multiple images based on the graph cuts

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F12%3A86084770" target="_blank" >RIV/61989100:27240/12:86084770 - isvavai.cz</a>
Result on the web
<a href="http://download.springer.com/static/pdf/496/chp%253A10.1007%252F978-3-642-33179-4_26.pdf?auth66=1364565987_0df40d17670fc13265efea2784ac81a5&ext=.pdf" target="_blank" >http://download.springer.com/static/pdf/496/chp%253A10.1007%252F978-3-642-33179-4_26.pdf?auth66=1364565987_0df40d17670fc13265efea2784ac81a5&ext=.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-642-33179-4_26" target="_blank" >10.1007/978-3-642-33179-4_26</a>

Result language
angličtina
Original language name
Object detection from multiple images based on the graph cuts
Original language description
In this paper, we present a new method for detecting objects from multiple images. Unlike the general stereo-reconstruction methods, we propose a method for speci?c scenes only, which is motivated by the known fact that, in special circumstances, a specialized method will probably perform better than a general one. The theoretical model of the scene expects that the objects are created by the areas placed in a certain height over the scene base plane. The method is based on minimisation of an energy function. The function that has been found useful for the model is presented. For minimisation, the graph cut technique is used, which is modi?ed by an iterative process in which the original edge weights are changed on the basis of the residual graph. Themethod has been tested on detecting the cars in parking lots; examples of the results are presented.
Czech name
—
Czech description
—

Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)