Cortical Multiscale Line-Edge Disparity Model

Abstract

Abstract. Most biological approaches to disparity extraction rely on the disparity energy model (DEM). In this paper we present an alternative approach which can complement the DEM model. This approach is based on the multiscale coding of lines and edges, because surface structures are composed of lines and edges and contours of objects often cause edges against their background. We show that the line/edge approach can be used to create a 3D wireframe representation of a scene and the objects therein. It can also significantly improve the accuracy of the DEM model, such that our biological models can compete with some state-of-the-art algorithms from computer vision.

Luminance, Colour, Viewpoint and Border Enhanced Disparity Energy Model

“…Finally, the horizontal disparity Δ x belonging to the maximum value is stored in the depth map D LE ( x , y ). For more implementation details see Rodrigues et al [ 10 ].…”

“…Some authors have proposed alternative biological models which are not based on the DEM, e. g., [ 9 ] combining geometric information and local edge features, [ 10 ] using multiscale lines and edges to retrieve a disparity wireframe model of the scene—the Line and Edge Disparity Model (LEDM) which is further explored in this paper in §5.1—and also du Buf et al [ 11 ], employing the phase differences of simple cell responses to the left and right views. The latter model is often applied to real-world problems, although it has been shown to be very imprecise in terms of localisation of depth transitions.…”

“…Most DEM research has considered theoretical or synthetic data, while biological models applied to real-world scenes appeared only recently [ 7 , 9 , 10 , 12 ]. This is mainly due to the fact that computational DEM implementations are usually focused on evaluating theoretical results using very specific stimuli, like bar/grating patterns or random-dot stereograms [ 6 ], or in psychophysical experiments [ 4 ].…”

“…Basically, this second population implements a template-matching process similar to those of [ 16 ] and Read [ 6 ]. This initial DEM model (disparity gist) is then integrated with colour and different viewpoints (§4), and finally with object border information retrieved from the multi-scale line and edge disparity model (LEDM) [ 10 ] and low-level processes from object salience research [ 17 ] (§5).…”

BINK: Biological binary keypoint descriptor

“…Models of simple, complex and end-stopped cells in visual area V1 have been developed and these models have been used for line, edge and keypoint detection du Buf, 2006, 2009). Lines and edges have been successfully used for multiple applications like object segregation, scale selection, saliency maps and disparity maps (Rodrigues et al, 2012), optical flow (Farrajota et al, 2011), face detection and recognition (Rodrigues and du Buf, 2006), facial expression recognition (Sousa et al, 2010), etc. The model for keypoint detection was computationally too expensive to be used in real-time applications at the time it was developed, but recent advances in computer hardware and code optimizations led to a much faster model that can now be used in real time (Terzic et al, 2015).…”