Untitled

Funder

Organizational Unit

Publications

A parametric spectral model for texture-based salience

Publication . Terzic, Kasim; Krishna, Sai; du Buf, J. M. H.; Gall, J.; Gehler, P.; Leibe, B.

We present a novel saliency mechanism based on texture. Local texture at each pixel is characterised by the 2D spectrum obtained from oriented Gabor filters. We then apply a parametric model and describe the texture at each pixel by a combination of two 1D Gaussian approximations. This results in a simple model which consists of only four parameters. These four parameters are then used as feature channels and standard Difference-of-Gaussian blob detection is applied in order to detect salient areas in the image, similar to the Itti and Koch model. Finally, a diffusion process is used to sharpen the resulting regions. Evaluation on a large saliency dataset shows a significant improvement of our method over the baseline Itti and Koch model.

2015Conference object

Open Access

Texture features for object salience

Publication . Terzic, Kasim; Krishna, Sai; du Buf, J. M. H.

Although texture is important for many vision-related tasks, it is not used in most salience models. As a consequence, there are images where all existing salience algorithms fail. We introduce a novel set of texture features built on top of a fast model of complex cells in striate cortex, i.e., visual area V1. The texture at each position is characterised by the two-dimensional local power spectrum obtained from Gabor filters which are tuned to many scales and orientations. We then apply a parametric model and describe the local spectrum by the combination of two one-dimensional Gaussian approximations: the scale and orientation distributions. The scale distribution indicates whether the texture has a dominant frequency and what frequency it is. Likewise, the orientation distribution attests the degree of anisotropy. We evaluate the features in combination with the state-of-the-art VOCUS2 salience algorithm. We found that using our novel texture features in addition to colour improves AUC by 3.8% on the PASCAL-S dataset when compared to the colour-only baseline, and by 62% on a novel texture-based dataset. (C) 2017 Elsevier B.V. All rights reserved.

2017-11Journal article

Open Access

Dialectical polyptych: an interactive movie

Publication . António, Rui; Silva, Bruno; Rodrigues, J. M. F.

Most of the known video games developed by big software companies usually establish an approach to the cinematic language in an attempt to create a perfect combination of narrative, visual technique and interaction. Unlike most video games, interactive film narratives normally involve an interruption in time whenever the spectator has to make choices. “Dialectical Polyptych” is an interactive movie included in a project called “Characters looking for a spect-actor”, which aims to give the spectator on-the-fly control over film editing, thus exploiting the role of the spectator as an active subject in the presented narrative. This paper presents a system based on a 3D sensor for tracking the spectator's movements and positions, which allows seamless real-timeinteractivity with the movie. Different positions of the body prompt a change in the angle or shot within each narrative, and hand swipes allow the spectator to alternate between the two parallel narratives, both producing a complementary narrative.

2015Journal article

Open Access

Luminance, colour, viewpoint and border enhanced disparity energy model

Publication . Martins, Jaime; Rodrigues, Joao; du Buf, J. M. H.

The visual cortex is able to extract disparity information through the use of binocular cells. This process is reflected by the Disparity Energy Model, which describes the role and functioning of simple and complex binocular neuron populations, and how they are able to extract disparity. This model uses explicit cell parameters to mathematically determine preferred cell disparities, like spatial frequencies, orientations, binocular phases and receptive field positions. However, the brain cannot access such explicit cell parameters; it must rely on cell responses. In this article, we implemented a trained binocular neuronal population, which encodes disparity information implicitly. This allows the population to learn how to decode disparities, in a similar way to how our visual system could have developed this ability during evolution. At the same time, responses of monocular simple and complex cells can also encode line and edge information, which is useful for refining disparities at object borders. The brain should then be able, starting from a low-level disparity draft, to integrate all information, including colour and viewpoint perspective, in order to propagate better estimates to higher cortical areas.

2015Journal article

Open Access

Soft-bottom fishes and spatial protection: findings from a temperate marine protected area

Publication . Sousa, Inês; Gonçalves, Jorge Manuel Santos; Claudet, Joachim; Coelho, Rui; Gonçalves, Emanuel J.; Erzini, Karim

Numerous studies over the last decades have focused on marine protected areas (MPAs) and their effects on fish communities. However, there is a knowledge gap regarding how species that live associated with soft-substrates (e.g., sand, mud) respond to spatial protection. We analyzed abundance, biomass and total lengths of the soft-bottom fishes in a multiple-use MPA in the north-eastern Atlantic, the Luiz Saldanha Marine Park (Portugal), during and after the implementation of its management plan. Data were collected by experimental fishing in areas with three different levels of protection, during the implementation period and for three years after full implementation of the MPA. Univariate analysis detected significant biomass increases between the two periods. Fish assemblages were mainly structured by depth and substrate, followed by protection level. Community composition analyses revealed significant differences between protection levels and between the two periods. Species exhibited a broad variation in their response to protection, and we hypothesize that factors such as species habitat preferences, body size and late maturity might be underlying determinants. Overall, this study provides some evidence of protection effectiveness in soft-bottom fish communities, supported by the significant increase in biomass in the protected areas and the positive trends of some species.

2018-06Journal article

Open Access