Information Divergence Based Saliency Detection with a Global Center-Surround Mechanism

Rahman, Ibrahim M. H.; Hollitt, Christopher; Zhang, Mengjie

doi:10.1109/icpr.2014.590

Cited by 4 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since we do not compute features on multiscale, a different computational based mechanism is required. The information divergence based centre-surround mechanism is not only more computationally efficient than the contrast based approach but also has achieved a very good performance in saliency detection comparable to state-of-the-art techniques for single scale features [120].…”

Section: Modificationmentioning

confidence: 97%

“…The contrast based centre-surround mechanism is replaced by an information theoretic approach called Information divergence proposed in [120]. The centre-surround proposed in Itti model is a biological mechanism that is implemented through multi-scale difference of Gaussian operation.…”

Section: Modificationmentioning

confidence: 99%

“…The obtained PCs are assumed to describe important features contained in the images. Previously, PCA was used for extracting useful features for salient object detection [94,113,120]. One way to implement PCA on the input image is to consider square patches of the input image and then to extract the PCs of the patches separately [120].…”

Section: Pca Based Featuresmentioning

confidence: 99%

“…Previously, PCA was used for extracting useful features for salient object detection [94,113,120]. One way to implement PCA on the input image is to consider square patches of the input image and then to extract the PCs of the patches separately [120]. However, in this work PCA is applied colour wise rather than patch wise for better efficiency as the number of patches L 3, where three colour channels are considered.…”

Section: Pca Based Featuresmentioning

confidence: 99%

“…The Itti attention model is the baseline technique to compare against. The proposed saliency detection technique referred to as IDM-PCA [120] that utilizes the PCA for dimensionality reduction is also included for comparison. The rest of the techniques are abbreviated as follows:…”

Section: Experiments 1: Bottom-up Saliency Performancementioning

confidence: 99%

See 4 more Smart Citations

Visual attention strategies for target object detection

Rahman¹

View full text Add to dashboard Cite

<p>The human visual attention system (HVA) encompasses a set of interconnected neurological modules that are responsible for analyzing visual stimuli by attending to those regions that are salient. Two contrasting biological mechanisms exist in the HVA systems; bottom-up, data-driven attention and top-down, task-driven attention. The former is mostly responsible for low-level instinctive behaviors, while the latter is responsible for performing complex visual tasks such as target object detection. Very few computational models have been proposed to model top-down attention, mainly due to three reasons. The first is that the functionality of top-down process involves many influential factors. The second reason is that there is a diversity in top-down responses from task to task. Finally, many biological aspects of the top-down process are not well understood yet. For the above reasons, it is difficult to come up with a generalized top-down model that could be applied to all high level visual tasks. Instead, this thesis addresses some outstanding issues in modelling top-down attention for one particular task, target object detection. Target object detection is an essential step for analyzing images to further perform complex visual tasks. Target object detection has not been investigated thoroughly when modelling top-down saliency and hence, constitutes the may domain application for this thesis. The thesis will investigate methods to model top-down attention through various high-level data acquired from images. Furthermore, the thesis will investigate different strategies to dynamically combine bottom-up and top-down processes to improve the detection accuracy, as well as the computational efficiency of the existing and new visual attention models. The following techniques and approaches are proposed to address the outstanding issues in modelling top-down saliency: 1. A top-down saliency model that weights low-level attentional features through contextual knowledge of a scene. The proposed model assigns weights to features of a novel image by extracting a contextual descriptor of the image. The contextual descriptor plays the role of tuning the weighting of low-level features to maximize detection accuracy. By incorporating context into the feature weighting mechanism we improve the quality of the assigned weights to these features. 2. Two modules of target features combined with contextual weighting to improve detection accuracy of the target object. In this proposed model, two sets of attentional feature weights are learned, one through context and the other through target features. When both sources of knowledge are used to model top-down attention, a drastic increase in detection accuracy is achieved in images with complex backgrounds and a variety of target objects. 3. A top-down and bottom-up attention combination model based on feature interaction. This model provides a dynamic way for combining both processes by formulating the problem as feature selection. The feature selection exploits the interaction between these features, yielding a robust set of features that would maximize both the detection accuracy and the overall efficiency of the system. 4. A feature map quality score estimation model that is able to accurately predict the detection accuracy score of any previously novel feature map without the need of groundtruth data. The model extracts various local, global, geometrical and statistical characteristic features from a feature map. These characteristics guide a regression model to estimate the quality of a novel map. 5. A dynamic feature integration framework for combining bottom-up and top-down saliencies at runtime. If the estimation model is able to predict the quality score of any novel feature map accurately, then it is possible to perform dynamic feature map integration based on the estimated value. We propose two frameworks for feature map integration using the estimation model. The proposed integration framework achieves higher human fixation prediction accuracy with minimum number of feature maps than that achieved by combining all feature maps. The proposed works in this thesis provide new directions in modelling top-down saliency for target object detection. In addition, dynamic approaches for top-down and bottom-up combination show considerable improvements over existing approaches in both efficiency and accuracy.</p>

show abstract

Section: Modificationmentioning

confidence: 97%

Section: Modificationmentioning

confidence: 99%