Image Segmentation Based on Visual Attention Mechanism

The concept of inspection robot is born in the strong & smart grid. By studying on the mechanism of human visual attention, this paper presents a method to detect the encroachments on transmission Lines from the perspective of the saLiency-based visual attention system. There are conspicuous diffidence between the encroachments and transmission Lines and it is easy for human to distinguish the encroachments from the transmission Lines because the encroachments were always the saLient objects in the view, consequently, it is a reasonable way to detect the encroachments based on the mechanism of visual attention. The experiment results show that this method can effectively detect and locate different types of encroachments in different natural environments.

This paper proposed a supervised visual attention mechanism for multimodal neural machine translation (MNMT), trained with constraints based on manual alignments between words in a sentence and their corresponding regions of an image. The proposed visual attention mechanism captures the relationship between a word and an image region more precisely than a conventional visual attention mechanism trained through MNMT in an unsupervised manner. Our experiments on English-German and German-English translation tasks using the Multi30k dataset and on English-Japanese and Japanese-English translation tasks using the Flickr30k Entities JP dataset show that a Transformer-based MNMT model can be improved by incorporating our proposed supervised visual attention mechanism and that further improvements can be achieved by combining it with a supervised cross-lingual attention mechanism (up to +1.61 BLEU, +1.7 METEOR).

Selective visual attention can direct our gaze rapidly towards objects of interest in the view. Better coverage of target region for attention can better serve for recognition. A novel method for evaluating how well the attended regions contribute to the recognition of the target based on SIFT descriptors is proposed in this paper. The method is used to evaluate the attended regions extracted by some visual attention mechanisms on real remote sensor images with different geometric and photometric transformations and for different scene types. The evaluation method proposed in this paper give an explicit, accurate and robust expression about the attended region in visual attention mechanisms and we believe this method could be applicable in visual attention mechanisms in the future work.

A novel video salient object extraction method based on visual attention

Atypical visual selective attention in children with dyslexia: evidence from N2pc and PD.

It is a challenging and important task to perceive and interact with other traffic participants in a complex driving environment. The human vision system plays one of the crucial roles to achieve this task. Particularly, visual attention mechanisms allow a human driver to cleverly attend to the salient and relevant regions of the scene to further make necessary decisions for the safe driving. Thus, it is significant to investigate human vision systems with great potential to improve assistive, and even autonomous, vehicular technologies. In this paper, we investigate driver's gaze behavior to understand visual attention. We, first, present a Bayesian framework to model visual attention of a human driver. Further, based on the framework, we develop a fully convolutional neural network to estimate the salient region in a novel driving scene. We systematically evaluate the proposed method using on-road driving data and compare it with other state-of-the-art saliency estimation approaches. Our analyses show promising results.

According to the characteristics of steel strip, This paper propose the strip defect detection algorithm which is based on visual attention mechanism. First, extract the input image color, brightness and orientation characteristics and form simple feature map; secondly, prognosis on the features, get defective attention region by threshold segmentation to color characteristics of colored defect image. The wavelet decomposition to colorless defect image of brightness and direction features will form the multi-feature subgraph; then construct feature difference molecular graph through the feature decomposition map around central difference operations, and the characteristic difference of molecular graph is formed by the fusion of feature saliency map; finally, defect targets by using local threshold method and region growing segmentation. The experimental results show that this method can rapidly and accurately detect the defects of the strip image, at the same time it can improve the efficiency of detection.

In change detection analysis, it is important to distinguish the real change targets and pseudo change targets accurately. Supervised change detection has been regarded as the best way to reduce the effects of pseudo change information. This is because human visual system has the ability to find the real changes. By imitating human visual characteristic, visual attention mechanism can bring the improvement of accuracy and speed of unsupervised change detection. In this paper, a change detection approach based on visual attention mechanism is proposed to reduce the influence of pseudo change information. Experiments show that the proposed method significantly reduces the false alarm rate and missed alarm rate and also shows insensitive to noise.

To address the issues of low accuracy and significant noise impact in edge continuity detection of art and design images, this paper proposes a visual attention-based edge continuity detection method for art and design images. Determine the edge position points of art and design images using the Laplace operator, and obtain the horizontal and vertical gradients of the image edges by calculating the first-order difference method to determine the amplitude of the image edge gradient; By using the maximum and minimum operations in binary morphology instead of intersection and union operations, the image grayscale is determined, and the HSI color space features are determined to complete the edge feature extraction of art and design images. Using the SUSAN operator to clarify the kernel similarity zone of the edges of art and design images, removing similar edge image pixels, using spatial domain denoising and frequency domain denoising to reduce the edge noise of art and design images, and achieving edge preprocessing of art and design images. Introducing visual attention mechanism to transform the pixel space of edge features in art and design images, performing threshold segmentation on the edges of art and design images, and continuously annotating the segmented edge pixels. Introducing loss function to improve the convergence speed of detection, constructing an art and design image edge continuity detection model based on visual attention mechanism, outputting detection results, and implementing research. The experimental results show that the proposed method has better continuity due to the successful avoidance of noise interference by introducing visual attention mechanisms and other operations. As the number of detected pixels increases, the detection deviation rate of the proposed method remains between 0.02% and 0.03%. The proposed method has a lower detection bias rate and can effectively improve the performance of edge continuity detection in art and design images.

Under natural viewing conditions humans tend to fixate on specific parts of the image that interests them naturally. Understanding the mechanisms of the human visual attention may benefit numerous applications in a various fields of engineering, marketing and art such as image quality evaluation, label design, human computer interaction, etc.Saliency map, proposed by Dirk Walther et al., represents the regions which are more prominent than other regions in terms of low level image properties such as intensity, color and orientation. We propose in this paper to modify this saliency map algorithm to account for one high-level feature, human faces, to better mimic the natural human attention and compare it to gaze maps obtained experimentally. The fixations of the gaze map are compared with the most salient regions of the saliency map. The factors that influence the relationship between the saliency maps and gaze maps are analyzed. Gaze map analysis was done for 20 test subjects using eye tracking device as they were shown a set of 190 images.

This paper proposed a new approach of extracting regions of interest based on visual attention model, which segmented image regions with the region growing algorithm. According to the physiological characteristics of Human Visual System (HVS), image features were extracted by non-uniform sampling of image and computing “center-surround”, which were used to simulate the human visual receptive field properties. Features became multi-scale conspicuity maps, which were combined into a saliency map. The focus of attention (FOA) as seeds of the region growing algorithm was obtained by the “winner-take-all” (WTA) competition. Then the regions of interest were extracted by using the region growing algorithm. The experiment results show that this approach can select suitable seeds automatically and the extraction of regions of interest can be consistent with human visual attention mechanism.

A visual attention mechanism is believed to be responsible for the most informative spots in complex scenes. We proposed a novel biologically inspired attention model based on Cortex-like mechanisms and sparse representation. Biological Inspired model, HMAX model, is a feature extraction method and this method is motivated by a quantitative model of visual cortex. This biological inspired feature will be used to build the Saliency Criteria to measure the perspective fields. Saliency Criteria is obtained from Shannon's information entropy and sparse representation. We demonstrate that the proposed model achieves superior accuracy with the comparison to classical approach in static saliency map generation on real data of natural scenes and psychology stimuli patterns.

Traditional moving target detection methods usually yield a poor performance when used in through-the-wall radar (TWR) because of the low signal-to-clutter ratio caused by obstacles. In this paper, a new moving target detection method based on the visual attention mechanism is proposed for TWR. The proposed method employs the information stored in the system memory to reduce false alarms while maintain a high detection performance, which is extracted from the TWR multi-frame images. The updating of memory information is based on the principle of visual attention mechanism to fulfill the real-time requirement. Real data collected by the experimental TWR system with multiple-input-multiple-output arrays have been used to validate the efficiency of the proposed method.

Multiscale face recognition in cluttered backgrounds based on visual attention

Mechanisms of visual attention revealed by saccadic eye movements