High Saliency Research Articles

Boundary-Guided Optimization Framework for Saliency Refinement

Salient object detection has made a rapid progress in recent years. To improve the quality of initial saliency maps, existing algorithms typically refine them via a neighbor-constrained smoothing model, which assigns similar saliency values to neighboring regions. Since the adjacent regions could also cross the boundary between the salient object and background, these spatial distance-based methods easily cause false detection by involving the background regions that are close to the salient objects. To address this problem, we propose a boundary-guided optimization framework to jointly improve the region smoothness and correct the false detect regions. Specifically, we introduce a latent segmentation variable to regularize the consistency between the refined saliency map and the latent segmentation mask, which penalizes high (low) saliency values of the regions lying outside (inside) the estimated object boundary. To optimize the proposed objective function, we decompose the primary problem into two subproblems: submodular optimization problem and convex optimization problem. The submodular optimization problem can be quickly optimized using the off-the-shelf technique while the convex optimization can be solved with a closed-form solution. The experimental results show that the proposed method consistently improve the performances of eight state-of-the-art salient object detection algorithms on three datasets, including latest deep convolutional neural network-based algorithms. Meanwhile, our method outperforms state-of-the-art saliency refinement algorithms.

Focusness Extraction from Images for Automatic Camera Control by Measuring Objectness

Current digital cameras have various automatic control systems. In automatic camera systems, extracting focusness from an image is a very important problem. Automatic extraction of the main subject makes taking photos very easy, even for an amateur photographer. Methods have been proposed to evaluate focusness by visual saliency, which assume that an area with high saliency also has high focusness. However, various differences exist between focusness and saliency. In this study, the authors compare the values between focusness and saliency maps. They evaluate the focusness of 80 images in an image evaluation experiment with 20 observers. Saliency maps are calculated using six conventional algorithms. They show that the individual variations of focusness are insignificant in images that include only one major object. Furthermore, the authors apply a GIST feature to the saliency method by using a center‐surround histogram and extract focusness from images with high accuracy.

RGBD co-saliency detection via multiple kernel boosting and fusion

RGBD co-saliency detection, which aims at extracting common salient objects from a group of RGBD images with the additional depth information, has become an emerging branch of saliency detection. In this regard, this paper proposes a novel framework via multiple kernel boosting (MKB) and co-saliency quality based fusion. First, on the basis of pre-segmented regions at multiple scales, the regional clustering by feature bagging is exploited to generate the base co-saliency maps. Then the clustering-based samples selection is performed to select the most similar regions with high saliency from different images in the image set. The selected samples are utilized to learn a MKB-based regressor, which is applied to all regions at multiple scales to generate the MKB-based co-saliency maps. Finally, to make full use of both MKB and clustering-based co-saliency maps, a co-saliency quality criterion is proposed for adaptive fusion to generate the final co-saliency maps. Experimental results on a public RGBD co-saliency detection dataset demonstrate that the proposed co-saliency model outperforms the state-of-the-art co-saliency models.

Saliency detection and region of interest extraction based on multi-image common saliency analysis in satellite images

Abstract Saliency analysis is an effective method to extract interesting target regions from satellite images. However, when the satellite image contains salient background information or interference, it is difficult to eliminate this information and interference accurately only using single-image saliency analysis. In this paper, a novel multi-image saliency analysis (MSA) model based on multiple multispectral-images clustering saliency analysis (MMCS) and panchromatic image co-occurrence histogram saliency analysis (PCHS) is proposed to extract regions of interest (ROIs) with the common salient features. In MMCS, bisecting K-means clustering on the entire image set extracts the global correspondence in multispectral images. Then, cluster-based saliency using spectral contrast efficiently assigns the common ROIs with high saliency. Therefore, saliency maps of MMCS are computed, which effectively depress the background information and interference. In PCHS, saliency maps are obtained by computing co-occurrence histogram of panchromatic images, which aim to enhance the saliency of ROIs. After that, multi-image saliency maps are computed by a novel fusion strategy, which can depress the background information and highlight the ROIs. Finally, ROIs of multiple images are acquired by binarizing these saliency maps. Experimental results show that the MSA model can effectively eliminate the salient background information and exclude the images that contain no common salient information, thus achieving the highest ROC and PRF value.

Why Consumers Switch Energy Suppliers: The Role of Individual Attitudes

ABSTRACT Since 2008, fewer customers switched suppliers in British electricity and gas markets despite the potential for financial gains, suggesting that psychological factors may affect switching behaviors. Using a unique nation-wide British survey, we explore the influence of consumers’ attitudes and perceptions on switching behaviors and assess the differences in switching propensity across different groups. Support for simplifying energy tariffs, professed less difficulty in understanding energy bills, expected difficulty in changing suppliers and lack of attention to the issue of energy prices are associated with lower switching activity. At a time of high saliency, political party voting intention was strongly related to switching. Unlike the bivariate analyses conducted by the regulator and the competition authority, our multivariate analysis show few demographic factors affect the likelihood of switching except for educational attainment and tariff payment patterns. Remedies aiming to encourage switching cannot be targeted correctly unless the supporting analysis is robust to alternative model specifications.

High Quality Video Assessment Using Salient Features

<p class="Abstract">An efficient modified video compression HEVC technique based on high quality assessment saliency features presented for the assessment of high quality videos. To create an efficient saliency map we extract global temporal alignment component and robust spatial components. To obtain high quality saliency here, we combine spatial saliency features and temporal saliency features together for different macroblocks in association with transformed residuals. In this way, our saliency model outperforms all the existing techniques. In this paper, we have generated high reconstruction quality video after compression considering SFU dataset. Our experimental results outperforms all the existing techniques in terms of saliency map detection, PSNR and high-resolution quality.</p>

Development of a Stator-Magnetless Linear Synchronous Motor for Sensorless Control

Sensorless control techniques that do not use a linear scale are desired for applications that require a long-stroke linear synchronous motor (LSM). This paper discusses the development of a stator-magnetless LSM (i.e., no magnet is mounted on the stator of the LSM) for sensorless control that includes a high-speed position estimation algorithm based on the magnetic hysteresis phenomenon. This paper presents a new structure of a flux-switching LSM that achieves a high saliency ratio using a cutout that results in magnetic saturation in the armature core. The effect of the sub-tooth on reducing the cogging thrust is also discussed. Furthermore, the analytical and experimental characteristics of inductance, thrust, cogging thrust, and sensorless drive control are discussed based on a prototype.

Detection and Monitoring of Oil Spills Using Moderate/High-Resolution Remote Sensing Images.

Current marine oil spill detection and monitoring methods using high-resolution remote sensing imagery are quite limited. This study presented a new bottom-up and top-down visual saliency model. We used Landsat 8, GF-1, MAMS, HJ-1 oil spill imagery as dataset. A simplified, graph-based visual saliency model was used to extract bottom-up saliency. It could identify the regions with high visual saliency object in the ocean. A spectral similarity match model was used to obtain top-down saliency. It could distinguish oil regions and exclude the other salient interference by spectrums. The regions of interest containing oil spills were integrated using these complementary saliency detection steps. Then, the genetic neural network was used to complete the image classification. These steps increased the speed of analysis. For the test dataset, the average running time of the entire process to detect regions of interest was 204.56s. During image segmentation, the oil spill was extracted using a genetic neural network. The classification results showed that the method had a low false-alarm rate (high accuracy of 91.42%) and was able to increase the speed of the detection process (fast runtime of 19.88s). The test image dataset was composed of different types of features over large areas in complicated imaging conditions. The proposed model was proved to be robust in complex sea conditions.

Salient object detection via color and texture cues

In this paper, we present a new bottom-up salient object detection approach by constructing two graphs using color and texture features within the manifold ranking framework. First, we calculate the saliency of boundary patches and exclude the ones with high saliency which might be a part of saliency object. Second, we adopt a two-stage scheme for salient detection via affinity propagation clustering and graph-based manifold ranking. The background-based saliency detection aims to obtain the salient object regions as much as possible. In the foreground-based saliency detection, a similar computation is processed as that in the former step and yet slightly different. Instead of simultaneously using all the extracted boundary patches or foreground patches as queries, we compute saliency by using the patches in each cluster in turn and integrating them. At last, the final saliency map is generated by linearly combining two saliency maps respectively exploring color and texture cues. Both qualitative and quantitative evaluations on three publicly available datasets demonstrate the robustness and efficiency of our proposed approach against 21 state-of-the-art methods.

Complex networks driven salient region detection based on superpixel segmentation

In this paper, we propose an efficient method for salient region detection. First, the image is decomposed by using superpixel segmentation which groups similar pixels and generates compact regions. Based upon the generated superpixels, similarity between the regions is calculated by benefiting from color, location, histogram, intensity, and area information of each region as well as community identification via complex networks theory in the over-segmented image. Then, contrast, distribution and complex networks based saliency maps are generated by using the mentioned features. These saliency maps are used to create a final saliency map. The applicability, effectiveness and consistency of the proposed approach are illustrated by conducting some experiments using publicly available datasets. The tests have been used to compare the proposed method with some state-of-the-art methods. The reported results cover qualitative and quantitative assessments which demonstrate that our approach outputs high quality saliency maps and mostly achieves the highest precision rate compared to the other methods.

Analytical Field Calculation and Analysis of Surface Inset Permanent Magnet Machines With High Saliency Ratio

In this paper, an analytical field calculation model is built for surface inset permanent magnet (SIPM) machines with high saliency ratio. The high saliency ratio of SIPM machine is obtained using unequal $d$ - $q$ axis air-gap length based on the SIPM rotor structure. High saliency ratio can produce large reluctance torque and wide speed range. To get a fast and exact knowledge of flux distribution and operation parameters of the SIPM machine with high saliency ratio, the field solving domain is divided into five subdomains, i.e., stator slots, stator slot openings, air-gap, rotor air slots, and rotor magnets. The vector potential in each subdomain is governed by Maxwell’s equation and can be solved using the variable separation method and boundary conditions between adjacent subdomains. In addition, the cogging torque, back electromotive force (EMF), inductance, output torque, and unbalanced magnetic force (UMF) are calculated based on the field model. All the field calculation results are compared with those of finite element analysis (FEA), and it is shown that analytical field calculation model is fast and accurate. Furthermore, the effects of $q$ -axis air-gap length and pole arc ratio on machine parameters, such as cogging torque, back EMF, saliency ratio, output torque, and UMF, are also investigated using the analytical field calculation model.

No-Reference Image Quality Assessment Using Image Saliency for JPEG Compressed Images

Image quality assessment (IQA) is one of the most important issues in the field of image processing. Traditional IQA methods usually assume that the “reference” or “perfect” image is given. Obviously, this assumption is limited because the reference image may not be available in most practical applications. In addition, the mechanisms of human visual system (HVS) have not been explicitly exploited in the majority of existing IQA methods. In this article, to reduce dependence on reference image while introducing one mechanism of HVS, we propose a new method, referred to as Image-Saliency-based No-reference Image Quality Index (ISNIQI), by incorporating image saliency derived from visual attention models into the quality assessment of JPEG compressed images. Since the high saliency image region attracts more visual attention, ISNIQI assigns larger weight to the quality of image region with higher saliency. Experimental results on JPEG compressed images demonstrate the effectiveness of the proposed method in terms of the correlation with subjective perception.

유도전동기 대체 라인기동식 동기형 릴럭턴스 전동기 회전자의 설계 연구

In this paper, LS-SynRM (Line Start-Synchronous Reluctance Motor) has been attracting attention in replace of induction motor which hardly provides high efficiency. Compared to induction motor, LS-SynRM has better efficiency per unit area. This study demonstrated the electromagnetic design methods of LS-SynRM while maintaining the frame of existing IE3 induction motor for blower. We documented the design procedures for generating high saliency which is the most essential and mechanical stress analysis is also treated. In conclusion, we proved the validity of our design by manufacturing and testing our LS-SynRM models.

A sensitive object‐oriented approach to big surveillance data compression for social security applications in smart cities

SummarySurveillance has become a fairly common practice with the global boom in “smart cities”. How to efficiently store and manage the vast quantities of surveillance data is a persistent challenge in terms of analyzing social security problems. Developing data compression technology under the analytic requirements of surveillance data is the key to solving the storage problem. Criminal investigation demands the quality preservation of sensitive objects, typically pedestrians, human faces, vehicles, and license plates; however, the analytical value of surveillance data is rapidly lost as the compression ratio increases. In this paper, we propose a sensitive object‐oriented regions of interest‐based coding strategy for preserving the analytical value of surveillance data. In the proposed method, instead of generating a saliency map based on human visual perception, we consider saliency as a set of characteristics important for object detection and recognition. By making this modification, almost all sensitive objects necessary in a criminal investigation are assigned high saliency value rather than only one or two salient regions. Motions in the temporal domain are integrated to place emphasis on moving objects, namely moving sensitive objects, which then gain the highest saliency. Finally, a saliency‐based rate control algorithm embedded in High Efficiency Video Coding is used to maintain the quality of sensitive objects in the encoded video under a fixed bitrate. Experiments were conducted on two analytical indexes: Feature similarity and object detection accuracy. The results showed that by achieving the same feature similarity and object detection accuracy, our method can save 20% and 40% bitrate over High Efficiency Video Coding, respectively, for the storage of big surveillance data. Copyright © 2016 John Wiley & Sons, Ltd.

Negative mood disrupts self- and reward-biases in perceptual matching.

There are established effects of self- and reward-biases even on simple perceptual matching tasks [Sui, J., He, X., & Humphreys, G. W. (2012). Perceptual effects of social salience: Evidence from self-prioritization effects on perceptual matching. Journal of Experimental Psychology, Human Perception and Performance, 38, 1105-1117]; however we know little about whether these biases can be modulated by particular interventions, and whether the biases then change in the same way. Here we assessed how the biases alter under conditions designed to induce negative mood. We had participants read a list of self-related negative or neutral mood statements [Velten, E. (1968). A laboratory task for induction of mood states. Behavior Research and Therapy, 6, 473-482] and also listen for 10 min to a passage of negative or neutral music, prior to carrying out perceptual matching with shapes associated to personal labels (self or stranger) or reward (£12 or £1). Responses to the self- and high-reward-associated shapes were selectively slower and less sensitive (d') following the negative mood induction procedures, and the decrease in mood correlated with decreases in the reaction time bias across "high saliency" (self and high-reward) stimuli. We suggest that negative mood may decrease self- and reward-biases through reducing attention to salient external stimuli.

Joint Multi-Image Saliency Analysis for Region of Interest Detection in Optical Multispectral Remote Sensing Images

The automatic detection of regions of interest (ROI) is useful for remote sensing image analysis, such as land cover classification, object recognition, image compression, and various computer vision related applications. Recently, approaches based on visual saliency have been utilized for ROI detection. However, most existing methods focus on detecting ROIs from a single image, which generally cannot precisely extract ROIs against a complicated background or exclude images with no ROIs. In this paper, we propose a joint multi-image saliency (JMS) algorithm to simultaneously extract the common ROIs in a set of optical multispectral remote sensing images with the additional ability to identify images that do not contain the common ROIs. First, bisecting K-means clustering on the entire image set allows us to extract the global correspondence among multiple images in RGB and CIELab color spaces. Second, clusterwise saliency computation aggregating global color and shape contrast efficiently assigns common ROIs with high saliency, while effectively depressing interfering background that is salient only within its own image. Finally, binary ROI masks are generated by thresholding saliency maps. In addition, we construct an edge-preserving JMS model through edge-preserving mask optimization strategy, so as to facilitate the generation of a uniformly highlighted ROI mask with sharp borders. Experimental results demonstrate the advantages of our model in detection accuracy consistency and runtime efficiency.

Examining the influence of saliency of peer-induced distractions on direction of gaze and lecture recall

In two experiments, we recorded participants' direction of gaze as they watched a lecture video while a nearby researcher (sitting in-view of the participant) either: (a) attentively watched the lecture video with their laptop turned off (no distraction), (b) read through a research article on their laptop (Low Saliency distraction), or (c) watched a soccer match on their laptop with muted volume (High Saliency distraction). After the lecture video, a test was given to gauge memory of lecture content. In Experiment 1, an analysis of direction of gaze revealed that participants were objectively more distracted with increasing levels of distractor saliency. However, no differences between saliency conditions were found in retention for lecture content. These results were replicated in Experiment 2, in which we administered a different repertoire of lecture-content questions. Findings are discussed in terms of the ability to strategically and opportunistically engage with lecture content, the availability of multiple cognitive-resource pools, and the varying impact that multitasking in the classroom might have on the user and nearby peers.

Quaternion discrete cosine transformation signature analysis in crowd scenes for abnormal event detection

In this paper, an abnormal event detection approach inspired by the saliency attention mechanism of human visual system is presented. Conventionally, statistics-based methods suffer from visual scale, complexity of normal events and insufficiency of training data, for the reason that a normal behavior model established from normal video data is used to detect unusual behaviors with an assumption that anomalies are events with rare appearance. Instead, we make the assumption that anomalies are events that attract human attention. Temporal and spatial anomaly saliency are considered consistently by representing the pixel value in each frame as a quaternion, with weighted components that composed of intensity, contour, motion-speed and motion-direction feature. For each quaternion frame, Quaternion Discrete Cosine Transformation (QDCT) and signature operation are applied. The spatio-temporal anomaly saliency map is developed by inverse QDCT and Gaussian smoothing. By multi-scale analyzing, abnormal events appear at those areas with high saliency score. Experiments on typical datasets show that our method can achieve high accuracy results.

Perceptual grouping by similarity of surface roughness in haptics: the influence of task difficulty.

We investigated grouping by similarity of surface roughness in the context of task difficulty. We hypothesized that grouping yields a larger benefit at higher levels of task complexity, because efficient processing is more helpful when more cognitive resources are needed to execute a task. Participants searched for a patch of a different roughness as compared to the distractors in two strips of similar or dissimilar roughness values. We reasoned that if the distractors could be grouped based on similar roughness values, exploration time would be shorter and fewer errors would occur. To manipulate task complexity, we varied task difficulty (high target saliency equalling low task difficulty), and we varied the fingers used to explore the display (two fingers of one hand being more cognitive demanding than two fingers of opposite hands). We found much better performance in the easy condition as compared to the difficult condition (in both error rates and mean search slopes). Moreover, we found a larger effect for the similarity manipulation in the difficult condition as compared to the easy condition. Within the difficult condition, we found a larger effect for the one-hand condition as compared to the two-hand condition. These results show that haptic search is accelerated by the use of grouping by similarity of surface roughness, especially when the task is relatively complex. We conclude that the effect of perceptual grouping is more prominent when more cognitive resources are needed to perform a task.

Contextual-based top-down saliency feature weighting for target detection

Target detection using attention models has recently become a major research topic in active vision. One of the major problems in this area of research is how to appropriately weight low-level features to get high quality top-down saliency maps that highlight target objects. Learning of such weights has previously been done using example images having similar feature distributions without considering contextual information. In this paper, we propose a model that we refer to as the top-down contextual weighting (TDCoW) that incorporates high-level knowledge of the gist context of images to apply appropriate weights to the features. The proposed model is tested on four challenging datasets, two for cricket balls, one for bikes and one for person detection. The obtained results show the effectiveness of contextual information for modelling the TD saliency by producing better feature weights than those produced without contextual information.