Egomotion perception using visual tracking

The ability of a biological organism to visually track a perceptually significant feature in its environment has been argued to be an important feedback mechanism guiding locomotion. This paper analyzes the constraints available from the visual motion stimuli in the context of tracking. Our aim is to show that the act of tracking simplifies the decoding of egomotion parameters from motion stimuli. The constraints obtainable under tracking are utilized to analyze a possible egomotion decoding strategy for a binocular robot eye system, modeled after the human ocular tracking (smooth pursuit) mechanism. The main result of the paper is in the derivation of a closed-form solution of the egomotion parameters using feedback information concerning the movement of the tracking motors over time. The theoretical results are verified by experiments. We believe that the active tracking approach presented here is a more simple, practical, and manageable technique in a robot navigation setting, compared to passive methods.     

EEG-based approach for recognizing human social emotion perception

Social emotion perception plays an important role in our daily social interactions and is involved in the treatments for mental disorders. Hyper-scanning technique enables to measure brain activities simultaneously from two or more persons, which was employed in this study to explore social emotion perception. We analyzed the recorded electroencephalogram (EEG) to explore emotion perception in terms of event related potential (ERP) and phase synchronization, and classified emotion categories based on convolutional neural network (CNN). The results showed that (1) ERP was significantly different among four emotion categories (i.e., anger, disgust, neutral, and happy), but there was no significant difference for ERP in the comparison of rating orders (the order of rating actions of the paired participants); (2) the intra-brain phase lag index (PLI) was higher than the inter-brain PLI but its number of connections exhibiting significant difference was less in all typical frequency bands (from delta to gamma); (3) the emotion classification accuracy of inter-PLI-Conv outperformed that of intra-PLI-Conv for all cases of using each frequency band (five frequency bands totally). In particular, the classification accuracies averaged across all participants in the alpha band were 65.55% and 50.77% (much higher than the chance level) for the inter-PLI-Conv and intra-PLI-Conv, respectively. According to our results, the emotion category of happiness can be classified with a higher performance compared to the other categories.     

Auto-organized visual perception using distributed camera network

Camera networks are complex vision systems difficult to control if the number of sensors is getting higher. With classic approaches, each camera has to be calibrated and synchronized individually. These tasks are often troublesome because of spatial constraints, and mostly due to the amount of information that need to be processed. Cameras generally observe overlapping areas, leading to redundant information that are then acquired, transmitted, stored and then processed. We propose in this paper a method to segment, cluster and codify images acquired by cameras of a network. The images are decomposed sequentially into layers where redundant information are discarded. Without the need of any calibration operation, each sensor contributes to build a global representation of the entire network environment. The information sent by the network is then represented by a reduced and compact amount of data using a codification process. This framework allows structures to be retrieved and also the topology of the network. It can also provide the localization and trajectories of mobile objects. Experiments will present practical results in the case of a network containing 20 cameras observing a common scene.     

Feature extraction for high-resolution imagery based on human visual perception

Feature extraction is highly important for classification of remote-sensing (RS) images. However, extraction of comprehensive spatial features from high-resolution imagery is still challenging, leading to many misclassifications in various applications. To address the problem, a shape-adaptive neighbourhood (SAN) technique is presented based on human visual perception. The SAN technique is an adaptive feature-extraction method that not only considers spectral feature information but also the spatial neighbourhood as well as the shape of features. The distinct advantage of this approach is that it can be adjusted to different feature sizes and shapes. Assessment experiments on a Système Pour l'Observation de la Terre 5 (SPOT-5) image were conducted to perform classification of land use/land cover. Results showed that improvement with SAN features is not significant for supervised classifiers due to the spectral confusion problem that resulted from similar spectral signatures between farmland and green areas, but a particularly significant improvement is observed for the unsupervised classifier. For the unsupervised classification, the SAN features noticeably improved the overall accuracy from 0.58 to 0.86, and the kappa coefficient from 0.45 to 0.80, indicating promise in the application of SAN features in the auto-interpretation of RS images.     

Measurement of human visual perception for Mura with some features

Abstract— The defects of flat‐panel liquid‐crystal display are usually not uniform, and the defects are called as “Mura.” There are many factors that cause the Mura phenomenon. At present, the human eyes define the seriousness of Mura, and different operators define the same Mura phenomenon with different meanings. For this reason, there have been many conflicts between the suppliers of flat‐panel liquid‐crystal display and customers. In order to solve the conflicts between the suppliers and customers, some researchers proposed a regression equation for the luminance contrast threshold and the size of Mura. In addition to the effect of Mura size on luminance contrast threshold, this study investigated the relationship between other factors and luminance contrast threshold. An analysis of the results show that Mura size, polarity of Mura, Mura position, and different color backgrounds significantly affect the visual contrast threshold. However, polarity did not significantly affect visual contrast threshold. In this study, it was found that Mura size was more important than the other factors for visual contrast threshold. The results of this study is expected to be referenced for inspection by the LCD industry.     

Nature-inspired framework for measuring visual image resemblance: A near rough set approach

The problem considered in this paper is how to determine the degree of nearness between complex visual objects. The proposed solution to this problem stems from a natural computing approach to solving the visual acuity problem in terms of a granular representation of visual information that is quantifiable as well as understandable for humans. This is accomplished via a near rough set framework in the approximation of a pair of disjoint sets and measurement of distances between sets using various fuzzy pseudometrics. Pseudometrics, in general, and fuzzy pseudometrics, in particular, are useful in measuring the distance between pairs of objects such as sets. Such distances are indicators of the nearness of (resemblance between) visual objects. These observations lead to a number of practical applications such as object recognition and object retrieval in digital image analysis. One such application is reported in this article. The contribution of this article is threefold: introduction of a nature-inspired framework for measurement of visual object resemblance, four different incarnations of the standard fuzzy metric and application of fuzzy metrics in content-based image retrieval experiments.     

基于人眼视觉感知驱动的井下图像增强算法

为解决传统的对比度增强方法在对井下图像进行处理时不能兼顾压缩动态范围、调整亮度以及增强图像对比度等问题,提出一种基于人眼视觉感知特性的井下图像对比度增强算法。首先根据人眼亮度掩蔽特性对图像进行区域划分,然后基于非线性亮度映射模型,对图像的不同区域进行不同尺度的非线性调整,最后再将亮度调整后的不同区域组合成新的图像。实验结果表明,该方法能有效增强井下低照度图像的对比度,提升图像的视觉效果。     

The visual perception of depth using electro-optical display systems

A review of the theory of human depth perception provides the basis for a discussion of the limitations imposed on the perception of the third dimension when viewing images transmitted by electro-optical systems such as television. The problem is explained in terms of the lack of sufficient number and strength of the appropriate visual cues, and possible methods of improving the situation are outlined.     

Evaluation of TFT-LCD defects based on human visual perception

In this paper, we propose an evaluation method of the TFT-LCD defect. Although several detection methods based on image processing techniques detect TFT-LCD defects, the majority of them are un-noticeable to the human eye because of the low contrast and unclear defect boundary. Therefore, to minimize the yield loss, all defects are re-inspected by visual inspector. The proposed method evaluates each defect and gives a corresponding level that objectively agrees with the assessment of a group of inspectors. The basic idea is to use the characteristics of the human visual perception in the evaluation. Crucial features of the defect were selected and the human perception degree was approximated through the regression analysis. In the process, we define the “just noticeable difference surface” (JND) and evaluate the level of defect as the distance from a defect consisting of a vector of selected features to the JND.     

A graph grammar‐based approach for graph layout

As a two‐dimensional formal tool, graph grammars are capable of handling the layout problems of visual programming languages. Based on an edge‐based graph grammar (EGG), this paper proposes a novel layout approach that uses the unique features of EGG and overcomes the weakness of existing layout approaches. In order to make the approach rigorous yet concise, the graph grammar mechanisms with layout constraints and quantitative analysis techniques are combined together as an integrity. First, the basic notions of EGG are briefly introduced; second, the layout approach is presented that consists of two phases, ie, bottom‐up parsing and top‐down derivation. Finally, a case study is given by taking the standard flowchart as an example to demonstrate the working process of the proposed approach.     

融合视觉感知和等周理论的图像阈值分割

提出一种融合视觉感知和等周理论的图像阈值分割方法。此方法先利用人类视觉感知的特性来寻找候选阈值所在的灰度区间,然后将等周理论中的等周率作为准则从候选阈值中挑选出最佳分割阈值。在工业无损检测等一系列图像上的实验结果表明,与现有的几种经典阈值分割方法相比,本文方法的分割效果更好。     

A visual path-following learning approach for industrial robots using DRL

Manufacturing companies are in constant need for improved agility. An adequate combination of speed, responsiveness, and business agility to cope with fluctuating raw material costs is essential for today’s increasingly demanding markets. Agility in robots is key in operations requiring on-demand control of a robot’s tool position and orientation, reducing or eliminating extra programming efforts. Vision-based perception using full-state or partial-state observations and learning techniques are useful to create truly adaptive industrial robots. We propose using a Deep Reinforcement Learning (DRL) approach to solve path-following tasks using a simplified virtual environment with domain randomisation to provide the agent with enough exploration and observation variability during the training to generate useful policies to be transferred to an industrial robot. We validated our approach using a KUKA KR16HW robot equipped with a Fronius GMAW welding machine. The path was manually drawn on two workpieces so the robot was able to perceive, learn and follow it during welding experiments. It was also found that small processing times due to motion prediction (3.5 ms) did not slow down the process, which resulted in smooth robot operations. The novel approach can be implemented onto different industrial robots to carry out different tasks requiring material deposition.     

Comparison between multiple-choice and analytic hierarchy process: measuring human perception

The objective of this study is to examine the effectiveness of the multiple‐choice method in measuring human perception. Specifically, the results of comparisons of the answers to two questions on the same issue are shown, each formatted in a different way: multiple‐choice (MC) and Analytic Hierarchy Process (AHP). AHP not only clearly identifies the most important alternative but also the preference for each alternative by each decision‐maker. Therefore, using AHP to analyze the decision‐making process results in a precise clarification of preference for alternatives. Based on public opinion research using AHP, two findings are shown: (1) MC and AHP yield different aggregated rankings of alternatives, and (2) AHP reveals that in modified MC format, which gives respondents the option of indicating their second‐best alternatives, the choice of a second‐best alternative is independent of the difference in the degree of importance between the best and the second best.     

A novel approach for ransomware detection based on PE header using graph embedding

Journal of Computer Virology and Hacking Techniques - The development of cryptocurrency has led to an increase in a type of malware called ransomware. Ransomware is a family of malware that uses...     

融合视觉感知和等周理论的数码迷彩纹理提取

现阶段数码迷彩纹理的提取方法缺乏主观视觉感知,针对其提取效果和质量欠佳的问题,提出一种融合视觉感知和等周理论的数码迷彩纹理提取方法。此方法先利用人的视觉感知特性构造边权值函数,将等周率作为选择分割阈值的准则选取最小等周率所对应的候选阈值作为最终分割阈值,完成数码迷彩纹理的提取。在一系列自然纹理图像上的实验结果表明,与现有的几种经典多阈值分割方法相比,此方法的分割效果更好。     

MDA-based visual modeling approach for resources link relationships using UML profile

Current XML editors do not provide conceptual modeling for XLink. This leads to inefficient development processes, and a low potential for reuse. To address these shortcomings, this study presents a Model Driven Architecture (MDA) approach with the UML profile to build XLink applications for various domains. This investigation demonstrates how users can use the UML profile to provide a conceptual and visual modeling for XLink applications, and automatically generate different XLink-based documents for various domains. The proposed methodology enables Web-based system developers to generate relationships between resources, and to improve software quality by adopting software engineering techniques in XML development.     

Object-difference drived graph convolutional networks for visual question answering

Multimedia Tools and Applications - Visual Question Answering(VQA), an important task to evaluate the cross-modal understanding capability of an Artificial Intelligence model, has been a hot...