Sequence Of Static Images Research Articles

Aesthetic preference in the production of image sequences

IntroductionThis research uses the production method to study aesthetic preference for sequences of human body postures. In two experiments, participants produced image sequences based on their aesthetic preferences, while we measured the visual aesthetic features displayed in the compositions.MethodsIn Experiment 1, participants created static image sequences based on their preferences. In Experiment 2, participants sorted images into apparent motion sequences they preferred to view.ResultsIn Experiment 1, good continuation of successive bodies and body-like objects was the preferred order. In Experiment 2, participants preferred abstract images with local sequential symmetry and human body postures exhibiting global sequential symmetry.DiscussionOur findings are compared to those of previous studies that employed the more widely used method of choice. Our experiments propose novel methods and conceptualizations for investigating aesthetic preferences for human body movement and other types of stimulus sequences.

Research on Animated GIFs Emotion Recognition Based on ResNet-ConvGRU

Animated Graphics Interchange Format (GIF) images have become an important part of network information interaction, and are one of the main characteristics of analyzing social media emotions. At present, most of the research on GIF affection recognition fails to make full use of spatial-temporal characteristics of GIF images, which limits the performance of model recognition to a certain extent. A GIF emotion recognition algorithm based on ResNet-ConvGRU is proposed in this paper. First, GIF data is preprocessed, converting its image sequences to static image format for saving. Then, the spatial features of images and the temporal features of static image sequences are extracted with ResNet and ConvGRU networks, respectively. At last, the animated GIFs data features are synthesized and the seven emotional intensities of GIF data are calculated. The GIFGIF dataset is used to verify the experiment. From the experimental results, the proposed animated GIFs emotion recognition model based on ResNet-ConvGRU, compared with the classical emotion recognition algorithms such as VGGNet-ConvGRU, ResNet3D, CNN-LSTM, and C3D, has a stronger feature extraction ability, and sentiment classification performance. This method provides a finer-grained analysis for the study of public opinion trends and a new idea for affection recognition of GIF data in social media.

Nearshore Bathymetry Retrieval from Wave-Based Inversion for Video Imagery

A wavelet-based method for bathymetry retrieval using a sequence of static images of the surface wave field, as obtained from video imagery, is proposed. Synthetic images of the water surface are generated from a numerical Boussinesq type model simulating the propagation of irregular waves. The spectral analysis is used to retrieve both wave periods and wavelengths by evaluating the spectral peaks in the time and spatial domains, respectively. The water depths are estimated using the linear dispersion relation and the results are validated with the model’s bathymetry. To verify the proposed methodology, 2D and 3D simulations considering effects of wave shoaling and refraction were performed for different sea conditions over different seafloors. The method’s ability to reproduce the original bathymetry is shown to be robust in intermediate and shallow waters, being also validated with a real case with images obtained with a shore-based video station. The main improvements of the new method compared to the consideration of a single image, as often used in Satellite Derived Bathymetry, is that the use of successive images enables the consideration of different wave periods, improving depth estimations and not requiring the use of subdomains or filters. This image processing methodology shows very positive results to provide bathymetry maps for shallow marine environments and can be useful to monitor the nearshore with high time- and space-resolution at low cost.

정적 영상 기반 행동 인식을 활용한 낙상 감지 기술 및 운전자 부주의 감지 기술 개발

Given image-level training data, a single test image can be used to identify a person’s actions or behaviors. This study highlights how the use of keypoint-based representation from single images can simplify the visual patterns of image events. Over the past few decades, deep learning techniques have successfully been applied in data-driven keypoint detection and skeletal analysis. While some engineered features from RGB or RGB-D datasets fail in image recognition applications due to ambiguous lightning conditions, previous knowledge from machine learning experimentation on large-scale data can be transferred into a new domain to improve performance. This idea of applying previously trained data can be applied to other applications as well. By adopting pre-trained convolutional neural network (CNN) models utilizing action recognition, new applications can be developed for events such as fall detection and driver drowsiness detection. Using state-of-the-art CNNs as a deep feature extractor to extract important key points of a human body or face, the geometric relationship of the predicted joints or facial features can be analyzed to aid in the design of hazardous event detection methods. The methods in this report were validated with publicly available datasets and successfully demonstrated in real-time. Two different data acquisition systems were used to train and validate these methods using real-world images and qualitatively verify them with a sequence of static images. Details of the algorithms and two practical applications are also outlined. The approach used in this study is scalable and can be extended to other hazardous event detection methods in the future.

An Advanced Deep Generative Framework for Temporal Link Prediction in Dynamic Networks.

Temporal link prediction in dynamic networks has attracted increasing attention recently due to its valuable real-world applications. The primary challenge of temporal link prediction is to capture the spatial-temporal patterns and high nonlinearity of dynamic networks. Inspired by the success of image generation, we convert the dynamic network into a sequence of static images and formulate the temporal link prediction as a conditional image generation problem. We propose a novel deep generative framework, called NetworkGAN, to tackle the challenging temporal link prediction task efficiently, which simultaneously models the spatial and temporal features in the dynamic networks via deep learning techniques. The proposed NetworkGAN inherits the advantages of the graph convolutional network (GCN), the temporal matrix factorization (TMF), the long short-term memory network (LSTM), and the generative adversarial network (GAN). Specifically, an attentive GCN is first designed to automatically learn the spatial features of dynamic networks. Second, we propose a TMF enhanced attentive LSTM (TMF-LSTM) to capture the temporal dependencies and evolutionary patterns of dynamic networks, which predicts the network snapshot at next timestamp based on the network snapshots observed at previous timestamps. Furthermore, we employ a GAN framework to further refine the performance of temporal link prediction by using a discriminative model to guide the training of the deep generative model (i.e., TMF-LSTM) in an adversarial process. To verify the effectiveness of the proposed model, we conduct extensive experiments on five real-world datasets. Experimental results demonstrate the significant advantages of NetworkGAN compared to other strong competitors.

Corrigendum to “Identification of Behavioral Features of Bridge Structure Based on Static Image Sequences”

Corrigendum to “Identification of Behavioral Features of Bridge Structure Based on Static Image Sequences”

Lexical processing in sign language: A visual mismatch negativity study

Event-related potential studies of spoken and written language show the automatic access of auditory and visual words, as indexed by mismatch negativity (MMN) or visual MMN (vMMN). The present study examined whether the same automatic lexical processing occurs in a visual-gestural language, i.e., Hong Kong Sign Language (HKSL). Using a classic visual oddball paradigm, deaf signers and hearing non-signers were presented with a sequence of static images representing HKSL lexical signs and non-signs. When compared with hearing non-signers, deaf signers exhibited an enhanced vMMN elicited by the lexical signs at around 230 ms, and a larger P1–N170 complex evoked by both lexical sign and non-sign standards at the parieto-occipital area in the early time window between 65 ms and 170 ms. These findings indicate that deaf signers implicitly process the lexical sign and that neural response differences between deaf signers and hearing non-signers occur at the early stage of sign processing.

A Novel Dense Full-Field Displacement Monitoring Method Based on Image Sequences and Optical Flow Algorithm

This paper aims to achieve a large bridge structural health monitoring (SHM) efficiently, economically, credibly, and holographically through noncontact remote sensing (NRS). For these purposes, the author proposes a NRS method for collecting the holographic geometric deformation of test bridge, using static image sequences. Specifically, a uniaxial automatic cruise acquisition device was designed to collect static images on bridge elevation under different damage conditions. Considering the strong spatiotemporal correlations of the sequence data, the relationships between six fixed fields of view were identified through the SIFT algorithm. On this basis, the deformation of the bridge structure was obtained by tracking a virtual target using the optical flow algorithm. Finally, the global holographic deformation of the test bridge was derived. The research results show that: The output data of our NRS method are basically consistent with the finite-element prediction (maximum error: 11.11%) and dial gauge measurement (maximum error: 12.12%); the NRS method is highly sensitive to the actual deformation of the bridge structure under different damage conditions, and can capture the deformation in a continuous and accurate manner. The research findings lay a solid basis for structure state interpretation and intelligent damage identification.

Identification of Behavioral Features of Bridge Structure Based on Static Image Sequences

This paper aims to further enhance the accuracy and efficiency of large bridge structural health monitoring (SHM) through noncontact remote sensing (NRS). For these purposes, the authors put forward an intelligent NRS method that collects the holographic geometric deformation of the test bridge, using the static image sequences. Specifically, a uniaxial automatic cruise acquisition device was designed to collect the dynamic and static images on bridge facade under different damage conditions. Considering the strong spatiotemporal correlations of the sequence data, the relationships between the time history images in six fixed fields of view were identified through deep learning under spatiotemporal sequences. On this basis, the behavioral features of the bridge structure were obtained under vehicle load. Finally, the global holographic deformation of the test bridge and the envelope spectrum of the global holographic deformation were derived from the deformation data. The research results show that the output data of our NRS method were basically consistent with the finite‐element prediction (maximum error: 11.11%) and dial gauge measurement (maximum error: 12.12%); the NRS method is highly sensitive to the actual deformation of the bridge structure under different damage conditions and can capture the deformation in a continuous and accurate manner. Compared with the limited number of measuring points, holographic deformation data also shows higher sensitivity in damage identification.

Deep Guided Learning for Fast Multi-Exposure Image Fusion.

We propose a fast multi-exposure image fusion (MEF) method, namely MEF-Net, for static image sequences of arbitrary spatial resolution and exposure number. We first feed a low-resolution version of the input sequence to a fully convolutional network for weight map prediction. We then jointly upsample the weight maps using a guided filter. The final image is computed by a weighted fusion. Unlike conventional MEF methods, MEF-Net is trained end-to-end by optimizing the perceptually calibrated MEF structural similarity (MEF-SSIM) index over a database of training sequences at full resolution. Across an independent set of test sequences, we find that the optimized MEF-Net achieves consistent improvement in visual quality for most sequences, and runs 10 to 1000 times faster than state-of-the-art methods. The code is made publicly available at.

Deterministic character of all-optical magnetization switching in GdFe-based ferrimagnetic alloys

Using photo-emission electron microscopy with X-ray magnetic circular dichroism as a contrast mechanism, new insights into the all-optical magnetization switching (AOS) phenomenon in GdFe based rare-earth transition metal ferrimagnetic alloys are provided. From a sequence of static images taken after single linearly polarized laser pulse excitation, the repeatability of AOS can be measured with a correlation coefficient. It is found that low coercivity enables thermally activated domain wall motion, limiting in turn the repeatability of the switching. Time-resolved measurement of the magnetization dynamics reveal that while AOS occurs below and above the magnetization compensation temperature $T_\text{M}$, it is not observed in GdFe samples where $T_\text{M}$ is absent. Finally, AOS is experimentally demonstrated against an applied magnetic field of up to 180 mT.

Non-rigid, but not rigid, motion interferes with the processing of structural face information in developmental prosopagnosia

There is growing evidence to suggest that facial motion is an important cue for face recognition. However, it is poorly understood whether motion is integrated with facial form information or whether it provides an independent cue to identity. To provide further insight into this issue, we compared the effect of motion on face perception in two developmental prosopagnosics and age-matched controls. Participants first learned faces presented dynamically (video), or in a sequence of static images, in which rigid (viewpoint) or non-rigid (expression) changes occurred. Immediately following learning, participants were required to match a static face image to the learned face. Test face images varied by viewpoint (Experiment 1) or expression (Experiment 2) and were learned or novel face images. We found similar performance across prosopagnosics and controls in matching facial identity across changes in viewpoint when the learned face was shown moving in a rigid manner. However, non-rigid motion interfered with face matching across changes in expression in both individuals with prosopagnosia compared to the performance of control participants. In contrast, non-rigid motion did not differentially affect the matching of facial expressions across changes in identity for either prosopagnosics (Experiment 3). Our results suggest that whilst the processing of rigid motion information of a face may be preserved in developmental prosopagnosia, non-rigid motion can specifically interfere with the representation of structural face information. Taken together, these results suggest that both form and motion cues are important in face perception and that these cues are likely integrated in the representation of facial identity.

Motion facilitates face perception across changes in viewpoint and expression in older adults.

Faces are inherently dynamic stimuli. However, face perception in younger adults appears to be mediated by the ability to extract structural cues from static images and a benefit of motion is inconsistent. In contrast, static face processing is poorer and more image-dependent in older adults. We therefore compared the role of facial motion in younger and older adults to assess whether motion can enhance perception when static cues are insufficient. In our studies, older and younger adults learned faces presented in motion or in a sequence of static images, containing rigid (viewpoint) or nonrigid (expression) changes. Immediately following learning, participants matched a static test image to the learned face which varied by viewpoint (Experiment 1) or expression (Experiment 2) and was either learned or novel. First, we found an age effect with better face matching performance in younger than in older adults. However, we observed face matching performance improved in the older adult group, across changes in viewpoint and expression, when faces were learned in motion relative to static presentation. There was no benefit for facial (nonrigid) motion when the task involved matching inverted faces (Experiment 3), suggesting that the ability to use dynamic face information for the purpose of recognition reflects motion encoding which is specific to upright faces. Our results suggest that ageing may offer a unique insight into how dynamic cues support face processing, which may not be readily observed in younger adults' performance. (PsycINFO Database Record (c) 2014 APA, all rights reserved).

Lecturers' faces fatigue their students: Face identity aftereffects for dynamic and static faces

Face adaptation has been used as a tool to probe our representations for facial identity. It has also been claimed to play a functional role in face processing, perhaps calibrating the visual system towards encountered faces. However, for this to be so, face aftereffects must be observable following adaptation to ecologically valid moving stimuli, not just after prolonged viewing of static images. We adapted our participants to videos, static image sequences or single images of the faces of lecturers who were personally familiar to them. All three stimulus types produced significant, and equivalent, face identity aftereffects, demonstrating that aftereffects are not confined to static images but can occur after exposure to more naturalistic stimuli. It is also further evidence against explanations of face adaptation effects solely in terms of low-level visual processing.

Exploiting Multimedia in Reproductive Science Education: Research Findings

Education in reproductive science is operating from an outdated paradigm of teaching and learning. Traditionally, reproductive education follows the pattern where students read a textbook, listen to instructor presentations, re-read the textbook and class notes and then complete a test. This paradigm is inefficient, costly and has not incorporated the potential that technology can offer with respect to increases in student learning. Further, teachers of reproductive science (and all of science for that matter) have little training in the use of documented methods of instructional design and cognitive psychology. Thus, most of us have learned to teach by repeating the approaches our mentors used (both good and bad). The technology now exists to explain complex topics using multimedia presentations in which digital animation and three-dimensional anatomical reconstructions greatly reduce time required for delivery while at the same time improving student understanding. With funding from the Small Business Innovation Research program through the U.S. Department of Education, we have developed and tested a multimedia approach to teaching complex concepts in reproductive physiology. The results of five separate experiments involving 1058 university students and 122 patients in an OB/GYN clinic indicate that students and patients learned as much or more in less time when viewing the multimedia presentations when compared to traditional teaching methodologies.

Learning Invariance from Natural Images Inspired by Observations in the Primary Visual Cortex

The human visual system has the remarkable ability to largely recognize objects invariant of their position, rotation, and scale. A good interpretation of neurobiological findings involves a computational model that simulates signal processing of the visual cortex. In part, this is likely achieved step by step from early to late areas of visual perception. While several algorithms have been proposed for learning feature detectors, only few studies at hand cover the issue of biologically plausible learning of such invariance. In this study, a set of Hebbian learning rules based on calcium dynamics and homeostatic regulations of single neurons is proposed. Their performance is verified within a simple model of the primary visual cortex to learn so-called complex cells, based on a sequence of static images. As a result, the learned complex-cell responses are largely invariant to phase and position.

Modeling time and topology for animation and visualization with examples on parametric geometry

The art of animation relies upon modeling objects that change over time. A sequence of static images is displayed to produce an illusion of motion. Even for simple cases, a careful analysis exposes that formal topological guarantees are often lacking. This absence of rigor can result in subtle, but significant, topological flaws. A new modeling approach is proposed to integrate topological rigor with a continuous model of time. Examples will be given for Bézier curves, while indicating extensions to a richer class of parametric curves and surfaces. Applications to scientific visualization for molecular modeling are discussed. Prototype animations are available for viewing over the web.

Human eye-head co-ordination in natural exploration

During natural behavior humans continuously adjust their gaze by moving head and eyes, yielding rich dynamics of the retinal input. Sensory coding models, however, typically assume visual input as smooth or a sequence of static images interleaved by volitional gaze shifts. Are these assumptions valid during free exploration behavior in natural environments? We used an innovative technique to simultaneously record gaze and head movements in humans, who freely explored various environments (forest, train station, apartment). Most movements occur along the cardinal axes, and the predominance of vertical or horizontal movements depends on the environment. Eye and head movements co-occur more frequently than their individual statistics predicts under an independence assumption. The majority of co-occurring movements point in opposite directions, consistent with a gaze-stabilizing role of eye movements. Nevertheless, a substantial fraction of eye movements point in the same direction as co-occurring head movements. Even under the very most conservative assumptions, saccadic eye movements alone cannot account for these synergistic movements. Hence nonsaccadic eye movements that interact synergistically with head movements to adjust gaze cannot be neglected in natural visual input. Natural retinal input is continuously dynamic, and cannot be faithfully modeled as a mere sequence of static frames with interleaved large saccades.

Two-stroke: A new illusion of visual motion based on the time course of neural responses in the human visual system

A sequence of static images presented in rapid succession can create a powerful impression of visual movement, a fact exploited by the visual media (television and cinema) and by animators. A new illusion of movement called “two-stroke” is described, in which repeated presentation of a two-frame pattern displacement can create an impression of continuous forward motion, without the inclusion of any additional pattern displacements. The illusion can be explained by a biphasic temporal impulse response that modifies the stimulus delivered to motion energy sensors. It offers a basis for further research on temporal and motion responses in the visual system as well as a tool for animators and graphic artists to create consistent apparent movement from minimal external stimulation.

Understanding dynamic and static displays: using images to reason dynamically

We examined expert meteorologists as they created a weather forecast while working in a naturalistic environment. We examined the type of external representation they chose to examine (a static image, a sequence of static images, or a dynamic display) and the kind of information they extracted from those representations (static or dynamic). We found that even though weather is an extremely dynamic domain, expert meteorologists examined very few animations, examining primarily static images. However, meteorologists did extract large amounts of dynamic information from these static images, suggesting that they reasoned about the weather by mentally animating the static images rather than letting the software do it for them.