Scene Learning Research Articles

Multi-modal remote perception learning for object sensory data.

When it comes to interpreting visual input, intelligent systems make use of contextual scene learning, which significantly improves both resilience and context awareness. The management of enormous amounts of data is a driving force behind the growing interest in computational frameworks, particularly in the context of autonomous cars. The purpose of this study is to introduce a novel approach known as Deep Fused Networks (DFN), which improves contextual scene comprehension by merging multi-object detection and semantic analysis. To enhance accuracy and comprehension in complex situations, DFN makes use of a combination of deep learning and fusion techniques. With a minimum gain of 6.4% in accuracy for the SUN-RGB-D dataset and 3.6% for the NYU-Dv2 dataset. Findings demonstrate considerable enhancements in object detection and semantic analysis when compared to the methodologies that are currently being utilized.

Systematic Bibliometric Analysis of Research Hotspots and Trends on the Application of Virtual Reality in Nursing

BackgroundWith the emergence of the metaverse, virtual reality, as a digital technology, must be getting hotter. High quality virtual reality related nursing knowledge scene learning is gradually replacing traditional education and intervention skills.ObjectiveThis systematic study aimed to gain insights into the overall application of virtual reality technology in the study of nursing.MethodsCitations downloaded from the Web of Science Core Collection database for use in VR in nursing publications published from January 1, 2012, to December 31, 2021, were considered in the research. Information retrieval was analyzed using https://bibliometric.com/app, CiteSpace.5.8. R3, and VOS viewer.ResultsA total of 408 institutions from 95 areas contributed to relevant publications, of which the United States is the most influential country in this research field. The clustering labels of cited documents were obtained from the citing documents. Virtual simulation, virtual learning, clinical skills, and dementia are the clustering labels of co-cited documents. The burst keywords represented the research frontiers in 2020–2021, which were knowledge and simulation.ConclusionVirtual nursing has had an impact on both nurses and clients. With the emergence of the concept of the metaverse, the research and application of virtual reality technology in nursing will gradually increase.

Active Sketch Scene Learning

Active Sketch Scene Learning

Balance learning for ship detection from synthetic aperture radar remote sensing imagery

Synthetic aperture radar (SAR) is playing an important role in maritime domain awareness. As a fundamental ocean mission, SAR ship detection can offer high-quality services for marine surveillance. It receives widespread concern in the SAR remote sensing community. Recently, deep learning (DL) has greatly improved SAR ship detection accuracy. However, there are still some unperceived imbalance problems that seriously hinder further accuracy improvements among current DL-based SAR ship detectors. Therefore, we propose a novel concept of balance learning (BL) for high-quality SAR ship detection. We first point out the four unperceived imbalance problems, i.e., image sample scene imbalance, positive negative sample imbalance, ship scale feature imbalance, and classification regression task imbalance. Then, we offer some profound insights into these imbalances. Immediately, we propose four effective solutions to handle the above four imbalances correspondingly, i.e., balance scene learning mechanism (BSLM), balance interval sampling mechanism (BISM), balance feature pyramid network (BFPN), and balance classification regression network (BCRN). Finally, combined with the four solutions, a novel balance learning network (BL-Net) is proposed. Ablation studies can confirm each solution’s effectiveness. Experimental results on five open datasets (SSDD, Gaofen-SSDD, Sentinel-SSDD, SAR-Ship-Dataset, and HRSID) reveal BL-Net’s state-of-the-art SAR ship detection performance compared to the other 30 DL-based SAR ship detectors. Specifically, in contrast to the current most competitive method, the accuracy increase of BL-Net is 2.98% on SSDD, 1.97% on Gaofen-SSDD, 1.49% on Sentinel-SSDD, 0.55% on SAR-Ship-Dataset, and 4.95% on HRSID. Last but not least, the satisfactory ship detection results on another two large-scene Sentinal-1 SAR images confirm BL-Net’s strong migration capability. This indicates BL-Net’s potential value in marine surveillance.

Balance Scene Learning Mechanism for Offshore and Inshore Ship Detection in SAR Images

Huge imbalance of different scenes’ sample numbers seriously reduces synthetic aperture radar (SAR) ship detection accuracy. Thus, to solve this problem, this letter proposes a balance scene learning mechanism (BSLM) for offshore and inshore ship detection in SAR images. BSLM involves three steps: 1) based on unsupervised representation learning, a generative adversarial network (GAN) is used to extract the scene features of SAR images; 2) using these features, a scene binary cluster (offshore/inshore) is conducted by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> -means; and 3) finally, the small cluster’s samples (inshore) are augmented via replication, rotation transformation or noise addition to balance another big cluster (offshore), so as to eliminate scene learning bias and obtain balanced learning representation ability that can enhance learning benefits and improve detection accuracy. This letter applies BSLM to four widely used and open-sourced deep learning detectors, i.e., faster regions-convolutional neural network (Faster R-CNN), Cascade R-CNN, single shot multibox detector (SSD), and RetinaNet, to verify its effectiveness. Experimental results on the open SAR ship detection data set (SSDD) reveal that BSLM can greatly improve detection accuracy, especially for more complex inshore scenes.

Trajectory-Based Scene Understanding Using Dirichlet Process Mixture Model.

Appropriate modeling of a surveillance scene is essential for the detection of anomalies in road traffic. Learning usual paths can provide valuable insight into road traffic conditions and thus can help in identifying unusual routes taken by commuters/vehicles. If usual traffic paths are learned in a nonparametric way, manual interventions in road marking can be avoided. In this paper, we propose an unsupervised and nonparametric method to learn the frequently used paths from the tracks of moving objects in Θ(kn) time, where k denotes the number of paths and n represents the number of tracks. In the proposed method, temporal dependencies of the moving objects are considered to make the clustering meaningful using temporally incremental gravity model (TIGM). In addition, the distance-based scene learning makes it intuitive to estimate the model parameters. Further, we have extended the TIGM hierarchically as a dynamically evolving model (DEM) to represent notable traffic dynamics of a scene. The experimental validation reveals that the proposed method can learn a scene quickly without prior knowledge about the number of paths ( k ). We have compared the results with various state-of-the-art methods. We have also highlighted the advantages of the proposed method over the existing techniques popularly used for designing traffic monitoring applications. It can be used for administrative decision making to control traffic at junctions or crowded places and generate alarm signals, if necessary.

Scene learning: Deep convolutional networks for wind power prediction by embedding turbines into grid space

Wind power prediction is of vital importance in wind power utilization. There have been a lot of researches based on the time series of the wind power or speed, but In fact, these time series cannot express the temporal and spatial changes of wind, which fundamentally hinders the advance of wind power prediction. In this paper, a new kind of feature that can describe the process of temporal and spatial variation is proposed, namely, Spatio-Temporal Features. We first map the data collected at each moment from the wind turbine to the plane to form the state map, namely, the scene, according to the relative positions. The scene time series over a period of time is a multi-channel image, i.e. the Spatio-Temporal Features. Based on the Spatio-Temporal Features, the deep convolutional network is applied to predict the wind power, achieving a far better accuracy than the existing methods. Compared with the starge-of-the-art method, the mean-square error (MSE) in our method is reduced by 49.83%, and the average time cost for training models can be shortened by a factor of more than 150.

Not scene learning, but attentional processing is superior in team sport athletes and action video game players.

We tested if high-level athletes or action video game players have superior context learning skills. Incidental context learning was tested in a spatial contextual cueing paradigm. We found comparable contextual cueing of visual search in repeated displays in high-level amateur handball players, dedicated action video game players and normal controls. In contrast, both handball players and action video game players showed faster search than controls, measured as search time per display item, independent of display repetition. Thus, our data do not indicate superior context learning skills in athletes or action video game players. Rather, both groups showed more efficient visual search in abstract displays that were not related to sport-specific situations.

Enhancing semantic image retrieval with limited labeled examples via deep learning

With the rapid growth of the Internet, a large number of multi-modal objects such as images and their social tags can easily be downloaded from the Web. The use of such objects can improve training process in the presence of few or limited number of labeled images provided. In order to leverage these unlabeled and labeled multi-modal Web objects for enhancing the performance of unimodal image retrieval, we propose a novel approach called Semi-supervised Multi-concept Retrieval to semantic image retrieval via Deep Learning (SMRDL) in this paper. Differing from conventional methods that use multiple and independent concepts in a semantic multi-concept query, our proposed approach regards multiple concepts as a holistic scene for multi-concept scene learning of unimodal retrieval. In particular, we first train a multi-modal Convolutional Neural Network (CNN) as a concept classifier for images and texts, and then use it to annotate unlabeled Web images. For each of unlabeled images, we then obtain its most relevant concept annotations by using a new strategy of annotation promotion. Finally, we employ a unimodal visual CNN to train a concept classifier in visual modality, which uses both unlabeled and labeled examples for concept learning of unimodal retrieval. The results of our comprehensive experiments on two datasets of MIR Flickr 2011 and NUS-WIDE have shown that our proposed approach outperforms several state-of-the-art methods.

Combining Convolutional Neural Network and Markov Random Field for Semantic Image Retrieval

With the rapidly growing number of images over the Internet, efficient scalable semantic image retrieval becomes increasingly important. This paper presents a novel approach for semantic image retrieval by combining Convolutional Neural Network (CNN) and Markov Random Field (MRF). As a key step, image concept detection, that is, automatically recognizing multiple semantic concepts in an unlabeled image, plays an important role in semantic image retrieval. Unlike previous work that uses single-concept classifiers one by one, we detect semantic multiconcept by using a multiconcept scene classifier. In other words, our approach takes multiple concepts as a holistic scene for multiconcept scene learning. Specifically, we first train a CNN as a concept classifier, which further includes two types of classifiers: a single-concept fully connected classifier that is best suited to single-concept detection and a multiconcept scene fully connected classifier that is good for holistic scene detection. Then we propose an MRF-based late fusion approach that is able to effectively learn the semantic correlation between the single-concept classifier and multiconcept scene classifier. Finally, the semantic correlation among the subconcepts of images is cought to further improve detection precision. In order to investigate the feasibility and effectiveness of our proposed approach, we conduct comprehensive experiments on two publicly available image databases. The results show that our proposed approach outperforms several state-of-the-art approaches.

Visual search for changes in scenes creates long-term, incidental memory traces.

Humans are very good at remembering large numbers of scenes over substantial periods of time. But how good are they at remembering changes to scenes? In this study, we tested scene memory and change detection two weeks after initial scene learning. In Experiments 1-3, scenes were learned incidentally during visual search for change. In Experiment 4, observers explicitly memorized scenes. At test, after two weeks observers were asked to discriminate old from new scenes, to recall a change that they had detected in the study phase, or to detect a newly introduced change in the memorization experiment. Next, they performed a change detection task, usually looking for the same change as in the study period. Scene recognition memory was found to be similar in all experiments, regardless of the study task. In Experiment 1, more difficult change detection produced better scene memory. Experiments 2 and 3 supported a "depth-of-processing" account for the effects of initial search and change detection on incidental memory for scenes. Of most interest, change detection was faster during the test phase than during the study phase, even when the observer had no explicit memory of having found that change previously. This result was replicated in two of our three change detection experiments. We conclude that scenes can be encoded incidentally as well as explicitly and that changes in those scenes can leave measurable traces even if they are not explicitly recalled.

Visual search for changes in scenes creates long-term, incidental memory traces

Humans are very good at remembering large numbers of scenes over substantial periods of time. But how good are they at remembering changes to scenes? In this study, we tested scene memory and change detection two weeks after initial scene learning. In Experiments 1-3, scenes were learned incidentally during visual search for change. In Experiment 4, observers explicitly memorized scenes. At test, after two weeks observers were asked to discriminate old from new scenes, to recall a change that they had detected in the study phase, or to detect a newly introduced change in the memorization experiment. Next, they performed a change detection task, usually looking for the same change as in the study period. Scene recognition memory was found to be similar in all experiments, regardless of the study task. In Experiment 1, more difficult change detection produced better scene memory. Experiments 2 and 3 supported a depth-of-processing account for the effects of initial search and change detection on incidental memory for scenes. Of most interest, change detection was faster during the test phase than during the study phase, even when the observer had no explicit memory of having found that change previously. This result was replicated in two of our three change detection experiments. We conclude that scenes can be encoded incidentally as well as explicitly and that changes in those scenes can leave measurable traces even if they are not explicitly recalled.

A novel framework for intelligent surveillance system based on abnormal human activity detection in academic environments

Abnormal activity detection plays a crucial role in surveillance applications, and a surveillance system that can perform robustly in an academic environment has become an urgent need. In this paper, we propose a novel framework for an automatic real-time video-based surveillance system which can simultaneously perform the tracking, semantic scene learning, and abnormality detection in an academic environment. To develop our system, we have divided the work into three phases: preprocessing phase, abnormal human activity detection phase, and content-based image retrieval phase. For motion object detection, we used the temporal-differencing algorithm and then located the motions region using the Gaussian function. Furthermore, the shape model based on OMEGA equation was used as a filter for the detected objects (i.e., human and non-human). For object activities analysis, we evaluated and analyzed the human activities of the detected objects. We classified the human activities into two groups: normal activities and abnormal activities based on the support vector machine. The machine then provides an automatic warning in case of abnormal human activities. It also embeds a method to retrieve the detected object from the database for object recognition and identification using content-based image retrieval. Finally, a software-based simulation using MATLAB was performed and the results of the conducted experiments showed an excellent surveillance system that can simultaneously perform the tracking, semantic scene learning, and abnormality detection in an academic environment with no human intervention.

Scene Learning for Cloud Detection on Remote-Sensing Images

Cloud detection plays a major role for remote-sensing image processing. To accomplish the task, a novel automatic supervised approach based on the “scene-learning” scheme is proposed in this paper. Scene learning aims at training and applying a cloud detector on the whole image scenes. The cloud detector herein is a special classifier that is used to separate clouds from the backgrounds. Concretely, scene learning regards each pixel of scenes in training image as a sample, and uses it to train a cloud detector. Accordingly, the detecting process is also implemented on each pixel of testing image using the trained detector. Generally, scene-learning scheme contains two modules: feature data simulating and cloud detector learning and applying. We first simulate a kind of cubic structural data (also named feature data) by stacking different fundamental image features, including color, statistical information, texture, and structure. Such data synthesize different image features, and it is used for cloud detector training and applying. Cloud detector is designed based on minimizing the residual error between the feature data and its labels. The detector is easy to be trained because of its closed-form. Applying the detector and some necessary cloud refinement methods to the testing images, we could finally detect clouds. We also theoretically analyze the influence of feature number and prove that more features lead to better performance of scene learning under certain circumstance. Comparisons of qualitative and quantitative analyses of the experimental results are implemented. Results indicate the efficacy of the proposed method.

Viewpoint Independence in Implicit Scene Learning Revealed in a Contextual Cueing Paradigm

Viewpoint Independence in Implicit Scene Learning Revealed in a Contextual Cueing Paradigm

Global scene layout modulates contextual learning in change detection

Change in the visual scene often goes unnoticed – a phenomenon referred to as “change blindness.” This study examined whether the hierarchical structure, i.e., the global–local layout of a scene can influence performance in a one-shot change detection paradigm. To this end, natural scenes of a laid breakfast table were presented, and observers were asked to locate the onset of a new local object. Importantly, the global structure of the scene was manipulated by varying the relations among objects in the scene layouts. The very same items were either presented as global-congruent (typical) layouts or as global-incongruent (random) arrangements. Change blindness was less severe for congruent than for incongruent displays, and this congruency benefit increased with the duration of the experiment. These findings show that global layouts are learned, supporting detection of local changes with enhanced efficiency. However, performance was not affected by scene congruency in a subsequent control experiment that required observers to localize a static discontinuity (i.e., an object that was missing from the repeated layouts). Our results thus show that learning of the global layout is particularly linked to the local objects. Taken together, our results reveal an effect of “global precedence” in natural scenes. We suggest that relational properties within the hierarchy of a natural scene are governed, in particular, by global image analysis, reducing change blindness for local objects through scene learning.

Visual Memory in the Process of Scene Perception

It was a key issue how people did get and store information during scene perception, but there were debates whether visual memory existed and affected scene perception. Earlier studies believed that visual representations were impoverished in the process of scene perception, and visual memory systems did not accumulate scene information which had been searched. However, related researches showed that visual memory affected visual searching and scene learning, which indicated visual memory systems played important roles in the scene perception. Future research should focus on information acquisition, the interaction of different visual memory stores in the process of scene perception, as well as explicit and implicit learning for scenes.

Viewpoint Independence in Implicit Scene Learning

Viewpoint Independence in Implicit Scene Learning

A fully online and unsupervised system for large and high-density area surveillance

For reasons of public security, an intelligent surveillance system that can cover a large, crowded public area has become an urgent need. In this article, we propose a novel laser-based system that can simultaneously perform tracking, semantic scene learning, and abnormality detection in a fully online and unsupervised way. Furthermore, these three tasks cooperate with each other in one framework to improve their respective performances. The proposed system has the following key advantages over previous ones: (1) It can cover quite a large area (more than 60×35m), and simultaneously perform robust tracking, semantic scene learning, and abnormality detection in a high-density situation. (2) The overall system can vary with time, incrementally learn the structure of the scene, and perform fully online abnormal activity detection and tracking. This feature makes our system suitable for real-time applications. (3) The surveillance tasks are carried out in a fully unsupervised manner, so that there is no need for manual labeling and the construction of huge training datasets. We successfully apply the proposed system to the JR subway station in Tokyo, and demonstrate that it can cover an area of 60×35m, robustly track more than 150 targets at the same time, and simultaneously perform online semantic scene learning and abnormality detection with no human intervention.

애니메이팅 감각 증진을 위한 신체 서행동작(徐行動作:Slow motion) 체조효과 연구

Many educational facilities have been formed due to the nation`s revival policy in the animation industry since about 1995. Owed to the active financial support of the nation, the production industry rapidly vitalized, production technology rapidly advanced, and a large workforce is being passed into society through educational institutions. The reality of many developing countries appearing to be putting emphasis the industrialization of animation, similar to our country, is becoming a great pressure us industrially. It is never easy to develop a certain field into a globally competitive industry in a short period of time. Our countermeasure, pursuant to these international circumstances, lies in innovation and creativity that has broken away from the existing methods of production, and mass production of high quality animation specialists. This paper is a new educational proposition for the consolidation of national competitiveness. Animating, the core of producing an animation, completely depends the animator`s artistic and technical ability. In order to supplement the existing methods of studying by theory and make up for the biggest weak point, which is the lack of on the scene learning contents, I propose incorporating movements based frequently appearing characters in popular animations and acting them out slowly and including the Slow Motion kinetic effect, a way of enabling someone to learn and sense astrodynamic fundamental principles by oneself. It is a new method of learning movement, a plan made to achieve sensual performance gestures, and an improvement in direction for students who wish to become animators in the future.