Dynamic Background Conditions Research Articles

Numerical simulation of fault activity in the Qilian tectonic belt and dynamic background of Menyuan earthquake series

Some faults in the Qilian tectonic belt are seismogenic areas for strong earthquakes, including the western section of the Lenglongling fault, which frequently occures moderate-strong Menyuan earthquakes. In this study, using GPS velocity data of 1991–2015 as the boundary constraints, a three-dimensional viscoelastic finite element dynamic model is constructed by comprehensively considering the regional dynamic environment, crust-mantle transverse-longitudinal inhomogeneity, and spatial spreading of a complex fault system. The objective is to investigate the long-period characteristics of fault movement and stress change in the Qilian tectonic belt caused by tectonic loading, and to discuss the seismogenic conditions of the Menyuan earthquakes. The results show that the annual change of long-period movement and stress of the major faults in the Qilian Mountain tectonic zone are characterized by significant segmentation. Due to its unique geometric bend morphology, the western section of Lenglongling fault has a low movement rate, significant slip deficit and high shear stress accumulation, which are conducive to the gestation and occurrence of earthquakes. Furthermore, the seismogenic area of the Menyuan earthquake series is jointly subjected to NE-SW compressive and NW-SE tensile stress fields, and the maximum shear stress and elastic strain energy accumulate faster than in the surrounding areas. Overall, the western section of the Lenglongling fault has a strong dynamic background and favorable conditions for the frequent occurrence of the Menyuan earthquake series.

Moving object detection in dynamic background

The application of RPCA model in moving object detection can accurately extract the moving foreground, but the effect of the model is not ideal under complex dynamic background conditions. Based on this, this paper proposes an improved RPCA model based on rank–1 regulation and 3D-TV. The improved model uses regulation term to describe the low rank of video background, 3D-TV to constrain the spatiotemporal continuity of moving objects, and F-norm to eliminate the dynamic interference in video background. The experimental results show that the improved model proposed in this paper can effectively deal with the complex dynamic background and obtain a complete foreground object.

Intraseasonal Variability of the East Asia-Pacific Teleconnection and Its Impacts on Multiple Tropical Cyclone Genesis Over the Western North Pacific

A daily East Asia–Pacific teleconnection (EAP) index was constructed to investigate the impact of the intraseasonal variability (ISV) of this index on the genesis of multiple tropical cyclones (MTC) in boreal summer over the western North Pacific (WNP). The result indicates that the EAP index has dominant intraseasonal periods of 10–20 days, 20–40 days and 50–70 days, respectively. The ISV of the EAP during 1979–2019 can be classified into three types, a single-period-domination type (37%), a multiple period coexistence type (24%) and a transition type (39%). It is found that during El Niño (La Niña) summers, the ISV of the EAP is dominated by a higher-frequency (lower-frequency) oscillation with a period of around 20–30 (50–70) days. The distinctive ISV characteristics during the different ENSO years were accompanied with different dynamic and thermodynamic background conditions over the WNP and the South China Sea, which modulated the frequency and location of MTC genesis. By examining the relative contributions of individual environmental variables of the Genesis Potential Index, we found that the low-level absolute vorticity and mid-level relative humidity are two important environmental factors modulating MTC genesis. However, the relative role of these variables tends to change with the EAP ISV phase. The environmental condition over the SCS appears less influenced by ENSO. A more southern location of MTC genesis during El Niño is attributed to the change of the environmental humidity.

Distinctly Trained Multi-Source CNN for Multi-Camera Based Vehicle Tracking System

In the last few years the exponential rise in the demands or robust surveillance systems have revitalized academia-industries to achieve more efficient vision based computing systems. Vision based computing methods have been found potential for the different surveillance purposes such as Intelligent Transport System (ITS), civil surveillance, defense and other public-private establishment security. However, computational complexities turn-out to be more complicate for ITS under occlusion where multiple cameras could be synchronized together to track certain target vehicle. Classical texture, color based approaches are confined and often leads false positive outcome thus impacting decision making efficiency. Considering this as motivation, in this paper a highly robust and novel Distinctly Trained Multi-Source Convolutional Neural Network (DCNN) has been developed that exhibits pre-training of the real-time traffic videos from multiple cameras to track certain targeted vehicle. Our proposed DCNNvehicle tracking model encompasses multiple shared layers with multiple branchesof the source-specific layers. In other words, DCNN is implemented on each camera or source where it performs feature learning and enables a set of features shared by each camera, which is then learnt to identify Region of Interest (ROI) signifying the “targeted vehicle”. Our proposed DCNNmodel trains each source input iteratively to achieve ROI representations in the shared layers. To perform tracking in a new sequence, DCNNforms a new network by combining the shared layers in the pre-trained DCNN with a new binary classification layer, which is updated online. This process enables online tracking by retrieving the ROI windows arbitrarily sampled near the previous ROI state. It helps achieving real-time vehicle tracking even under occlusion and dynamic background conditions.

Moving Object Localization in Video Sequences under Static and Dynamic Background Conditions

Moving Object Localization in Video Sequences under Static and Dynamic Background Conditions

Interval-Valued Model Level Fuzzy Aggregation-Based Background Subtraction.

In a recent work, the effectiveness of neighborhood supported model level fuzzy aggregation was shown under dynamic background conditions. The multi-feature fuzzy aggregation used in that approach uses real fuzzy similarity values, and is robust for low and medium-scale dynamic background conditions such as swaying vegetation, sprinkling water, etc. The technique, however, exhibited some limitations under heavily dynamic background conditions, as features have high uncertainty under such noisy conditions and these uncertainties were not captured by real fuzzy similarity values. Our proposed algorithm is particularly focused toward improving the detection under heavy dynamic background conditions by modeling uncertainties in the data by interval-valued fuzzy set. In this paper, real-valued fuzzy aggregation has been extended to interval-valued fuzzy aggregation by considering uncertainties over real similarity values. We build up a procedure to calculate the uncertainty that varies for each feature, at each pixel, and at each time instant. We adaptively determine membership values at each pixel by the Gaussian of uncertainty value instead of fixed membership values used in recent fuzzy approaches, thereby, giving importance to a feature based on its uncertainty. Interval-valued Choquet integral is evaluated using interval similarity values and the membership values in order to calculate interval-valued fuzzy similarity between model and current. Adequate qualitative and quantitative studies are carried out to illustrate the effectiveness of the proposed method in mitigating heavily dynamic background situations as compared to state-of-the-art.

Acoustic adaptation to dynamic background conditions with asynchronous transformations

This paper proposes a framework for performing adaptation to complex and non-stationary background conditions in Automatic Speech Recognition (ASR) by means of asynchronous Constrained Maximum Likelihood Linear Regression (aCMLLR) transforms and asynchronous Noise Adaptive Training (aNAT). The proposed method aims to apply the feature transform that best compensates the background for every input frame. The implementation is done with a new Hidden Markov Model (HMM) topology that expands the usual left-to-right HMM into parallel branches adapted to different background conditions and permits transitions among them. Using this, the proposed adaptation does not require ground truth or previous knowledge about the background in each frame as it aims to maximise the overall log-likelihood of the decoded utterance. The proposed aCMLLR transforms can be further improved by retraining models in an aNAT fashion and by using speaker-based MLLR transforms in cascade for an efficient modelling of background effects and speaker. An initial evaluation in a modified version of the WSJCAM0 corpus incorporating 7 different background conditions provides a benchmark in which to evaluate the use of aCMLLR transforms. A relative reduction of 40.5% in Word Error Rate (WER) was achieved by the combined use of aCMLLR and MLLR in cascade. Finally, this selection of techniques was applied in the transcription of multi-genre media broadcasts, where the use of aNAT training, aCMLLR transforms and MLLR transforms provided a relative improvement of 2–3%.

Video object extraction and its tracking using background subtraction in complex environments

Summary Background subtraction is an efficient way to localize and obtain the centroid of the connected pixels moving on the foreground despite the prior information of the scene. It is suitable under fixed camera arrangement, which incorporates many vision applications such as object tracking, human monitoring, etc. However, the moving object extraction task becomes sophisticated and challenging due to some annoying factors such as local motion in background (waving tree, rippling water, etc.), camouflage region, sleeping object, which in turn degrades the tracking performance. In order to alleviate these problems, an efficient background subtraction algorithm is proposed to support the object-tracking task under static and dynamic background conditions. The work is focus to realize the relevant moving blobs on foreground by aiding the proper initialization and updating of the background module in order to improve the tracking accuracy. It generates an initial motion field using spatial-temporal filtering on the consecutive video frames. The block-wise entropy is evaluated above a certain range of the pixels of the difference image in order to extract the relevant moving pixels from the initial motion field. A suitable threshold value is estimated to assign an appropriate label to the moving blobs on the foreground mask. Finally, an adapting Kalman filter is integrated to the object extraction module in order to track the object on the foreground. Extensive quantitative experiments prove that the proposed method competently handles the object extraction, which in turn improves the tracking task under static and dynamic background conditions.

Statistical background model-based target detection

This paper proposes a statistical background modeling framework to deal with the issue of target detection, where the global and local information is utilized to achieve more accurate detection of moving objects. Specifically, for the target detection problem under illumination change conditions, a novel self-adaptive Gaussian mixture model mixed with the global information is utilized to construct a statistical background model to detect moving objects; for the target detection problem under dynamic background conditions, the self-tuning spectral clustering method is first utilized to cluster background images, and then the kernel density estimation method mixed with the local information is utilized to construct a statistical background model to detect moving objects. Experimental results demonstrate that the proposed framework can improve the detection performance under illumination change conditions or dynamic background conditions.

An Optimized Framework for Detection and Tracking of Video Objects in Challenging Backgrounds

Segmentation and tracking are two important aspects in visual surveillance systems. Many barriers such as cluttered background, camera movements, and occlusion make the robust detection and tracking a difficult problem, especially in case of multiple moving objects. Object detection in the presence of camera noise and with variable or unfavourable luminance conditions is still an active area of research. This paper propose a framework which can effectively detect the moving objects and track them despite of occlusion and a priori knowledge of objects in the scene. The segmentation step uses a robust threshold decision algorithm which uses a multi-background model. The video object tracking is able to track multiple objects along with their trajectories based on Continuous Energy Minimization. In this work, an effective formulation of multi-target tracking as minimization of a continuous energy is combined with multibackground registration. Apart from the recent approaches, it focus on making use of an energy that corresponds to a more complete representation of the problem, rather than one that is amenable to global optimization. Besides the image evidence, the energy function considers physical constraints, such as target dynamics, mutual exclusion, and track persistence. The proposed tracking framework is able to track multiple objects despite of occlusions under dynamic background conditions.

Neighborhood Supported Model Level Fuzzy Aggregation for Moving Object Segmentation

We propose a new algorithm for moving object detection in the presence of challenging dynamic background conditions. We use a set of fuzzy aggregated multifeature similarity measures applied on multiple models corresponding to multimodal backgrounds. The algorithm is enriched with a neighborhood-supported model initialization strategy for faster convergence. A model level fuzzy aggregation measure driven background model maintenance ensures more robustness. Similarity functions are evaluated between the corresponding elements of the current feature vector and the model feature vectors. Concepts from Sugeno and Choquet integrals are incorporated in our algorithm to compute fuzzy similarities from the ordered similarity function values for each model. Model updating and the foreground/background classification decision is based on the set of fuzzy integrals. Our proposed algorithm is shown to outperform other multi-model background subtraction algorithms. The proposed approach completely avoids explicit offline training to initialize background model and can be initialized with moving objects also. The feature space uses a combination of intensity and statistical texture features for better object localization and robustness. Our qualitative and quantitative studies illustrate the mitigation of varieties of challenging situations by our approach.

Generating and Using Data of Higher Dimension for Gas-Phase Chemical Sensing

Methods to acquire and analyze rich data streams from sensors are helpful, if not required, to track chemical components within complex gas-phase environments. We describe a MEMS-based microsensor technology that populates multi-element arrays with multiple sensing materials and also cycles the temperatures of the elements as a function of time. Various processing methods have been applied to the resulting databases in order to recognize and classify target analytes in dynamic background conditions.