Background Update Research Articles

Data-driven background representation method to video surveillance.

Background subtraction is the fundamental step of moving object detection. As current methods use specific data-based or data learning methods to represent background, this will induce the problem of model distortion while the scenarios cannot meet their assumptions or model conditions. A novel data-driven framework is proposed to represent the background using the intrinsic characteristics of the background. In the framework, the model-free adaptive control method is used as an instance to analyze the background by its status of the nearest time instants, and linearize them dynamically from a pure data perspective. To overcome the occlusion of foreground objects, the selective update method is employed to satisfy the background update. Experiments are carried out under different video conditions to compare algorithm performance with state-of-the-art background models. The results show that the proposed method has reached over 95% in F-measure and percentage of correct classification in most cases, which is better than other state-of-the-art methods. Furthermore, the proposed method shows better robustness in severe video conditions, including bad weather and night cases, and its simplified data-driven control laws make it suitable for outdoor video surveillance.

High-resolution model building with multistage full-waveform inversion for narrow-azimuth acquisition data

Full-waveform inversion (FWI) is an attractive tool for high-resolution velocity-model building without a high-frequency assumption compared to conventional reflection tomography. However, there are two main challenges to the application of FWI on narrow-azimuth acquisition (NAZ) data: cycle skipping and acquisition footprints. Here, a multistage FWI is proposed to build a high-resolution model for NAZ data. It is well known that FWI may suffer from a cycle-skipping problem when the starting model is not close enough to the true solution. To mitigate this problem, we introduce dynamic-warping preconditioned full-waveform inversion (DWFWI) as the first stage of the velocity inversion. DWFWI iteratively preconditions the observed early arrivals through dynamic warping to avoid cycle skipping in the model, which allows large-scale background updates. The second stage of our workflow is the conventional FWI with image-guided smoothing (IGFWI). On top of DWFWI, more reflection events are included and inverted through the conventional L2-norm FWI, which can add more detailed updates to the velocity model with much higher resolution. Due to poor crossline sampling, there are strong acquisition footprints on FWI updates in the crossline direction. Image-guided smoothing is used to reduce the acquisition footprints in the FWI gradient as well as to preserve the detailed update around the faults. It is then followed by an additional tomography to update the deep portion. This approach was applied on the Hoop Fault Complex data in the southwestern Barents Sea. The results show that a more geologically realistic and higher-resolution model of the Hoop Fault Complex was obtained, and the migration image and gathers were significantly improved.

Assimilation of thermospheric measurements for ionosphere‐thermosphere state estimation

AbstractWe develop a method that uses data assimilation to estimate ionospheric‐thermospheric (IT) states during midlatitude nighttime storm conditions. The algorithm Estimating Model Parameters from Ionospheric Reverse Engineering (EMPIRE) uses time‐varying electron densities in the F region, derived primarily from total electron content data, to estimate two drivers of the IT: neutral winds and electric potential. A Kalman filter is used to update background models based on ingested plasma densities and neutral wind measurements. This is the first time a Kalman filtering technique is used with the EMPIRE algorithm and the first time neutral wind measurements from 630.0 nm Fabry‐Perot interferometers (FPIs) are ingested to improve estimates of storm time ion drifts and neutral winds. The effects of assimilating remotely sensed neutral winds from FPI observations are studied by comparing results of ingesting: electron densities (N) only, N plus half the measurements from a single FPI, and then N plus all of the FPI data. While estimates of ion drifts and neutral winds based on N give estimates similar to the background models, this study's results show that ingestion of the FPI data can significantly change neutral wind and ion drift estimation away from background models. In particular, once neutral winds are ingested, estimated neutral winds agree more with validation wind data, and estimated ion drifts in the magnetic field‐parallel direction are more sensitive to ingestion than the field‐perpendicular zonal and meridional directions. Also, data assimilation with FPI measurements helps provide insight into the effects of contamination on 630.0 nm emissions experienced during geomagnetic storms.

Cisgenesis and intragenesis in microalgae: promising advancements towards sustainable metabolites production.

Microalgae are an economically important source of biomolecules and metabolites that can be exploited as feed, nutraceuticals and, potentially, as biofuels, among other biotechnological applications. Microalgae biotechnology involves both culture and metabolic pathways manipulation to obtain high-value products, such as omega-3 fatty acids and carotenoids. However, the introduction of genes and/or foreign regulatory sequences has caused public concern about the effect of genetically modified microalgae to achieve greater secondary metabolite accumulations. To placate these worries, we have focused on two cutting-edge concepts, cisgenesis and intragenesis in order to sustainably produce commercially relevant metabolites. This review provides updated background on current and future uses for microalgae molecular farming. We also discuss the development of genetic tools used in terrestrial plants to obtain genetically modified microalgae free of foreign DNA by means of (i) site-specific mutations, (ii) excision of selectable markers, (iii) zinc-finger nuclease and transcription activator-like effectors, and (iv) CRISPR/Cas9 systems. It is currently important to consider scientific debate not only from a technological standpoint but also in terms of conceptual, socioeconomic, ethical, and legal aspects.

A novel infrared moving target detection algorithm based on multiscale codebook model

Traditional target detection algorithm based on codebook model only use pixel information of video image while spatial scale information of image is ignored, so the detection result usually has high false detection rate and the target’s characteristics is not obvious. To overcome this difficulty, a novel infrared (IR) moving target detection algorithm based on multiscale codebook model is presented in this paper. The main principle of this algorithm is to make full use of image pixel information and scale information for moving target detection. First, by Gauss pyramid image hierarchical model, the IR video is stratified into three layers, namely the original layer, the second layer and the top layer. Second, background codebook model is built for each layer image, the main feature information is discovered to update background codebook models, and then moving target in IR video is detected according to the updated background model. Finally, the fusion operation is done on detection results of three layers to get the final detection result. Compared with traditional detection algorithm based on codebook model, this IR target detection algorithm combines image pixel information and scale characteristics. By using this novel algorithm, the experiments on some real world IR images are performed. The whole algorithm implementing processes and results are analyzed, and this novel detection algorithm is evaluated from the two aspects: subjective evaluation and objective evaluation. From the experiment results, we can see that the proposed method has better detection effects, richer target information and lower false detection rate.

DETERMINANTS OF REAL EXCHANGE RATE IN ETHIOPIA

Real exchange rate has direct effects on trade particularly on international trade and has indirect effects on productions and employments, so it is crucial to understand the factors which determine its variations. This study analyses the main determinants of the real exchange rate and the dynamic adjustment of the real exchange rate following shocks to those determinants using yearly Ethiopian time series data covering the period 1971 to 2010. It begins with a review of literatures on Exchange rate, real exchange rate, determinants of the real exchange rate and provides an updated background on the exchange rate system in Ethiopia. An empirical model linking the real exchange rate to its theoretical determinants is then specified. This study had employed the cointegration and vector autoregression (VAR) analysis with impulse response and variance decomposition analyses to provide robust long run effects and short run dynamic effects on the real exchange rate.
 Share of investment, foreign exchange reserve, capital inflow and government consumption of non-tradable goods were the variable that have been found to have a long run relationship with the real exchange rate. The estimate of the speed of adjustment coefficient found in this study indicates that about a third of the variation in the real exchange rate from its equilibrium level is corrected within a year.
 The regression result of VECM reveals that terms of trade, nominal exchange rate, and one period lag of capital flow were the variables significantly affects the real exchange rate in the short run. However, the impulse response and variance decomposition analysis shows a better picture of the short run dynamics. The their analysis provided evidence that the Shocks to terms of trade, nominal exchange rate, capital inflow and share of investment have persistent effects on the real exchange rate in the short run. In general the regression results of both long run and short run models mostly suggest that the fluctuations of real exchange rates are predominantly responses to monetary policies shocks rather than fiscal policy shocks.

Extension of Cellular Automata for Dynamic Vehicle Tracking

Detecting and tracking moving vehicles in real-time traffic scenes are an emerging research area for intelligent transportation systems. This paper presents the computational model of Fuzzy Cellular Automata (FCA) to address the susceptible to environmental changes’ problem associated with the background subtraction methods for dynamic vehicle tracking. The suggested model deploys FCA that is configured with rules supporting least sensitive fuzzy “Exclusive or” function as next state logic to handle degrees of uncertainty in rule similarly operations. Indeed, at each step, the update of background in frame difference approaches is determined according to the number of active cells and fuzzy mapping function; so moving vehicles that their gray level is entirely similar to the background gray level are simply detected. Furthermore, an occlusion handling technique based on visual measurement is employed to detect the classes of the vehicle occlusions and segment the vehicle from each occlusive class. The experimental results show that the suggested method is more robust, accurate and powerful than traditional methods, for real-time vehicle detection and tracking.

Two‐dimension principal component analysis‐based motion detection framework with subspace update of background

Object detection plays a critical role for automatic video analysis in many vision applications. Background subtraction has been the mainstream in the field of moving objects detection. However, most of state‐of‐the‐art techniques of background subtraction operate on each pixel independently ignoring the global features of images. A motion detection method based on subspace update of background is proposed in this study. This method uses a subspace spanned by the principal components of background sequence to characterise the background and integrates the regional continuity of objects to segment the foreground. To deal with changes in the background geometry, a learning factor is introduced into the authors’ model to update the subspace timely. Additionally, to reduce computational complexity, they use two‐dimension principal component analysis (PCA) rather than traditional PCA to obtain the principal components of background. Experiments demonstrate that the update policy is effective and in most cases this proposed method can achieve better results than others compared in this study.

A time-slice optimization based weak feature association algorithm for video condensation

There are a lot of complex environments in real scene, such as illumination variation, shadow variation, object occlusion, which will directly affect the performance of video synopsis. In this paper, we adopt Grid Background Model as object detection algorithm, proposing algorithm based on weak feature to solve the object occlusion problem, at last we propose to use time-slice optimization algorithm to solve the visualization problem of video condensation. Specifically, Grid Background Model is adopted to segment the foreground from the background, then we use current frame to update background frame, and then binarize the foreground frame to perform Neighborhood illumination invariant shadow elimination. A clear foreground can be obtained by doing the procedure above as well as Gaussian noise elimination and morphological operation such as inflation and corrosion to remove cavities. Meanwhile, the outline of the object is extracted by using the canny edge detector. In the object tracking section, we will introduce how to use the weak features, such as color, speed and direction on the basis of location prediction based on tracking algorithm to perform object association, and the extraction of accurate information of abstract and outline of the object at the same time. Finally, in the video condensation section, we will describe how to use optical time-slice based minimum energy model to perform video condensation according to frame sequence. The experimental result shows that, the method mentioned above can provide a new approach for solving the occlusion problems of video condensation, and have better visualization of abstract video, and achieve up to 6 times concentration to the original video.

Hardware Design of Moving Object Detection on Reconfigurable System

Moving object detection including background subtraction and morphological processing is a critical research topic for video surveillance because of its high computational loading and power consumption. This paper proposes a hardware design to accelerate the computation of background subtraction with low power consumption. A real-time background subtraction method is designed with a frame-buffer scheme and function partition to improve throughput, and implemented using Verilog HDL on FPGA. The design parallelizes the computations of background update and subtraction with a seven-stage pipeline. A stripe-based morphological processing and accounting for the completion of detected objects is devised. Simulation results for videos of VGA resolutions on a low-end FPGA device show 368 fps throughput for only the real-time background subtraction module, and 51 fps for the whole system, including off-chip memory access. Real-time efficiency with low power consumption and low resource utilization is thus demonstrated.

On the evolutionary advantage of coagulation factor V Leiden (FVL).

Carriership of coagulation factor V Leiden (FVL) is by far the most common thrombophilia in Western populations. FVL is caused by a single point mutation in the gene coding for coagulation factor V (FV) causing a lifelong procoagulatory state with an increased risk of venous thromboembolism (VTE) which might be fatal. It is believed that the mutation occurred in one person 21,000 years ago and today 3% to 15% of the Western populations are carriers. A potentially dangerous mutation such as FVL ought to be rare and should have been reduced, if not eradicated, by selection during the course of human evolution. Thus, FVL must confer the carriers with an evolutionary advantage in order to be so prevalent. Lower risk of profuse bleeding and increased fecundity might give carriers an advantage. In this paper we give an updated short background and discuss possible evolutionary advantages and disadvantages.

Research on Background Extraction of Dynamic Video

As for heavy traffic, road congestion and the hard extraction of vehicles in dynamic video, an improved method of dynamic video background updating is proposed. By using frame-to-frame differences and mask technology, the hole of difference image is eliminated, then extracts the reliably initial background. The image is segmented by using double threshold based on the combination of Bacterial Foraging Optimization Algorithm and Otsu Algorithm to improve the effect and reliability of background updating. Experiments shows that it is an effective way that is good in speed and effective in background extraction, and provides a good foundation for further study of the vehicle tracking.

Early Fire Smoke Image Segmentation in a Complex Large Space

Aiming at the problem that the fire smoke image segmentation algorithm cannot obtain integral smoke information, the adaptive background updating smoke foreground object extraction algorithm based on block segmentation is proposed. According to the characteristics that the smoke internal pixels continuously roll in the heat of the driver and the pixel concentration from near the fire source to edge decreases in turn, the method for different blocks using different difference threshold is adopted to ensure the integrity of the extracted foreground target. Under the difference between the current frame and the background frame, block difference thresholds are updated to let the differential threshold adjustment with continuous adaptive monitoring. In the new weighted average updated background image corrected by the original background image, the interference suspicious target edge pixels are removed. Simulation experimental results show that the method is able to extract more complete information of smoke in a suspected area of the edge, and eliminate the interference of light and pedestrian in complex space.

Binary Descriptor Based Nonparametric Background Modeling for Foreground Extraction by Using Detection Theory

Recently, most background modeling approaches represent distributions of background changes by using parametric models such as Gaussian mixture models. Because of significant illumination changes and dynamic moving backgrounds with time, variations of background changes are hard to be modeled by parametric background models. Moreover, how to efficiently and effectively update parameters of parametric models to reflect background changes remains a problem. In this paper, we propose a novel coarse-to-fine detection theory algorithm to extract foreground objects on the basis of nonparametric background and foreground models represented by binary descriptors. We update background and foreground models by a first-in–first-out strategy to maintain the most recent observed background and foreground instances. As shown in the experiments, our method can achieve better foreground extraction results and fewer false alarms of surveillance videos with lighting changes and dynamic backgrounds in both collected and CDnet 2012 benchmark data sets.

LMS algorithm을 이용한 배경분리 알고리즘 구현 및 성능 비교에 관한 연구

Recently, with the rapid advancement in information and comput er vision technology, a CCTV system using object rec- ognition and tracking has been studied in a variety of fields. However, it is difficult to recognize a precise object outdoors due to varying pixel values by moving background elements such as shadows, lighting change, and moving elements of the scene. In order to adapt the background outdoors, this paper presents to analyze a variety of background models and proposed background update algorithms based on the weight factor. The experimental results show that the accuracy of object detection is maintained, and the number of misrecognized objects are reduced compared to previous study by using the proposed algorithm.

Vehicle Detection Research Based on USILTP Operator

This paper presents a uniform SILTP operator based on the SILTP operator. In the vehicle detection, SILTP can solve the problems caused by the change of sunshine, the shadow of vehicle and the noise in the surrounding environment. But the algorithm has high dimensionality which can lead to error because of the deviation of the texture characteristics. The USILTP operator can reduce the dimensionality of the detection data which adapts to the problems caused by illumination variations and the noise in the surrounding environment. First, the method uses the SILTP operator to extract the vehicle image texture characteristics and reduce the dimensionality of the detection data, and then it uses the Gauss mixture model to do background modeling, and uses the texture characteristics of the new image to update background dynamically. At last, it gets the vehicle by contracting with the background model. It has been proved that this detection algorithm has a good performance with the test of the vehicle on public roads.

Extracting Foreground Based on Codebook for Early Forest Smoke Video

Shaking leaves has been the biggest interference for early forest smoke video detection. Moving average method, Gaussian mixture method and its improved methods are often used to update background, but the performance is not good through background subtraction. Codebook algorithm is applied to extract foreground for early forest smoke detection, quantization techniques are used to obtain background model from time series, then getting foreground image through background subtraction. Through multiple video tests, the experimental results that the filtering performance, anti-noise performance and accuracy are better than other methods above.

An Improved Background Update Algorithm and Application in Traffic Engineering

The statistical histogram algorithm is one of the common background update algorithms. Considering the statistical histogram algorithm disadvantages of large complex computation, the paper proposes an improved method named fixed window statistical background updating algorithm. The algorithm sets a window which contains N records for each pixel point firstly, every record records value in the permissible range of error and the number of pixel point occurrence, and then counting pixel values for every record through statistical histogram algorithm. When the window is full, the new pixel values will replace the smaller counting, while the pixel which counting larger will be adaptively updated by adaptive background updating formula. The experimental result shows that this method has a high real-time performance and robustness in background updating.

Hybrid multi-resolution detection of moving targets in infrared imagery

A hybrid moving target detection approach in multi-resolution framework for thermal infrared imagery is presented. Background subtraction and optical flow methods are widely used to detect moving targets. However, each method has some pros and cons which limits the performance. Conventional background subtraction is affected by dynamic noise and partial extraction of targets. Fast independent component analysis based background subtraction is efficient for target detection in infrared image sequences; however the noise increases for small targets. Well known motion detection method is optical flow. Still the method produces partial detection for low textured images and also computationally expensive due to gradient calculation for each pixel location. The synergistic approach of conventional background subtraction, fast independent component analysis and optical flow methods at different resolutions provide promising detection of targets with reduced time complexity. The dynamic background noise is compensated by the background update. The methodology is validated with benchmark infrared image datasets as well as experimentally generated infrared image sequences of moving targets in the field under various conditions of varying illumination, ambience temperature and the distance of the target from the sensor location. The significant value of F-measure validates the efficiency of the proposed methodology with high confidence of detection and low false alarms.

An Improved Moving Object Detection Algorithm Based on Colour Separation

An improved background subtraction algorithm based on color separation method is improved to solve the problem of high rate of missing detection of moving targets in video surveillance. First, the algorithm implements the background subtraction of the current frame and the background frame for pixel blocks in independent RGB channels. Then the three foreground targets after denoising extracted respectively from three channels are combined by or operation to get a complete moving target. And then this algorithm removes the shadow in color model. After that the background frame from each channel is updated individually by recursive algorithm. The algorithm adopts a nonlinear way to change the learning factor for background updating. The experiments show that this improved algorithm can extract effectively foreground targets which are similar to the background’s grey level, with better accuracy and robustness.