Background Subtraction Method Research Articles

Fast approach for moving vehicle localization and bounding box estimation in highway traffic videos

Detection and accurate localization of position of moving vehicles in a video sequence are the primary tasks in every computer vision-based traffic monitoring system. In this paper, a moving vehicle localization and bounding box estimation algorithm is proposed. The moving vehicle foreground is separated from the static background by the adaptive background subtraction method, and the bounding box of moving vehicles is estimated with two-dimensional binary histogram projection profile (2D-BHPP) algorithm. The foreground object refinement is performed by means of morphological closing operation prior to apply the 2D-BHPP algorithm. The proposed method only computes the four necessary minimum bounding box coordinates, i.e., left, right, upper, and lower of moving vehicles in every frame. The proposed method is tested over three publicly available data sets, and the results show that the localization algorithm works comparatively faster and accurately than the existing localization methods. The detection error rate, IoU metric, and execution time per frame signify that this approach can be implemented in edge-based real-time applications.

Establishment of a comprehensive analysis method for the microfaunal movement in activated sludge.

Microfaunal identification and analysis are very complex; thus, an image analysis method was utilized in this paper to overcome the shortcomings of using the number, dominant species, and diversity of population structure of microfauna as activated sludge indicators. Based on a classification of microfaunal movement, the quantitative processing and analysis of the micro-video frame image of microfaunal movement were carried out by using the Image J software. Background subtraction method was utilized to detect target microfauna by matching target area features to track microfaunal movement. Three parameters, namely, motion trajectory (L), consecutive frame of motion paths (Si), and average change rate of extent [Formula: see text], were selected to represent the motion trajectory and mass center of microfauna. Four motion-velocity parameters, namely, the left and right rotation angles of adjacent frames (∆αi), instantaneous velocity (Vi), average linear velocity ([Formula: see text]), and average angular velocity ([Formula: see text]), were selected to characterize the movement modes of microfauna. Finally, a motion analysis method based on the Image J software was established to demonstrate the different motion modes of microfauna in activated sludge. This study provides a methodological foundation for the establishment of a new method of microfauna as indicator. Based on this method, the correlation between the microfaunal motion velocity and activated sludge flocs was analyzed.

基于背景扣除法消除土壤基底中Al元素干扰的LIBS实验研究

基于背景扣除法消除土壤基底中Al元素干扰的LIBS实验研究

基于背景扣除法消除土壤基底中Al元素干扰的LIBS实验研究

基于背景扣除法消除土壤基底中Al元素干扰的LIBS实验研究

Communication—A Simple Empirical Method for Determination of CuOOH/CuO Redox Couple in Electrochemical Nonenzymatic Glucose Sensing

In this work, we introduced a model of glucose reaction at the electrode and determined the reduction potential of CuOOH/CuO redox couple at CuO nanowires/ITO electrode (CNIE) via an empirical study. The cyclic voltage scanning of CNIE to glucose in different concentrations of NaOH electrolyte solution was conducted using the background subtraction (BS-CV) method. By interpolating the glucose concentration to zero based on the curve of glucose concentration versus oxidation potential in different pH media of NaOH, the standard electrode potential of the CuOOH/CuO redox couple was calculated to be +0.433 (V vs SHE).

Touch-Point Detection Using Thermal Video With Applications to Prevent Indirect Virus Spread.

Viral and bacterial pathogens can be transmitted through direct contact with contaminated surfaces. Efficient decontamination of contaminated surfaces could lead to decreased disease transmission, if optimized methods for detecting contaminated surfaces can be developed. Here we describe such a method whereby thermal tracking technology is utilized to detect thermal signatures incurred by surfaces through direct contact. This is applicable in public places to assist with targeted sanitation and cleaning efforts to potentially reduce chance of disease transmission. In this study, we refer to the touched region of the surface as a “touch-point” and examine how the touch-point regions can be automatically localized with a computer vision pipeline of a thermal image sequence. The pipeline mainly comprises two components: a single-frame and a multi-frame analysis. The single-frame analysis consists of a Background subtraction method for image pre-processing and a U-net deep learning model for segmenting the touch-point regions. The multi-frame analysis performs a summation of the outputs from the single-frame analysis and creates a cumulative map of touch-points. Results show that the touch-point detection pipeline can achieve 75.0% precision and 81.5% F1-score for the testing experiments of predicting the touch-point regions. This preliminary study shows potential applications of preventing indirect pathogen spread in public spaces and improving the efficiency of cleaning sanitation.

Fuzzy model based on local injection of MTX combined with traditional Chinese medicine guided by ultrasound intervention to treat CSP

In view of pregnancy at the uterine scar after cesarean section, there is an urgent need to find a conservative treatment mode with drugs that can improve the success rate of treatment, shorten the conservative treatment time, and cause little harm to the body. This research combines ultrasound intervention technology to construct a fuzzy model to comprehensively evaluate the clinical effects of traditional Chinese medicine combined with western medicine in the treatment of CSP. Moreover, this research combines the current application algorithms of machine vision to explain the relevant principles of ultrasound interventional vision. In addition, this research uses the background subtraction method to extract the target, and uses the machine vision algorithm to extract the ultrasonic detection target object. Finally, this research adjusts the control parameters according to the fuzzy control, and outputs the optimal control plan with BP network training. The results of this study show that the combination of Chinese and Western medicines in the treatment of uterine scars after cesarean section has the advantages of small gestational sacs, short pregnancy, and low blood β-HCG, and it has the advantages of less pain, economy, fewer side effects, and successfully preserves the uterus. Therefore, it is worthy of clinical application.

Morse Code Receiver On Invisible Light Using Background Subtraction Method

Morse code is a system of representation of letters, numbers, punctuation marks and signals using a code of dots and lines that are arranged to represent certain characters in the alphabet or certain signals (signs) that are agreed upon for use throughout the world was studied by nilas[1]. This code was coined by Samuel F.B. Morse and Alfred Vail in 1835 was studied by ming[2]. This research aims at how to apply the Background Subtraction method in the design of the morse sign language receiver in the invisible light. Build an Android-based application for recognition of Morse sign language by keeping messages sent using Morse sign language secret through infrared light from the sight of those who can read the message. From the results of the tests that have been carried out, it is concluded that the level of accuracy of testing using the False Match Rate (FMR) obtained a success percentage of 65% from the 26 character data tested. From the 26 character data tested, it was obtained data with the number of characters that were successfully counted correctly, namely 17 characters, while the character data that failed to be counted was 9 characters with a detection result of 26 characters.

WITHDRAWN: Enhanced key frame identification and background subtraction methods for automatic license plate recognition of motorcyclists without helmets

With the increasing number of cameras available in the cities, there is an increasing interest in recognizing license plate of two wheelers riders who do not wear helmet. This can be performed in four stages, background modeling, vehicle detection, helmet detection and automatic license plate recognition. This work is focused on the background modeling to extract foreground objects from its background. In this work, a 2-step method is proposed. The first step proposes and uses a key frame identification algorithm to extract a set of optimal frames. The background subtraction is then performed on these frames in the second step. A discrete wavelet packet transformation based method is used to separate background and foreground objects. Experimental results prove that the proposed algorithm is more effective when compared with the existing approaches.

An Improved Near-Field Computer Vision for Jet Trajectory Falling Position Prediction of Intelligent Fire Robot.

An improved Near-Field Computer Vision (NFCV) system for intelligent fire robot was proposed that was based on our previous works in this paper, whose aims are to realize falling position prediction of jet trajectory in fire extinguishing. Firstly, previous studies respecting the NFCV system were briefly reviewed and several issues during application testing were analyzed and summarized. The improved work mainly focuses on the segmentation and discrimination of jet trajectory adapted to complex lighting environment and interference scenes. It mainly includes parameters adjustment on the variance threshold and background update rate of the mixed Gaussian background method, jet trajectory discrimination based on length and area proportion parameters, parameterization, and feature extraction of jet trajectory based on superimposed radial centroid method. When compared with previous works, the proposed method reduces the average error of prediction results from 1.36 m to 0.1 m, and the error variance from 1.58 m to 0.13 m. The experimental results suggest that every part plays an important role in improving the functionality and reliability of the NFCV system, especially the background subtraction and radial centroid methods. In general, the improved NFCV system for jet trajectory falling position prediction has great potential for intelligent fire extinguishing by fire-fighting robots.

A multisensor approach for improved protein A load phase monitoring by conductivity-based background subtraction of UV spectra.

Real-time monitoring and control of protein A capture steps by process analytical technologies (PATs) promises significant economic benefits due to the improved usage of the column's binding capacity, by eliminating time-consuming off-line analytics and costly resin lifetime studies, and enabling continuous production. The PAT method proposed in this study relies on ultraviolet (UV) spectroscopy with a dynamic background subtraction based on the leveling out of the conductivity signal. This point in time can be used to collect a reference spectrum for removing the majority of spectral contributions by process-related contaminants. The removal of the background spectrum facilitates chemometric model building and model accuracy. To demonstrate the benefits of this method, five different feedstocks from our industry partner were used to mix the load material for a case study. To our knowledge, such a large design space, which covers possible variations in upstream condition besides the product concentration, has not been disclosed yet. By applying the conductivity-based background subtraction, the root mean square error of prediction (RMSEP) of the partial least squares (PLS) model improved from 0.2080to0.0131 g . Finally, the potential of the background subtraction method was further evaluated for single wavelength-based predictions to facilitate implementation in production processes. An RMSEP of 0.0890 g with univariate linear regression was achieved, showing that by subtraction of the background better prediction accuracy is achieved then without subtraction and a PLS model. In summary, the developed background subtraction method is versatile, enables accurate prediction results, and is easily implemented into existing chromatography setups with typically already integrated sensors.

Numerical Resolving of Net Faradaic Current in Fast-Scan Cyclic Voltammetry Considering Induced Charging Currents.

In this paper, we study theoretically and experimentally the effect of induced charging currents on the fast-scan cyclic voltammetry. As explained in this paper, the phenomenon originates from the coupling between faradaic and capacitive currents in the presence of uncompensated resistance. Due to the existence of induced charging currents, the capacitive contribution to the total current is different from the capacitive current measured in the absence of electroactive species. In this paper, we show that this effect is particularly important when the ratio of the capacitive current and the total current is close to unity, even for a relatively low cell time constant. Consequently, the conventional background subtraction method may be inaccurate in these situations. In this work, we develop a method that separates the faradaic and capacitive currents, combining simulation and experimental data. The method is applicable even in the presence of potential-dependent capacitance. The theoretical results are compared with some previously reported results and with experiments carried out on the potassium ferrocyanide/ferricyanide redox couple. Platinum disk electrodes of different diameters and NaClO4 support electrolyte of different concentrations were used to obtain different cell time constants. The proposed method allowed us to separate the real capacitive current even in the situations where the conventional background subtraction used in many published papers is clearly inappropriate.

AN IMPROVED MOVING OBJECTS DETECTION ALGORITHM IN VIDEO SEQUENCES

Context. The implementation of video analytics functions in video surveillance systems makes it possible to increase the efficiency of these systems. One of the functions of these intelligent video surveillance systems is to detect dynamic objects in the surveillance sectors of video surveillance cameras. Existing methods of background subtractoin and object recognition have important disadvantages that limit their application in practice: under low contrast algorithms can not select an object from the background; some moving objects can be recognized as a background, algorithms critical to lighting conditions, and so on. Therefore, an important task is to develop and improve methods for detecting dynamic objects in video sequences.Objective. The research is devoted to the development of an improved method for detecting dynamic objects in video sequences.Method. For moving objects detection in video sequences we used background subtraction methods based on pixel-by-pixel analysis of frames using elements of the expert systems theory.Results. In this paper, we propose an improved method for detecting dynamic objects in video sequences, which is based on the ViBe algorithm. The proposed approach differs from original the using of U*V*W* color model, using double threshold levels and some elements of theory expert systems for removal of vaguenesses in pixel classification (Dempster-Shafer theory) and dynamic method for updating background pixel models. Proposed algorithm include following stages: initialization of the background model (for each pixel with known parameters, the number of previous values in the current frame is stored); foreground detection; the next step is a calculation amounts of points, that belong to the foreground and to the background. For removal of vaguenesses in pixel classification we used some elements of Dempster-Shafer theory. After initialization of the background model and foreground detection next stage is updating background model. For this we used a three-level constructed neighborhood of the studied pixel and used of the even distribution of random values is into each of three levels.Conclusions. Experimental research of the improved algorithm in comparing to original ViBe conducted with the use of test frames from a set of CDNET in the various variants of environment and with the different variants of discriminability. The consolidated results specify on the improvement of results of an offer method as compared to original ViBe on the average on 6,7%.

Long-distanceinfrared video pedestrian detection using deep learning and backgroundsubtraction

Infrared video-based pedestrian detectionplays an important role in surveillance and automatic driving. Compared with vision cameras, infrared cameras have the characteristics of all-day and all-weather availability. The current infrared video detection methods generally follow the traditional paradigm. However, when objectsare at a long distance, it is challenging for existing methods to achieve accurate detection. Meanwhile, deep learning-based methods have been widely used in visible light object detection. In this paper, we introduce an algorithm which combines deep learning and background subtraction methods to achieve infrared pedestrian detection. Firstly, background subtraction method is performed to provide the inter-frame information for the deep learning module. Secondly, the RefineDet equipped with an attention module is used to improve the detection accuracy for small pedestrian. Moreover, we develop a novel infrared video dataset which includes long-distance pedestrian for performance evaluation. Experiments demonstrated that our method can achieve a superior performance as compared to RefinDetand SSD methods.

Vision‐based approach for predicting the probability of vehicle–pedestrian collisions at intersections

Road accidents impose serious problems on society. Possible collisions between vehicles and pedestrians must be detected before they occur so that a timely warning may be issued. By using the vision-based approach, this study presents an effective and efficient algorithm to estimate the vehicle-pedestrian collision probability at intersections. The real-time trajectories and movement parameters (position, speed, acceleration or direction) of vehicles and pedestrians are obtained based on state-of-the-art detection and tracking algorithm which include background subtraction method, faster regions with convolutional neural networks and optical flow method. To find the appropriate time to identify the latent collision risk for calculating the collision probability, this study defines the critical time based on different collision patterns of perception-reaction failure and evasive action failure. In addition, based on discrete acceleration and discrete angle, the authors get different extended trajectories which can include most situation when the conflict happened. Trajectories generation probability are given by the discrete choice probability model based on the Logit model to get the accurate collision probability. Real-world video data is implemented to demonstrate the approach. This proposed collision prediction method can provide some important results for designing the intelligent pedestrian signal timing schemes at intersections.

Automatic foreground extraction from imperfect backgrounds using multi-agent consensus equilibrium

Extracting accurate foreground objects from a scene is an essential step for many video applications. Traditional background subtraction algorithms can generate coarse estimates, but generating high quality masks requires professional softwares with significant human interventions, e.g., providing trimaps or labeling key frames. We propose an automatic foreground extraction method in applications where a static but imperfect background is available. Examples include filming and surveillance where the background can be captured before the objects enter the scene or after they leave the scene. Our proposed method is very robust and produces significantly better estimates than state-of-the-art background subtraction, video segmentation and alpha matting methods. The key innovation of our method is a novel information fusion technique. The fusion framework allows us to integrate the individual strengths of alpha matting, background subtraction and image denoising to produce an overall better estimate. Such integration is particularly important when handling complex scenes with imperfect background. We show how the framework is developed, and how the individual components are built. Extensive experiments and ablation studies are conducted to evaluate the proposed method.

Comprehensive comparative evaluation of background subtraction algorithms in open sea environments

In autonomous-ship and maritime security surveillance operations involving electro-optical sensors, the first phase of foreground segmentation and change detection using background subtraction (BS) algorithms is crucial. However, it is also the most complex in terms of execution time. Despite the development of several BS algorithms, maritime foreground segmentation and change detection remain major challenges owing to the complex, unconstrained, and diverse nature of ocean scenarios. However, only a few studies have investigated the applications of BS algorithms in maritime environments, especially those involving boats in the open sea. This study compares BS methods involving use of a non-static electro-optical sensor in combination with visible-light and infrared cameras to identify the best method for use in open sea scenarios, especially from the viewpoint of avoiding piracy and armed robbery. Thirty-seven methods, ranging from simple temporal differencing to more sophisticated ones, were validated via extensive experiments and analyses using realistic maritime datasets and practical maritime applications. In addition, because most methods considered in this study were not previously evaluated at the pixel level on open sea datasets, this paper proposes an appropriate maritime BS benchmark, based on which the 37 methods were compared to compensate for their prior lack of detailed analyses. The experimental results indicate that BS algorithms of the multiple features category can better handle maritime challenges, thereby realizing higher accuracies when analyzing visible-light and thermal videos. The proposed evaluation, therefore, complements those reported previously. Consequently, the proposed study enables users to identify the most suitable BS algorithm for use in intelligent maritime transportation, maritime security surveillance systems, and autonomous ships in the open sea.

Research on Active Intelligent Perception Technology of Vessel Situation Based on Multisensor Fusion

In this paper, we focus on the safety supervision of inland vessels. This paper especially aims at studying the vessel target detection and dynamic tracking algorithm based on computer vision and the target fusion algorithm based on multisensor. For the vessel video target detection and tracking, this paper analyzes the current widely used methods and theories. Additionally, facing the application scenarios and characteristics of inland vessels, a comprehensive vessel video target detection algorithm is proposed in this paper. It is combined with a three-frame difference method based on Canny edge detection and a background subtraction method based on mixed Gaussian background modeling. Besides, for the multisensor target fusion, the processing method of laser point cloud data and automatic identification system (AIS) data is analyzed in this paper. Based on the idea of fuzzy mathematics, this paper proposes a method for calculating the fuzzy correlation matrix with normal membership function, which realizes the fusion of vessel track features of laser point cloud data and AIS data under dynamic video correction. Finally, through this method, a set of vessel situation active intelligent perception systems based on multisensor fusion was developed. Experiments show that this method has better environmental applicability and detection accuracy than traditional manual detection and any single monitoring method.

HMR-vid: a comparative analytical survey on human motion recognition in video data

According to the rapid spread of multimedia data and online observations by users, the importance of researching on machine vision also, analyzing and automatic understanding of video data content is progressively increasing. Human motion recognition in video data is a crucial research subject in machine vision science that has plenty of applications, for instance, video surveillance, video indexing, robotics, human-computer interface and multimedia retrieval. Despite a high number of researches conducted on this topic, there is a necessity to achieve a more in-depth understanding, complete classification, and evaluation of existing human motion recognition stages. The novelty of this paper, our comparative analytical framework includes three major parts. Firstly, three different stages are introduced in recognizing human motion consisting of background subtraction, feature extraction, and machine learning classification. Secondly, five essential criteria are defined for evaluating the proposed human motion recognition methods. Finally, our comparative analysis of human motion recognition stages comprises two models. The analysis of background subtraction methods is based on applying the criteria for a qualitative comparison. Next, the feature extraction and machine learning classification methods are examined by specifying their main idea, benefits and challenges. Our comparative analytical framework can be beneficial for every researcher in this field by simplifying accurate selection and development of human motion recognition methods in future works.

Blind background extraction from videos in the cloud

Nowadays, more and more people choose to upload their data and information to cloud. The cloud saves users’ data and information and starts providing computing services and artificial intelligence analysis. However, the privacy of users’ information and data will be completely exposed to the cloud without any protection. In this paper, we propose two methods of the blind (privacy-preserving) background extraction from video surveillance for both scenarios with the single-party cloud server (SCS) and multi-party cloud servers (MCS). We combine 1D logistics chaotic encryption with background subtraction based on a mixed Gaussian model, and propose a blind background subtraction method for a single server (SCS) . We combine the Chinese Remainder Theorem (CRT) and the ViBE background subtraction method and propose a multi-server blind background subtraction method (MCS). The test set for the experiment is CDW-2014, the experimental results show that our method has satisfactory results in recognition accuracy, recognition speed, and security analysis. The proposed methods have several advantages: (1) Based on our encryption method, the background extraction method in the original video does not need to be changed; (2) The server does not recognize any valid information for the calculation results; (3) Single cloud server (SCS) uses the chaotic mapping can ensure high-level security and resistance to several attacks; (4) Multiple cloud servers (MCS) can improve data security and improve processing efficiency. This method can accurately extract the background like the original ViBE algorithm while protecting the privacy of client video data.