Adaptive Background Model Research Articles

Unsupervised detection and mapping of sparks in the Electrochemical Discharge Machining (ECDM) process

Material removal in electrochemical discharge machining is caused by sparks generated in a tool immersed in an electrolytic solution. Being the primary machining agent in this non-contact machining process, mapping the locations of microscopic sparks is of great interest. The distribution of sparks around the tool surface could give insights into the machined hole properties like the size, surface finish, and depth as compared to the machining parameters such as applied voltage, tool size, rotation speed, and feed rate. This paper is focused on detecting sparks in photographs of the ECDM process captured using a high-speed camera. A novel approach of using a tri-planar reflective surface for capturing the location of sparks in 3D space using a 2D camera output is attempted. Traditional spark detection methods use neural network classifiers that need labeled data for training. This labeled data often comes from human intervention and contains inherent biases that could lead to misclassification. In this paper, an unsupervised spark detection methodology is demonstrated, which eliminates the need for human intervention and relies on the number of neighboring pixels detected in regions of interest (ROIs). The feasibility of using adaptive background modeling to classify thousands of images and identify the ones with sparks is demonstrated in this work. The masking technique combining effects of erosion followed by dilation is used to determine the exact boundaries of the spark contours in every image. Centroids for each of these contours are then transformed from the skewed coordinate system as observed in camera images, to a three-dimensional orthogonal coordinates system centered around the tool. The same procedure is repeated for various voltages to benchmark the distribution of sparks around a tool tip in an ECDM process.

Smart traffic management of vehicles using faster R-CNN based deep learning method

With constant growth of civilization and modernization of cities all across the world since past few centuries smart traffic management of vehicles is one of the most sorted after problem by research community. Smart traffic management basically involves segmentation of vehicles, estimation of traffic density and tracking of vehicles. The vehicle segmentation from videos helps realization of niche applications such as monitoring of speed and estimation of traffic. When occlusions, background with clutters and traffic with density variations, this problem becomes more intractable in nature. Keeping this motivation in this research work, we investigate Faster R-CNN based deep learning method towards segmentation of vehicles. This problem is addressed in four steps viz minimization with adaptive background model, Faster R-CNN based subnet operation, Faster R-CNN initial refinement and result optimization with extended topological active nets. The computational framework uses adaptive background modeling. It also addresses shadow and illumination issues. Higher segmentation accuracy is achieved through topological active net deformable models. The topological and extended topological active nets help to achieve stated deformations. Mesh deformation is achieved with minimization of energy. The segmentation accuracy is improved with modified version of extended topological active net. The experimental results demonstrate superiority of this framework with respect to other methods.

Multi-Modal Information Fusion for Localization of Emergency Vehicles

In urban and city environments, road transportation contributes significantly to the generation of substantial traffic. However, this surge in vehicles leads to complex issues, including hindered emergency vehicle movement due to high density and congestion. Scarcity of human personnel amplifies these challenges. As traffic conditions worsen, the need for automated solutions to manage emergency situations becomes more evident. Intelligent traffic monitoring can identify and prioritize emergency vehicles, potentially saving lives. However, categorizing emergency vehicles through visual analysis faces difficulties such as clutter, occlusions, and traffic variations. Visual-based techniques for vehicle detection rely on clear rear views, but this is problematic in dense traffic. In contrast, audio-based methods are resilient to the Doppler Effect from moving vehicles, but handling diverse background noises remains unexplored. Using acoustics for emergency vehicle localization presents challenges related to sensor range and real-world noise. Addressing these issues, this study introduces a novel solution: combining visual and audio data for enhanced detection and localization of emergency vehicles in road networks. Leveraging this multi-modal approach aims to bolster accuracy and robustness in emergency vehicle management. The proposed methodology consists of several key steps. The presence of an emergency vehicle is initially detected through the preprocessing of visual images, involving the removal of clutter and occlusions via an adaptive background model. Subsequently, a cell-wise classification strategy utilizing a customized Visual Geometry Group Network (VGGNet) deep learning model is employed to determine the presence of emergency vehicles within individual cells. To further reinforce the accuracy of emergency vehicle presence detection, the outcomes from the audio data analysis are integrated. This involves the extraction of spectral features from audio streams, followed by classification utilizing a support vector machine (SVM) model. The fusion of information derived from both visual and audio sources is utilized in the construction of a more comprehensive and refined traffic state map. This augmented map facilitates the effective management of emergency vehicle transit. In empirical evaluations, the proposed solution demonstrates its capability to mitigate challenges like visual clutter, occlusions, and variations in traffic density common issues encountered in traditional visual analysis methods. Notably, the proposed approach achieves an impressive accuracy rate of approximately 98.15% in the localization of emergency vehicles.

Intelligent Wearable Devices Enabled Automatic Vehicle Detection and Tracking System with Video-Enabled UAV Networks Using Deep Convolutional Neural Network and IoT Surveillance.

The discipline of computer vision is becoming more popular as a research subject. In a surveillance-based computer vision application, item identification and tracking are the core procedures. They consist of segmenting and tracking an object of interest from a sequence of video frames, and they are both performed using computer vision algorithms. In situations when the camera is fixed and the backdrop remains constant, it is possible to detect items in the background using more straightforward methods. Aerial surveillance, on the other hand, is characterized by the fact that the target, as well as the background and video camera, are all constantly moving. It is feasible to recognize targets in the video data captured by an unmanned aerial vehicle (UAV) using the mean shift tracking technique in combination with a deep convolutional neural network (DCNN). It is critical that the target detection algorithm maintains its accuracy even in the presence of changing lighting conditions, dynamic clutter, and changes in the scene environment. Even though there are several approaches for identifying moving objects in the video, background reduction is the one that is most often used. An adaptive background model is used to create a mean shift tracking technique, which is shown and implemented in this work. In this situation, the background model is provided and updated frame-by-frame, and therefore, the problem of occlusion is fully eliminated from the equation. The target tracking algorithm is fed the same video stream that was used for the target identification algorithm to work with. In MATLAB, the works are simulated, and their performance is evaluated using image-based and video-based metrics to establish how well they operate in the real world.

Hybrid Deep Learning Signature based Correlation Filter for Vehicle Tracking in Presence of Clutters and Occlusion

This vehicle tracking is an important task of smart traffic management. Tracking is very challenging in presence of occlusions, clutters, variation in real world lighting, scene conditions and camera vantage. Joint distribution of vehicle movement, clutter and occlusions introduces larger errors in particle tracking based approaches. This work proposes a hybrid tracker by adapting kernel and particle-based filter with aggregation signature and fusing the results of both to get the accurate estimation of target vehicle in video frames. Aggregation signature of object to be tracked is constructed using a probabilistic distribution function of lighting variation, clutters and occlusions with deep learning model in frequency domain. The work also proposed a fuzzy adaptive background modeling and subtraction algorithm to remove the backgrounds and clutters affecting the tracking performance. This hybrid tracker improves the tracking accuracy even in presence of larger disturbances in the environment. The proposed solution is able to track the objects with 3% higher precision compared to existing works even in presence of clutters.

Deep learning assisted active net segmentation of vehicles for smart traffic management

Vehicle segmentation, traffic density estimation and vehicle tracking are some of the important functionalities in smart traffic management. Segmentation of vehicles from traffic surveillance videos can help to realize many applications like speed monitoring, traffic estimation etc. Vehicle segmentation from surveillance videos becomes very challenging due to presence of occlusions, cluttered backgrounds and traffic density variations. In this work, we propose a deep learning adapted active net segmentation model for vehicle segmentation. The proposed solution involves three stages: adaptive background model based subtraction, active net sub netting with CNN, refined from CNN results with ETAN optimization. Adaptive background modeling is based on an adaptive gain function which is constructed from the pixels of the frames in the video. The gain function is able to compensate for the shadow and illumination problems affecting the vehicle segmentation. Deep learning assisted topological active net deformable model is able to provide higher segmentation accuracy in presence of occlusions, cluttered backgrounds and traffic density variations.

An effective motion object detection using adaptive background modeling mechanism in video surveillance system

Automatic moving object detection has gained increased research interest due to its widespread applications like security provision, traffic monitoring, and various types of anomalies detection, etc. In the video surveillance system, the video is processed for the detection of motion objects in a step-by-step process. However, the detection has become complex and less effective due to various complex constraints. To obtain an effective performance in the detection of motion objects, this research work focuses to develop an automatic motion object detection system based on the statistical properties of video and supervised learning. In this paper, a novel Background Modeling mechanism is proposed with the help of a Biased Illumination Field Fuzzy C-means algorithm to detect the moving objects more accurately. Here, the non-stationary pixels are separated from stationary pixels through the Background Subtraction. Afterward, the Biased Illumination Field Fuzzy C-means approach has accomplished to improve the segmentation accuracy through clustering under noise and varying illumination conditions. The performance of the proposed algorithm compared with conventional methods in terms of accuracy, precision, recall, and F- measure.

A rail detection algorithm for accurate recognition of train fuzzy video

ABSTRACT The research follows the mainstream physics and network system architecture. Aiming at the problem of poor data processing ability and poor robustness of traditional trajectory detection algorithms, a trajectory detection method that can be accurately extracted from the fuzzy video of a locomotive is proposed. Firstly, in order to ensure the accuracy of rail detection of trains in complex environments and improve the safety of driverless driving, the video image captured by on-board camera is stored as RGB video frame set, and then processed as single-channel greyscale image carrier set; Secondly, after the initial colour and brightness treatment, the redundant and useless noise features in the greyscale image carrier set still exist. After secondary Gaussian filtering and de-noising, canny operator is used to detect the track edge details of interest; Finally, the rail area is taken as the interested target for Hough line detection, the background subtraction method of adaptive mixed Gaussian background modelling is introduced, the structure element function and the morphologyEx theory of morphological transformation function are introduced, and the left and right tracks are fitted after the calculation and judgement of pixel coordinates. Algorithm for visual tracking experiments show that, rail detection algorithm has already meet need to detect rails in low-quality videos recorded by the on-board cameras of different models of trains at different speed. It not only can process large quantity of data from the on-board camera videos in real time, but also can accurately detect the target rails adaptively where rail conditions are complex with obstructive objects, which shows that this algorithm has very robust performance.

Two-Level Classification in Determining the Age and Gender Group of a Speaker

In this study, the classification of the speakers according to age and gender was discussed. Age and gender classes were first examined separately, and then by combining these classes a classification with a total of 7 classes was made. Speech signals represented by Mel-Frequency Cepstral Coefficients (MFCC) and delta parameters were converted into Gaussian Mixture Model (GMM) mean supervectors and classified with a Support Vector Machine (SVM). While the GMM mean supervectors were formed according to the Maximum-a-posteriori (MAP) adaptive GMM-Universal Background Model (UBM) configuration, the number of components was changed from 16 to 512, and the optimum number of components was decided. Gender classification accuracy of the system developed using aGender dataset was measured as 99.02% for two classes and 92.58% for three classes and age group classification accuracy was measured as 67.03% for female and 63.79% for male. In the classification of age and gender classes together in one step, an accuracy of 61.46% was obtained. In the study, a two-level approach was proposed for classifying age and gender classes together. According to this approach, the speakers were first divided into three classes as child, male and female, then males and females were classified according to their age groups and thus a 7-class classification was realized. This two-level approach was increased the accuracy of the classification in all other cases except when 32-component GMMs were used. While the highest improvement of 2.45% was achieved with 64 component GMMs, an improvement of 0.79 was achieved with 256 component GMMs.

Evaluation and Simulation of Sports Balance Training and Testing Equipment Based on Medical Video Image Analysis

Aiming at the shortcomings of video analysis system in the current process of balance force training, a new video analysis system for balance force training is proposed to analyze the test effect of balance force training. This paper evaluates and tests the function and utility of balance testing equipment by using the methods of sports training, sports biomechanics, mechanical design, sensors, video image analysis and computer-related research, combined with the latest research results of physical training at home and abroad. Firstly, several representative algorithms are selected in the frame difference method and background difference method. Then, these methods are tested according to the typical scene conditions, and the experimental results are used to compare and analyze the algorithms qualitatively and quantitatively, and the paper proposes the moving object detection and tracking based on GVF-Snake image model. The experimental results show that our proposed model has good detection effect compared with the background difference method based on Vibe algorithm, codebook model, Mixed Gauss model, adaptive Mixed Gauss model, median filter and adaptive background modeling. The system can accurately analyze the video and image information of sports training. The accuracy of key frame extraction is high, and the recall rate is high. It can be used to guide and evaluate balance force training. And the final evaluation results show the effectiveness of video image algorithm.

Enhanced Unsupervised Change Detector for Industrial Surveillance Systems

Detecting an intruder that is trespassing a prohibited area is a critical task of intelligent surveillance systems. This task requires a change detector to segment an intruder (foreground object) from the background. The task suffers the inherent drawbacks of change detectors due to the dual-camera sensor (color/IR), illumination changes, night time, static, and camouflaged foreground objects. This article proposes an enhanced unsupervised change detector to compensate for the aforementioned challenges for industrial sterile zone monitoring. The camera switch detection based on skewness patterns detects a switch between the dual-camera sensors (color/IR). The optimal color space selection based on the mean squared error will select tolerant color space (RGB/YCbCr) to illumination changes for modeling the background. In addition, the IR camera frames are contrast-enhanced to tackle the camouflaged intruders during the night. The incoming frames are split into respective channels before modeling the background. The background is modeled by Gaussian mixture models. The adaptive background model update scheme is proposed to tackle the various challenges posed by environment and object such as a static foreground object. The comparison is performed on three databases with top-ranked unsupervised change detection algorithms.

Vehicle Detection and Counting Using Adaptive Background Model Based on Approximate Median Filter and Triangulation Threshold Techniques

Background subtraction method is widely used for vehicle detection. One of the issues in this method is to find a suitable and accurate background model that works in all conditions. Moreover, setting an appropriate threshold value to discriminate between the moving objects and stationary background plays a crucial role in increasing the detection performance. In this paper, an adaptive background model combined with an adaptive threshold method is proposed. It is demonstrated that the proposed method can efficiently differentiate between moving vehicles and background in urban roads under different weather conditions (i.e., normal, rainy, foggy, and snowy). Comparisons between the proposed method and other methods, such as the adaptive local threshold (ALT) and the three frame-differencing methods show the potential of our approach. The experimental results show that the proposed method increases the average recall value by 16.4% and the average precision value by 21.7% in comparison to the ALT method with a negligible increase in the processing time.

An Improved Non-Parametric Method for Multiple Moving Objects Detection in the Markov Random Field

Detecting moving objects in the stationary background is an important problem in visual surveillance systems. However, the traditional background subtraction method fails when the background is not completely stationary and involves certain dynamic changes. In this paper, according to the basic steps of the background subtraction method, a novel non-parametric moving object detection method is proposed based on an improved ant colony algorithm by using the Markov random field. Concretely, the contributions are as follows: 1) A new nonparametric strategy is utilized to model the background, based on an improved kernel density estimation; this approach uses an adaptive bandwidth, and the fused features combine the colours, gradients and positions. 2) A Markov random field method based on this adaptive background model via the constraint of the spatial context is proposed to extract objects. 3) The posterior function is maximized efficiently by using an improved ant colony system algorithm. Extensive experiments show that the proposed method demonstrates a better performance than many existing state-of-the-art methods.

Moving object extraction based on saliency detection and adaptive background model

For the ghost in visual background extractor (ViBe) algorithm and the influence of dynamic background, an improved ViBe algorithm is proposed to extract moving object in this paper. The way of background acquisition during modeling is improved to eliminate the ghost. Detect the saliency of the pre-M-frame, and synthetic relatively real background. Modeling with the background can avoid the generation of ghost. The selection of thresholds in the model is improved to reduce the impact of the dynamic background. Adjust the thresholds adaptively according to the background complexity. In addition, find the inner contour of extracted object to fill, which makes the detected targets more complete. Experimental results show that the presented algorithm effectively removes ghosts and enhances anti-interference ability. Compared with several existing methods, the presented algorithm has better performance.

Background modeling and foreground extraction in video data using spatio-temporal region persistence features

The proposed work describes an efficient methodology for adaptive background modeling and foreground extraction from video data using the newly proposed Spatio-temporal region persistence (STRP) descriptor. The STRP background descriptor includes block-wise statistics of intensity bins and their temporal persistency. Blockwise feature extraction helps to consider the local changes, while intensity bins provide consistent output for a group of similar intensities in an intra-regional sense. In this work, we have tried to minimize the effect of different video irregularities like dynamic background, ghosting effect, change in illuminations, video noise, etc. Additionally, adaptive threshold selection and regular adjustment of modeled background descriptors make the procedure robust. Two benchmark datasets, Changed Detection and Scene Background Modeling, and Initialization (SBMI) have been used to verify the efficiency of our work. The results and comparative studies with the related works justify the effectiveness of our proposed technique.

Foreground Segmentation Using Adaptive 3 Phase Background Model

An extensive collection of algorithms have been proposed over the years to identify the foreground from a video scene, but none of them considers the classification history of previous frames for discovering moving objects. All the existing algorithms focus on a single background model to cope with all types of challenging and complex video environments. In this paper, a real-time pixel level classification method is proposed that uses its previous output history to update its parameters. The model has three components designed to handle various types of challenging background environments. For each pixel, three sub-parts, namely the Adaptive Background Model, the Neighborhood Background Model, and the Change Detection Background Model are constructed to detect various types of complex background changes. A pixel level model updating method uses the previous foreground/background binary classification results to periodically refresh all the three background models. This update method helps to recognize the foreground accurately by adjusting the algorithmic parameters to efficiently detect complex background changes. This novel method shows a significant improvement in performance for a variety of complex video scenes.

Moving Object Detection for a Moving Camera Based on Global Motion Compensation and Adaptive Background Model

A fast and effective moving object detection method for a moving camera is proposed in this paper. The global motion is estimated through tracking the grid-based key points using optical flow. After the motion compensation, the background model, candidate background model and candidate age are used for the background modelling. Then the local pixel difference and the consistency of local changes between the current frame and the background model are used for the background subtraction. The lighting influence threshold and the local pixel difference between the current frame and two previous aligned frames are used to reduce the lighting influences. Finally, Gaussian filter, connected-components analysis, erosion and dilation are used to refine the results. The performance evaluation shows that this proposed method works very fast in real time and has competitive results compared with others in the public dataset.

Dynamic background modelling using multi-swarm optimisation

Background modelling is a fundamental task in video analytics. This paper presents an adaptive background modelling for real-time indoor and outdoor videos. This proposed method treats background modelling as an optimisation problem and, it fetches multiple peaks from the histogram of the video frame and optimises them using a multi-swarm technique. The background is successfully adapted whenever there is a change in the environment as well as a number of objects in the background. The experimental result of foreground extraction confirms the effectiveness and robustness of the proposed background modelling technique against the various background modelling approaches.

Adaptive background modelling technique for moving object detection in video under dynamic environment

Adaptive background modelling technique for moving object detection in video under dynamic environment

Adaptive background modelling technique for moving object detection in video under dynamic environment

This work proposes a novel method for detection of motion based object having dynamic scenario in the background. The suggested scheme has a strong potential for real-time applications especially for rafting, river, sea-beach, swimming pools, ponds, etc. Apart from these, this work is very beneficial for surveillance of border, tunnel, traffic in the sea, forest, restricted zones, deep zones, etc. This work develops a statistical p based background subtraction method and implemented in three stages. In the first stage, a background model is developed using few initial frames. In the second stage, this work classifies the foreground using the difference frame and the appropriate threshold value. An automatic threshold value is generated at run-time and updated iteratively. It also reduces the problem of using a constant threshold. In the third stage, morphological filters and connected component based region filtering technique is applied to enhance the detection quality. The extensive experimental result shows more accurate results of proposed method. It also demonstrates better performance against considered state-of-the-art methods.