Adaptive Background Subtraction Research Articles

OPTIMAL TRAFFIC CONTROL SYSTEM FOR TRAFFIC CONGESTION

A smart city's traffic management system is regarded as one of its primary components. Traffic jams are a common sight on the roadways in metropolitan areas due to the rapid increase in population and urban mobility. In order to address road traffic management issues and assist authorities with appropriate planning, an intelligent traffic management system utilizing the Yolo algorithm and Open CV approach is proposed in this project. A workable model for counting automobiles in traffic was developed using image processing as the basis. image processing methods classified and tallied moving vehicles in traffic scene video streams captured by stationary cameras. The following is the detection and tracking methodology. The adaptive background subtraction technique is initially used to separate the moving vehicles from the traffic scene. Using videos to isolated picture blobs are recognized as individual vehicles once the background is subtracted. Following blob identification, vehicles in a certain area are counted and classified. A count of vehicles was observed with an accuracy of ideal camera calibration. To support the goal, data is gathered from video footage of vehicles traveling toward and away from the camera in order to count and use signal switching. The created system's results demonstrate that, with more enhancements, it applicable to count and categorize vehicles in real-time. After that, an optimization framework makes use of these predictions to dynamically modify signal timings in response to shifting traffic conditions. The optimization method seeks to increase overall traffic flow efficiency, decrease delays, and shorten travel times. To sum up, utilizing real-time traffic data to optimize signal control presents a viable approach to improving urban traffic management. This method makes use yolo techniques to facilitate the creation of flexible and effective traffic control, which in turn helps to create more sustainable and seamless urban transportation networks. KEYWORDS: Image classification, Video tracking, Information analysis, Vehicle detection, Signal Switching.

Effective Moving Object Tracking Using Adaptive Background Subtraction with Advanced Probability Evolutionary Algorithm

Tracking moving objects is a very difficult task for many computers. The task of tracking is a moving object. There are many virtual applications such as video surveillance and object recognition. Many ideas have been suggested for moving objects tracking and detection. One of the main problems solving tracking is finding identical objects in different frames. In this article, this application mainly focuses on the detection and tracking of moving objects using adaptive Background subtraction with adaptive probability evolutionary algorithm (AREA) method. Normal probability evolutionary algorithm will track only human motion but our algorithm tracks all the moving objects very accurately. Our proposed system shows the tracked objects with the red mark border.

ABGS Segmenter: pixel wise adaptive background subtraction and intensity ratio based shadow removal approach for moving object detection

ABGS Segmenter: pixel wise adaptive background subtraction and intensity ratio based shadow removal approach for moving object detection

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.

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.

Vehicle Counting and Detection

This paper describes about the system to count the number of vehicles on roads and highways by using adaptive background subtraction and blob tracking technologies. Overall, system requires a video stream captured from static cameras installed on roads and highways .The proposed system consists of four stages: 1) Adaptive background subtraction 2) image segmentation 3) vehicle counting 4) vehicle tracking. The necessity of tracing and counting the vehicles is helpful for traffic surveillance. The primary key features of the system are 1) Ability to count the vehicles 2) efficiency, to show that system would give the results with high perfection.

Probabilistic static foreground elimination for background subtraction

ABSTRACTBackground subtraction is generally used to detect moving objects, because it has low complexity, and it is easy to implement. However, the detection error increases when the background is changing. Therefore, adaptive background subtraction is applied to overcome this problem, and it continuously requires updating the background with a fixed learning rate. The learning rate should be tuned for a consistently evolving background. This paper proposes the Probabilistic Static Foreground Elimination for Background Subtraction (PSFE) algorithm. It consisted of two parameters: the number of frames for static foreground elimination, and the probability of changes in background pixels. These two parameters can tune the learning rate and update background for better detection. The average results of the detection error rate from Wallflower datasets were tested with PSFE and well-known method. They demonstrated that PSFE provides moving object detection with minimum detection error (5.95%), especially in Camouflage, Moved object, and Light switch dataset.

Patch-Based Adaptive Background Subtraction for Vascular Enhancement in X-Ray Cineangiograms.

Automatic vascular enhancement in X-ray cineangiography is of crucial interest, for instance, for better visualizing and quantifying coronary arteries in diagnostic and interventional procedures. A novel patch-based adaptive background subtraction method (PABSM) is proposed automatically enhancing vessels in coronary X-ray cineangiography. First, pixels in the cineangiogram are described by the vesselness and Gabor features. Second, a classifier is utilized to separate the cineangiogram into the rough vascular and non-vascular region. Dilation is applied to the classified binary image to include more vascular region. Third, a patch-based background synthesis is utilized to fill the removed vascular region. A database containing 320 cineangiograms of 175 patients was collected, and then an interventional cardiologist annotated all vascular structures. The performance of PABSM is compared with six state-of-the-art vascular enhancement methods regarding the precision-recall curve and C-value. The area under the precision-recall curve is 0.7133, and the C-value is 0.9659. PABSM can automatically enhance the coronary artery in the cineangiograms. It preserves the integrity of vascular topological structures, particularly in complex vascular regions, and removes noise caused by the non-uniform gray-level distribution in the cineangiogram. PABSM can avoid the motion artifacts and it eases the subsequent vascular segmentation, which is crucial for the diagnosis and interventional procedures of coronary artery diseases.

A Low-Power Vision System With Adaptive Background Subtraction and Image Segmentation for Unusual Event Detection

This paper presents a smart ultra-low power vision system targeted to video surveillance applications. The sensor embeds a low-level image processing technique that autonomously detects unusual events occurring in the scene, relying on adaptive background subtraction. The resulting binary image is then directly segmented by an FPGA, which triggers the higher layer of processing, transferring only aggregate feature information. The on-board processing relieves the rest of the vision system from expensive computation. The $104\times 104$ pixels vision chip consumes $80~\mu \text{W}$ at 30 frames/s, while segmentation dramatically cuts down the amount of data to be transferred, resulting in an extremely low-power system suitable for embedded applications.

Moving object detection using an adaptive background subtraction method based on block-based structure in dynamic scene

Today, determining background which forms the basis of the video surveillance system whose use is increasing in parallel with developing technology, is a complicated process to implement for cases involving dynamic scene. In this study, we proposed a block-based adaptive method which can be adaptable to dynamic environmental conditions. By grouping the pixels in the picture frame as 2 × 2 non-overlapped blocks, we reduced the amount of noise and the time delay caused by processing of pixels. By a simple counter structure, we created an adaptive threshold parameter which can be adapted according to the case in N surrounding. We used this parameter to perform an update of the background model and reduced background model normalization process. So, we reduced the update time of background operably. Our proposed method achieved successful results in levels of grey levels.

A comprehensive shape analysis pipeline for stereoscopic measurements of particulate populations in suspension

A state-of-the-art, compact optomechanical setup coupled with an image analysis routine to measure multi-dimensional particle size and shape distributions (nD PSSDs) for crystallization processes is presented. A novel image processing pipeline to process the raw images from the cameras is presented. The pipeline consists of a stereoscopic camera calibration model, adaptive background subtraction, particle contour matching, and 3D reconstruction of the segmented crystals. The reconstructed crystals are subjected to a supervised shape classification strategy, which categorizes each detected crystal into spheres, needles, quasi-equant particles, platelets and non-convex particles. Additionally, a high-speed image capture mode, capable of monitoring processes with fast kinetics, is presented. The device discussed in this work is subjected to an experimental campaign, to validate size measurements, characterize steady state, and confirm repeatability of measurements to affirm and assess the non-invasive nature of the setup on the measurement. An experiment aimed at evaluating the enhancement in the proposed image analysis pipeline performance, more specifically the automatic shape classification, is further conducted. Finally, a dissolution process is monitored using a stereoscopic imaging setup for the first time, and the size and shape evolution of the population in a growth and dissolution phase is monitored for about 18h.

A vision-based system to support tactical and physical analyses in futsal

This paper presents a vision-based system to support tactical and physical analyses of futsal teams. Most part of the current analyses in this sport are manually performed, while the existing solutions based on automatic approaches are frequently composed of costly and complex tools, developed for other kind of team sports, making it difficult their adoption by futsal teams. Our system, on the other hand, represents a simple yet efficient dedicated solution, which is based on the analyses of image sequences captured by a single stationary camera used to obtain top-view images of the entire court. We use adaptive background subtraction and blob analysis to detect players, as well as particle filters to track them in every video frame. The system determines the distance traveled by each player, his/her mean and maximum speeds, as well as generates heat maps that describe players’ occupancy during the match. To present the collected data, our system uses a specially developed mobile application. Experimental results with image sequences of an official match and a training match show that our system provides data with global mean tracking errors below 40 cm, demanding on 25 ms to process each frame and, thus, demonstrating its high application potential.

Efficient Human Motion Detection with Adaptive Background for Vision-Based Security System

Motion detection is very important in video surveillance system especially for video compression, human detection and behaviour analysis. Various approaches have been used for detecting motion in a continuous video stream but for real-time video surveillance system, we need a motion detection that can provide accurate detection even in non-static background regardless of surroundings (outdoor or indoor), object speed and size, robust to camera noisy pixels or sudden change in light intensity. This is very important to ensure that the security of a monitored parameter or area is not compromised. In this paper, we propose a method for human motion detection which employs adaptive background subtraction, camera noise reduction and white pixel counts threshold for real-time video streams.

Automated Detection and Tracking of Cell Clusters in Time-Lapse Fluorescence Microscopy Images

Fluorescence microscopy imaging of live cells has drawn the attention of many researchers in the past decade. Because of the large amount of image data produced by a fluorescence microscope, automated cell detection and tracking algorithms have become an emerging need to help cell biologists visualize and analyze cell kinematics such as changes in cell population caused by proliferation, attachment, and differentiation. This study uses the adaptive background subtraction technique to detect cell clusters in time-lapse fluorescence microscopy images and the discrete Kalman filter to track the position, motion, merging and splitting of these clusters. A set of two-dimensional (2D) time-series images from mouse embryonic stem cells obtained using wide-field microscopy and a set of three-dimensional (3D) time-series from HeLa cells obtained using confocal microscopy are used to demonstrate that biologists can visualize various quantitative measures such as motion, merging and splitting, centroids, areas, and growth rates of cell clusters to acquire useful information through 2D and 3D interfaces.

An effective algorithm to detect both smoke and flame using color and wavelet analysis

Fire detection is an important task in many applications. Smoke and flame are two essential symbols of fire in images. In this paper, we propose an algorithm to detect smoke and flame simultaneously for color dynamic video sequences obtained from a stationary camera in open space. Motion is a common feature of smoke and flame and usually has been used at the beginning for extraction from a current frame of candidate areas. The adaptive background subtraction has been utilized at a stage of moving detection. In addition, the optical flow-based movement estimation has been applied to identify a chaotic motion. With the spatial and temporal wavelet analysis, Weber contrast analysis and color segmentation, we achieved moving blobs classification. Real video surveillance sequences from publicly available datasets have been used for smoke detection with the utilization of our algorithm. We also have conducted a set of experiments. Experiments results have shown that our algorithm can achieve higher detection rate of 87% for smoke and 92% for flame.

A Memristive Pixel Architecture for Real-Time Tracking

We report on a pixel architecture relying on memristive devices to perform pixel-level adaptive background subtraction. Core of the processing is the pixel, containing a light-to-frequency converter. Its output digital pulses, proportional to the intensity of light, are applied in turn to a memristor, changing its resistance accordingly. Two additional memristors are used to store the dynamic boundaries, outside which the behavior of the photo-generated signal is recognized to be anomalous, i.e., unexpectedly fast changing. The main advantages of using memristors over all-CMOS implementations are a smaller pixel pitch and non-volatility, the latter allowing the image background to be modeled with programmable time constants.

Crowd modeling framework using fast head detection and shape-aware matching

A framework for crowd modeling using a combination of multiple kernel learning (MKL)-based fast head detection and shape-aware matching is proposed. First, the MKL technique is used to train a classifier for head detection using a combination of the histogram of oriented gradient and local binary patterns feature sets. Further, the head detection process is accelerated by implementing the classification procedure only at those spatial locations in the image where the gradient points overlap with moving objects. Such moving objects are determined using an adaptive background subtraction technique. Finally, the crowd is modeled as a deformable shape through connected boundary points (head detection) and matched with the subsequent detection from the next frame in a shape-aware manner. Experimental results obtained from crowded videos show that the proposed framework, while being characterized by a low computation load, performs better than other state-of-art techniques and results in reliable crowd modeling.

Human Action Recognition Based on Fusion Features Extraction of Adaptive Background Subtraction and Optical Flow Model

A novel method based on hybrid feature is proposed for human action recognition in video image sequences, which includes two stages of feature extraction and action recognition. Firstly, we use adaptive background subtraction algorithm to extract global silhouette feature and optical flow model to extract local optical flow feature. Then we combine global silhouette feature vector and local optical flow feature vector to form a hybrid feature vector. Secondly, in order to improve the recognition accuracy, we use an optimized Multiple Instance Learning algorithm to recognize human actions, in which an Iterative Querying Heuristic (IQH) optimization algorithm is used to train the Multiple Instance Learning model. We demonstrate that our hybrid feature-based action representation can effectively classify novel actions on two different data sets. Experiments show that our results are comparable to, and significantly better than, the results of two state-of-the-art approaches on these data sets, which meets the requirements of stable, reliable, high precision, and anti-interference ability and so forth.

Application of Object Detection and Tracking Techniques for Unmanned Aerial Vehicles

In this research, the information captured by Unmanned Aerial Vehicles (UAVs) are eminently utilized in detecting and tracking moving objects which pose a primary security threat against the United States southern border. Illegal trespassing and border encroachment by immigrants is a huge predicament against the United States border security force and the Department of Homeland Security. It becomes insurmountable to warranty suspicious behaviour, monitoring by human operators for long periods of time, due to the massive amount of data involved. The main objective of this research is to assist the human operators, by implementing intelligent visual surveillance systems which help in detecting and tracking suspicious or unusual events in the video sequence. The visual surveillance system requires fast and robust methods of detecting and tracking moving objects. In this research, we have investigated methods for detecting and tracking objects from UAVs. Moving objects were detected using adaptive background subtraction technique successfully and these detected objects were tracked by using Lucas-Kanade optical flow tracking, Continuously Adaptive Mean-Shift tracking based techniques. The simulation results show the efficacy of these techniques in detecting and tracking moving objects in the video sequences acquired by the UAV.

Observation of vehicle-related events on highways using openCV

Monitoring and observation of moving vehicles is beneficial for the analysis of traffic flow and cognition of other events. For identifying motion from the video feed, the system applies adaptive background subtraction using the OpenCV library for obtaining the threshold images containing blobs which represent moving vehicles. Applying certain operations on the blobs, the speed, class and number of vehicles can be procured.