Background Subtraction Algorithm Research Articles

A Pedestrian Detection and Tracking Method for Robot Equipped with Laser Radar

In order to detect and track pedestrians in complex indoor backgrounds, a pedestrian detection and tracking method for indoor robots equipped with Laser radar is proposed. Firstly, The SLAM (Simultaneous Location and Mapping) technology is applied to obtain 2D grid map for a strange environment; then, Monte Carlo localization is employed to obtain the posterior pose of the robot in the map; then, an improved likelihood field background subtraction algorithm is proposed to extract the interesting foreground in changeable environment; then, the hierarchical clustering algorithm combining with an improved leg model is proposed to detect the objective pedestrian; at last, an improved tracking intensity formula is designed to track and follow the objective pedestrian. Experimental results in some complex environments show that our method can effectively reduce the impact of confusing scenarios which are challenges for other algorithms, such as the motion of the chair, the suddenly passing by person and when the objective pedestrian close to the wall and so on, and can detect, track and follow pedestrians in real time with high accuracy.

A Light Weight Background Subtraction Algorithm for Motion Detection in Fog Computing

A novel light weight background subtraction algorithm proposed in this letter addresses the issue of executing real time motion detection in fog computing, which is a resource constrained environment. The proposed algorithm compresses the original high dimensional video frame into low dimensional space using random projection (RP) and the motion detection is identified using the structural similarity (SSIM) index. The objective of the proposed algorithm is to select the frames with motion and discard the remaining frame in order to reduce the storage and computational cost for the cloud users. The proposed algorithm is evaluated using CDNET 2014 video data and the results are verified in terms of selected frames per video(SFPV), percentage of reduction (POR) and running time. From the experiment, it is evident that the proposed algorithm reduces nearly 67 percent of storage cost with trifling computational expense.

Quality Assessment and Prediction of Philippine Mangoes: A Convolutional Neural Network Approach

Philippines is one of the world’s leading exporter of mangoes. The country produces many varieties of mangoes, one of which is the ‘Carabao’ mango. Several metric tons of mangoes are produced, and these have to be checked for defects before entering the market. With recent advances in technology, it has become efficient and relatively easy to use for these applications. The objective of this paper is to present a non-destructive method to check the quality of mangoes using computer vision (CV) and convolutional neural network (CNN) with a minimal number of samples. An experimental setup was created to simulate a production line. A webcam was used for capturing images of the mangoes, while a mini computer was used for controlling the peripherals. As basis for categorizing the mangoes as either good or bad, the Philippine National Standard (PNS) for mangoes was used. A basic background subtraction algorithm was used to extract the mango’s image. With these extracted images, a 2-category network was trained, and the achieved classification accuracy was 97.21%. The goal of having a high accuracy in classifying mangoes was achieved. There are multiple paths to explore in the future, including additional feature extraction methods, different neural networks, and hardware improvements, in order to speed up the sorting process. Moreover, it may be necessary to be able to identify mangoes with only slight defects to be used for other products, such as dried mangoes, to reduce product wastage.

Обгрунтування показника вибору оптимального алгоритму виділення фону у відеопослідовностях з камер відеоспостереження відомчих систем відео спостереження

The background subtraction is an important stage in the process of detecting moving objects in video sequences derived from stationary cameras of video surveillance systems (VSS cameras). variety of approaches to addressing the background selection problem in video sequences from stationary cameras of video surveillance systems has created the need for research on the choice of optimal algorithms. In this paper, we described the problem factors that complicate the background allocation process and described the basic background subtraction algorithms classifications. After analyzing the location of VSS cameras for certain objects within the Information and Telecommunication Systems of the State Border Guard Service and their inspection sectors, we have identified the features of the use of cameras from these systems. We researched the most common algorithms of background subtraction in video sequences, methods of comparative analysis and methodes for selecting optimal background subtraction algorithms in video sequences from stationary VSS cameras. We developed an improved efficiency index for the choice optimal algorithms for the background subtraction in video sequences derived from stationary cameras of video surveillance systems оn the basis method proposed Sobral Andrews and Vacavant Antoine in the Comprehensive review of subtraction algorithms evaluated using synthetic and real video. The essence of the improved method is that we propose to calculate the overall performance of the background subtraction algorithm using Matthews correlation coefficient, because this coefficient takes into account all possible variants of the matrix of algorithm responses (TP, TN, FP, FN). The proposed method was tested by calculating the results of the experimental study in the A comprehensive review of the subtraction algorithms evaluated using synthetic and real videos. As a result, we have developed the index of efficiency of an algorithm of background subtraction , that differs from that offered gathered Sobral Andrews and Vacavant Antoine (FSD), because it takes into account all options matrix classifier responses, and therefore is more accurate than the FSD.

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.

Efficient adaptive load balancing approach for compressive background subtraction algorithm on heterogeneous CPU–GPU platforms

Mixture of Gaussians (MoG) and compressive sensing (CS) are two common approaches in many image and audio processing systems. The combination of these algorithms is recently used for the compressive background subtraction task. Nevertheless, the result of this combination has not been exploited to take advantage of the evolution of parallel computing architectures. This paper proposes an efficient strategy to implement CS-MoG on heterogeneous CPU–GPU computing platforms. This is achieved through two elements. The first one is ensuring the better acceleration and accuracy that can be achieved for this algorithm on both CPU and GPU processors: The obtained results of the improved CS-MoG are more accurate and performant than other published MoG implementations. The second contribution is the proposition of the Optimal Data Distribution Cursor ODDC, a novel adaptive data partitioning approach to exploit simultaneously the heterogeneous processors on any given platform. It aims to ensure an automatic workload balancing by estimating the optimal data chunk size that must be assigned to each processor, with taking into consideration its computing capacity. Furthermore, our method ensures an update of the partitioning at runtime to take into account any influence of data content irregularity. The experimental results, on different platforms and data sets, show that the combination of these two contributions allows reaching 98% of the maximal possible performance of targeted platforms.

An Efficient Algorithm for Detection of Vacant Spaces in Delimited and Non-Delimited Parking Lots

Smart parking management systems that provide drivers with real-time information about availability and location of parking spaces are high among the wish list of urban dwellers. This paper proposes a machine learning approach for automatic detection of vacant lots in delimited parking spaces where the boundaries of the individual parking lots are predefined, which is then extended to a more general scenario of non-delimited parking spaces. A bag of features (bof) representation for the lots is used with a single svm classifier to discriminate between occupied and vacant lots. For non-delimited spaces, a customized background subtraction algorithm is used to generate proposal regions where vehicles can possibly be found, which are then verified using a bof plus svm approach. When tested on public datasets with images of real parking spaces, the proposed method shows robustness against large intra-class variabilities of vehicles and wide variations in vehicle pose and scale in each parking lot. Compared to state-of-the-art methods, the major advantages of the proposed approach are that it requires fewer images to train the classifier, accepts non-rectangular, variable sized images as input and can also be applied to non-delimited parking spaces, making it suitable for practical deployment.

Vision‐based garbage dumping action detection for real‐world surveillance platform

In this paper, we propose a new framework for detecting the unauthorized dumping of garbage in real‐world surveillance camera. Although several action/behavior recognition methods have been investigated, these studies are hardly applicable to real‐world scenarios because they are mainly focused on well‐refined datasets. Because the dumping actions in the real‐world take a variety of forms, building a new method to disclose the actions instead of exploiting previous approaches is a better strategy. We detected the dumping action by the change in relation between a person and the object being held by them. To find the person‐held object of indefinite form, we used a background subtraction algorithm and human joint estimation. The person‐held object was then tracked and the relation model between the joints and objects was built. Finally, the dumping action was detected through the voting‐based decision module. In the experiments, we show the effectiveness of the proposed method by testing on real‐world videos containing various dumping actions. In addition, the proposed framework is implemented in a real‐time monitoring system through a fast online algorithm.

Assessment of Rib Spalling Hazard Degree in Mining Face Based on Background Subtraction Algorithm and Support Vector Machine

Assessment of Rib Spalling Hazard Degree in Mining Face Based on Background Subtraction Algorithm and Support Vector Machine

A novel background subtraction algorithm based on parallel vision and Bayesian GANs

To address the challenges of change detection in the wild, we present a novel background subtraction algorithm based on parallel vision and Bayesian generative adversarial networks (GANs). First, we use the median filtering algorithm for background image extraction. Then, we build the background subtraction model by using Bayesian GANs to classify all pixels into foreground and background, and use parallel vision theory to improve the background subtraction results in complex scenes. The proposed algorithm has been evaluated on the well-known, publicly available changedetection.net dataset. Experiment results show that the proposed algorithm results in better performance than many state-of-the-art ones. In addition, our model trained on CDnet dataset can generalize very well to unseen datasets, outperforming multiple state-of-art methods. The major contribution of this work is to apply parallel vision and Bayesian GANs to solve the difficulties in background subtraction, achieving high detection accuracy.

Hierarchical Improvement of Foreground Segmentation Masks in Background Subtraction

A plethora of algorithms have been defined for foreground segmentation, a fundamental stage for many computer vision applications. In this paper, we propose a post-processing framework to improve the foreground segmentation performance of background subtraction algorithms. We define a hierarchical framework for extending segmented foreground pixels to undetected foreground object areas and for removing erroneously segmented foreground. First, we create a motion-aware hierarchical image segmentation of each frame that prevents merging foreground and background image regions. Then, we estimate the quality of the foreground mask through the fitness of the binary regions in the mask and the hierarchy of segmented regions. Finally, the improved foreground mask is obtained as an optimal labeling by jointly exploiting foreground quality and spatial color relations in a pixel-wise fully connected conditional random field. Experiments are conducted over four large and heterogeneous data sets with varied challenges (CDNET2014, LASIESTA, SABS, and BMC) demonstrating the capability of the proposed framework to improve background subtraction results.

Implementation and Performance Testing of Background Subtraction Algorithm on ESP32

This paper describes the background subtraction algorithm and its performance in low power processing units, this algorithm has low complexity and can be used to detect objects so that it has the potential to be applied to security cameras. This study has succeeded in applying basic image processing algorithms to detect and track objects, such as background subtraction in the ESP32 module. The ESP32 module equipped with Xtensa® 32-bit LX6 microprocessor running at 240MHz can process 10000 times background subtraction algorithms in ~ 2000ms using 80x60 pixel image input.
 Background Subtraction; Embedded; ESP32; Image Processing; Microcontroller; Object Detection;

Object Detection in a Maritime Environment: Performance Evaluation of Background Subtraction Methods

This paper provides a benchmark of the performance of 23 classical and state-of-the-art background subtraction (BS) algorithms on visible range and near infrared range videos in the Singapore Maritime dataset. Importantly, our study indicates the limitations of the conventional performance evaluation criteria for maritime vision and proposes new performance evaluation criteria that is better suited to this problem. This paper provides insight into the specific challenges of BS in maritime vision. We identify four open challenges that plague BS methods in maritime scenario. These include spurious dynamics of water, wakes, ghost effect, and multiple detections. Poor recall and extremely poor precision of all the 23 methods, which have been otherwise successful for other challenging BS situations, allude to the need for new BS methods custom designed for maritime vision.

Soccer Players Detection Using GDLS Optimization and Spatial Bitwise Operation Filter

Advancement computer vision technology in order to help coach creates strategy has been affecting the sport industry evolving very fast. Players movement patterns and other important behavioral activities regarding the tactics during playing the game are the most important data obtained in applying computer vision in Sport Industry. The basic technique for extracting those information during the game is player detection. Three fundamental challenges of computer vision in detecting objects are random object’s movement, noise and shadow. Background subtraction is an object’s detection method that used widely for separating moving object as foreground and non moving object as background. This paper proposed a method for removing shadow and unwanted noise by improving traditional background subtraction technique. First, we employed GDLS algorithm to optimize background-foreground separation. Then, we did filter shadows and crumbs-like object pixels by applying digital spatial filter which is created from implementation of digital arithmetic algorithm (bitwise operation). Finally, our experimental result demonstrated that our algorithm outperform conventional background subtraction algorithms. The experiments result proposed method has obtained 80.5% of F1-score with average 20 objects were detected out of 24 objects.

Performance Analysis of Multi-Level HAAR in Background Removal for Object Detection

Objective: This study proposes performance improvement in speed of multi-level HAAR processed images for object detection. Method: Background subtraction algorithm is implemented using phase as a feature to reduce illumination variation. The algorithm is implemented on level 2 and level 3 HAAR compressed images. Simulation results are obtained on kit ware database. Findings: Simulation results show that object detection is faster in level 3 HAAR compressed images as compared to level 2 and level 1 HAAR compressed images. Average time required for processing single frame is in range of 6.53 to 29.22 ms in level 3 while that in level 2 is 6.65 to 36.46 ms. Improvement: Using this approach saving of 5% to 22% of processing time is observed at level 2 of HAAR while a saving of 9% to 48% of time is observed at level 3 of HAAR. Keywords: Background Subtraction, Illumination Variation, Multi-Level HAAR, Phase as a Feature

Statistical Properties of Soft X-Ray Emission of Solar Flares

Abstract We present a statistical analysis of properties of Soft X-Ray (SXR) emission, plasma temperature (T), and emission measure (EM), derived from Geostationary Operational Environmental Satellite observations of flares in 2002–2017. The temperature and EMs are obtained using the Temperature and EM-based Background Subtraction algorithm, which delivers reliable results together with uncertainties even for weak B-class flare events. More than 96% of flares demonstrate a sequential appearance of T, SXR, and EM maxima, in agreement with the expected behavior of the chromospheric evaporation process. The relative number of such flares increases with increasing the SXR flux maximum. The SXR maximum is closer in time to the T maximum for B-class flares than for ≥C-class flares, while it is very close to the EM maximum for M- and X-class flares. We define flares as “T-controlled” if the time interval between the SXR and T maxima is at least two times shorter than the interval between the EM and SXR maxima, and as “EM-controlled” if the time interval between the EM and SXR maxima is at least two times shorter than the interval between the SXR and T maxima. For any considered flare class range, the T-controlled events compared to EM-controlled events have: (a) higher EM but lower T; (b) longer durations and shorter relative growth times; and (c) longer FWHM and characteristic decay times. Interpretation of these statistical results based on analysis of a single loop dynamics suggests that for flares of the same class range, the T-controlled events can be developed in longer loops than the EM-controlled events.

Detection Object on Sea Surface to Avoid Collision with Post-Processed in Background Subtraction Image

Data on shipping accident investigations from the National Transportation Safety Committee (NTSC) throughout 2010-2016 of fifty-four accident cases at sea, seventeen of which were accidents caused by collisions on ships in Indonesian waters, act to avoid a collision by detecting an object on the sea surface. Detection object is challenging because so many varieties object on the sea surface. Illumination variations with different seasons, periods, illumination intensity and direction affect the detection of objects directly. A rough sea is seen as a dynamic background of moving objects with size order and shape. All these factors make it difficult to object detection. Therefore, it is possible to conclude that background subtraction on sea surface problem remains open and a definitive robust solution is still missing. In this paper, we have applied a selection of background subtraction algorithms with post-processed to the problem. Experimental results with our dataset verify the high efficiency of our proposed method

Refining background subtraction using consistent motion detection in adverse weather

Most background subtraction algorithms developed to detect moving objects are potentially problematic in that they experience performance degradation when weather conditions are adverse. We solve this problem by proposing a refinement method using a consistent motion detection method, the performance of which is robust to weather related changes in video images captured by a static camera. The proposed algorithm reduces the number of false-positive regions and fills parts that are missing as a result of the nature of the background subtraction methods. We show the extent of the improvement afforded by our algorithm in the handling of moving object detection in adverse weather conditions.

SMALL-LABS: Measuring Single-Molecule Intensity and Position in Obscuring Backgrounds

Single-molecule and super-resolution imaging relies on successful, sensitive, and accurate detection of the emission from fluorescent molecules. Yet, despite the widespread adoption of super-resolution microscopies, single-molecule data processing algorithms can fail to provide accurate measurements of the brightness and position of molecules in the presence of backgrounds that fluctuate significantly over time and space. Thus, samples or experiments that include obscuring backgrounds can severely, or even completely, hinder this process. To date, no general data analysis approach to this problem has been introduced that is capable of removing obscuring backgrounds for a wide variety of experimental modalities. To address this need, we present the Single-Molecule Accurate LocaLization by LocAl Background Subtraction (SMALL-LABS) algorithm, which can be incorporated into existing single-molecule and super-resolution analysis packages to accurately locate and measure the intensity of single molecules, regardless of the shape or brightness of the background. Accurate background subtraction is enabled by separating the foreground from the background based on differences in the temporal variations of the foreground and the background (i.e., fluorophore blinking, bleaching, or moving). We detail the function of SMALL-LABS here, and we validate the SMALL-LABS algorithm on simulated data as well as real data from single-molecule imaging in living cells.

Combining background subtraction algorithms with convolutional neural network

Accurate and fast extraction of foreground objects is a key prerequisite for a wide range of computer vision applications, such as object tracking and recognition. Thus, many background subtraction (BGS) methods for foreground object detection have been proposed in recent decades. However, this is still regarded as a tough problem due to a variety of challenges, such as illumination variations, camera jitter, dynamic backgrounds, and shadows. Currently, there is no single method that can handle all the challenges in a robust way. We try to solve this problem from a perspective of combining different state-of-the-art BGS algorithms to create a more robust and more advanced foreground detection algorithm. More specifically, an encoder–decoder fully convolutional neural network architecture is adapted and trained to automatically learn how to leverage the characteristics of different algorithms to fuse the results produced by different BGS algorithms and produce a more precise result. Comprehensive experiments evaluated on the CDnet 2014 dataset demonstrate that the proposed method outperforms all the considered single BGS algorithms. We show that our solution is more efficient than other BGS combination strategies.