Motion Tracking with Fast Adaptive Background Subtraction

To extract and tr ack moving objects is usually one of the most important tasks of intelligent video surveillance systems. This paper presents a fast and adaptive background subtraction algorithm and the motion tracking process using this algorithm. The algorithm uses only luminance components of sampled image sequence pixels and models every pixel in a statistical model. The algorithm is characterized by its ability of real time detecting sudden lighting changes, and extracting and tracking motion objects faster. It is shown that our algorithm can be realized with lower time and space complexity and adjustable object detection error rate with comparison to other background subtraction algorithms. Making use of the algorithm, an indoor monitoring system is also worked out and the motion tracking process is presented in this paper. Experimental results testify the algorithm's good performances when used in an indoor monitoring system.

Target detection method for moving cows based on background subtraction

Target detection is the fundamental work for perceiving the behavior of cows using video analysis automatically.The videos captured in farming scenes often suffer from a complex background,which leads to difficulty in detecting the target and inconvenience in the subsequent images analysis.In this study,a method was proposed to detect the moving target accurately for cows based on background subtraction.Firstly,the bounding rectangle of cows was calculated using the frames difference method to extract the local background in frames,which were averaged and spliced into one image as the entire background image.Secondly,the size and location of a cow’s body were determined by the bounding rectangle of cows,and the body area was tracked through the video by the binary images.Thirdly,the summation coefficients on RGB channels were adjusted to improve the contrast between the target and background images.Finally,taking the body area in every frame as reference area,the performance of target detection was evaluated by the reference area to determine the optimal summation coefficients on RGB channels,and then background subtraction was processed again to finish the detection.A total of 129 videos were used to test the detection algorithm,and the accuracy of the algorithm was 88.34%,which was 24.85%higher than the classical background subtraction method.The study shows that the algorithm proposed in this study is feasible to detect the target accurately and timely when cows are walking straight in the farming environment under natural light,and this method can improve the detection performance and is an extension to the classical background subtraction method.

Diversity Sampling Based Kernel Density Estimation for Background Modeling

A novel diversity-sampling based nonparametric multi-modal background model is proposed. Using the samples having more popular and various intensity values in the training sequence, a nonparametric model is built for background subtraction. According to the related intensifies, different weights are given to the distinct samples in kernel density estimation. This avoids repeated computation using all samples, and makes computation more efficient in the evaluation phase. Experimental results show the validity of the diversity- sampling scheme and robustness of the proposed model in moving objects segmentation. The proposed algorithm can be used in outdoor surveillance systems.

Moving Multi-Object Detection and Tracking Using MRNN and PS-KM Models

On grounds of the advent of real-time applications,like autonomous driving,visual surveillance,and sports analysis,there is an augmenting focus of attention towards Multiple-Object Tracking(MOT).The tracking-by-detection paradigm,a commonly utilized approach,connects the existing recognition hypotheses to the formerly assessed object trajectories by comparing the simila-rities of the appearance or the motion between them.For an efficient detection and tracking of the numerous objects in a complex environment,a Pearson Simi-larity-centred Kuhn-Munkres(PS-KM)algorithm was proposed in the present study.In this light,the input videos were,initially,gathered from the MOT dataset and converted into frames.The background subtraction occurred whichfiltered the inappropriate data concerning the frames after the frame conversion stage.Then,the extraction of features from the frames was executed.Afterwards,the higher dimensional features were transformed into lower-dimensional features,and feature reduction process was performed with the aid of Information Gain-centred Singular Value Decomposition(IG-SVD).Next,using the Modified Recurrent Neural Network(MRNN)method,classification was executed which identified the categories of the objects additionally.The PS-KM algorithm identi-fied that the recognized objects were tracked.Finally,the experimental outcomes exhibited that numerous targets were precisely tracked by the proposed system with 97%accuracy with a low false positive rate(FPR)of 2.3%.It was also proved that the present techniques viz.RNN,CNN,and KNN,were effective with regard to the existing models.

Real-time moving object detection for video monitoring systems

Moving object detection is one of the challenging problems in video monitoring systems, especially when the illumination changes and shadow exists. Amethod for real-time moving object detection is described. Anew background model is proposed to handle the illumination varition problem. With optical flow technology and background subtraction, a moving object is extracted quickly and accurately. An effective shadow elimination algorithm based on color features is used to refine the moving obj ects. Experimental results demonstrate that the proposed method can update the background exactly and quickly along with the varition of illumination, and the shadow can be eliminated effectively. The proposed algorithm is a real-time one which the foundation for further object recognition and understanding of video mum＇toting systems.

MonkeyTrail:A scalable video-based method for tracking macaque movement trajectory in daily living cages

Behavioral analysis of macaques provides important experimental evidence in the field of neuroscience.In recent years,video-based automatic animal behavior analysis has received widespread attention.However,methods capable of extracting and analyzing daily movement trajectories of macaques in their daily living cages remain underdeveloped,with previous approaches usually requiring specific environments to reduce interference from occlusion or environmental change.Here,we introduce a novel method,called MonkeyTrail,which satisfies the above requirements by frequently generating virtual empty backgrounds and using background subtraction to accurately obtain the foreground of moving animals.The empty background is generated by combining the frame difference method(FDM)and deep learning-based model(YOLOv5).The entire setup can be operated with low-cost hardware and can be applied to the daily living environments of individually caged macaques.To test MonkeyTrail performance,we labeled a dataset containing>8000 video frames with the bounding boxes of macaques under various conditions as ground-truth.Results showed that the tracking accuracy and stability of MonkeyTrail exceeded that of two deep learningbased methods(YOLOv5 and Single-Shot MultiBox Detector),traditional frame difference method,and na?ve background subtraction method.Using MonkeyTrail to analyze long-term surveillance video recordings,we successfully assessed changes in animal behavior in terms of movement amount and spatial preference.Thus,these findings demonstrate that MonkeyTrail enables low-cost,large-scale daily behavioral analysis of macaques.

Extraction algorithm for longitudinal and transverse mechanical information of AFM

The atomic force microscope(AFM)can measure nanoscale morphology and mechanical properties and has a wide range of applications.The traditional method for measuring the mechanical properties of a sample does so for the longitudinal and transverse properties separately,ignoring the coupling between them.In this paper,a data processing and multidimensional mechanical information extraction algorithm for the composite mode of peak force tapping and torsional resonance is proposed.On the basis of a tip–sample interaction model for the AFM,longitudinal peak force data are used to decouple amplitude and phase data of transverse torsional resonance,accurately identify the tip–sample longitudinal contact force in each peak force cycle,and synchronously obtain the corresponding characteristic images of the transverse amplitude and phase.Experimental results show that the measured longitudinal mechanical characteristics are consistent with the transverse amplitude and phase characteristics,which verifies the effectiveness of the method.Thus,a new method is provided for the measurement of multidimensional mechanical characteristics using the AFM.

Intelligent Deep Learning Based Automated Fish Detection Model for UWSN

An exponential growth in advanced technologies has resulted in the exploration of Ocean spaces.It has paved the way for new opportunities that can address questions relevant to diversity,uniqueness,and difficulty of marine life.Underwater Wireless Sensor Networks(UWSNs)are widely used to leverage such opportunities while these networks include a set of vehicles and sensors to monitor the environmental conditions.In this scenario,it is fascinating to design an automated fish detection technique with the help of underwater videos and computer vision techniques so as to estimate and monitor fish biomass in water bodies.Several models have been developed earlier for fish detection.However,they lack robustness to accommodate considerable differences in scenes owing to poor luminosity,fish orientation,structure of seabed,aquatic plantmovement in the background and distinctive shapes and texture of fishes from different genus.With this motivation,the current research article introduces an Intelligent Deep Learning based Automated Fish Detection model for UWSN,named IDLAFD-UWSN model.The presented IDLAFD-UWSN model aims at automatic detection of fishes from underwater videos,particularly in blurred and crowded environments.IDLAFD-UWSN model makes use of Mask Region Convolutional Neural Network(Mask RCNN)with Capsule Network as a baseline model for fish detection.Besides,in order to train Mask RCNN,background subtraction process using GaussianMixtureModel(GMM)model is applied.This model makes use of motion details of fishes in video which consequently integrates the outcome with actual image for the generation of fish-dependent candidate regions.Finally,Wavelet Kernel Extreme Learning Machine(WKELM)model is utilized as a classifier model.The performance of the proposed IDLAFD-UWSN model was tested against benchmark underwater video dataset and the experimental results achieved by IDLAFD-UWSN model were promising in comparison with other state-of-the-art methods under different aspects with the maximum accuracy of 98%and 97%on the applied blurred and crowded datasets respectively.

Real-time detection of moving objects in video sequences

An approach to detection of moving objects in video sequences, with application to video surveillance is presented. The algorithm combines two kinds of change points, which are detected from the region-based frame difference and adjusted background subtraction. An adaptive threshold technique is employed to automatically choose the threshold value to segment the moving objects from the still background. And experiment results show that the algorithm is effective and efficient in practical situations. Furthermore, the algorithm is robust to the effects of the changing of lighting condition and can be applied for video surveillance system.

Back Ground Segmentation of Cucumber Target Based on DSP

In order to realize automatic and accurate grading of cucumber, the first thing is to make sure the high accuracy and integrity in cucumber shape segmentation. As the core processor of this dissertation, DSP TMS320DM6437 acquired and processed digital image, it solved the common shadowing problem associated with the natural light. Ultimately, the background subtraction was proposed. Compared with the result of above-mentioned image data processing, the error rate of classic background subtraction method was often high. The result of optimization showed that the improved background subtraction method worked well, and it could meet an accurate segmentation of the fruit in comparison with the original methods.

Fall detection system in enclosed environments based on single Gaussian model

In this paper,we propose an efficient fall detection system in enclosed environments based on single Gaussian model using the maximum likelihood method.Online video clips are used to extract the features from two cameras.After the model is constructed,a threshold is set,and the probability for an incoming sample under the single Gaussian model is compared with that threshold to make a decision.Experimental results show that if a proper threshold is set,a good recognition rate for fall activities can be achieved.

A Study on the Methods for Estimating the Distribution of Pedestrians in an Underground Mall by Use of Watch Cameras

This paper shows the method of estimating spatiotemporal distribution of pedestrians by using watch cameras. We estimate the distribution without tracking technology, with pedestrian＇s privacy protected and in Umeda underground mall. Lately spatiotemporal distribution of pedestrians has being increasingly important in the field of urban planning, disaster prevention planning, marketing and so on. Although many researchers have tried to capture the information of location as dealing with some sensors, some problems still remain, such as the investment of sensors, the restriction of the number of people who has the device they are able to capture. From such background, we develop an original labelling algorithm and estimate the spatiotemporal distribution of pedestrians and the information of the passing time and the direction of pedestrians from sequential images of a watch camera.

Practical automatic background substitution for live video

In this paper we present a novel automatic background substitution approach for live video. The objective of background substitution is to extract the foreground from the input video and then combine it with a new background. In this paper, we use a color line model to improve the Gaussian mixture model in the background cut method to obtain a binary foreground segmentation result that is less sensitive to brightness differences. Based on the high quality binary segmentation results, we can automatically create a reliable trimap for alpha matting to refine the segmentation boundary. To make the composition result more realistic, an automatic foreground color adjustment step is added to make the foreground look consistent with the new background. Compared to previous approaches, our method can produce higher quality binary segmentation results, and to the best of our knowledge, this is the first time such an automatic and integrated background substitution system has been proposed which can run in real time, which makes it practical for everyday applications.

Deep Learning-based Moving Object Segmentation:Recent Progress and Research Prospects

Moving object segmentation(MOS),aiming at segmenting moving objects from video frames,is an important and challenging task in computer vision and with various applications.With the development of deep learning(DL),MOS has also entered the era of deep models toward spatiotemporal feature learning.This paper aims to provide the latest review of recent DL-based MOS methods proposed during the past three years.Specifically,we present a more up-to-date categorization based on model characteristics,then compare and discuss each category from feature learning(FL),and model training and evaluation perspectives.For FL,the methods reviewed are divided into three types:spatial FL,temporal FL,and spatiotemporal FL,then analyzed from input and model architectures aspects,three input types,and four typical preprocessing subnetworks are summarized.In terms of training,we discuss ideas for enhancing model transferability.In terms of evaluation,based on a previous categorization of scene dependent evaluation and scene independent evaluation,and combined with whether used videos are recorded with static or moving cameras,we further provide four subdivided evaluation setups and analyze that of reviewed methods.We also show performance comparisons of some reviewed MOS methods and analyze the advantages and disadvantages of reviewed MOS methods in terms of technology.Finally,based on the above comparisons and discussions,we present research prospects and future directions.

Automatic Segmentation of Moving Objects in Video Sequences for Indoor and Outdoor Applications

Computer vision systems have an impressive spread both for their practicalapplication and for theoretical research . The common approach used in such systems consists of agood segmentation of moving objects from video sequences . This paper presents an automaticalgorithm for segmenting and extracting moving objects suitable for indoor and outdoor videoapplications, where the background scene can be captured beforehand . Since edge detection is oftenused to extract accurate boundaries of the image's objects, the first step in our algorithm isaccomplished by combining two edge maps which are detected from the frame difference in twoconsecutive frames and the background subtraction . After removing edge points that belong to thebackground, the resulting moving edge map is fed to the object extraction step . A fundamental taskin this step is to declare the candidates of the moving object, followed by applying morphologicaloperations. The algorithm is implemented on a real video sequence as well as MPEG- 4 sequence andgood segmentation results are achieved.

Indoor and outdoor people detection and shadow suppression by exploiting HSV color information

An adaptive background model based on max-imum statistical probability and a shadow suppression scheme for indoor and outdoor people detection by exploiting hue saturation value(HSV)color information is proposed.To obtain the initial background scene,the frequency of R,G,and B component values for each pixel at the same position in the learning sequence are respec-tively calculated;the R,G,and B component values with the biggest ratios are incorporated to model the initial background.The background maintenance,or the so-called background re-initiation,is also proposed to adapt to scene changes such as illumination changes and scene geometry changes.Moving cast shadows generally exhibit a challenge for accurate moving target detection.Based on the observation that a shadow cast on a background region lowers its brightness but does not change its chro-maticity significantly,we address this problem in the ar-ticle by exploiting HSV color information.In addition,quantitative metrics is introduced to evaluate the algo-rithm on a benchmark suite of indoor and outdoor video sequences.The experimental results are given to show the performance of the algorithm.

Motion Segmentation Based on Dual Interrelated Models

Motion segmentation plays an important role in many vision applications,yet it is still a challenging problem in complex scenes.The typical conditions in real world scenarios like illumination variations,dynamic backgrounds and camera shaking make negative effects on segmentation performance.In this paper,a newly designed method for robust motion segmentation is proposed,which is mainly composed of two interrelated models.One is a normal random model（N-model）,and the other is called enhanced random model（E-model）.They are constructed and updated in spatio-temporal information for adapting to illumination changes and dynamic backgrounds,and operate in an AdaBoost-like strategy.The exhaustive experimental evaluations on complex scenes demonstrate that the proposed method outperforms the state-of-the-art methods.

Adaptive Contour Model for Real-Time Foreground Detection

A multiscale foreground detection method was developed to segment moving objects from a sta- tionary background. The algorithm is based on a fixed-mesh-based contour model, which starts at the bounding box of the difference map between an input image and its background and ends at a final contour. An adaptive algorithm was developed to calculate an appropriate energy threshold to control the contours to identify the foreground silhouettes. Experiments show that this method more successfully ignores the nega- tive influence of image noise to obtain an accurate foreground map than other foreground detection algo- rithms. Most shadow pixels are also eliminated by this method.

A fast luminosity monitor for BEPCⅡ

The fast luminosity monitor counting the γ photons above a given energy threshold emitted from radiative Bhabha scattering has been operated in the BEPC Ⅱ to measure the relative luminosity bunch by bunch for the first time and used successfully in beam tuning of BEPC Ⅱ. In the relative mode the monitor is able to deliver the relative luminosities with an accuracy of 0.8 %. By steering the electron beam while observing the counting rate changes of the monitor the horizontal and vertical sizes of the bunch spots can be estimated as： Sxe＋ =Sxe =0.356 mm, Sye＋ =Sye- =0.011 mm.