Robust background subtraction in traffic video sequence

For intelligent transportation surveillance, a novel background model based on Mart wavelet kernel and a background subtraction technique based on binary discrete wavelet transforms were introduced. The background model kept a sample of intensity values for each pixel in the image and used this sample to estimate the probability density function of the pixel intensity. The density function was estimated using a new Marr wavelet kernel density estimation technique. Since this approach was quite general, the model could approximate any distribution for the pixel intensity without any assumptions about the underlying distribution shape. The background and current frame were transformed in the binary discrete wavelet domain, and background subtraction was performed in each sub-band. After obtaining the foreground, shadow was eliminated by an edge detection method. Experimental results show that the proposed method produces good results with much lower computational complexity and effectively extracts the moving objects with accuracy ratio higher than 90%, indicating that the proposed method is an effective algorithm for intelligent transportation system.

Adaptive learning algorithm based on mixture Gaussian background

The key problem of the adaptive mixture background model is that the parameters can adaptively change according to the input data. To address the problem, a new method is proposed. Firstly, the recursive equations are inferred based on the maximum likelihood rule. Secondly, the forgetting factor and learning rate factor are redefined, and their still more general formulations are obtained by analyzing their practical functions. Lastly, the convergence of the proposed algorithm is proved to enable the estimation converge to a local maximum of the data likelihood function according to the stochastic approximation theory. The experiments show that the proposed learning algorithm excels the formers both in converging rate and accuracy.

Bidirectional Background Modeling for Video Surveillance

Traditional background model methods often require complicated computations, and are sensitive to illumination and shadow. In this paper, we propose a block-based background modeling method, and use our proposed method to combine color and texture characteristics. Suppression and relaxation are the two key strategies to resist illumination changes and shadow disturbance. The proposed method is quite efficient and is capable of resisting illumination changes. Experimental results show that our method is suitable for real-word scenes and real-time applications.

Background modeling methods in video analysis： A review and comparative evaluation

Foreground detection methods can be applied to efficiently distinguish foreground objects including moving or static objects from back- ground which is very important in the application of video analysis, especially video surveillance. An excellent background model can obtain a good foreground detection results. A lot of background modeling methods had been proposed, but few comprehensive evaluations of them are available. These methods suffer from various challenges such as illumination changes and dynamic background. This paper first analyzed advantages and disadvantages of various background modeling methods in video analysis applications and then compared their performance in terms of quality and the computational cost. The Change detection.Net （CDnet2014） dataset and another video dataset with different envi- ronmental conditions （indoor, outdoor, snow） were used to test each method. The experimental results sufficiently demonstrated the strengths and drawbacks of traditional and recently proposed state-of-the-art background modeling methods. This work is helpful for both researchers and engineering practitioners. Codes of background modeling methods evaluated in this paper are available atwww.yongxu.org/lunwen.html.

Modeling and Generating Realistic Background Traffic by Hybrid Approach

One of the key challenges in largescale network simulation is the huge computation demand in fine-grained traffic simulation.Apart from using high-performance computing facilities and parallelism techniques,an alternative is to replace the background traffic by simplified abstract models such as fluid flows.This paper suggests a hybrid modeling approach for background traffic,which combines ON/OFF model with TCP activities.The ON/OFF model is to characterize the application activities,and the ordinary differential equations(ODEs) based on fluid flows is to describe the TCP congestion avoidance functionality.The apparent merits of this approach are(1) to accurately capture the traffic self-similarity at source level,(2) properly reflect the network dynamics,and(3) efficiently decrease the computational complexity.The experimental results show that the approach perfectly makes a proper trade-off between accuracy and complexity in background traffic simulation.

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.

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.

An improved ViBe algorithm based on adaptive detection of moving targets

There exists a Ghost region in the detection result of the traditional visual background extraction(ViBe)algorithm,and the foreground extraction is prone to false detection or missed detection due to environmental changes.Therefore,an improved ViBe algorithm based on adaptive detection of moving targets was proposed.Firstly,in the background model initialization process,the real background could be obtained by setting adjusting parameters in mean background modeling,and the ViBe background model was initialized by using the background.Secondly,in the foreground detection process,an adaptive radius threshold was introduced according to the scene change to adaptively detect the foreground.Finally,mathematical morphological close operation was used to fill the holes in the detection results.The experimental results show that the improved method can effectively suppress the Ghost region and detect the foreground target more completely under the condition of environmental changes.Compared with the traditional ViBe algorithm,the detection accuracy is improved by more than 10%,the false detection rate and the missed detection rate are reduced by 20% and 7% respectively.In addition,the improved method satisfies the real-time requirements.

Crustal Electrical Structure and Deep Metallogenic Potential in Northern Wuyi Area(South China),based on Magnetotelluric Data

The northern Wuyi area,which is located in the northern Wuyi metallogenic belt,has superior mineralization conditions.The Pingxiang-Guangfeng-Jiangshan-Shaoxing fault(PSF)extends across the whole region regardless of whether or how the PSF relates to the near-surface mineralization.We carried out an MT survey in the region and obtained a reliable 2D model of the crustal electrical structure to a depth of 30 km.In the resistivity model,we inferred that a continuous high conductivity belt that ranges from the shallow to deep crust is a part of the PSF.Then,we estimated the fluid content and pressure gradient to identify the deep sources of fluid as well as its pattern of motion pattern.Finally,we proposed a model for the deep metallogenic migration processes that combines geological data,fluid content data,pressure gradient data,and the subsurface resistivity model.The model analysis showed that the Jiangnan orogenic belt and the Cathaysia block formed the PSF during the process of com.The deep fluid migrated upward through the PSF to the shallow crust.Therefore,we believe that the PSF is an ore-forming fluid migration channel and that it laid the material basis for large-scale mineralization in the shallow crust.

Vehicle detection algorithm based on codebook and local binary patterns algorithms

Detecting the moving vehicles in jittering traffic scenes is a very difficult problem because of the complex environment.Only by the color features of the pixel or only by the texture features of image cannot establish a suitable background model for the moving vehicles. In order to solve this problem, the Gaussian pyramid layered algorithm is proposed, combining with the advantages of the Codebook algorithm and the Local binary patterns(LBP) algorithm. Firstly, the image pyramid is established to eliminate the noises generated by the camera shake. Then, codebook model and LBP model are constructed on the low-resolution level and the high-resolution level of Gaussian pyramid, respectively. At last, the final test results are obtained through a set of operations according to the spatial relations of pixels. The experimental results show that this algorithm can not only eliminate the noises effectively, but also save the calculating time with high detection sensitivity and high detection accuracy.

Improved Real-time Implementation of Adaptive Gassian Mixture Model-based Object Detection Algorithm for Fixed-point DSP Processors

Foreground moving object detection is an important process in various computer vision applications such as intelligent visual surveillance, HCI, object-based video compression, etc. One of the most successful moving object detection algorithms is based on Adaptive Gaussian Mixture Model （AGMM）. Although ACMM-hased object detection shows very good performance with respect to object detection accuracy, AGMM is very complex model requiring lots of floatingpoint arithmetic so that it should pay for expensive computational cost. Thus, direct implementation of the AGMM-based object detection for embedded DSPs without floating-point arithmetic HW support cannot satisfy the real-time processing requirement. This paper presents a novel rcal-time implementation of adaptive Gaussian mixture model-based moving object detection algorithm for fixed-point DSPs. In the proposed implementation, in addition to changes of data types into fixed-point ones, magnification of the Gaussian distribution technique is introduced so that the integer and fixed-point arithmetic can be easily and consistently utilized instead of real nmnher and floatingpoint arithmetic in processing of AGMM algorithm. Experimental results shows that the proposed implementation have a high potential in real-time applications.

High efficient moving object extraction and classification in traffic video surveillance

Moving object extraction and classification are important problems in automated video surveillance systems. A background model based on region segmentation is proposed. An adaptive single Gaussian background model is used in the stable region with gradual changes, and a nonparametric model is used in the variable region with jumping changes. A generalized agglomerative scheme is used to merge the pixels in the variable region and fill in the small interspaces. A two-threshold sequential algorithmic scheme is used to group the background samples of the variable region into distinct Gaussian distributions to accelerate the kernel density computation speed of the nonparametric model. In the feature-based object classification phase, the surveillance scene is first partitioned according to the road boundaries of different traffic directions and then re-segmented according to their scene localities. The method improves the discriminability of the features in each partition. AdaBoost method is applied to evaluate the relative importance of the features in each partition respectively and distinguish whether an object is a vehicle, a single human, a human group, or a bike. Experimental results show that the proposed method achieves higher performance in comparison with the existing method.

COMBINING SCENE MODEL AND FUSION FOR NIGHT VIDEO ENHANCEMENT

This paper presents a video context enhancement method for night surveillance. The basic idea is to extract and fuse the meaningful information of video sequence captured from a fixed camera under different illuminations. A unique characteristic of the algorithm is to separate the image context into two classes and estimate them in different ways. One class contains basic surrounding scene in- formation and scene model, which is obtained via background modeling and object tracking in daytime video sequence. The other class is extracted from nighttime video, including frequently moving region, high illumination region and high gradient region. The scene model and pixel-wise difference method are used to segment the three regions. A shift-invariant discrete wavelet based image fusion technique is used to integral all those context information in the final result. Experiment results demonstrate that the proposed approach can provide much more details and meaningful information for nighttime video.

EMOTIONAL SPEECH RECOGNITION BASED ON SVM WITH GMM SUPERVECTOR

Emotion recognition from speech is an important field of research in human computer interaction. In this letter the framework of Support Vector Machines (SVM) with Gaussian Mixture Model (GMM) supervector is introduced for emotional speech recognition. Because of the importance of variance in reflecting the distribution of speech, the normalized mean vectors potential to exploit the information from the variance are adopted to form the GMM supervector. Comparative experiments from five aspects are conducted to study their corresponding effect to system performance. The experiment results, which indicate that the influence of number of mixtures is strong as well as influence of duration is weak, provide basis for the train set selection of Universal Background Model (UBM).

Adaptive learning rate GMM for moving object detection in outdoor surveillance for sudden illumination changes

A dynamic learning rate Gaussian mixture model（GMM）algorithm is proposed to deal with the problem of slow adaption of GMM in the case of moving object detection in the outdoor surveillance,especially in the presence of sudden illumination changes.The GMM is mostly used for detecting objects in complex scenes for intelligent monitoring systems.To solve this problem,a mixture Gaussian model has been built for each pixel in the video frame,and according to the scene change from the frame difference,the learning rate of GMM can be dynamically adjusted.The experiments show that the proposed method gives good results with an adaptive GMM learning rate when we compare it with GMM method with a fixed learning rate.The method was tested on a certain dataset,and tests in the case of sudden natural light changes show that our method has a better accuracy and lower false alarm rate.

Neural network based method for background modeling and detecting moving objects

This paper proposes a novel method, primarily based on the fuzzy adaptive resonance theory （ART） neural network with forgetting procedure, for moving object detection and background modeling in natural scenes. With the ability, inheriting from the ART neural network, of extracting patterns from arbitrary sequences, the background model based on the proposed method can learn new scenes quickly and accurately. To guarantee that a long-life model can derived from the proposed mothed, a forgetting procedure is employed to find the neuron that needs to be discarded and reconstructed, and the finding procedure is based on a neural network which can find the extreme value quickly. The results of a suite of quantitative and qualitative experiments conducted verify that for processes of modeling background and detecting moving objects our method is more effective than five other proven methods with which it is compared.

Emission inventory evaluation using observations of regional atmospheric background stations of China

Any accurate simulation of regional air quality by numerical models entails accurate and up-to-date emissions data for that region.The INTEX-B2006 （I06）,one of the newest emission inventories recently popularly used in China and East Asia,has been assessed using the Community Multiscale Air Quality model and observations from regional atmospheric background stations of China.Comparisons of the model results with the observations for the species SO2,NO 2,O 3 and CO from the three regional atmospheric background stations of Shangdianzi,Longfengshan and Linan show that the model can basically capture the temporal characteristics of observations such as the monthly,seasonal and diurnal variance trends.Compared to the other three species,the simulated CO values were grossly underestimated by about two-third or one-half of the observed values,related to the uncertainty in CO emissions.Compared to the other two stations,Shangdianzi had poorer simulations,especially for SO2 and CO,which partly resulted from the site location close to local emission sources from the Beijing area;and the regional inventory used was not capable of capturing the influencing factors of strong regional sources on stations.Generally,the fact that summer gave poor simulation,especially for SO2 and O 3,might partly relate to poor simulations of meteorological fields such as temperature and wind.

Dynamic background modeling using tensor representation and ant colony optimization

Background modeling and subtraction is a fundamental problem in video analysis. Many algorithms have been developed to date, but there are still some challenges in complex environments, especially dynamic scenes in which backgrounds are themselves moving, such as rippling water and swaying trees. In this paper, a novel background modeling method is proposed for dynamic scenes by combining both tensor representation and swarm intelligence. We maintain several video patches, which are naturally represented as higher order tensors,to represent the patterns of background, and utilize tensor low-rank approximation to capture the dynamic nature. Furthermore, we introduce an ant colony algorithm to improve the performance. Experimental results show that the proposed method is robust and adaptive in dynamic environments, and moving objects can be perfectly separated from the complex dynamic background.

Research of whispered speech vocal tract system conversion based on universal background model and effective Gaussian components

Directing to the weakness of the present fixed values mapping methods （method_F）, a vocal tract system conversion method based on the universal background model （UBM） is proposed for improving the performance of the speech conversion system from Chinese whis- pered speech to normal speech. For the numerous components of UBM, the errors produced by the acoustical probability density statistical model can＇t be ignored. Thus an effective Gaus- sian mixture components chosen method based on the posterior probability summation of the minimum spectral distortion is developed to optimizing the system performance. The proposed method （method_U） is analyzed and compared using the performance index （PI） based on Itakura-Saito spectral distortion measure. It is shown experimentally that the performance of method_U is more stability for different speakers and different phonemes than that of method_F. The average PI of method_U is better than method_F. It is shown that by selecting effective Gaussian mixture components, the PI of method_U can be further improved 5.11%. Subjective auditory tests also show that the proposed method can improve the definition and intelligibility of conversion speech.

A temporal-spatial background modeling of dynamic scenes

Moving object detection in dynamic scenes is a basic task in a surveillance system for sensor data collection. In this paper, we present a powerful back- ground subtraction algorithm called Gaussian-kernel density estimator （G-KDE） that improves the accuracy and reduces the computational load. The main innovation is that we divide the changes of background into continuous and stable changes to deal with dynamic scenes and moving objects that first merge into the background, and separately model background using both KDE model and Gaussian models. To get a temporal- spatial background model, the sample selection is based on the concept of region average at the update stage. In the detection stage, neighborhood information content （NIC） is implemented which suppresses the false detection due to small and un-modeled movements in the scene. The experimental results which are generated on three separate sequences indicate that this method is well suited for precise detection of moving objects in complex scenes and it can be efficiently used in various detection systems.