Local Background Model Research Articles

Moving Object Detection in Freely Moving Camera via Global Motion Compensation and Local Spatial Information Fusion.

Motion object detection (MOD) with freely moving cameras is a challenging task in computer vision. To extract moving objects, most studies have focused on the difference in motion features between foreground and background, which works well for dynamic scenes with relatively regular movements and variations. However, abrupt illumination changes and occlusions often occur in real-world scenes, and the camera may also pan, tilt, rotate, and jitter, etc., resulting in local irregular variations and global discontinuities in motion features. Such complex and changing scenes bring great difficulty in detecting moving objects. To solve this problem, this paper proposes a new MOD method that effectively leverages local and global visual information for foreground/background segmentation. Specifically, on the global side, to support a wider range of camera motion, the relative inter-frame transformations are optimized to absolute transformations referenced to intermediate frames in a global form after enriching the inter-frame matching pairs. The global transformation is fine-tuned using the spatial transformer network (STN). On the local side, to address the problem of dynamic background scenes, foreground object detection is optimized by utilizing the pixel differences between the current frame and the local background model, as well as the consistency of local spatial variations. Then, the spatial information is combined using optical flow segmentation methods, enhancing the precision of the object information. The experimental results show that our method achieves a detection accuracy improvement of over 1.5% compared with the state-of-the-art methods on the datasets of CDNET2014, FBMS-59, and CBD. It demonstrates significant effectiveness in challenging scenarios such as shadows, abrupt changes in illumination, camera jitter, occlusion, and moving backgrounds.

Reconstructing robust background integral field unit spectra using machine learning

ABSTRACT In astronomy, spectroscopy consists of observing an astrophysical source and extracting its spectrum of electromagnetic radiation. Once extracted, a model is fit to the spectra to measure the observables, leading to an understanding of the underlying physics of the emission mechanism. One crucial, and often overlooked, aspect of this model is the background emission, which contains foreground and background astrophysical sources, intervening atmospheric emission, and artefacts related to the instrument such as noise. This paper proposes an algorithmic approach to constructing a background model for SITELLE observations using statistical tools and supervised machine learning algorithms. SITELLE is an imaging Fourier transform spectrometer located at the Canada-France-Hawaii Telescope, which produces a three-dimensional data cube containing the position of the emission (two dimensions) and the spectrum of the emission. SITELLE has a wide field of view (11 arcmin × 11 arcmin), which makes the background emission particularly challenging to model. We apply a segmentation algorithm implemented in photutils to divide the data cube into background and source spaxels. After applying a principal component analysis (PCA) on the background spaxels, we train an artificial neural network to interpolate from the background to the source spaxels in the PCA coefficient space, which allows us to generate a local background model over the entire data cube. We highlight the performance of this methodology by applying it to SITELLE observations obtained of a Star-formation, Ionized Gas and Nebular Abundances Legacy Survey galaxy, NGC 4449, and the Perseus galaxy cluster of galaxies, NGC 1275. We discuss the physical interpretation of the principal components and noise reduction in the resulting PCA-based reconstructions. Additionally, we compare the fit results using our new background modelling approach with standard methods used in the literature and find that our method better captures the emission from H ii regions in NGC 4449 and the faint emission regions in NGC 1275. These methods also demonstrate that the background does change as a function of the position of the data cube. While the approach is applied explicitly to SITELLE data in this study, we argue that it can be readily adapted to any integral field unit style data, enabling the user to obtain more robust measurements on the flux of the emission lines.

Anomaly Detection of Remote Sensing Images Based on the Channel Attention Mechanism and LRX

Anomaly detection of remote sensing images has gained significant attention in remote sensing image processing due to their rich spectral information. The Local RX (LRX) algorithm, derived from the Reed–Xiaoli (RX) algorithm, is a hyperspectral anomaly detection method that focuses on identifying anomalous pixels in hyperspectral images by exploiting local statistics and background modeling. However, it is still susceptible to the noises in the Hyperspectral Images (HSIs), which limits its detection performance. To address this problem, a hyperspectral anomaly detection algorithm based on channel attention mechanism and LRX is proposed in this paper. The HSI is feed into the auto-encoder network that is constrained by the channel attention module to generate a more representative reconstructed image that better captures the characteristics of different land covers and has less noises. The channel attention module in the auto-encoder network aims to explore the effective spectral bands corresponding to different land covers. Subsequently, the LRX algorithm is utilized for anomaly detection on the reconstructed image obtained from the auto-encoder network with the channel attention mechanism, which avoids the influence of noises on the anomaly detection results and improves the anomaly detection performance. The experiments are conducted on three HSIs to verify the performance of the proposed method. The proposed hyperspectral anomaly detection method achieves higher Area Under Curve (AUC) values of 0.9871, 0.9916 and 0.9642 on HYDICE urban dataset, AVIRIS aircraft dataset and Salinas Valley dataset, respectively, compared with other six methods. The experimental results demonstrate that the proposed algorithm has better anomaly detection performance than LRX and other algorithms.

A new cast shadow detection method for traffic surveillance video analysis using color and statistical modeling

In traffic surveillance video analysis systems, the cast shadows of vehicles often have a negative effect on video analysis results. A novel cast shadow detection framework, which consists of a new foreground detection method and a cast shadow detection method, is presented in this paper to detect and remove the cast shadows from the foreground. The new foreground detection method applies an innovative Global Foreground Modeling (GFM) method, a Gaussian mixture model or GMM, and the Bayes classifier for foreground and background classification. While the GFM method is for global foreground modeling, the GMM is for local background modeling, and the Bayes classifier applies both the foreground and the background models for foreground detection. The rationale of the GFM method stems from the observation that the foreground objects often appear in recent frames and their trajectories often lead them to different locations in these frames. As a result, the statistical models used to characterize the foreground objects should not be pixel based or locally defined. The cast shadow detection method contains four hierarchical steps. First, a set of new chromatic criteria is presented to detect the candidate shadow pixels in the HSV color space. Second, a new shadow region detection method is proposed to cluster the candidate shadow pixels into shadow regions. Third, a statistical shadow model, which uses a single Gaussian distribution to model the shadow class, is presented for classifying shadow pixels. Fourth, an aggregated shadow detection method is presented for final shadow detection. Experiments using the public video data ‘Highway-1’ and ‘Highway-3’, and the New Jersey Department of Transportation (NJDOT) real traffic video sequences show the feasibility of the proposed method. In particular, the proposed method achieves better shadow detection performance than the popular shadow detection methods, and is able to improve the traffic video analysis results.

OncodriveCLUSTL: a sequence-based clustering method to identify cancer drivers.

MotivationIdentification of the genomic alterations driving tumorigenesis is one of the main goals in oncogenomics research. Given the evolutionary principles of cancer development, computational methods that detect signals of positive selection in the pattern of tumor mutations have been effectively applied in the search for cancer genes. One of these signals is the abnormal clustering of mutations, which has been shown to be complementary to other signals in the detection of driver genes.ResultsWe have developed OncodriveCLUSTL, a new sequence-based clustering algorithm to detect significant clustering signals across genomic regions. OncodriveCLUSTL is based on a local background model derived from the simulation of mutations accounting for the composition of tri- or penta-nucleotide context substitutions observed in the cohort under study. Our method can identify known clusters and bona-fide cancer drivers across cohorts of tumor whole-exomes, outperforming the existing OncodriveCLUST algorithm and complementing other methods based on different signals of positive selection. Our results indicate that OncodriveCLUSTL can be applied to the analysis of non-coding genomic elements and non-human mutations data.Availability and implementationOncodriveCLUSTL is available as an installable Python 3.5 package. The source code and running examples are freely available at https://bitbucket.org/bbglab/oncodriveclustl under GNU Affero General Public License.Supplementary information Supplementary data are available at Bioinformatics online.

Promoter-enhancer interactions identified from Hi-C data using probabilistic models and hierarchical topological domains

Proximity-ligation methods such as Hi-C allow us to map physical DNA–DNA interactions along the genome, and reveal its organization into topologically associating domains (TADs). As the Hi-C data accumulate, computational methods were developed for identifying domain borders in multiple cell types and organisms. Here, we present PSYCHIC, a computational approach for analyzing Hi-C data and identifying promoter–enhancer interactions. We use a unified probabilistic model to segment the genome into domains, which we then merge hierarchically and fit using a local background model, allowing us to identify over-represented DNA–DNA interactions across the genome. By analyzing the published Hi-C data sets in human and mouse, we identify hundreds of thousands of putative enhancers and their target genes, and compile an extensive genome-wide catalog of gene regulation in human and mouse. As we show, our predictions are highly enriched for ChIP-seq and DNA accessibility data, evolutionary conservation, eQTLs and other DNA–DNA interaction data.

Discovery of Cancer Driver Long Noncoding RNAs across 1112 Tumour Genomes: New Candidates and Distinguishing Features

Long noncoding RNAs (lncRNAs) represent a vast unexplored genetic space that may hold missing drivers of tumourigenesis, but few such “driver lncRNAs” are known. Until now, they have been discovered through changes in expression, leading to problems in distinguishing between causative roles and passenger effects. We here present a different approach for driver lncRNA discovery using mutational patterns in tumour DNA. Our pipeline, ExInAtor, identifies genes with excess load of somatic single nucleotide variants (SNVs) across panels of tumour genomes. Heterogeneity in mutational signatures between cancer types and individuals is accounted for using a simple local trinucleotide background model, which yields high precision and low computational demands. We use ExInAtor to predict drivers from the GENCODE annotation across 1112 entire genomes from 23 cancer types. Using a stratified approach, we identify 15 high-confidence candidates: 9 novel and 6 known cancer-related genes, including MALAT1, NEAT1 and SAMMSON. Both known and novel driver lncRNAs are distinguished by elevated gene length, evolutionary conservation and expression. We have presented a first catalogue of mutated lncRNA genes driving cancer, which will grow and improve with the application of ExInAtor to future tumour genome projects.

An Effective Method for Modeling Two-dimensional Sky Background of LAMOST

AbstractEach CCD of LAMOST accommodates 250 spectra, while about 40 are used to observe sky background during real observations. How to estimate the unknown sky background information hidden in the observed 210 celestial spectra by using the known 40 sky spectra is the problem we solve. In order to model the sky background, usually a pre-observation is performed with all fibers observing sky background. We use the observed 250 skylight spectra as training data, where those observed by the 40 fibers are considered as a base vector set. The Locality-constrained Linear Coding (LLC) technique is utilized to represent the skylight spectra observed by the 210 fibers with the base vector set. We also segment each spectrum into small parts, and establish the local sky background model for each part. Experimental results validate the proposed method, and show the local model is better than the global model.

Local-to-global background modeling for moving object detection from non-static cameras

This paper investigates efficient and robust moving object detection from non-static cameras. To tackle the motion of background caused by moving cameras and to alleviate the interference of noises, we propose a local-to-global background model for moving object detection. Firstly, motion compensation based local location-specific background model is deployed to roughly detect the foreground regions in non-static cameras. More specifically, the local background model is built for each pixel and represented by a set of pixel values drawn from its location and neighborhoods. Each pixel can be classified as foreground or background pixel according to the compensated background model based on the fast optical flow. Secondly, we estimate the global background model by the rough superpixel-based background regions to further separate foregrounds from background accurately. In particular, we use the superpixel to generate the initial background regions based on the detection results generated by local background model to alleviate the noises. Then, a Gaussian Mixture Model (GMM) is estimated for the backgrounds on superpixel level to refine the foreground regions. Extensive experiments on newly created dataset, including 10 challenging video sequences recorded in PTZ cameras and hand-held cameras, suggest that our method outperforms other state-of-the-art methods in accuracy.

Background Subtraction Based on Pulse Coupled Neural Network

Dynamic environments often bring great challenges to moving object detection. Solving this problem will promote expansion of application fields of moving object detection. Unlike those background subtraction methods using local feature-based background models, inspired by integrity of human visual perception, we present a background subtraction method for moving object detection in dynamic environments, building its background models based on global features extracted by pulse coupled neural network. We employ the pulse coupled neural network to take good advantage of their global coupling characters, in order to imitate the human biological visual activity. After sensing images via the pulse coupled neural network, we extract global information of the scenes and then build background models robust to background disturbances based on the global features. Experimental results prove that, our method behaves well in terms of visual and quantitative evaluations for dynamic environments.

An object tracking method based on local matting for night fusion image

This paper presents a new tracking method based on local matting approach for accurate and robust night fusion image tracking. Firstly, frame difference is applied to produce the coarse target, which helps to generate foreground and local background models. These models provide sufficient and accurate restriction for matting, which makes matting applicable in tracking process. Then accurate boundaries of the target can be extracted from matting results. Finally tracking results is used to construct and update foreground and background models in time. Extensive experiments show that our scheme can largely avoid model drift and show good performance when targets are deforming and quick moving.

Lane Detection in Video-Based Intelligent Transportation Monitoring via Fast Extracting and Clustering of Vehicle Motion Trajectories

Lane detection is a crucial process in video-based transportation monitoring system. This paper proposes a novel method to detect the lane center via rapid extraction and high accuracy clustering of vehicle motion trajectories. First, we use the activity map to realize automatically the extraction of road region, the calibration of dynamic camera, and the setting of three virtual detecting lines. Secondly, the three virtual detecting lines and a local background model with traffic flow feedback are used to extract and group vehicle feature points in unit of vehicle. Then, the feature point groups are described accurately by edge weighted dynamic graph and modified by a motion-similarity Kalman filter during the sparse feature point tracking. After obtaining the vehicle trajectories, a roughk-means incremental clustering with Hausdorff distance is designed to realize the rapid online extraction of lane center with high accuracy. The use of rough set reduces effectively the accuracy decrease, which results from the trajectories that run irregularly. Experimental results prove that the proposed method can detect lane center position efficiently, the affected time of subsequent tasks can be reduced obviously, and the safety of traffic surveillance systems can be enhanced significantly.

Particle Filter Tracking of Camouflaged Targets by Adaptive Fusion of Thermal and Visible Spectra Camera Data

This paper presents a method for tracking a moving target by fusing bi-modal visual information from a deep infra-red thermal imaging camera and a conventional visible spectrum color camera. The tracking method builds on well-known methods for color-based tracking using particle filtering, but it extends these to handle fusion of color and thermal information when evaluating each particle. The key innovation is a method for continuously relearning local background models for each particle in each imaging modality, comparing these against a model of the foreground object being tracked, and thereby adaptively weighting the data fusion process in favor of whichever imaging modality is currently the most discriminating at each successive frame. The method is evaluated by testing on a variety of extremely challenging video sequences, in which people and other targets are tracked past occlusion, clutter, and distracters causing severe and sustained camouflage conditions in one or both imaging modalities.

Robust tracking via patch-based appearance model and local background estimation

In this paper, to simultaneously address the tracker drift and occlusion problem, we propose a robust visual tracking algorithm via a patch-based adaptive appearance model driven by local background estimation. Inspired by human visual mechanisms (i.e., context-awareness and attentional selection), an object is represented with a patch-based appearance model, in which each patch outputs a confidence map during the tracking. Then, these confidence maps are combined via a robust estimator to finally get more robust and accurate tracking results. Moreover, we present a local spatial co-occurrence based background modeling approach to automatically estimate the local context background model of an interested object captured from a single camera, which may be stationary or moving. Finally, we utilize local background estimation to provide supervision to an analysis of possible occlusions and the adaption of patch-based appearance model of an object. Qualitative and quantitative experimental results on challenging videos demonstrate the robustness of the proposed method.

ONLINE SPEAKER DIARIZATION FOR MULTIMEDIA DATA RETRIEVAL ON MOBILE DEVICES

Speaker diarization detects speaker change points in spoken data and organizes speaker clusters so that each cluster contains one speaker's segments. This study aims to develop online speaker diarization for multimedia data retrieval on mobile devices. Researchers have proposed various methods of diarization, but most approaches thus far depend on an empirically determined threshold as a criterion or work in an offline manner that requires prior knowledge, such as the overall number of speakers. There are therefore clear drawbacks with mobile devices, on which various types of spoken data are frequently played and replaced. A new approach to online speaker segmentation and clustering is proposed for overcoming these drawbacks. The proposed segmentation method considers the temporal locality of an analysis window, assuming that each window contains only a small number of speakers. In accordance with this property, a local universal background model (UBM) is constructed in a window and the model is used to detect speaker change points. A cluster boundary-based dynamic decision criterion is proposed for speaker clustering. This approach estimates the internal characteristics of clusters and uses them to determine cluster boundaries. In experiments using a broadcast news corpus, our techniques exhibited superior performance compared to conventional approaches.

Statistical Local Difference Pattern for Background Modeling

Object detection is an important task for computer vision applications. Many researchers have proposed a number of methods to detect the objects through background modeling. To adapt to “illumination changes” in the background, local feature-based background models are proposed. They assume that local features are not affected by background changes. However, “motion changes”, such as the movement of trees, affect the local features in the background significantly. Therefore, it is difficult for local feature-based models to handle motion changes in the background. To solve this problem, we propose a new background model in this paper by applying a statistical framework to a local feature-based approach. Our proposed method combines the concepts of statistical and local feature-based approaches into a single framework. In particular, we use illumination invariant local features and describe their distribution by Gaussian Mixture Models (GMMs). The local feature has the ability to tolerate the effects of “illumination changes”, and the GMM can learn the variety of “motion changes”. As a result, this method can handle both background changes. Some experimental results show that the proposed method can detect the foreground objects robustly against both illumination changes and motion changes in the background.

CompleteMOTIFs: DNA motif discovery platform for transcription factor binding experiments

CompleteMOTIFs (cMOTIFs) is an integrated web tool developed to facilitate systematic discovery of overrepresented transcription factor binding motifs from high-throughput chromatin immunoprecipitation experiments. Comprehensive annotations and Boolean logic operations on multiple peak locations enable users to focus on genomic regions of interest for de novo motif discovery using tools such as MEME, Weeder and ChIPMunk. The pipeline incorporates a scanning tool for known motifs from TRANSFAC and JASPAR databases, and performs an enrichment test using local or precalculated background models that significantly improve the motif scanning result. Furthermore, using the cMOTIFs pipeline, we demonstrated that multiple transcription factors could cooperatively bind to the upstream of important stem cell differentiation regulators. http://cmotifs.tchlab.org.