Background subtraction for night videos

Motion analysis is important in video surveillance systems and background subtraction is useful for moving object detection in such systems. However, most of the existing background subtraction methods do not work well for surveillance systems in the evening because objects are usually dark and reflected light is usually strong. To resolve these issues, we propose a framework that utilizes a Weber contrast descriptor, a texture feature extractor, and a light detection unit, to extract the features of foreground objects. We propose a local pattern enhancement method. For the light detection unit, our method utilizes the finding that lighted areas in the evening usually have a low saturation in hue-saturation-value and hue-saturation-lightness color spaces. Finally, we update the background model and the foreground objects in the framework. This approach is able to improve foreground object detection in night videos, which do not need a large data set for pre-training.

Download Full-text

Low Shot Box Correction for Weakly Supervised Object Detection

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/125 ◽

2019 ◽

Author(s):

Tianxiang Pan ◽

Bin Wang ◽

Guiguang Ding ◽

Jungong Han ◽

Junhai Yong

Keyword(s):

Object Detection ◽

Large Data ◽

Detection Accuracy ◽

Detection Problem ◽

Data Set ◽

Supervised Methods ◽

Weakly Supervised ◽

Bounding Boxes ◽

State Of Art ◽

Discriminative Parts

Weakly supervised object detection (WSOD) has been widely studied but the accuracy of state-of-art methods remains far lower than strongly supervised methods. One major reason for this huge gap is the incomplete box detection problem which arises because most previous WSOD models are structured on classification networks and therefore tend to recognize the most discriminative parts instead of complete bounding boxes. To solve this problem, we define a low-shot weakly supervised object detection task and propose a novel low-shot box correction network to address it. The proposed task enables to train object detectors on a large data set all of which have image-level annotations, but only a small portion or few shots have box annotations. Given the low-shot box annotations, we use a novel box correction network to transfer the incomplete boxes into complete ones. Extensive empirical evidence shows that our proposed method yields state-of-art detection accuracy under various settings on the PASCAL VOC benchmark.

Download Full-text

The histogram of partitioned localized image textures

10.32469/10355/62032 ◽

2017 ◽

Author(s):

◽

Eric B. Brewster

Keyword(s):

Object Detection ◽

Texture Classification ◽

Texture Feature ◽

Texture Features ◽

Directional Pattern ◽

Bag Of Words ◽

Data Set ◽

Pixel Location ◽

Local Direction ◽

Robustness To Noise

In the field of machine learning and pattern recognition, texture has been a prominent area of research. Humans are uniquely equipped to distinguish texture; however, computers are more equipped to automate the process. Computers accomplish this by taking images and extracting meaningful features that describe their texture. Some of these features are the Haralick texture features, local binary pattern (LBP), and the local direction pattern (LDP). Using the local directional pattern as an example, we propose a new texture feature called the histogram of partitioned localized image textures (HoPLIT). This feature utilizes a set of filters, not necessarily directional, and generates filter response vectors at every pixel location. These response vectors can be thought of as words in a document, which causes one to think of the bag-of-words model. Using the bag-of-words model, a codebook is created by partitioning a subset of response vectors from the entire data set. The partitions are represented by their mean texture and thus a word in the codebook. The mean textures now represent the keywords within the document, i.e. image. A histogram descriptor for an image is the frequency of pixels that belong to each partition. This feature is applied to a texture classification and segmentation problem as well as object detection. Within each problem domain, the HoPLIT feature is compared to the Haralick texture features, LBP, and LDP. The HoPLIT feature does very well classifying texture as well as segmenting large texture mosaics. HoPLIT also shows a surprising robustness to noise. Object detection proves to be slightly more difficult than texture classification for HoPLIT. However, it continues to outperform LBP and LDP.

Download Full-text

Child abuse and neglect surveillance systems via minimum data set indicators

PsycEXTRA Dataset ◽

10.1037/e578482014-143 ◽

2013 ◽

Author(s):

Athanasios Ntinapogias ◽

George Nikolaidis

Keyword(s):

Child Abuse ◽

Child Abuse And Neglect ◽

Minimum Data Set ◽

Surveillance Systems ◽

Data Set ◽

Minimum Data ◽

Abuse And Neglect

Download Full-text

Some statistical and CI models to predict chaotic high-frequency financial data

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189107 ◽

2020 ◽

Vol 39 (5) ◽

pp. 6419-6430

Author(s):

Dusan Marcek

Keyword(s):

Time Series Data ◽

Moving Average ◽

Methodological Approach ◽

Back Propagation ◽

Large Data ◽

Series Data ◽

Data Set ◽

Training Time ◽

Optimal Population ◽

Forecast Time

To forecast time series data, two methodological frameworks of statistical and computational intelligence modelling are considered. The statistical methodological approach is based on the theory of invertible ARIMA (Auto-Regressive Integrated Moving Average) models with Maximum Likelihood (ML) estimating method. As a competitive tool to statistical forecasting models, we use the popular classic neural network (NN) of perceptron type. To train NN, the Back-Propagation (BP) algorithm and heuristics like genetic and micro-genetic algorithm (GA and MGA) are implemented on the large data set. A comparative analysis of selected learning methods is performed and evaluated. From performed experiments we find that the optimal population size will likely be 20 with the lowest training time from all NN trained by the evolutionary algorithms, while the prediction accuracy level is lesser, but still acceptable by managers.

Download Full-text

In silico Prediction of Inhibitory Constant of Thrombin Inhibitors Using Machine Learning

Combinatorial Chemistry & High Throughput Screening ◽

10.2174/1386207322666181220130232 ◽

2019 ◽

Vol 21 (9) ◽

pp. 662-669 ◽

Cited By ~ 1

Author(s):

Junnan Zhao ◽

Lu Zhu ◽

Weineng Zhou ◽

Lingfeng Yin ◽

Yuchen Wang ◽

...

Keyword(s):

Machine Learning ◽

Prediction Models ◽

Regression Tree ◽

Large Data ◽

Thrombin Inhibitors ◽

Coagulation Cascade ◽

Gradient Boosting ◽

Support Vector ◽

Data Set ◽

Descriptor Selection

Background: Thrombin is the central protease of the vertebrate blood coagulation cascade, which is closely related to cardiovascular diseases. The inhibitory constant Ki is the most significant property of thrombin inhibitors. Method: This study was carried out to predict Ki values of thrombin inhibitors based on a large data set by using machine learning methods. Taking advantage of finding non-intuitive regularities on high-dimensional datasets, machine learning can be used to build effective predictive models. A total of 6554 descriptors for each compound were collected and an efficient descriptor selection method was chosen to find the appropriate descriptors. Four different methods including multiple linear regression (MLR), K Nearest Neighbors (KNN), Gradient Boosting Regression Tree (GBRT) and Support Vector Machine (SVM) were implemented to build prediction models with these selected descriptors. Results: The SVM model was the best one among these methods with R2=0.84, MSE=0.55 for the training set and R2=0.83, MSE=0.56 for the test set. Several validation methods such as yrandomization test and applicability domain evaluation, were adopted to assess the robustness and generalization ability of the model. The final model shows excellent stability and predictive ability and can be employed for rapid estimation of the inhibitory constant, which is full of help for designing novel thrombin inhibitors.

Download Full-text

A New Approach of Moving Object Detection Using Background Subtraction Method

2019 3rd International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE) ◽

10.1109/icecte48615.2019.9303552 ◽

2019 ◽

Author(s):

Rathyatul Rifat ◽

Jannatul Robaiat Mou ◽

Ragib Shahariar ◽

Abid Ahsan

Keyword(s):

Object Detection ◽

Background Subtraction ◽

Moving Object Detection ◽

Moving Object ◽

Subtraction Method ◽

New Approach

Download Full-text

Correlation between the structure and skin permeability of compounds

Scientific Reports ◽

10.1038/s41598-021-89587-5 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Ruolan Zeng ◽

Jiyong Deng ◽

Limin Dang ◽

Xinliang Yu

Keyword(s):

Large Data ◽

Qsar Model ◽

Coefficient Of Determination ◽

Support Vector ◽

Skin Permeability ◽

Data Set ◽

Test Set ◽

Svm Algorithm ◽

Svm Model ◽

Toxicity Relationship

AbstractA three-descriptor quantitative structure–activity/toxicity relationship (QSAR/QSTR) model was developed for the skin permeability of a sufficiently large data set consisting of 274 compounds, by applying support vector machine (SVM) together with genetic algorithm. The optimal SVM model possesses the coefficient of determination R2 of 0.946 and root mean square (rms) error of 0.253 for the training set of 139 compounds; and a R2 of 0.872 and rms of 0.302 for the test set of 135 compounds. Compared with other models reported in the literature, our SVM model shows better statistical performance in a model that deals with more samples in the test set. Therefore, applying a SVM algorithm to develop a nonlinear QSAR model for skin permeability was achieved.

Download Full-text

Galaxy spin direction distribution in HST and SDSS show similar large-scale asymmetry

Publications of the Astronomical Society of Australia ◽

10.1017/pasa.2020.46 ◽

2020 ◽

Vol 37 ◽

Author(s):

Lior Shamir

Keyword(s):

Large Scale ◽

Spiral Galaxies ◽

Hubble Space Telescope ◽

Gravitational Interaction ◽

Large Data ◽

Sloan Digital Sky Survey ◽

Data Sets ◽

Dipole Axis ◽

Data Set ◽

The Asymmetry

Abstract Several recent observations using large data sets of galaxies showed non-random distribution of the spin directions of spiral galaxies, even when the galaxies are too far from each other to have gravitational interaction. Here, a data set of $\sim8.7\cdot10^3$ spiral galaxies imaged by Hubble Space Telescope (HST) is used to test and profile a possible asymmetry between galaxy spin directions. The asymmetry between galaxies with opposite spin directions is compared to the asymmetry of galaxies from the Sloan Digital Sky Survey. The two data sets contain different galaxies at different redshift ranges, and each data set was annotated using a different annotation method. The results show that both data sets show a similar asymmetry in the COSMOS field, which is covered by both telescopes. Fitting the asymmetry of the galaxies to cosine dependence shows a dipole axis with probabilities of $\sim2.8\sigma$ and $\sim7.38\sigma$ in HST and SDSS, respectively. The most likely dipole axis identified in the HST galaxies is at $(\alpha=78^{\rm o},\delta=47^{\rm o})$ and is well within the $1\sigma$ error range compared to the location of the most likely dipole axis in the SDSS galaxies with $z>0.15$ , identified at $(\alpha=71^{\rm o},\delta=61^{\rm o})$ .

Download Full-text

The Complete DNA Sequence of the Mitochondrial Genome of a “Living Fossil,” the Coelacanth (Latimeria chalumnae)

Genetics ◽

10.1093/genetics/146.3.995 ◽

1997 ◽

Vol 146 (3) ◽

pp. 995-1010 ◽

Cited By ~ 1

Author(s):

Rafael Zardoya ◽

Axel Meyer

Keyword(s):

Mitochondrial Genome ◽

Tandem Repeats ◽

Phylogenetic Analyses ◽

Large Data ◽

Molecular Data ◽

Phylogenetic Position ◽

Data Set ◽

Living Fossil ◽

Latimeria Chalumnae ◽

Relationship Of

The complete nucleotide sequence of the 16,407-bp mitochondrial genome of the coelacanth (Latimeria chalumnae) was determined. The coelacanth mitochondrial genome order is identical to the consensus vertebrate gene order which is also found in all ray-finned fishes, the lungfish, and most tetrapods. Base composition and codon usage also conform to typical vertebrate patterns. The entire mitochondrial genome was PCR-amplified with 24 sets of primers that are expected to amplify homologous regions in other related vertebrate species. Analyses of the control region of the coelacanth mitochondrial genome revealed the existence of four 22-bp tandem repeats close to its 3′ end. The phylogenetic analyses of a large data set combining genes coding for rRNAs, tRNA, and proteins (16,140 characters) confirmed the phylogenetic position of the coelacanth as a lobe-finned fish; it is more closely related to tetrapods than to ray-finned fishes. However, different phylogenetic methods applied to this largest available molecular data set were unable to resolve unambiguously the relationship of the coelacanth to the two other groups of extant lobe-finned fishes, the lungfishes and the tetrapods. Maximum parsimony favored a lungfish/coelacanth or a lungfish/tetrapod sistergroup relationship depending on which transversion:transition weighting is assumed. Neighbor-joining and maximum likelihood supported a lungfish/tetrapod sistergroup relationship.

Download Full-text