3D Local Spatio-temporal Ternary Patterns for Moving Object Detection in Complex Scenes

Vasamsetti, Srikanth; Mittal, Neerja; Neelapu, Bala Chakravarthy; Sardana, Harish Kumar

doi:10.1007/s12559-018-9594-5

Cited by 12 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To eliminate most of the effects of changing illumination and noise, Tan X and Triggs B [26] introduced the local ternary pattern (LTP) operator, which is more discriminant and less sensitive to noise in uniform regions. Then, the scale invariant local ternary patterns (SILTP) [27] and 3D local spatiotemporal ternary patterns (3D-LStTP) [28] were applied to the background model. An SILTP that improved the performance of the LTP was combined with the pattern kernel density estimation technique to model the probability distribution of local patterns under varying illumination situations.…”

Section: Compared With Histogram Of Oriented Gradients (Hog) Andmentioning

confidence: 99%

Background Subtraction Using an Adaptive Local Median Texture Feature in Illumination Changes Urban Traffic Scenes

et al. 2020

View full text Add to dashboard Cite

Background subtraction is commonly employed in foreground object detection in urban traffic scenes. Most of the current color or texture feature-based background subtraction models are easily contaminated by sudden and gradual illumination variations in urban traffic scenes. To resolve this deficiency, an adaptive local median texture feature, which extracts the adaptive distance threshold employing the median information in a predefined local region of a pixel and Weber's law, is introduced. In addition, a sample consensus-based model that evolved from portable visual background extractor is proposed using an adaptive local median texture feature. Then, the foreground is labeled by comparing the input video frames feature with the model. Moreover, to adapt the dynamic background, the random update scheme is used to update the model. Extensive experimental results on the public Change Detection data set of 2014 (CDnet2014) and the real-world urban traffic videos demonstrate that our background subtraction method is superior to the other state-of-the-art texture-feature-based methods. The qualitative and quantitative results show the encouraging efficiency of the proposed technique to deal with sudden and gradual illumination variations in real-world urban traffic scenes. INDEX TERMS background modeling, illumination variations, local median texture feature, urban traffic scenes

show abstract

Section: Compared With Histogram Of Oriented Gradients (Hog) Andmentioning

confidence: 99%

Background Subtraction Using an Adaptive Local Median Texture Feature in Illumination Changes Urban Traffic Scenes

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Specifically, they used a CRF-based optimization to concatenate the shadow pixels to produce a more coherent shadow contour and remove the high unlikely shadow boundaries and isolate weak edges. In contrast, in this study, we propose an ADT filter able to extract HOS and optical features only along the direction of boundary (in simple and complex real scenes) avoiding redundant information [67]. The estimated parameters are then used as input to a very simple and computationally not expensive MLP architecture to perform the 2-way classification task: shadow vs. non-shadow.…”

Section: Comparison Of Shadow Detection Modelsmentioning

confidence: 99%

A Novel Approach to Shadow Boundary Detection Based on an Adaptive Direction-Tracking Filter for Brain-Machine Interface Applications

Hussain

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

In this paper, a Brain-Machine Interface (BMI) system is proposed to automatically control the navigation of wheelchairs by detecting the shadows on their route. In this context, a new algorithm to detect shadows in a single image is proposed. Specifically, a novel adaptive direction tracking filter (ADT) is developed to extract feature information along the direction of shadow boundaries. The proposed algorithm avoids extraction of features around all directions of pixels, which significantly improves the efficiency and accuracy of shadow features extraction. Higher-order statistics (HOS) features such as skewness and kurtosis in addition to other optical features are used as input to different Machine Learning (ML) based classifiers, specifically, a Multilayer Perceptron (MLP), Autoencoder (AE), 1D-Convolutional Neural Network (1D-CNN) and Support Vector Machine (SVM), to perform the shadow boundaries detection task. Comparative results demonstrate that the proposed MLP-based system outperforms all the other state-of-the-art approaches, reporting accuracy rates up to 84.63%.

show abstract

“…В интересах этого могут использоваться как рекуррентные, так и нейронные сети прямого распространения. Среди сетей прямого распространения для обработки потоков кадров нашли широкое применение двухмерные и трехмерные сверточные нейронные сети [4,[7][8][9][10][11]. Эти сети после глубокого обучения позволя-ют успешно распознавать наблюдаемые объекты и динамические сцены.…”

Section: Introductionunclassified

Recurrent neural networks with controlled elements in restoring frame flows

Osipov¹,

Nikiforov²

2019

ICS

View full text Add to dashboard Cite

Introduction: Various interfering influences raise pressing problems of promptly restoring the flow of distorted frames,remembering about the background and dynamics of the event measurement laws. The traditional methods of recovering flows ofdistorted frames do not fully take into account the peculiarities of this process. Purpose: Exploring the possibilities of recurrent neuralnetworks with controlled elements for restoring frame flows. Results: It is proposed to evaluate the potential of a recurrent neuralnetwork with controlled elements by the number of successful options for restoring a distorted sequence of frames. Evaluation of thecapabilities of such neural networks according to the introduced indicator showed their strong dependence on the type of networkstructure and settings. Recurrent neural networks with spiral structures of layers work better. As the number of the turns in the helixgrows, the network capabilities also grow. Enhancing the capacity of a network to restore distorted frame flows is feasible if we replaceunipolar functions of the synapse weights by bipolar ones. A significant increase in the capabilities of the neural networks under studyis possible by controlling the neuron excitation thresholds in order to provide sequential rather than parallel elimination of variouserrors. In contrast to the conventional neural networks, recurrent neural networks with controlled elements can adapt to changes in№ 5, 2019 ИНФОРМАЦИОННОУПРАВЛЯЮЩИЕ СИСТЕМЫ 17ОБРАБОТКА ИНФОРМАЦИИ И УПРАВЛЕНИЕthe laws inherent in frame flows, and implement controlled associative signal processing. Experiments have shown that these neuralnetworks can use associative connections for taking into account deep current experience in signal processing, and be successfully usedfor restoring distorted frame flows.

show abstract

3D Local Spatio-temporal Ternary Patterns for Moving Object Detection in Complex Scenes

Cited by 12 publications

References 39 publications

Background Subtraction Using an Adaptive Local Median Texture Feature in Illumination Changes Urban Traffic Scenes

Background Subtraction Using an Adaptive Local Median Texture Feature in Illumination Changes Urban Traffic Scenes

A Novel Approach to Shadow Boundary Detection Based on an Adaptive Direction-Tracking Filter for Brain-Machine Interface Applications

Recurrent neural networks with controlled elements in restoring frame flows

Contact Info

Product

Resources

About