Application of EM algorithm in problems of pattern recognition on satellite images

Akinin, Maxim V.; Akinina, Alexandra V.; Соколов, А. В.; Tarasov, Andrey S.

doi:10.1109/meco.2017.7977190

Cited by 4 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notation: ↑ (↓) represents the higher (lower) the measure, the better the performance. T2 [1,20] T3 [1,30] T4 [1,20]& [20,35] T5 [5,20]& [30,40] T6 [1,10]& [15,25]& [30,40] Fig. 3: The targets tracking trajectories and lifetime in ground coordinate system.…”

Section: B Performance Measuresmentioning

confidence: 99%

“…The expectation maximization (EM) algorithm is an effectively iterative optimization approach to compute maximum likelihood estimates, useful in the presence of incomplete data [24]. Akinin et al aimed to tackle pattern recognition on satellite images by presenting a new expectation maximization image segmentation method [25]. Einicke et al adopted Kmeans algorithm as the initial setting for clustering results to speed up the convergence of EM algorithm [26].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Joint Multitarget Detection and Tracking in Multipath Environment Using Expectation Maximization Algorithm

Liu

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Joint detection and tracking is fundamentally important in signal processing, navigation, and radar applications. Especially, multitarget detection and tracking in multipath environments is a promising issue and broadening range for joint detection and tracking. However, its wide adoption in realworld systems is challenged by the unknown data association, complex and changeable motion environment, and data mutual coupling. To address those problems, we propose a joint detection and tracking scheme based on expectation maximization (EM) algorithm. By alternately computing the complete likelihood function and optimizing it with respect to target existence state (detection) and target kinematic state (tracking), the proposed scheme iteratively optimizes estimation and data association. Furthermore, we provide a hybrid forward and backward algorithm during the M-step to deal with the coupling of the target existence state and target kinematic state. We also provide a convergence speed-up algorithm based on K-means method and stochastic initialization method to accelerate convergence speed. Finally, we verify the effectiveness of the proposed joint detection and tracking scheme by conducting extensive simulations with different tracking scenarios. The simulation results show that the proposed algorithm not only improves the detection and tracking performance but also stays stable performance in complex and changeable motion environment and high noise background.

show abstract

Section: B Performance Measuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Joint Multitarget Detection and Tracking in Multipath Environment Using Expectation Maximization Algorithm

Liu

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The authors consider computer vision implementation in the context of embedding it in automobiles to automate road traffic by analyzing video stream, that is why its incorrect work can cause fatal consequences. Authors of various scientific works agree that one of the main purposes in the area of computer vision is the error percentage reduction in the pattern recognition [3], [4]. The pattern recognition error is understood as situation when the needed object either is not detected or is detected incorrectly.…”

Section: A Computer Vision Implementationmentioning

confidence: 99%

Methods of Semantic Integrity Preservation in the Pattern Recognition Process

Kim

Matveeva

Viksnin

et al. 2019

International Journal of Embedded and Real-Time Communication Systems

View full text Add to dashboard Cite

Computer vision is a wide area of theoretical research and technical methods connected with object detection, object tracking and object classification. In this article computer vision is considered in context of embedding it into automobiles in order to automate the road traffic process through video stream analysis. During road traffic it is vital to detect objects quickly and correctly, so the authors pay attention to the pattern recognition quality, especially to the visual information semantic integrity preservation. Their main purpose is to find the ways of its possible improvement respectively to three basic stages of the pattern recognition process. To avoid semantic integrity violations of information in the initial stage of the image analysis the authors propose normalization; in the second stage new clustering method was developed based on particle swarm optimization and k-means algorithm; in the final stage of the pattern recognition process the Haar cascade classifier was used with normalized training samples. The obtained image processing algorithm was implemented in case of blurred and noisy images and proved its effectiveness respectively to the visual information semantic integrity preservation.

show abstract

“…Texture is one of the key structural characteristics of an image, used to identify objects or regions of interest in an image, and it is also in line with human visual characteristics [25,26]. Texture extraction is critical as it serves as an input for further advanced processing and has a significant impact on the quality of extraction [27]; therefore, numerous studies on texture extraction from remote sensing data have been conducted (e.g., [27][28][29][30]). Moreover, texture-related research is still a hotspot for researchers in computer vision and image processing, while it is continuously evolving [31].…”

Section: Introductionmentioning

confidence: 99%

Building Change Detection Based on a Gray-Level Co-Occurrence Matrix and Artificial Neural Networks

Christaki

Vasilakos

Papadopoulou

et al. 2022

Drones

View full text Add to dashboard Cite

The recovery phase following an earthquake event is essential for urban areas with a significant number of damaged buildings. A lot of changes can take place in such a landscape within the buildings’ footprints, such as total or partial collapses, debris removal and reconstruction. Remote sensing data and methodologies can considerably contribute to site monitoring. The main objective of this paper is the change detection of the building stock in the settlement of Vrissa on Lesvos Island during the recovery phase after the catastrophic earthquake of 12 June 2017, through the analysis and processing of UAV (unmanned aerial vehicle) images and the application of Artificial Neural Networks (ANNs). More specifically, change detection of the settlement’s building stock by applying an ANN on Gray-Level Co-occurrence Matrix (GLCM) texture features of orthophotomaps acquired by UAVs was performed. For the training of the ANN, a number of GLCM texture features were defined as the independent variable, while the existence or not of structural changes in the buildings were defined as the dependent variable, assigning, respectively, the values 1 or 0 (binary classification). The ANN was trained based on the Levenberg–Marquardt algorithm, and its ability to detect changes was evaluated on the basis of the buildings’ condition, as derived from the binary classification. In conclusion, the GLCM texture feature changes in conjunction with the ANN can provide satisfactory results in predicting the structural changes of buildings with an accuracy of almost 92%.

show abstract

Application of EM algorithm in problems of pattern recognition on satellite images

Cited by 4 publications

References 3 publications

Joint Multitarget Detection and Tracking in Multipath Environment Using Expectation Maximization Algorithm

Joint Multitarget Detection and Tracking in Multipath Environment Using Expectation Maximization Algorithm

Methods of Semantic Integrity Preservation in the Pattern Recognition Process

Building Change Detection Based on a Gray-Level Co-Occurrence Matrix and Artificial Neural Networks

Contact Info

Product

Resources

About