Real-Time Landmine Detection with Ground-Penetrating Radar Using Discriminative and Adaptive Hidden Markov Models

Frigui, Hichem; Ho, K. C.; Gader, Paul D.

doi:10.1155/asp.2005.1867

Cited by 47 publications

(32 citation statements)

References 30 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ground penetrating radar (GPR) sensors have been used in a variety of land mine detection systems for quite some time [1,12] and various algorithms for precessing GPR data to detect mines and discriminate between landmines and non-mine clutter objects have been employed [39,38,40,36,34,29,50,117].…”

Section: Ground Penetrating Radar (Gpr)mentioning

confidence: 99%

“…The principal component transform is a common feature extraction tool [129], as are wavelets [13], image processing based differentiation [38], and Hough and Radon transforms [116]. Confidence assignment can be performed using methods such as Bayesian [116], hidden Markov Models [38,29]' fuzzy logic [39], rules and order statistics [37], neural networks, or nearest neighbor classifiers [28].…”

Section: Landmine Detection Algorithmsmentioning

confidence: 99%

“…In Equation The HMM algorithm for land mine detection using GPR [38,29] The HMM classifier for land mine detection consists of two HMM models, one for mine and one for background. Each model has three states and produces a probability value by backtracking through model states using the Viterbi algorithm [24] .…”

Section: Data Preprocessingmentioning

confidence: 99%

See 2 more Smart Citations

A generic framework for context-dependent fusion with application to landmine detection.

Abdallah¹

View full text Add to dashboard Cite

Whoever slays a soul, ... , it is as though he slew all men; and whoever keeps it alive, it is as though he kept alive all men Quran 5:32As afootballer I can't imagine life without the use of one of my legs ... Sadly this is exactly what happens to thousands of children every yearwhen they accidentally step on a landmine. Ryan Giggs iii ACKNOWLEDGEMENTSI would like to express my deepest gratitude to my advisor, Dr. Hichem Frigui, for giving me the opportunity to be a member in his research group and for his support over the course of this work. He provided a very rich working environment with many opportunities to develop new ideas, work in promising applications and get experience in diverse areas. I am indebted to his support and help. For complex detection and classification problems, involving data with large intraclass variations and noisy inputs, no single source of information can provide a satisfactory solution. As a result, combination of multiple classifiers is playing an increasing role in solving these complex pattern recognition problems, and has proven to be a viable alternative to using a single classifier.Over the past few years, a variety of schemes have been proposed for combining multiple classifiers. Most of these were global as they assign a degree of worthiness to each classifier, that is averaged over the entire training data. This may not be the optimal way to combine the different experts since the behavior of each one may not be uniform over the different regions of the feature space. To overcome this issue, few local methods have been proposed in the last few years. Local fusion methods aim to adapt the classifiers' worthiness to different regions of the feature space. First, they partition the input samples. Then, they identify the best classifier for each partition and designate it as the expert for that partition. Unfortunately, current local methods are either computationally expensive and/or perform these two tasks independently of each other. However, feature space partition and algorithm selection are not independent and their optimization should be simultaneous. CELF-CA is another extension of CELF that adds a regularization term to the objective function to introduce competition among the clusters and to find the optimal number of clusters in an unsupervised way. CELF-CA starts by partitioning the data into a large number of small clusters. As the algorithm progresses, adjacent clusters compete for data points, and clusters that lose the competition gradually become depleted and vanish. Third, we propose CELF-M that generalizes CELF to support multiple classes data sets.The baseline CELF and its extensions were formulated to use linear aggregation to combine the output of the different algorithms within each context. For some applications, this can be too restrictive and non-linear fusion may be needed. To address this potential drawback, we propose two other variations of CELF that use non-linear aggregation. The first one is based on Neural Networks (CELF-NN) and the second ...

show abstract

Section: Ground Penetrating Radar (Gpr)mentioning

confidence: 99%

Section: Landmine Detection Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

A generic framework for context-dependent fusion with application to landmine detection.

Abdallah¹

View full text Add to dashboard Cite

show abstract

“…Confidence assignment algorithms can use methods such as Bayesian [87], hidden Markov Models [86,88,34], fuzzy logic [89], rules and order statistics [90], neural networks, or nearest neighbor classifiers [91,92], to assign a confidence that a mine is present at a point. Decision-making algorithms often post-process the data to remove spurious responses and use a set of confidence values produced by the confidence assignment algorithm to make a final mine/no-mine decision.…”

Section: Introductionmentioning

confidence: 99%

“…In [86,88], hidden Markov modeling was proposed for detecting both metal and nonmetal mine types using data collected by a moving-vehicle-mounted GPR system and has proved that HMM …”

Section: Introductionmentioning

confidence: 99%

Ensemble learning method for hidden markov models.

Hamdi¹

View full text Add to dashboard Cite

This dissertation is dedicated to the memory of my father.iii Thus, there is a need for building a classification system that takes into account the variations within each class in the data.This dissertation introduces an ensemble learning method for temporal data that uses a mixture of Hidden Markov Model (HMM) classifiers. We hypothesize that the data are generated by K models, each of which reflects a particular trend in the data. Model identification could be achieved through clustering in the feature space or in the parameters space. However, this approach is inappropriate in the context of sequential data. The proposed approach is based on clustering in the log-likelihood space, and has two main steps. First, one HMM is fit to each of the N individual sequences. For each fitted model, we evaluate the log-likelihood of each sequence.This will result in an N-by-N log-likelihood distance matrix that will be partitioned into K groups using a relational clustering algorithm. In the second step, we learn the parameters of one HMM per group. We propose using and optimizing various training approaches for the different K groups depending on their size and homogeneity. In particular, we investigate the maximum likelihood (ML), the minimum classification error (MCE) based discriminative, and the Variational Bayesian (VB) training approaches. Finally, to test a new sequence, its likelihood is computed in all the models and a final confidence value is assigned by combining the multiple models outputs using a decision level fusion method such as an artificial neural network or a hierarchical mixture of experts.v Our approach was evaluated on two real-world applications: (1) identification of CardioPulmonary Resuscitation (CPR) scenes in video simulating medical crises; and (2) landmine detection using Ground Penetrating Radar (GPR). Results on both applications show that the proposed method can identify meaningful and coherent HMM mixture components that describe different properties of the data. Each HMM mixture component models a group of data that share common attributes. The results indicate that the proposed method outperforms the baseline HMM that uses one model for each class in the data.vi

show abstract

Applications of GPR for Humanitarian Assistance and Security

Núñez-Nieto

Solla

Lorenzo

2015

Springer Transactions in Civil and Environmental Engineering

View full text Add to dashboard Cite

This Chapter deals with a compilation of published works in the frame of the applications of the GPR for humanitarian assistance and security. The fields of application, in which the technique has experienced more advances, are the detection of mines and unexploded ordnances, as well as the location of underground spaces. Different types of defensive constructions were built throughout history to protect people from natural catastrophes, aerial bombardments and other attacks. Moreover, the use of the GPR technology in rescue operations is considered by including the main contributions in locating human remains or living victims in disaster areas. An overview of the main GPR works in humanitarian missions and their results are therefore mentioned. Specific systems, methodologies and processing algorithms developed in these applications are also analysed. As result, the method has shown significantly benefits when compared to other traditional searching methods.

show abstract

Real-Time Landmine Detection with Ground-Penetrating Radar Using Discriminative and Adaptive Hidden Markov Models

Cited by 47 publications

References 30 publications

A generic framework for context-dependent fusion with application to landmine detection.

A generic framework for context-dependent fusion with application to landmine detection.

Ensemble learning method for hidden markov models.

Applications of GPR for Humanitarian Assistance and Security

Contact Info

Product

Resources

About