Oualid Missaoui

Land-Mine Detection With Ground-Penetrating Radar Using Multistream Discrete Hidden Markov Models

We propose a multistream discrete hidden Markov model (DHMM) framework and apply it to the problem of land-mine detection using ground-penetrating radar (GPR). We hypothesize that each signature (mine or nonmine) can be characterized better by multiple synchronous sequences representing features that capture different environments and different radar characteristics. This paper is motivated by the fact that mines and clutter objects can have different characteristics depending on the mine type, soil and weather conditions, and burial depth. Thus, ideally different sets of specialized feature extraction mechanisms may be needed to achieve high detection and low false alarm rates. In order to fuse the different modalities, a multistream DHMM that includes a stream relevance weighting component is developed. The relevance weight of each stream depends on the symbols and the states. We reformulate the Baum-Welch and the minimum classification error/gradient probabilistic descent learning algorithms to include stream relevance weights and partial state probabilities. We generalize their objective functions and derive the necessary conditions to update all model parameters simultaneously. The results on a synthetic data set and a collection of GPR signatures show that the proposed multistream DHMM framework outperforms the basic single-stream DHMM where all the streams are treated equally important.

Landmine detection using discrete hidden Markov models with Gabor features

We propose a general method for detecting landmine signatures in vehicle mounted ground penetrating radar (GPR) using discrete hidden Markov models and Gabor wavelet features. Observation vectors are constructed based on the expansion of the signatures B-scan using a bank of scale and orientation selective Gabor filters. This expansion provides localized frequency description that gets encoded in the observation sequence. These observations do not impose an explicit structure on the mine model, and are used to naturally model the time-varying signatures produced by the interaction of the GPR and the landmines as the vehicle moves. The proposed method is evaluated on real data collected by a GPR mounted on a moving vehicle at three different geographical locations that include several lanes. The model parameters are optimized using the BaumWelch algorithm, and lane-based cross-validation, in which each mine lane is in turn treated as a test set with the rest of the lanes used for training, is used to train and test the model. Preliminary results show that observations encoded with Gabor wavelet features perform better than observation encoded with gradient-based edge features.

AN SVM classifier with HMM-based kernel for landmine detection using ground penetrating radar

We propose a landmine detection algorithm using ground penetrating radar data that is based on an SVM classifier. The kernel function for the SVM is constructed using discrete hidden Markov modeling (HMM). Typically, the kernel matrix could be obtained by defining an adequate similarity measure in the feature space. However, this approach is inappropriate as it is not trivial to define a meaningful distance metric for sequence comparison. Our proposed approach is based on HMM modeling 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 × N log-likelihood similarity matrix that will be adapted to serve as the kernel of the SVM classifier. In the second step, we train an SVM classifier to learn a decision boundary between the positive and negative samples.

Model level fusion of edge histogram descriptors and gabor wavelets for landmine detection with ground penetrating radar

We propose a discriminative method for combining heterogeneous sets of features for the continuous hidden Markov model classifier. We use a model level fusion approach and apply it to the problem of landmine detection using ground penetrating radar (GPR). We hypothesize that each signature (mine or non-mine) can be characterized better by multiple synchronous sequences that can capture different and complementary features. Our work is motivated by the fact that mines and clutter objects can have different characteristics depending on the mine type, soil and weather conditions, and burial depth. Thus, different sets of specialized feature extraction mechanisms, may be needed to achieve high detection and low false alarm rates. In order to fuse the different modalities, a multi-stream continuous HMM that includes a stream relevance weighting component is developed. In particular, we modify the probability density function that characterizes the standard continuousHMMto include state and component dependent stream relevance weights. We generalize the Minimum Classification Error (MCE) objective function to include stream relevance weights and derive the necessary conditions to update all model parameters simultaneously. Results on a large collection of GPR alarms show that the proposed model level fusion outperforms the baseline HMM when each feature is used independently and when both features are combined with equal weights.

Multi-stream continuous hidden Markov models with application to landmine detection

We propose a multi-stream continuous hidden Markov model (MSCHMM) framework that can learn from multiple modalities. We assume that the feature space is partitioned into subspaces generated by different sources of information. In order to fuse the different modalities, the proposed MSCHMM introduces stream relevance weights. First, we modify the probability density function (pdf) that characterizes the standard continuous HMM to include state and component dependent stream relevance weights. The resulting pdf approximate is a linear combination of pdfs characterizing multiple modalities. Second, we formulate the CHMM objective function to allow for the simultaneous optimization of all model parameters including the relevance weights. Third, we generalize the maximum likelihood based Baum-Welch algorithm and the minimum classification error/gradient probabilistic descent (MCE/GPD) learning algorithms to include stream relevance weights. We propose two versions of the MSCHMM. The first one introduces the relevance weights at the state level while the second one introduces the weights at the component level. We illustrate the performance of the proposed MSCHMM structures using synthetic data sets. We also apply them to the problem of landmine detection using ground penetrating radar. We show that when the multiple sources of information are equally relevant across all training data, the performance of the proposed MSCHMM is comparable to the baseline CHMM. However, when the relevance of the sources varies, the MSCHMM outperforms the baseline CHMM because it can learn the optimal relevance weights. We also show that our approach outperforms existing multi-stream HMM because the latter one cannot optimize all model parameters simultaneously.

Optimal feature weighting for the continuous HMM

We propose new continuous hidden Markov model (CHMM) structure that integrates feature weighting component. We assume that each feature vector could include different subsets of features that come from different sources of information or different feature extractors. We modify the probability density function that characterizes the standard CHMM to include state and component dependent feature relevance weights. To learn the optimal feature weights from the training data, we modify the maximum likelihood based Baum-Welch algorithm and we derive the necessary conditions. The proposed approach is validated using synthetic and real data sets. The results are shown to outperform the standard CHMM.

Landmine detection with ground penetrating radar using discrete hidden Markov models with symbol dependent features

In this paper, we propose an efficient Discrete Hidden Markov Models (DHMM) for landmine detection that rely on training data to learn the relevant features that characterize different signatures (mines and non-mines), and can adapt to different environments and different radar characteristics. Our work is motivated by the fact that mines and clutter objects have different characteristics depending on the mine type, soil and weather conditions, and burial depth. Thus, ideally different sets of specialized features may be needed to achieve high detection and low false alarm rates. The proposed approach includes three main components: feature extraction, clustering, and DHMM. First, since we do not assume that the relevant features for the different signatures are known a priori, we proceed by extracting several sets of features for each signature. Then, we apply a clustering and feature discrimination algorithm to the training data to quantize it into a set of symbols and learn feature relevance weights for each symbol. These symbols and their weights are then used in a DHMM framework to learn the parameters of the mine and the background models. Preliminary results on large and diverse ground penetrating radar data show that the proposed method outperforms the basic DHMM where all the features are treated equally important.

Landmine detection using mixture of discrete hidden Markov models

We propose a landmine detection algorithm that uses a mixture of discrete hidden Markov models. We hypothesize that the data are generated by K models. These different models reflect the fact that mines and clutter objects have different characteristics depending on the mine type, soil and weather conditions, and burial depth. Model identification could be achieved through clustering in the parameters space or in the feature space. However, this approach is inappropriate as it is not trivial to define a meaningful distance metric for model parameters or sequence comparison. Our 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 R individual sequence. For each fitted model, we evaluate the log-likelihood of each sequence. This will result in an R×R log-likelihood distance matrix that will be partitioned into K groups using a hierarchical clustering algorithm. In the second step, we pool the sequences, according to which cluster they belong, into K groups, and we fit one HMM to each group. The mixture of these K HMMs would be used to build a descriptive model of the data. An artificial neural networks is then used to fuse the output of the K models. Results on large and diverse Ground Penetrating Radar data collections show that the proposed method can identify meaningful and coherent HMM models that describe different properties of the data. Each HMM models a group of alarm signatures that share common attributes such as clutter, mine type, and burial depth. Our initial experiments have also indicated that the proposed mixture model outperform the baseline HMM that uses one model for the mine and one model for the background.

Landmine detection using ensemble discrete hidden Markov models with context dependent training methods

We propose a landmine detection algorithm that uses ensemble discrete hidden Markov models with context dependent training schemes. We hypothesize that the data are generated by K models. These different models reflect the fact that mines and clutter objects have different characteristics depending on the mine type, soil and weather conditions, and burial depth. Model identification is based on clustering in the log-likelihood space. First, one HMM is fit to each of the N individual sequence. For each fitted model, we evaluate the log-likelihood of each sequence. This will result in an N x N log-likelihood distance matrix that will be partitioned into K groups. In the second step, we learn the parameters of one discrete 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 will investigate the maximum likelihood, and the MCE-based discriminative training approaches. Results on large and diverse Ground Penetrating Radar data collections show that the proposed method can identify meaningful and coherent HMM models that describe different properties of the data. Each HMM models a group of alarm signatures that share common attributes such as clutter, mine type, and burial depth. Our initial experiments have also indicated that the proposed mixture model outperform the baseline HMM that uses one model for the mine and one model for the background.

Discriminative Multi-stream Discrete Hidden Markov Models

We propose a modified discrete HMM that handles multimodalities. We assume that the feature space is partitioned into subspaces generated by different sources of information. To combine these heteregoneous modalities we propose a multi-stream discrete HMM that assigns a relevance weight to each subspace. The relevance weights are set local and depend on the symbols and the states. In particular, we associate a partial probability with each symbol in each subspace. The overall observation state probability is then computed as an aggregation of the partial probabilities and their objective relevance weights based on a linear combination. The Minimum Classification Error (MCE) objective based on the Gradient Probabilistic Descent (GPD) optimization algorithm is reformulated to derive the update equations for the relevance weights and the partial state probabilities. The proposed approach is validated using synthetic and real data sets. The results are shown to outperform the baseline discrete HMM that treats all streams equally important.