Search

Vehicle detection plays a significant role in traffic monitoring. Vehicle detection approaches can be used for vehicle tracking, vehicle classification and traffic analysis. However, numerous attributes like shape, intensity, size, pose, illumination, shadows, occlusion, velocity of vehicles and environmental conditions, provide different challenges for the detection step. With an appropriate vehicle detection technique, we are able to extract valuable knowledge from video sequences, regardless these diverse factors. Since the vehicle detection method choice has a deep impact on this step and the whole traffic monitoring system performances, our objective in this study is to investigate different methods for vehicle detection. Comparison is made on the basis of different metrics such as recall, precision and detection accuracy. These approaches have been tested under different weather conditions (rainy, sunny) and various traffic conditions (light, medium, heavy).

In recent years, cities are experiencing a deep negative impact due to traffic congestion. As the number of vehicles is increasing rapidly, traffic congestion becomes unsustainable in urban domains specially in peak hours leading to time and fuel waste, accidents, additional costs for the economy, environmental problems and consequently impaired quality of life. Tremendous effort is done to provide solutions dealing with traffic congestion detection and monitoring. Based on used technologies, existing solutions can be classified into three categories: sensor technology, Vehicular Adhoc Networks and visual traffic surveillance. In this survey, we review the main recent works proposed in each category and discuss their strengths and weaknesses. We give an insight of future directions for handling congestion using the presented methods.

Segmentation and volume measurement of liver tumor are important tasks for surgical planning and cancer follow-up. In this work, a segmentation method from four-phase computed tomography images is proposed. It is based on the combination of the Expectation-Maximization algorithm and the Hidden Markov Random Fields. The latter considers the spatial information given by voxel neighbors of two contrast phases. The segmentation algorithm is applied on a volume of interest that decreases the number of processed voxels. To accelerate the classification steps within the segmentation process, a Bootstrap resampling scheme is also adopted. It consists in selecting randomly an optimal representative set of voxels. The experimental results carried out on three clinical datasets show the performance of our liver tumor segmentation method. It has been notably observed that the computing time of the classification algorithm is reduced without any significant impact on the segmentation accuracy.

X-ray angiography has been an effective modality for diagnosing coronary artery disease representing one of the leading causes of death. A 3D reconstruction of the coronary arteries is a very important step to facilitate the interpretation of angiograms. In this paper, we propose a 3D reconstruction method of the coronary arteries. In order to improve the pairwise matching performance of our approach, we introduce artificial interest points (nodes) to respect the topology variation between 3D vascular trees. New similarity measures are proposed to take into consideration the non-rigid coronary artery movement. To measure the performance of the proposed method, we evaluate the proposed method on clinical data. Results show that accuracy of vessel centerlines has the average projection error equal to 0.5 mm for 28 different patients.

In this paper we propose a new multi-scale fully automatic algorithm based on Graph cuts for vessel extraction. In fact, we combine vesselness, geodesic paths, a multi-scale edgeness map and the directional information for vessel tracking in order to personalize the Graph cuts approach to the segmentation of tubular structures.

In this paper we intend to introduce a new representativeness criterion of the Bootstrap sample for images segmentation. Using the plug-in method in order to estimate probability density functions (pdf), we present a robust and stable criterion based on L 2 distance between the estimated probability density from the bootstrap sample and the empirical probability density of the image. This criterion is tested on satellite images.

Here, we intend to introduce new face invariant descriptors, composed by two kinds of features, in order to explore the problem of faces classification. The first kind is defined from the p-order moments of a curvature function of the geodesic curve according to its arc length. The second one describes relative positions between important localities of faces. Two classes Fisher discriminate analysis is applied for a dimension reduction. A two dimensional multi classes Expectation Maximization algorithm (2D-EM) is used to identify the components of the mixture distribution. Then, the classification is obtained after applying the Bayes decision rule which is the most optimal for the minimization of the classification error. Such classification gives the sub groups having homogenous similar faces.