Abstract

I. INTRODUCTIONThis work is motivated by the problem of video motion class detection in order to understand object behaviors. The underlying issue is the content-based exploitation of video footage which is of continuously increasing interest in numerous applications, e.g., for retrieving video sequences in large TV archives [12] [42], creating automatic video summarization of sport TV programs [32], or detecting specific actions or activities in video-surveillance [6] [26]. It implies to shorten the well-known semantic gap between computed low-level features and high-level concepts. Considering 2D trajectories is attractive since they form computable image features which capture elaborated spatiotemporal information on the viewed actions. Methods for tracking moving objects in an image sequence are now available to get reliable enough 2D trajectories in various situations. These trajectories are given as a set of consecutive positions in the image plane (x, y) over time. If they are embedded in an appropriate modeling framework, highlevel information on the dynamic scene can then be reachable.

ABSTRACT:Scene analysis, in urban environments, deals with street modeling and understanding. A street mainly consists of roadways, pavements (i.e., walking areas), facades, still and moving obstacles. In this paper, we investigate the surface modeling of roadways and pavements using LIDAR data acquired by a mobile laser scanning (MLS) system. First, road border detection is considered. A system recognizing curbs and curb ramps while reconstructing the missing information in case of occlusion is presented. A user interface scheme is also described, providing an effective tool for semi-automatic processing of large amount of data. Then, based upon road edge information, a process that reconstructs surfaces of roads and pavements has been developed, providing a centimetric precision while reconstructing missing information. This system hence provides an important knowledge of the street, that may open perspectives in various domains such as path planning or road maintenance.

No abstract

ABSTRACT:We propose an integrated bottom-up/top-down approach to road-marking extraction from image space. It is based on energy minimization using marked point processes. A generic road marking object model enable us to define universal energy functions that handle various types of road-marking objects (dashed-lines, arrows, characters, etc.). A RJ-MCMC sampler coupled with a simulated annealing is applied to find the configuration corresponding to the minimum of the proposed energy. We used input data measurements to guide the sampler process (data driven RJ-MCMC). The approach is enhanced with a model-driven kernel using preprocessed autocorrelation and inter-correlation of road-marking templates, in order to resolve type and transformation ambiguities. The method is generic and can be applied to detect road-markings in any orthogonal view produced from optical sensors or laser scanners from aerial or terrestrial platforms. We show the results an ortho-image computed from ground-based laser scanning.

This paper describes an original method for classifying object motion trajectories in video sequences in order to recognize dynamic events. Similarities between trajectories are expressed from Hidden Markov Models representing each trajectory. We have favorably compared our method to several other ones, including histogram comparison, Longest Common Subsequence distance and SVM classification. Trajectory features are computed from the curvature and velocity values at each point of the trajectory, so that they are invariant to translation, rotation and scale. We have evaluated our method on two sets of data, a first one composed of typical classes of synthetic trajectories (such as parabola or clothoid), and a second one formed with trajectories obtained by tracking cars in a Formula1 race video.

ABSTRACT:Forest stands are the basic units for forest inventory and mapping. Stands are large forested areas (e.g., ≥ 2 ha) of homogeneous tree species composition. The accurate delineation of forest stands is usually performed by visual analysis of human operators on very high resolution (VHR) optical images. This work is highly time consuming and should be automated for scalability purposes. In this paper, a method based on the fusion of airborne laser scanning data (or lidar) and very high resolution multispectral imagery for automatic forest stand delineation and forest land-cover database update is proposed. The multispectral images give access to the tree species whereas 3D lidar point clouds provide geometric information on the trees. Therefore, multi-modal features are computed, both at pixel and object levels. The objects are individual trees extracted from lidar data. A supervised classification is performed at the object level on the computed features in order to coarsely discriminate the existing tree species in the area of interest. The analysis at tree level is particularly relevant since it significantly improves the tree species classification. A probability map is generated through the tree species classification and inserted with the pixel-based features map in an energetical framework. The proposed energy is then minimized using a standard graph-cut method (namely QPBO with α-expansion) in order to produce a segmentation map with a controlled level of details. Comparison with an existing forest land cover database shows that our method provides satisfactory results both in terms of stand labelling and delineation (matching ranges between 94% and 99%).

ABSTRACT:An energetical approach is proposed for classification decision fusion in urban areas using multispectral and hyperspectral imagery at distinct spatial resolutions. Hyperspectral data provides a great ability to discriminate land-cover classes while multispectral data, usually at higher spatial resolution, makes possible a more accurate spatial delineation of the classes. Hence, the aim here is to achieve the most accurate classification maps by taking advantage of both data sources at the decision level: spectral properties of the hyperspectral data and the geometrical resolution of multispectral images. More specifically, the proposed method takes into account probability class membership maps in order to improve the classification fusion process. Such probability maps are available using standard classification techniques such as Random Forests or Support Vector Machines. Classification probability maps are integrated into an energy framework where minimization of a given energy leads to better classification maps. The energy is minimized using a graph-cut method called quadratic pseudo-boolean optimization (QPBO) with α-expansion. A first model is proposed that gives satisfactory results in terms of classification results and visual interpretation. This model is compared to a standard Potts models adapted to the considered problem. Finally, the model is enhanced by integrating the spatial contrast observed in the data source of higher spatial resolution (i.e., the multispectral image). Obtained results using the proposed energetical decision fusion process are shown on two urban multispectral/hyperspectral datasets. 2-3% improvement is noticed with respect to a Potts formulation and 3-8% compared to a single hyperspectral-based classification.