This paper proposes a method for robustly matching active appearance models (AAMs) on images with gross disturbances (outliers). The method consists of two steps. First, an initial residual is calculated by comparing ...
详细信息
ISBN:
(数字)9783540264316
ISBN:
(纸本)3540250522
This paper proposes a method for robustly matching active appearance models (AAMs) on images with gross disturbances (outliers). The method consists of two steps. First, an initial residual is calculated by comparing model and image appearance, and modes of the residual are analyzed. Second, all possible mode combinations are tested by evaluating an objective function. The objective function allows the selection of an outlier-free mode combination. Experiments demonstrate the ability of the robust matching method to successfully cope with outliers - compared to standard AAM matching, no degeneration of the model during matching occurs.
This paper gives a robust motion detection and tracking solution for a video surveillance application on an airport's apron. As an outdoor application, the system must be capable of adapting to a wide range of wea...
详细信息
This paper gives a robust motion detection and tracking solution for a video surveillance application on an airport's apron. As an outdoor application, the system must be capable of adapting to a wide range of weather conditions and illumination changes, furthermore, the achromaticity of the scene and the presence of occlusions in the tracking process are issues considered in the selection of the motion detector and tracking system respectively. We propose an adapted mixture of Gaussiani model with RGB colour normalisation to detect mobile objects in the scene and a region tracking method based on significant mobile object features to track individuals and vehicles on the selected airport's apron. The performance of the proposed motion detector is evaluated using pixel-based performance metrics and compared with other existing methods. The capability of the application to handle partial occlusions is tested on the region tracker.
This paper presents a visual surveillance system for the automatic scene interpretation of airport aprons. The system comprises two modules - scene tracking and scene understanding. The scene tracking module, comprisi...
详细信息
This paper presents a visual surveillance system for the automatic scene interpretation of airport aprons. The system comprises two modules - scene tracking and scene understanding. The scene tracking module, comprising a bottom-up methodology, and the scene understanding module, comprising a video event representation and recognition scheme, have been demonstrated to be a valid approach for apron monitoring
Active shape models are powerful and widely used tool to interpret complex image data. By building models of shape variation they enable search algorithms to use a priori knowledge in an efficient and gainful way. How...
详细信息
Active shape models are powerful and widely used tool to interpret complex image data. By building models of shape variation they enable search algorithms to use a priori knowledge in an efficient and gainful way. However, due to the linearity of PCA, non-linearities like rotations or independently moving sub-parts in the data can deteriorate the resulting model considerably. Although non-linear extensions of active shape models have been proposed and application specific solutions have been used, they still need a certain amount of user interaction during model building. In this paper the task of building/choosing optimal models is tackled in a more generic information theoretic fashion. In particular, we propose an algorithm based on the minimum description length principle to find an optimal subdivision of the data into sub-parts, each adequate for linear modeling. This results in an overall more compact model configuration. Which in turn leads to a better model in terms of modes of variations. The proposed method is evaluated on synthetic data, medical images and hand contours.
The morphological top-hat operator for grayscale images is part of the basic toolbox of mathematical morphology operators. We discuss two ways of generalising the top-hat operator to multi-channel images, such as colo...
详细信息
The morphological top-hat operator for grayscale images is part of the basic toolbox of mathematical morphology operators. We discuss two ways of generalising the top-hat operator to multi-channel images, such as colour images. The first method presented is the use of a vectorial order in the relevant vector space. The second is based on the demonstration that the top-hat operator can be rewritten in terms of increments. These increments can be replaced by any vectorial distance function, removing the requirement to first impose an order on the vectors. We present examples of the use of the suggested top-hat operators in feature detection in colour images and defect detection in texture.
A major obstacle to the wider use of 3D object reconstruction and modeling is the extent of manual intervention needed. Such interventions are currently massive and exist throughout every phase of a 3D reconstruction ...
详细信息
A major obstacle to the wider use of 3D object reconstruction and modeling is the extent of manual intervention needed. Such interventions are currently massive and exist throughout every phase of a 3D reconstruction project: collection of images, image management, establishment of sensor position and image orientation, extracting the geometric detail describing an object, merging geometric, texture and semantic data. This work aims to develop a solution for automated documentation of archaeological pottery, which also leads to a more complete 3D model out of multiple fragments. Generally the 3D reconstruction of arbitrary objects from their fragments can be regarded as a 3D puzzle. In order to solve it we identified the following main tasks: 3D data acquisition, orientation of the object, classification of the object and reconstruction. We demonstrate the method and give results on synthetic and real data.
作者:
刘志杨杰Institute of Image Processing and Pattern Recognition
Shanghai Jiaotong University Shanghai 200030 Institute of Image Processing and Pattern Recognition
Shanghai Jiaotong University Shanghai 200030his paper proposes a novel video object tracking approach using birdirectional projection. Forward projection is exploited to locate the current video object with rough boundary information. Watershed segmentation is applied to the simplified gradient image of the current frame to obtain a reasonable partition. An improved backward projection which incorporates pixel classification with region classification is performed on some segmented regions in a rather small search range and the tracking performance is enhanced in respect to both reliability and efficiency. Experimental results for various types of the MPEG-4 (moving picture experts group) test sequences demonstrate an efficient and faithful segmentation performance of the proposed approach.
This paper proposes a novel video object tracking approach using birdirectional projection. Forward projection is exploited to locate the current video object with rough boundary information. Watershed segmentation is...
详细信息
This paper proposes a novel video object tracking approach using birdirectional projection. Forward projection is exploited to locate the current video object with rough boundary information. Watershed segmentation is applied to the simplified gradient image of the current frame to obtain a reasonable partition. An improved backward projection, which incorporates pixel classification with region classification, is performed on some segmented regions in a rather small search range, and the tracking performance is enhanced in respect to both reliability and efficiency. Experimental results for various types of the MPEG-4 (moving picture experts group) test sequences demonstrate an efficient and faithful segmentation performance of the proposed approach.
In this paper, we address the problem of multimodal registration of coronary vessels by developing a 3D parametrical model of vessel trees from computer tomography data and registering it to angiography images during ...
详细信息
In this paper, we address the problem of multimodal registration of coronary vessels by developing a 3D parametrical model of vessel trees from computer tomography data and registering it to angiography images during intervention. Thus, the interventionist takes profit from 3D data otherwise only available before the intervention. This facilitates orientation in ambiguous radiographs, interactive visualization of all vessel structures to estimate their mutual position and navigation within the vessel system and ultimately reduces the radiation the patient and the physicians are exposed to. The model is build by exploring the branching vessel tree starting from a single position and successively expanding through the vessels guided by a local deformable surface. The result is a tree of cylindrical segments each adapted to the vessel walls that is registered to angiography images in a fast and robust way. Validation on 8 patients confirms the robustness of our method.
Vehicle occupants that are out-of-position can be deadly injured by the deployment of the air bag in a crash situation. In recent years many different sensors and systems have been proposed to detect the type of occup...
详细信息
Vehicle occupants that are out-of-position can be deadly injured by the deployment of the air bag in a crash situation. In recent years many different sensors and systems have been proposed to detect the type of occupant and the position of the occupant's head. This work presents a method for classification and occupant's head detection based on passive stereo vision. The proposed system uses depth surface analysis and scene statistics together with support vector machines for classification and selection of head candidates. Evaluation of the method shows 99% correct for classification and 98% correct for head detection, using large sets of image data, and image sequences recorded in a driving vehicle.
Recent developments in computer vision are providing powerful tools for the evaluation of data gathered by art historians and archaeologists. New camera hardware allows new insights into cultural heritage, especially ...
详细信息
暂无评论