High-performance feature tracking from video input is a valuable tool in many computervision techniques and mixed reality applications. This work presents a refined and substantially accelerated approach to KLT featu...
详细信息
High-performance feature tracking from video input is a valuable tool in many computervision techniques and mixed reality applications. This work presents a refined and substantially accelerated approach to KLT feature tracking performed on the GPU. Additionally, a global gain ratio between successive frames is estimated to compensate for changes in the camera exposure. The proposed approach achieves more than 200 frames per second on state-of-the art consumer GPUs for PAL (720 times 576) resolution data, and delivers real-time performance even on low-end mobile graphics processors.
In this paper, we propose a system for the complete implementation of the advanced encryption standard (AES) for encryption and decryption of images and text on a graphics processing unit. The GPU acts as a valuable c...
详细信息
In this paper, we propose a system for the complete implementation of the advanced encryption standard (AES) for encryption and decryption of images and text on a graphics processing unit. The GPU acts as a valuable co-processor that relieves the load off the CPU. In the decryption stage, we use a novel technique to display the decrypted images and text on the screen without bringing it onto CPU memory. We also present a system for encryption and decryption of hybrid map tiles generated from GIS data sets.
This paper presents an efficient partial shape matching method based on the Smith-Waterman algorithm. For two contours of m and n points respectively, the complexity of our method to find similar parts is only O(mn). ...
详细信息
This paper presents an efficient partial shape matching method based on the Smith-Waterman algorithm. For two contours of m and n points respectively, the complexity of our method to find similar parts is only O(mn). In addition to this improvement in efficiency, we also obtain comparable accurate matching with fewer shape descriptors. Also, in contrast to arbitrary distance functions that are used by previous methods, we use a probabilistic similarity measurement, p-value, to evaluate the similarity of two shapes. Our experiments on several public shape databases indicate that our method outperforms state-of-the-art global and partial shape matching algorithms in various scenarios.
We present a GPU implementation to compute both mutual information and its derivatives. Mutual information computation is a highly demanding process due to the enormous number of exponential computations. It is theref...
详细信息
We present a GPU implementation to compute both mutual information and its derivatives. Mutual information computation is a highly demanding process due to the enormous number of exponential computations. It is therefore the bottleneck in many image registration applications. However, we show that these computations are fully parallizable and can be efficiently ported onto the GPU architecture. Compared with the same CPU implementation running on a workstation level CPU, we reached a factor of 170 in computing mutual information, and a factor of 400 in computing its derivatives.
The paper presents a compact vision system for efficient contours extraction in high-speed applications. By exploiting the ultra high temporal resolution and the sparse representation of the sensorpsilas data in react...
详细信息
The paper presents a compact vision system for efficient contours extraction in high-speed applications. By exploiting the ultra high temporal resolution and the sparse representation of the sensorpsilas data in reacting to scene dynamics, the system fosters efficient embedded computervision for ultra high-speed applications. The results reported in this paper show the sensor output quality for a wide range of object velocity (5-40 m/s), and demonstrate the object data volume independence from the velocity as well as the steadiness of the object quality. The influence of object velocity on high-performance embedded computervision is also discussed.
Most personal photos that are shared online are embedded in some form of social network, and these social networks are a potent source of contextual information that can be leveraged for automatic image understanding....
详细信息
Most personal photos that are shared online are embedded in some form of social network, and these social networks are a potent source of contextual information that can be leveraged for automatic image understanding. In this paper, we investigate the utility of social network context for the task of automatic face recognition in personal photographs. We combine face recognition scores with social context in a conditional random field (CRF) model and apply this model to label faces in photos from the popular online social network Facebook, which is now the top photo-sharing site on the Web with billions of photos in total. We demonstrate that our simple method of enhancing face recognition with social network context substantially increases recognition performance beyond that of a baseline face recognition system.
In this paper we present two efficient GPU-based visual hull computation algorithms. We compare them in terms of performance using image sets of varying size and different voxel resolutions. In addition, we present a ...
详细信息
In this paper we present two efficient GPU-based visual hull computation algorithms. We compare them in terms of performance using image sets of varying size and different voxel resolutions. In addition, we present a real-time 3D reconstruction system which uses the proposed GPU-based reconstruction method to achieve real-time performance (30 fps) using 16 cameras and 4 PCs.
We propose an algorithm for learning the semantics of a (motion) verb from videos depicting the action expressed by the verb, paired with sentences describing the action participants and their roles. Acknowledging tha...
详细信息
We propose an algorithm for learning the semantics of a (motion) verb from videos depicting the action expressed by the verb, paired with sentences describing the action participants and their roles. Acknowledging that commonalities among example videos may not exist at the level of the input features, our approximation algorithm efficiently searches the space of more abstract features for a common solution. We test our algorithm by using it to learn the semantics of a sample set of verbs; results demonstrate the usefulness of the proposed framework, while identifying directions for further improvement.
Automatic construction of shape and appearance models from examples via establishing correspondences across the training set has been successful in the last decades. One successful measure for establishing corresponde...
详细信息
Automatic construction of shape and appearance models from examples via establishing correspondences across the training set has been successful in the last decades. One successful measure for establishing correspondences of high quality is minimum description length (MDL). In other approaches it has been shown that parts+geometry models which model the appearance of parts of the object and the geometric relation between the parts have been successful for automatic model building. In this paper it is shown how to fuse the above approaches and use MDL to fully automatically build optimal parts+geometry models from unlabeled images.
We present an active learning approach for visual multiple object class recognition, using a conditional random field (CRF) formulation. We name our graphical model dasiacollaborativepsila, because it infers class pos...
详细信息
We present an active learning approach for visual multiple object class recognition, using a conditional random field (CRF) formulation. We name our graphical model dasiacollaborativepsila, because it infers class posteriors in in stances of occlusion and missing information by assessing the joint appearance and geometric assortment of neighboring sites. The model can handle scenes containing multiple classes and multiple objects inherently while using the confidence of its predictions to enforce label uniformity in areas where evidence supports similarity. Our method uses classification uncertainty to dynamically select new training samples to retrain the discriminative classifiers used in the CRF. We demonstrate the performance of our approach using cluttered scenes containing multiple objects and multiple class instances.
暂无评论