We present a method for 3D monocular kinematic pose estimation and activity recognition through the use of dynamical human motion vocabularies. A motion vocabulary is comprised as a set of primitives that each describ...
详细信息
We present a method for 3D monocular kinematic pose estimation and activity recognition through the use of dynamical human motion vocabularies. A motion vocabulary is comprised as a set of primitives that each describe the movement dynamics of an activity in a low-dimensional space. Given image observations over time, each primitive is used to infer the pose independently using its expected dynamics in the context of a particle filter. Pose estimates from a set of primitives are inferred in parallel and arbitrated to estimate the activity being performed. The approach presented is evaluated through tracking and activity recognition over extended motion trials. The results suggest robustness with respect to multi-activity movement, movement speed, and camera viewpoint.
In this paper, the effects of feature selection and feature normalization to the performance of a local appearance based face recognition scheme are presented. From the local features that are extracted using block-ba...
详细信息
In this paper, the effects of feature selection and feature normalization to the performance of a local appearance based face recognition scheme are presented. From the local features that are extracted using block-based discrete cosine transform, three feature sets are derived. These local feature vectors are normalized in two different ways; by making them unit norm and by dividing each coefficient to its standard deviation that is learned from the training set. The input test face images are then classified using four different distance measures: L1 norm, L2 norm, cosine angle and covariance between feature vectors. Extensive experiments have been conducted on the AR and CMU PIE face databases. The experimental results show the importance of using appropriate feature sets and doing normalization on the feature vector.
In this paper, a software-based system for the real-time synchronization of images captured by a low-cost camera framework is presented. It is most well suited for cases where special hardware cannot be utilized (e.g....
详细信息
In this paper, a software-based system for the real-time synchronization of images captured by a low-cost camera framework is presented. It is most well suited for cases where special hardware cannot be utilized (e.g. remote or wireless applications) and when cost efficiency is critical. The proposed method utilizes messages to establish a consensus on the time of image acquisition and NTP synchronization of computer clocks. It also provides with an error signal, in case of failure of the synchronization. The evaluation of the proposed algorithm using a precise LED array system (1ms accuracy) proves the effectiveness of this method.
This paper proposes a system which can handle illumination problem of face recognition systems by using "Retinex and color constancy" algorithm. The Retinex and color constancy approach has been plugged with...
详细信息
This paper proposes a system which can handle illumination problem of face recognition systems by using "Retinex and color constancy" algorithm. The Retinex and color constancy approach has been plugged with Elastic Bunch Graph Matching (EBGM). The proposed system has been tested on IITK database having more than 1000 face images. The experimental results demonstrate that performance of the proposed system is superior to the known systems. The overall accuracy has shown an increase of 3.14% as compared to the known EBGM based recognition system without using Retinex and Color Constancy method.
This paper presents a robotic vision system that can be taught to recognize novel objects in a semi-autonomous manner that does not require manual labeling or segmentation of any individual training images. Instead, u...
详细信息
This paper presents a robotic vision system that can be taught to recognize novel objects in a semi-autonomous manner that does not require manual labeling or segmentation of any individual training images. Instead, unfamiliar objects are simply shown to the system in varying poses and scales against cluttered background and the system automatically detects, tracks, segments, and builds representations for these objects. We demonstrate the feasibility of our approach by training the system to recognize one hundred household objects, which are presented to the system for about a minute each. Our method resembles the way that biological organisms learn to recognize objects and it paves the way for a wealth of applications in robotics and other fields.
Salient contour grouping/detection is one of the major topics in perceptual organization exploring the true meanings for contours. Extending contour’s discontinuity quality from low level discontinuity, we introduce ...
详细信息
Salient contour grouping/detection is one of the major topics in perceptual organization exploring the true meanings for contours. Extending contour’s discontinuity quality from low level discontinuity, we introduce a new perspective that a salient contour represents a sharp change in the ability to organize the image into meaningful parts. This new view gives a novel, general edge energy measure, which has important perceptual meanings. A new multiscale saliency function and its variational solution are also described. Experiments on real images validate our method.
Semantic scene classification is still a challenging problem in computervision. In contrast to the common approach of using low-level features computed from the scene, our approach uses explicit semantic object detec...
详细信息
Semantic scene classification is still a challenging problem in computervision. In contrast to the common approach of using low-level features computed from the scene, our approach uses explicit semantic object detectors and scene configuration models. To overcome faulty semantic detectors, it is critical to develop a region-based, generative model of outdoor scenes based on characteristic objects in the scene and spatial relationships between them. Since a fully connected scene configuration model is intractable, we chose to model pairwise relationships between regions and estimate scene probabilities using loopy belief propagation on a factor graph. We demonstrate the promise of this approach on a set of over 2000 outdoor photographs, comparing it with existing discriminative approaches and those using low-level features.
Image retrieval methods aim to retrieve relevant images from an image database that are similar to the query image. The ability to effectively retrieve non-alphanumeric data is a complex issue. The problem becomes eve...
详细信息
We describe an extension to ordinary patch-based edge detection in images using spatio-temporal volumetric patches from video. The inclusion of temporal information enables us to estimate motion normal to edges in add...
详细信息
We describe an extension to ordinary patch-based edge detection in images using spatio-temporal volumetric patches from video. The inclusion of temporal information enables us to estimate motion normal to edges in addition to edge strength and spatial orientation. The method can handle complex edges in clutter by comparing distributions of data on either half of an extracted patch, rather than modeling the intensity profile of the edge. An efficient approach is provided for building the necessary histograms which samples candidate edge orientations and motions. Results are compared to classical spatio-temporal filtering techniques.
Smart cameras using FPGAs require an automation method to simplify the design process and to ensure both computation and memory performance are met. Reconfigurable logic allows exploration of different hardware accele...
详细信息
Smart cameras using FPGAs require an automation method to simplify the design process and to ensure both computation and memory performance are met. Reconfigurable logic allows exploration of different hardware accelerators and memory-hierarchy configurations based on application needs. This paper presents a streaming architecture template that is generated from high level program descriptions. A smart camera development platform, the software architecture, and demonstration template are also described.
暂无评论