The Technology Transfer project employs a spiral development process to enhance the functionality and autonomy of mobile robot systems in the Joint robotics Program (JRP) robotic Systems Pool by converging existing co...
详细信息
ISBN:
(纸本)0819462861
The Technology Transfer project employs a spiral development process to enhance the functionality and autonomy of mobile robot systems in the Joint robotics Program (JRP) robotic Systems Pool by converging existing component technologies onto a transition platform for optimization. An example of this approach is the implementation of advanced computervision algorithms on small mobile robots. We demonstrate the implementation and testing of the following two algorithms useful on mobile robots: 1) object classification using a boosted Cascade of classifiers trained with the Adaboost training algorithm, and 2) human presence detection from a moving platform. Object classification is performed with an Adaboost training system developed at the University of California, San Diego (UCSD) computervision Lab. This classification algorithm has been used to successfully detect the license plates of automobiles in motion in real-time. While working towards a solution to increase the robustness of this system to perform generic object recognition, this paper demonstrates an extension to this application by detecting soda cans in a cluttered indoor environment. The human presence detection from a moving platform system uses a data fusion algorithm which combines results from a scanning laser and a thermal imager. The system is able to detect the presence of humans while both the humans and the robot are moving simultaneously. In both systems, the two aforementioned algorithms were implemented on embedded hardware and optimized for use in real-time. Test results are shown for a variety of environments.
In this paper we present our approach to 3D surface reconstruction from large sparse range data sets. In space robotics constructing an accurate model of the environment is very important for a variety of reasons. In ...
详细信息
ISBN:
(纸本)0769523196;0769523196
In this paper we present our approach to 3D surface reconstruction from large sparse range data sets. In space robotics constructing an accurate model of the environment is very important for a variety of reasons. In particular, the constructed model can be used for: safe tele-operation, path planning, planetary exploration and mapping of points of interest. Our approach is based on acquiring range scans from different view-points with overlapping regions, merge them, together into a single data set, and fit a triangular mesh on the merged data points. We demonstrate the effectiveness of our approach in a path planning scenario and also by creating the accessibility map for a portion of the Mars Yard located in the canadian Space Agency.
Degradation of images of outdoor scenes caused by, varying conditions of visibility, can be exploited in order to get information on the scene. We propose two new methods for detecting occlusion edges between textured...
详细信息
ISBN:
(纸本)0769523196;0769523196
Degradation of images of outdoor scenes caused by, varying conditions of visibility, can be exploited in order to get information on the scene. We propose two new methods for detecting occlusion edges between textured areas of a scene. These methods are based on the use of partial derivatives of two images acquired under different conditions of visibility. They were validated on images of both synthetic and real scenes.
In this paper, a top-down approach based on perceptual grouping is proposed for multi-part objects detection. The abstract conceptual category of multi-part objects is formalized by a set of global criteria. These cri...
详细信息
ISBN:
(纸本)0769523196
In this paper, a top-down approach based on perceptual grouping is proposed for multi-part objects detection. The abstract conceptual category of multi-part objects is formalized by a set of global criteria. These criteria will enable the evaluation of the segmentation quality in order to determine if the whole grouping is perceptually significant and if it has a good perceptual shape. A new cognitive vision methodology, called SAFE (Subjectivity And Formalism Explicitly), is presented. Its goal is to help identify the proper global criteria and to validate the judgement derived from formal calculations of these criteria by human judgement.
We introduce a new exact Euclidean distance transform algorithm for binary images based on the Linear-time Legendre Transform algorithm. The three-step algorithm uses dimension reduction and convex analysis results on...
详细信息
ISBN:
(纸本)0769523196;0769523196
We introduce a new exact Euclidean distance transform algorithm for binary images based on the Linear-time Legendre Transform algorithm. The three-step algorithm uses dimension reduction and convex analysis results on the Legendre-Fenchel transform to achieve linear-time complexity. First, computation on a grid (the image) is reduced to computation on a line, then the convex envelope is computed, and finally the squared Euclidean distance transform is obtained. Examples and an extension to non-binary images are provided.
In this paper, we develop a new tracking approach which is based on cooperation and coordination of multiple agents which are pan-tilt-zoom cameras to optimize the cost of tracking and communication while simultaneous...
详细信息
ISBN:
(纸本)0769523196;0769523196
In this paper, we develop a new tracking approach which is based on cooperation and coordination of multiple agents which are pan-tilt-zoom cameras to optimize the cost of tracking and communication while simultaneously focus on the details of the object of interest. Each agent is able to track the object individually but the problem arises when the object goes suddenly out of the field of view of one agent because of an occlusion or an unexpected event. So each agent has to decide to take an action among a set of finite possible actions to overcome this situation in a way that optimizes the task of tracking.
In video sequences, edges in 2D images (frames) produces 3D surface in the spatio-temporal volume. In this paper, we propose to consider temporal collisions between edges, and thus objects, as 3D ridges in the spatio-...
详细信息
ISBN:
(纸本)0769523196;0769523196
In video sequences, edges in 2D images (frames) produces 3D surface in the spatio-temporal volume. In this paper, we propose to consider temporal collisions between edges, and thus objects, as 3D ridges in the spatio-temporal volume. Collisions (i.e. ridge points) can be located using the maximum principal curvature and the principal curvature direction. Using the detected collisions, we then propose a technique to detect overlapping objects events in an image sequence, by neither computing depth or optical flow. We present successful experiments on real image sequences.
Automatic attention-seeking gesture recognition is an enabling element of synchronous distance learning. Recognizing attention seeking gestures is complicated by the temporal nature of the signal that must be recogniz...
详细信息
ISBN:
(纸本)0769523196;0769523196
Automatic attention-seeking gesture recognition is an enabling element of synchronous distance learning. Recognizing attention seeking gestures is complicated by the temporal nature of the signal that must be recognized and by the similarty between attention seeking gestures and non-attention seeking gestures. Here we describe two approaches to the recognition problem that utilize HMMs to learn the class of attention seeking gestures. An explicit approach that encodes the temporal nature of the gestures within the HMM, and an implicit approach that augments the input token sequence with temporal markers. Experimental results demonstrate that the explicit approach is more accurate.
Watershed transform is widely used in image segmentation. However, its shortcomings such as over-segmentation and sensitivity to noise often make it unsuitable as an automatic tool for segmenting medical images. Utili...
详细信息
ISBN:
(纸本)0769523196;0769523196
Watershed transform is widely used in image segmentation. However, its shortcomings such as over-segmentation and sensitivity to noise often make it unsuitable as an automatic tool for segmenting medical images. Utilizing prior shape knowledge has been demonstrated to improve robustness of medical image segmentation algorithms. In this paper we propose a novel method for incorporating prior shape and appearance knowledge into watershed segmentation. Our method is based on iteratively aligning a shape-histogram with the result of an improved k-means clustering algorithm. No human interaction is needed in the whole process. We demonstrate the robustness of our method through segmenting the corpora callosa from a set of 51 brain magnetic resonance (MR) images. Numerical validation of the results is provided.
We present an adaptive filtering based methodology for resampling 3-D time series images using an extension of the method presented by Westin in [11]. We simultaneously reduce the artifacts due to image noise and resa...
详细信息
ISBN:
(纸本)0769523196
We present an adaptive filtering based methodology for resampling 3-D time series images using an extension of the method presented by Westin in [11]. We simultaneously reduce the artifacts due to image noise and resample the data on a finer grid along the time dimension. This provides a methodology for obtaining high quality image resampling without the disadvantages of staircase artefacts created by more common interpolation methods such as linear interpolation. We present qualitative results of the algorithm on a data set of 4-D cardiac MRI. This is a useful approach for any situation where we have a data set of 4-D images needing to be resampled.
暂无评论