The author studies the differential geometry of straight homogeneous generalized cylinders (SHGCs). He derives a necessary and sufficient condition that an SHGC must verify to parameterize a regular surface, computer ...
详细信息
ISBN:
(纸本)0818608625
The author studies the differential geometry of straight homogeneous generalized cylinders (SHGCs). He derives a necessary and sufficient condition that an SHGC must verify to parameterize a regular surface, computer the Gaussian curvature of a regular SHGC, and prove that the parabolic lines of an SHGC are either meridians or parallels. Using these results, he addresses the following problem: under which conditions can a given surface have several descriptions by SHGCs? He proves several results. In particular, he proves that two SHGCs with the same cross-section plane and axis direction are necessarily deduced from each other through inverse scalings of their cross-sections and sweeping rule curve. He extends Shafer's pivot and slant theorems. Finally, he proves that a surface with at least two parabolic lines has at most three different SHGC descriptions, and that a surface with at leat four parabolic lines has at most a unique SHGC description.
The relationship between cellular behaviors and protein concentrations is central for embryonic development. An integrated cellular and gene interaction model is proposed to reveal this relationship. Protein concentra...
详细信息
3D semantic segmentation is a critical task in many real-world applications, such as autonomous driving, robotics, and mixed reality. However, the task is extremely challenging due to ambiguities coming from the unstr...
3D semantic segmentation is a critical task in many real-world applications, such as autonomous driving, robotics, and mixed reality. However, the task is extremely challenging due to ambiguities coming from the unstructured, sparse, and uncolored nature of the 3D point clouds. A possible solution is to combine the 3D information with others coming from sensors featuring a different modality, such as RGB cameras. Recent multi-modal 3D semantic segmentation networks exploit these modalities relying on two branches that process the 2D and 3D information independently, striving to maintain the strength of each modality. In this work, we first explain why this design choice is effective and then show how it can be improved to make the multi-modal semantic segmentation more robust to domain shift. Our surprisingly simple contribution achieves state-of-the-art performances on four popular multi-modal unsupervised domain adaptation benchmarks, as well as better results in a domain generalization scenario.
In this paper, we propose a real-time visual mapping scheme which can be implemented on a low-cost embedded system for consumer-level ratio control (RC) drones. In our work, a 3-dimensional occupancy grid map is obtai...
详细信息
In this paper, we propose a real-time visual mapping scheme which can be implemented on a low-cost embedded system for consumer-level ratio control (RC) drones. In our work, a 3-dimensional occupancy grid map is obtained based on an estimated trajectory from data fusion of multiple on-board sensors, composed of two downward-facing cameras, two forward-facing cameras, a GPS receiver, a magnetic compass and an inertial measurement unit (IMU) with 3-axis accelerometers and gyroscopes. Taking the advantages of the low-cost FPGA and ARM NEON intrinsics, we run our visual odometry and mapping algorithms at 10Hz on board. Meanwhile, we also present a hierarchical multi-sensor fusion algorithm to provide a robust trajectory for mapping usage. Finally, we verify the feasibility of our approaches and serval potential applications with experimental results in complex indoor/outdoor environments.
The recent years' progress in deep learning (DL) technology has resulted in convolutional neural networks (CNNs) capable of producing fast and accurate results, with minimal data preprocessing. Currently, gait ana...
详细信息
Boundary detection in natural images represents an important but also challenging problem in computervision. Motivated by studies in psychophysics claiming that humans use multiple cues for segmentation, several prom...
详细信息
Boundary detection in natural images represents an important but also challenging problem in computervision. Motivated by studies in psychophysics claiming that humans use multiple cues for segmentation, several promising methods have been proposed which perform boundary detection by optimally combining local image measurements such as color, texture, and brightness. Very interesting results have been reported by applying these methods on challenging datasets such as the Berkeley segmentation benchmark. Although combining different cues for boundary detection has been shown to outperform methods using a single cue, results can be further improved by integrating perceptual organization cues with the boundary detection process. The main goal of this study is to investigate how and when perceptual organization cues improve boundary detection in natural images. In this context, we investigate the idea of integrating with segmentation the iterative multi-scale tensor voting (IMSTV), a variant of tensor voting (TV) that performs perceptual grouping by analyzing information at multiple-scales and removing background clutter in an iterative fashion, preserving salient, organized structures. The key idea is to use IMSTV to post-process the boundary posterior probability (PB) map produced by segmentation algorithms. Detailed analysis of our experimental results reveals how and when perceptual organization cues are likely to improve or degrade boundary detection. In particular, we show that using perceptual grouping as a post-processing step improves boundary detection in 84% of the grayscale test images in the Berkeley segmentation dataset.
We present a two-layer representation of the locally sensed 3D indoor environment. Our representation moves one step forward from capturing the geometric structure of the environment to reason about the navigation opp...
详细信息
We present a two-layer representation of the locally sensed 3D indoor environment. Our representation moves one step forward from capturing the geometric structure of the environment to reason about the navigation opportunities for an agent in the environment. The first layer is the Planar Semantic Model (PSM), a geometric representation in terms of meaningful planes (ground and walls). PSM captures more semantics of the indoor environment than a pure planar model because it represents a richer set of relationships among planar segments. In the second layer, we present the Action Opportunity Star (AOS), which describes the set of qualitatively distinct opportunities for robot action available in the neighborhood of the robot. Our two-layer representation is a concise representation of indoor environments, semantically meaningful to both robot and to human. It is capable of capturing incomplete knowledge of the local environment so that unknown areas can be incrementally learned as observations become available. Experimental results on a variety of indoor environments demonstrate the expressive power of our representation.
The new non-parametric approach to unsegmented text recognition builds two bipartite graphs that result from the feature-level and lexical comparisons of the same word against a reference string which need not include...
详细信息
The new non-parametric approach to unsegmented text recognition builds two bipartite graphs that result from the feature-level and lexical comparisons of the same word against a reference string which need not include the query word. The lexical graph preserves the relative order of edges in the feature graph corresponding to correctly recognized features. This observation leads to a subgraph-matching formulation of the recognition problem. An initial implementation proves the robustness of the approach for up-to 20% noise introduced in the feature-level graph.
In this paper, we present a bio-inspired, purely passive, and embedded fall detection system for its application towards safety for elderly at home. Bio-inspired means the use of two optical detector chips with event-...
详细信息
In this paper, we present a bio-inspired, purely passive, and embedded fall detection system for its application towards safety for elderly at home. Bio-inspired means the use of two optical detector chips with event-driven pixels that are sensitive to relative light intensity changes only. The two chips are used as stereo configuration which enables a 3D representation of the observed area with a stereo matching technique. In contrast to conventional digital cameras, this image sensor delivers asynchronous events instead of synchronous intensity or color images, thus, the privacy issue is systematically solved. Another advantage is that stationary installed fall detection systems have a better acceptance for independent living compared to permanently worn devices. The fall detection is done by a trained neural network. First, a meaningful feature vector is calculated from the point clouds, then the neural network classifies the actual event as fall or non-fall. All processing is done on an embedded device consisting of an FPGA for stereo matching and a DSP for neural network calculation achieving several fall evaluations per second. The results evaluation showed that our fall detection system achieves a fall detection rate of more than 96% with false positives below 5% for our prerecorded dataset consisting of 679 fall scenarios.
MINPRAN, a new robust operator, finds good fits in data sets where more than 50% of the points are outliers. Unlike other techniques that handle large outlier percentages, MINPRAN does not rely on a known error bound ...
详细信息
MINPRAN, a new robust operator, finds good fits in data sets where more than 50% of the points are outliers. Unlike other techniques that handle large outlier percentages, MINPRAN does not rely on a known error bound for the good data. Instead it assumes that the bad data are randomly (uniformly) distributed within the dynamic range of the sensor. Based on this, MINPRAN uses random sampling to search for the fit and the number of inliers to the fit that are least likely to have occurred randomly. It runs in time O(N/sup 2/+SNlogN), where S is the number of random samples and N is the number of data points. We demonstrate analytically and experimentally that MINPRAN distinguishes good fits from fits to random data, and that MINPRAN finds accurate fits and nearly the correct number of inliers, regardless of the percentage of true inliers.< >
暂无评论