The extraction of drainage networks from digital elevation data is important for quantitative studies in geomorphology and hydrology. A method is presented for extracting drainage networks from gridded elevation data. The method handles artificial pits introduced by data collection systems and extracts only the major drainage paths. Its performance appears to be consistent with the visual interpretation of drainage patterns from elevation contours.

The extraction of drainage networks from digital elevation data : Computer Vision

Apercu sur les quadarbres et les structures de donnees hierarchiques. Elles sont basees sur le principe de decomposition recursive. L'accentuation est mise sur la representation de donnees dans les applications de traitement d'images, d'infographie, les systemes d'informations geographiques et la robotique. On examine en detail un certain nombre d'operations dans lesquelles de telles structures de donnees trouvent leur utilisation

/pdf/the-quadtree-and-related-hierarchical-data-structures-38sprs9bn9.pdf

The Quadtree and Related Hierarchical Data Structures

The extraction of drainage networks from digital elevation data

There are now a wide Abstract There are now a wide variety of image segmentation techniques, some considered general purpose and some designed for specific classes of images. These techniques can be classified as: measurement space guided spatial clustering, single linkage region growing schemes, hybrid linkage region growing schemes, centroid linkage region growing schemes, spatial clustering schemes, and split-and-merge schemes. In this paper, we define each of the major classes of image segmentation techniques and describe several specific examples of each class of algorithm. We illustrate some of the techniques with examples of segmentations performed on real images.

Image Segmentation Techniques

We consider the problem of detecting robotic grasps in an RGB-D view of a scene containing objects. In this work, we apply a deep learning approach to solve this problem, which avoids time-consuming hand-design of features. This presents two main challenges. First, we need to evaluate a huge number of candidate grasps. In order to make detection fast and robust, we present a two-step cascaded system with two deep networks, where the top detections from the first are re-evaluated by the second. The first network has fewer features, is faster to run, and can effectively prune out unlikely candidate grasps. The second, with more features, is slower but has to run only on the top few detections. Second, we need to handle multimodal inputs effectively, for which we present a method that applies structured regularization on the weights based on multimodal group regularization. We show that our method improves performance on an RGBD robotic grasping dataset, and can be used to successfully execute grasps on two different robotic platforms.

http://roboticsproceedings.org/rss09/p12.pdf

Deep learning for detecting robotic grasps

BS NBS NBS NBS NBS NBS NBS NBS NBS NBS N NBS NBS NBS NBS NBS NBS NBS NBS NBS NBS BS NBS NBS NBS NBS NBS NBS NBS NBS NBS N NBS NBS NBS NBS NBS NBS NBS NBS NBS NBS BS NBS NBS NBS NBS NBS NBS NBS NBS NBS N NBS NBS NBS NBS NBS NBS NBS NBS NBS NBS /?^ NBS NBS NBS NBS NBS NBS NBS NBS NBS N NBS NBS NBS NBS NBS NBS NBS NBS NBS NBS «S' NBS NBS NBS NBS NBS NBS NBS NBS NBS \ NBS NBS NBS NBS NBS NBS NBS NBS NBS NBS BS NBS NBS National Bureau ofStandards NBS NBS N NBS NBS NBS NBS NBS NBS NBS NBS NBS NBS NBS NBS NBS NBSNBS NBS NBS NBS N WBS NBS NBS NBS NBS NBS NBS NBS NBS \S NBS NBS NBS NBS NBS NBS fVBS NBS N

NASA/NBS Standard Reference Model for Telerobot Control System Architecture (NASREM)

A new algorithm for calculating the connected components of a binary image is presented, and a proof of correctness is given. For a large image, this algorithm required 1 hour of CPU time while the standard technique used over 36 hours. The storage requirements for this new algorithm are appropriate for small minicomputers as well as for larger machines.

A new connected components algorithm for virtual memory computers

Power towers are capable of producing solar-generated electricity and hydrogen on a large scale. Heliostats are the most important cost element of a solar power tower plant. Since they constitute {approx} 50% of the capital cost of the plant it is important to reduce heliostat cost as much as possible to improve the economic performance of power towers. In this study we evaluate current heliostat technology and estimate a price of $$126/m{sup 2} given year-2006 materials and labor costs for a deployment of {approx}600 MW of power towers per year. This 2006 price yields electricity at $$0.067/kWh and hydrogen at $3.20/kg. We propose research and development that should ultimately lead to a price as low as $$90/m{sup 2}, which equates to $$0.056/kWh and $2.75/kg H{sup 2}. Approximately 30 heliostat and manufacturing experts from the United States, Europe, and Australia contributed to the content of this report during two separate workshops conducted at the National Solar Thermal Test Facility.

/pdf/heliostat-cost-reduction-study-4ughivyrc3.pdf

Heliostat Cost Reduction Study

PIPE (pipelined image-processing engine)

/pdf/nasanbs-standard-reference-model-for-telerobot-control-385tt3ys1z.pdf

Ronald Lumia

Papers

NASA/NBS Standard Reference Model for Telerobot Control System Architecture (NASREM)

A new connected components algorithm for virtual memory computers

Heliostat Cost Reduction Study

PIPE (pipelined image-processing engine)

NASANBS standard reference model for telerobot control system architecture (NASREM) (supersedes NBS Technical Note 1235 issued July 1987)