Feature recognition & tool path generation for 5 axis step-nc machining of free form / irregular contoured surfaces

This research paper presents a five step algorithm to generate tool paths for machining Free form / Irregular Contoured Surface(s) (FICS) by adopting STEP-NC (AP-238) format. In the first step, a parametrized CAD model with FICS is created or imported in UG-NX6.0 CAD package. The second step recognizes the features and calculates a Closeness Index (CI) by comparing them with the B-Splines / Bezier surfaces. The third step utilizes the CI and extracts the necessary data to formulate the blending functions for identified features. In the fourth step Z-level 5 axis tool paths are generated by adopting flat and ball end mill cutters. Finally, in the fifth step, tool paths are integrated with STEP-NC format and validated. All these steps are discussed and explained through a validated industrial component.

Real-time image classification for adaptive mission planning using an Autonomous Underwater Vehicle

Real-time image analysis and classification onboard robotic marine vehicles, such as AUVs, is a key step in the realisation of adaptive mission planning for large-scale habitat mapping in previously unexplored environments. This paper describes a novel technique to train, process, and classify images collected onboard an AUV used in relatively shallow waters with poor visibility and non-uniform lighting. The approach utilises Förstner feature detectors and Laws texture energy masks for image characterisation, and a bag of words approach for feature recognition. To improve classification performance we propose a usefulness gain to learn the importance of each histogram component for each class. Experimental results illustrate the performance of the system in characterisation of a variety of marine habitats and its ability to operate onboard an AUV's main processor suitable for real-time mission planning.

Automation of underground LHD and truck haulage

This paper reviews the state-of-the-art in the automation of underground mining vehicles and reports on the development of an autonomous navigation system under development through the CMTE with sponsorship arranged by AMIRA. Past attempts at automating LHDs and haul trucks are described and their particular strengths and weaknesses are discussed. The auto-guidance system being developed overcomes some of the limitations of state-of-the-art prototype æcommercialÆ systems. It can be retrofitted to existing remote controlled vehicles, uses minimum installed infrastructure and is flexible enough for rapid relocation to alternate routes. The navigation techniques use data fusion of two separate sets of sensors combining natural feature recognition, nodal maps and inertial navigation techniques. Collision detection is incorporated and people and other traffic are excluded from the tramming area. This paper describes the work being done by the group with regard to auto-tramming and also outlines the future goals.

How are Three-Deminsional Objects Represented in the Brain?

We discuss a variety of object recognition experiments in which human subjects were presented with realistically rendered images of computer-generated three-dimensional objects, with tight control over stimulus shape, surface properties, illumination, and viewpoint, as well as subjects' prior exposure to the stimulus objects. In all experiments recognition performance was: (1) consistently viewpoint dependent; (2) only partially aided by binocular stereo and other depth information, (3) specific to viewpoints that were familiar; (4) systematically disrupted by rotation in depth more than by deforming the two-dimensional images of the stimuli. These results are consistent with recently advanced computational theories of recognition based on view interpolation.

Gestational drive and the green-bearded placenta.

A "green beard" refers to a gene, or group of genes, that is able to recognize itself in other individuals and direct benefits to these individuals. Green-beard effects have been dismissed as implausible by authors who have implicitly assumed sophisticated mechanisms of perception and complex behavioral responses. However, many simple mechanisms for genes to "recognize" themselves exist at the maternal-fetal interface of viviparous organisms. Homophilic cell adhesion molecules, for example, are able to interact with copies of themselves on other cells. Thus, the necessary components of a green-beard effect -- feature, recognition, and response -- can be different aspects of the phenotype of a single gene. Other green-beard effects could involve coalitions of genes at closely linked loci. In fact, any form of epistasis between a locus expressed in a mother and a closely linked locus expressed in the fetus has the property of "self-recognition." Green-beard effects have many formal similarities to systems of meiotic drive and, like them, can be a source of intragenomic conflict.

Distinct pharmacological properties and distribution in neurons and endocrine cells of two isoforms of the human vesicular monoamine transporter.

A second isoform of the human vesicular monoamine transporter (hVMAT) has been cloned from a pheochromocytoma cDNA library. The contribution of the two transporter isoforms to monoamine storage in human neuroendocrine tissues was examined with isoform-specific polyclonal antibodies against hVMAT1 and hVMAT2. Central, peripheral, and enteric neurons express only VMAT2. VMAT1 is expressed exclusively in neuroendocrine, including chromaffin and enterochromaffin, cells. VMAT1 and VMAT2 are coexpressed in all chromaffin cells of the adrenal medulla. VMAT2 alone is expressed in histamine-storing enterochromaffin-like cells of the oxyntic mucosa of the stomach. The transport characteristics and pharmacology of each VMAT isoform have been directly compared after expression in digitonin-permeabilized fibroblastic (CV-1) cells, providing information about substrate feature recognition by each transporter and the role of vesicular monoamine storage in the mechanism of action of psychopharmacologic and neurotoxic agents in human. Serotonin has a similar affinity for both transporters. Catecholamines exhibit a 3-fold higher affinity, and histamine exhibits a 30-fold higher affinity, for VMAT2. Reserpine and ketanserin are slightly more potent inhibitors of VMAT2-mediated transport than of VMAT1-mediated transport, whereas tetrabenazine binds to and inhibits only VMAT2. N-methyl-4-phenylpyridinium, phenylethylamine, amphetamine, and methylenedioxymethamphetamine are all more potent inhibitors of VMAT2 than of VMAT1, whereas fenfluramine is a more potent inhibitor of VMAT1-mediated monamine transport than of VMAT2-mediated monoamine transport. The unique distributions of hVMAT1 and hVMAT2 provide new markers for multiple neuroendocrine lineages, and examination of their transport properties provides mechanistic insights into the pharmacology and physiology of amine storage in cardiovascular, endocrine, and central nervous system function.

Use of fundus imaging in quantification of age-related macular change

This review will discuss the use of manual grading scales, digital photography, and automated image analysis in the quantification of fundus changes caused by age-related macular disease. Digital imaging permits processing of images for enhancement, comparison, and feature quantification, and these techniques have been investigated for automated drusen analysis. The accuracy of automated analysis systems has been enhanced by the incorporation of interactive elements, such that the user is able to adjust the sensitivity of the system, or manually add and remove pixels. These methods capitalize on both computer and human image feature recognition and the advantage of computer-based methodologies for quantification. The histogram-based adaptive local thresholding system is able to extract useful information from the image without being affected by the presence of other structures. More recent developments involve compensation for fundus background reflectance, which has most recently been combined with the Otsu method of global thresholding. This method is reported to provide results comparable with manual stereo viewing. Developments in this area are likely to encourage wider use of automated techniques. This will make the grading of photographs easier and cheaper for clinicians and researchers. © 2007 Elsevier Inc. All rights reserved.

Integration of cad/ tool path data for 5-axis step-nc machining of free form / irrregular contoured surfaces

This research paper presents the work on feature recognition, tool path data generation and integration with STEP-NC (AP-238 format) for features having Free form / Irregular Contoured Surface(s) (FICS). Initially, the FICS features are modelled / imported in UG CAD package and a closeness index is generated. This is done by comparing the FICS features with basic B-Splines / Bezier curves / surfaces. Then blending functions are caculated by adopting convolution theorem. Based on the blending functions, contour offsett tool paths are generated and simulated for 5 axis milling environment. Finally, the tool path (CL) data is integrated with STEP-NC (AP-238) format. The tool path algorithm and STEP- NC data is tested with various industrial parts through an automated UFUNC plugin.

2D-3D Face Recognition Based on PCA and Feature Modelling

Hybrid face recognition, using image (2D) and structural (3D) information, has explored the fusion of Nearest Neighbour classifiers. This paper examines the effectiveness of feature modelling for each individual modality, 2D and 3D. Furthermore, it is demonstrated that the fusion of feature modelling techniques for the 2D and 3D modalities yields performance improvements over the individual classifiers. By fusing the feature modelling classifiers for each modality with equal weights the average Equal Error Rate improves from 12.60% for the 2D classifier and 12.10% for the 3D classifier to 7.38% for the Hybrid 2D+3D clasiffier.

Feature-domain super-resolution for IRIS recognition

Uncooperative iris identification systems at a distance suffer from poor resolution of the captured iris images, which significantly degrades iris recognition performance. Superresolution techniques have been employed to enhance the resolution of iris images and improve the recognition performance. However, all existing super-resolution approaches proposed for the iris biometric super-resolve pixel intensity values. This paper considers transferring super-resolution of iris images from the intensity domain to the feature domain. By directly super-resolving only the features essential for recognition, and by incorporating domain specific information from iris models, improved recognition performance compared to pixel domain super-resolution can be achieved. This is the first paper to investigate the possibility of feature domain super-resolution for iris recognition, and experiments confirm the validity of the proposed approach.

Feature-based visual odometry and featureless place recognition for SLAM in 2.5D environments

In this paper we present a novel algorithm for localization during navigation that performs matching over local image sequences. Instead of calculating the single location most likely to correspond to a current visual scene, the approach finds candidate matching locations within every section (subroute) of all learned routes. Through this approach, we reduce the demands upon the image processing front-end, requiring it to only be able to correctly pick the best matching image from within a short local image sequence, rather than globally. We applied this algorithm to a challenging downhill mountain biking visual dataset where there was significant perceptual or environment change between repeated traverses of the environment, and compared performance to applying the feature-based algorithm FAB-MAP. The results demonstrate the potential for localization using visual sequences, even when there are no visual features that can be reliably detected.