Towards automatic object segmentation with sequential multiple views

Object segmentation is one of the fundamental steps for a number of robotic applications such as manipulation, object detection, and obstacle avoidance. This paper proposes a visual method for incorporating colour and depth information from sequential multiview stereo images to segment objects of interest from complex and cluttered environments. Rather than segmenting objects using information from a single frame in the sequence, we incorporate information from neighbouring views to increase the reliability of the information and improve the overall segmentation result. Specifically, dense depth information of a scene is computed using multiple view stereo. Depths from neighbouring views are reprojected into the reference frame to be segmented compensating for imperfect depth computations for individual frames. The multiple depth layers are then combined with color information from the reference frame to create a Markov random field to model the segmentation problem. Finally, graphcut optimisation is employed to infer pixels belonging to the object to be segmented. The segmentation accuracy is evaluated over images from an outdoor video sequence demonstrating the viability for automatic object segmentation for mobile robots using monocular cameras as a primary sensor.

An investigation of market segmentation theory and its impact on effective fundraising

This paper presents the findings of an indepth study into the effects and success of marketing segmentation, target marketing and fundraising. Organisations are constantly seeking new ways and more efficient means to raise funds so that they can fulfill their objectives. These organisations review and evaluate their resources to gain competitive advantage and increased fundraising success...

Mesoporous bioactive glass scaffolds for efficient delivery of vascular endothelial growth factor

In this article, we, for the first time, investigated mesoporous bioactive glass scaffolds for the delivery of vascular endothelial growth factor. We have found that mesoporous bioactive glass scaffolds have significantly higher loading efficiency and more sustained release of vascular endothelial growth factor than non-mesoporous bioactive glass scaffolds. In addition, vascular endothelial growth factor delivery from mesoporous bioactive glass scaffolds has improved the viability of endothelial cells. The study has suggested that mesopore structures in mesoporous bioactive glass scaffolds play an important role in improving the loading efficiency, decreasing the burst release, and maintaining the bioactivity of vascular endothelial growth factor, indicating that mesoporous bioactive glass scaffolds are an excellent carrier of vascular endothelial growth factor for potential bone tissue engineering applications.

Automatic Audio Segmentation Using the Generalized Likelihood Ratio

This paper presents a novel technique for segmenting an audio stream into homogeneous regions according to speaker identities, background noise, music, environmental and channel conditions. Audio segmentation is useful in audio diarization systems, which aim to annotate an input audio stream with information that attributes temporal regions of the audio into their specific sources. The segmentation method introduced in this paper is performed using the Generalized Likelihood Ratio (GLR), computed between two adjacent sliding windows over preprocessed speech. This approach is inspired by the popular segmentation method proposed by the pioneering work of Chen and Gopalakrishnan, using the Bayesian Information Criterion (BIC) with an expanding search window. This paper will aim to identify and address the shortcomings associated with such an approach. The result obtained by the proposed segmentation strategy is evaluated on the 2002 Rich Transcription (RT-02) Evaluation dataset, and a miss rate of 19.47% and a false alarm rate of 16.94% is achieved at the optimal threshold.

A multi-layered approach for site detection in UAS emergency landing scenarios using geometry-based image segmentation

This paper presents an alternative approach to image segmentation by using the spatial distribution of edge pixels as opposed to pixel intensities. The segmentation is achieved by a multi-layered approach and is intended to find suitable landing areas for an aircraft emergency landing. We combine standard techniques (edge detectors) with novel developed algorithms (line expansion and geometry test) to design an original segmentation algorithm. Our approach removes the dependency on environmental factors that traditionally influence lighting conditions, which in turn have negative impact on pixel-based segmentation techniques. We present test outcomes on realistic visual data collected from an aircraft, reporting on preliminary feedback about the performance of the detection. We demonstrate consistent performances over 97% detection rate.

Automatic object segmentation of unstructured scenes using colour and depth maps

This study presents a segmentation pipeline that fuses colour and depth information to automatically separate objects of interest in video sequences captured from a quadcopter. Many approaches assume that cameras are static with known position, a condition which cannot be preserved in most outdoor robotic applications. In this study, the authors compute depth information and camera positions from a monocular video sequence using structure from motion and use this information as an additional cue to colour for accurate segmentation. The authors model the problem similarly to standard segmentation routines as a Markov random field and perform the segmentation using graph cuts optimisation. Manual intervention is minimised and is only required to determine pixel seeds in the first frame which are then automatically reprojected into the remaining frames of the sequence. The authors also describe an automated method to adjust the relative weights for colour and depth according to their discriminative properties in each frame. Experimental results are presented for two video sequences captured using a quadcopter. The quality of the segmentation is compared to a ground truth and other state-of-the-art methods with consistently accurate results.

GrabCutSFM : how 3D information improves unsupervised object segmentation

In this paper, we present an unsupervised graph cut based object segmentation method using 3D information provided by Structure from Motion (SFM), called Grab- CutSFM. Rather than focusing on the segmentation problem using a trained model or human intervention, our approach aims to achieve meaningful segmentation autonomously with direct application to vision based robotics. Generally, object (foreground) and background have certain discriminative geometric information in 3D space. By exploring the 3D information from multiple views, our proposed method can segment potential objects correctly and automatically compared to conventional unsupervised segmentation using only 2D visual cues. Experiments with real video data collected from indoor and outdoor environments verify the proposed approach.

Nonparametric semantic segmentation for 3D street scenes

In this paper we propose a method to generate a large scale and accurate dense 3D semantic map of street scenes. A dense 3D semantic model of the environment can significantly improve a number of robotic applications such as autonomous driving, navigation or localisation. Instead of using offline trained classifiers for semantic segmentation, our approach employs a data-driven, nonparametric method to parse scenes which easily scale to a large environment and generalise to different scenes. We use stereo image pairs collected from cameras mounted on a moving car to produce dense depth maps which are combined into a global 3D reconstruction using camera poses from stereo visual odometry. Simultaneously, 2D automatic semantic segmentation using a nonparametric scene parsing method is fused into the 3D model. Furthermore, the resultant 3D semantic model is improved with the consideration of moving objects in the scene. We demonstrate our method on the publicly available KITTI dataset and evaluate the performance against manually generated ground truth.

Segmentation of cone-beam CT using a hidden Markov random field with informative priors

Purpose: Flat-detector, cone-beam computed tomography (CBCT) has enormous potential to improve the accuracy of treatment delivery in image-guided radiotherapy (IGRT). To assist radiotherapists in interpreting these images, we use a Bayesian statistical model to label each voxel according to its tissue type. Methods: The rich sources of prior information in IGRT are incorporated into a hidden Markov random field (MRF) model of the 3D image lattice. Tissue densities in the reference CT scan are estimated using inverse regression and then rescaled to approximate the corresponding CBCT intensity values. The treatment planning contours are combined with published studies of physiological variability to produce a spatial prior distribution for changes in the size, shape and position of the tumour volume and organs at risk (OAR). The voxel labels are estimated using the iterated conditional modes (ICM) algorithm. Results: The accuracy of the method has been evaluated using 27 CBCT scans of an electron density phantom (CIRS, Inc. model 062). The mean voxel-wise misclassification rate was 6.2%, with Dice similarity coefficient of 0.73 for liver, muscle, breast and adipose tissue. Conclusions: By incorporating prior information, we are able to successfully segment CBCT images. This could be a viable approach for automated, online image analysis in radiotherapy.

The role of vascular and hormonal genes in migraine susceptibility

Migraine is a primary headache disorder that involves both genetic and environmental components. Migraine is considered to be a polygenic disorder with a number of susceptibility genes having a minor but nonetheless significant impact on susceptibility. Migraine candidate gene studies have concentrated mainly on genes involved in neurotransmitter pathways, however evidence also exists for a role for alterations in vascular and hormonal function in migraine susceptibility. We present here a mini-review of genetic studies, investigating the potential role of vascular and hormonal gene variants, and discuss how vascular and hormonal dysfunction may impact on migraine susceptibility. We propose that the potential role of vascular and hormonal genes in this disorder warrants further investigation.

Electrospinning and crosslinking of low-molecular-weight poly(trimethylene carbonate-co-L-lactide) as an elastomeric scaffold for vascular engineering

The growth of suitable tissue to replace natural blood vessels requires a degradable scaffold material that is processable into porous structures with appropriate mechanical and cell growth properties. This study investigates the fabrication of degradable, crosslinkable prepolymers of l-lactide-co-trimethylene carbonate into porous scaffolds by electrospinning. After crosslinking by γ-radiation, dimensionally stable scaffolds were obtained with up to 56% trimethylene carbonate incorporation. The fibrous mats showed Young’s moduli closely matching human arteries (0.4–0.8 MPa). Repeated cyclic extension yielded negligible change in mechanical properties, demonstrating the potential for use under dynamic physiological conditions. The scaffolds remained elastic and resilient at 30% strain after 84 days of degradation in phosphate buffer, while the modulus and ultimate stress and strain progressively decreased. The electrospun mats are mechanically superior to solid films of the same materials. In vitro, human mesenchymal stem cells adhered to and readily proliferated on the three-dimensional fiber network, demonstrating that these polymers may find use in growing artificial blood vessels in vivo.

Cross-linked poly(trimethylene carbonate-co-L-lactide) as a biodegradable, elastomeric scaffold for vascular engineering applications

A series of copolymers of trimethylene carbonate (TMC) and l-lactide (LLA) were synthesized and evaluated as scaffolds for the production of artificial blood vessels. The polymers were end-functionalized with acrylate, cast into films, and cross-linked using UV light. The mechanical, degradation, and biocompatibility properties were evaluated. High TMC polymers showed mechanical properties comparable to human arteries (Young’s moduli of 1.2–1.8 MPa and high elasticity with repeated cycling at 10% strain). Over 84 days degradation in PBS, the modulus and material strength decreased gradually. The polymers were nontoxic and showed good cell adhesion and proliferation over 7 days using human mesenchymal stem cells. When implanted into the rat peritoneal cavity, the polymers elicited formation of tissue capsules composed of myofibroblasts, resembling immature vascular smooth muscle cells. Thus, these polymers showed properties which were tunable and favorable for vascular tissue engineering, specifically, the growth of artificial blood vessels in vivo.

Segmentation of cone-beam CT using a hidden Markov random field with informative priors

Cone-beam computed tomography (CBCT) has enormous potential to improve the accuracy of treatment delivery in image-guided radiotherapy (IGRT). To assist radiotherapists in interpreting these images, we use a Bayesian statistical model to label each voxel according to its tissue type. The rich sources of prior information in IGRT are incorporated into a hidden Markov random field model of the 3D image lattice. Tissue densities in the reference CT scan are estimated using inverse regression and then rescaled to approximate the corresponding CBCT intensity values. The treatment planning contours are combined with published studies of physiological variability to produce a spatial prior distribution for changes in the size, shape and position of the tumour volume and organs at risk. The voxel labels are estimated using iterated conditional modes. The accuracy of the method has been evaluated using 27 CBCT scans of an electron density phantom. The mean voxel-wise misclassification rate was 6.2\%, with Dice similarity coefficient of 0.73 for liver, muscle, breast and adipose tissue. By incorporating prior information, we are able to successfully segment CBCT images. This could be a viable approach for automated, online image analysis in radiotherapy.

Invading edge vs. inner (edvin) patterns of vascularization : an interplay between angiogenic and vascular survival factors defines the clinical behaviour of non-small cell lung cancer

Neo-angiogenesis during neoplastic growth involves endothelial mitogenic and migration stimuli produced by cancer or tumour stromal cells. Although this active angiogenesis takes place in the tumour periphery, the process of vessel growth and survival in inner areas and its clinical role remain largely unexplored. The present study compared the microvessel score (MS) as well as the single endothelial cell score (ECS) in the invading edge and in inner areas of non-small cell lung carcinomas (NSCLCs). Three different patterns of vascular growth were distinguished: the edvin (edge vs. inner) type 1, where a low MS was observed in both peripheral and inner tumour areas; the edvin type 2, where a high MS was noted in the invading front but a low MS in inner areas; and the edvin type 3, where both peripheral and inner tumour areas had a high MS. The ECS was high in the invading edge in edvin type 2 and 3 cases and was sharply decreased in both types in inner areas, suggesting that endothelial cell migration is unlikely to contribute to the angiogenic process in areas away from the tumour front. Expression of the vascular endothelial growth factor (VEGF) and of thymidine phosphorylase (TP) was associated with a high MS in the invading edge. VEGF was associated with a high MS in inner areas (edvin 3), while TP expression was associated with edvin type 2, showing that VEGF (and not TP) contributes to the preservation of the inner vasculature. Both edvin type 2 and 3 cases showed an increased incidence of node metastasis, but edvin type 3 cases had a poorer prognosis, even in the N1-stage group. The present study suggests that tumour factors regulating angiogenesis and vascular survival are not identical. A possible method is reported to quantify these two parameters by comparing the MS in the invading edge and inner areas (edvin types). This observation may contribute to the evaluation of the effectiveness of different therapeutic approaches, namely vascular targeting vs. anti-angiogenesis. Copyright (C) 2000 John Wiley and Sons, Ltd.