Segmentation of scenes of mobile objects and demonstrable backgrounds

In this paper we present a real-time foreground–background segmentation algorithm that exploits the following observation (very often satisfied by a static camera positioned high in its environment). If a blob moves on a pixel p that had not changed its colour significantly for a few frames, then p was probably part of the background when its colour was static. With this information we are able to update differentially pixels believed to be background. This work is relevant to autonomous minirobots, as they often navigate in buildings where smart surveillance cameras could communicate wirelessly with them. A by-product of the proposed system is a mask of the image regions which are demonstrably background. Statistically significant tests show that the proposed method has a better precision and recall rates than the state of the art foreground/background segmentation algorithm of the OpenCV computer vision library.

The evidence-based development of an intervention to address the information needs of adults newly diagnosed with primary brain tumours and their carers

Adults diagnosed with primary brain tumours often experience physical, cognitive and neuropsychiatric impairments and decline in quality of life. Although disease and treatment-related information is commonly provided to cancer patients and carers, newly diagnosed brain tumour patients and their carers report unmet information needs. Few interventions have been designed or proven to address these information needs. Accordingly, a three-study research program, that incorporated both qualitative and quantitative research methods, was designed to: 1) identify and select an intervention to improve the provision of information, and meet the needs of patients with a brain tumour; 2) use an evidence-based approach to establish the content, language and format for the intervention; and 3) assess the acceptability of the intervention, and the feasibility of evaluation, with newly diagnosed brain tumour patients. Study 1: Structured concept mapping techniques were undertaken with 30 health professionals, who identified strategies or items for improving care, and rated each of 42 items for importance, feasibility, and the extent to which such care was provided. Participants also provided data to interpret the relationship between items, which were translated into ‘maps’ of relationships between information and other aspects of health care using multidimensional scaling and hierarchical cluster analysis. Results were discussed by participants in small groups and individual interviews to understand the ratings, and facilitators and barriers to implementation. A care coordinator was rated as the most important strategy by health professionals. Two items directly related to information provision were also seen as highly important: "information to enable the patient or carer to ask questions" and "for doctors to encourage patients to ask questions". Qualitative analyses revealed that information provision was individualised, depending on patients’ information needs and preferences, demographic variables and distress, the characteristics of health professionals who provide information, the relationship between the individual patient and health professional, and influenced by the fragmented nature of the health care system. Based on quantitative and qualitative findings, a brain tumour specific question prompt list (QPL) was chosen for development and feasibility testing. A QPL consists of a list of questions that patients and carers may want to ask their doctors. It is designed to encourage the asking of questions in the medical consultation, allowing patients to control the content, and amount of information provided by health professionals. Study 2: The initial structure and content of the brain tumour specific QPL developed was based upon thematic analyses of 1) patient materials for brain tumour patients, 2) QPLs designed for other patient populations, and 3) clinical practice guidelines for the psychosocial care of glioma patients. An iterative process of review and refinement of content was undertaken via telephone interviews with a convenience sample of 18 patients and/or carers. Successive drafts of QPLs were sent to patients and carers and changes made until no new topics or suggestions arose in four successive interviews (saturation). Once QPL content was established, readability analyses and redrafting were conducted to achieve a sixth-grade reading level. The draft QPL was also reviewed by eight health professionals, and shortened and modified based on their feedback. Professional design of the QPL was conducted and sent to patients and carers for further review. The final QPL contained questions in seven colour-coded sections: 1) diagnosis; 2) prognosis; 3) symptoms and problems; 4) treatment; 5) support; 6) after treatment finishes; and 7) the health professional team. Study 3: A feasibility study was conducted to determine the acceptability of the QPL and the appropriateness of methods, to inform a potential future randomised trial to evaluate its effectiveness. A pre-test post-test design was used with a nonrandomised control group. The control group was provided with ‘standard information’, the intervention group with ‘standard information’ plus the QPL. The primary outcome measure was acceptability of the QPL to participants. Twenty patients from four hospitals were recruited a median of 1 month (range 0-46 months) after diagnosis, and 17 completed baseline and follow-up interviews. Six participants would have preferred to receive the information booklet (standard information or QPL) at a different time, most commonly at diagnosis. Seven participants reported on the acceptability of the QPL: all said that the QPL was helpful, and that it contained questions that were useful to them; six said it made it easier to ask questions. Compared with control group participants’ ratings of ‘standard information’, QPL group participants’ views of the QPL were more positive; the QPL had been read more times, was less likely to be reported as ‘overwhelming’ to read, and was more likely to prompt participants to ask questions of their health professionals. The results from the three studies of this research program add to the body of literature on information provision for brain tumour patients. Together, these studies suggest that a QPL may be appropriate for the neuro-oncology setting and acceptable to patients. The QPL aims to assist patients to express their information needs, enabling health professionals to better provide the type and amount of information that patients need to prepare for treatment and the future. This may help health professionals meet the challenge of giving patients sufficient information, without providing ‘too much’ or ‘unnecessary’ information, or taking away hope. Future studies with rigorous designs are now needed to determine the effectiveness of the QPL.

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 aspect query language model based on query decomposition and high-order contextual term associations

In information retrieval (IR) research, more and more focus has been placed on optimizing a query language model by detecting and estimating the dependencies between the query and the observed terms occurring in the selected relevance feedback documents. In this paper, we propose a novel Aspect Language Modeling framework featuring term association acquisition, document segmentation, query decomposition, and an Aspect Model (AM) for parameter optimization. Through the proposed framework, we advance the theory and practice of applying high-order and context-sensitive term relationships to IR. We first decompose a query into subsets of query terms. Then we segment the relevance feedback documents into chunks using multiple sliding windows. Finally we discover the higher order term associations, that is, the terms in these chunks with high degree of association to the subsets of the query. In this process, we adopt an approach by combining the AM with the Association Rule (AR) mining. In our approach, the AM not only considers the subsets of a query as “hidden” states and estimates their prior distributions, but also evaluates the dependencies between the subsets of a query and the observed terms extracted from the chunks of feedback documents. The AR provides a reasonable initial estimation of the high-order term associations by discovering the associated rules from the document chunks. Experimental results on various TREC collections verify the effectiveness of our approach, which significantly outperforms a baseline language model and two state-of-the-art query language models namely the Relevance Model and the Information Flow model

Tooth fracture risk analysis based on a new finite element dental structure models using micro-CT data

The finite element (FE) analysis is an effective method to study the strength and predict the fracture risk of endodontically-treated teeth. This paper presents a rapid method developed to generate a comprehensive tooth FE model using data retrieved from micro-computed tomography (μCT). With this method, the inhomogeneity of material properties of teeth was included into the model without dividing the tooth model into different regions. The material properties of the tooth were assumed to be related to the mineral density. The fracture risk at different tooth portions was assessed for root canal treatments. The micro-CT images of a tooth were processed by a Matlab software programme and the CT numbers were retrieved. The tooth contours were obtained with thresholding segmentation using Amira. The inner and outer surfaces of the tooth were imported into Solidworks and a three-dimensional (3D) tooth model was constructed. An assembly of the tooth model with the periodontal ligament (PDL) layer and surrounding bone was imported into ABAQUS. The material properties of the tooth were calculated from the retrieved CT numbers via ABAQUS user's subroutines. Three root canal geometries (original and two enlargements) were investigated. The proposed method in this study can generate detailed 3D finite element models of a tooth with different root canal enlargements and filling materials, and would be very useful for the assessment of the fracture risk at different tooth portions after root canal treatments.

Colour coding the fridge to reduce food waste

This paper introduces the first iteration of a study aimed at grouping similar food types together in a refrigerator to increase the awareness of available foods for consumers in a domestic environment. The goals of the project are twofold: i) Raise the awareness of available foods for all members of a household; ii) Reduce the amount of expired food waste in the household. The project implemented a paper-based colour scheme in refrigerators in households, assigning colours to particular food types (e.g. green to fruit and vegetables, red to meat, etc.). The findings show that the colour coding raised participants’ awareness of available food items in the fridge, particularly for those participants who were not directly involved in the shopping and initial storage of each food item. The findings also indicate that such awareness led to a reduction in expiration of food and thus general food waste in the household. These preliminary findings suggest that raising awareness of food availability through categorisation and efficient communication of this information may lead to a reduction in food waste in domestic environments.

Efficient real-time face detection for high resolution surveillance applications

This paper presents an efficient face detection method suitable for real-time surveillance applications. Improved efficiency is achieved by constraining the search window of an AdaBoost face detector to pre-selected regions. Firstly, the proposed method takes a sparse grid of sample pixels from the image to reduce whole image scan time. A fusion of foreground segmentation and skin colour segmentation is then used to select candidate face regions. Finally, a classifier-based face detector is applied only to selected regions to verify the presence of a face (the Viola-Jones detector is used in this paper). The proposed system is evaluated using 640 x 480 pixels test images and compared with other relevant methods. Experimental results show that the proposed method reduces the detection time to 42 ms, where the Viola-Jones detector alone requires 565 ms (on a desktop processor). This improvement makes the face detector suitable for real-time applications. Furthermore, the proposed method requires 50% of the computation time of the best competing method, while reducing the false positive rate by 3.2% and maintaining the same hit rate.

Improved foreground detection via block-based classifier cascade with probabilistic decision integration

Background subtraction is a fundamental low-level processing task in numerous computer vision applications. The vast majority of algorithms process images on a pixel-by-pixel basis, where an independent decision is made for each pixel. A general limitation of such processing is that rich contextual information is not taken into account. We propose a block-based method capable of dealing with noise, illumination variations, and dynamic backgrounds, while still obtaining smooth contours of foreground objects. Specifically, image sequences are analyzed on an overlapping block-by-block basis. A low-dimensional texture descriptor obtained from each block is passed through an adaptive classifier cascade, where each stage handles a distinct problem. A probabilistic foreground mask generation approach then exploits block overlaps to integrate interim block-level decisions into final pixel-level foreground segmentation. Unlike many pixel-based methods, ad-hoc postprocessing of foreground masks is not required. Experiments on the difficult Wallflower and I2R datasets show that the proposed approach obtains on average better results (both qualitatively and quantitatively) than several prominent methods. We furthermore propose the use of tracking performance as an unbiased approach for assessing the practical usefulness of foreground segmentation methods, and show that the proposed approach leads to considerable improvements in tracking accuracy on the CAVIAR dataset.

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.

Robust vision-based underwater homing using self-similar landmarks

Next-generation autonomous underwater vehicles (AUVs) will be required to robustly identify underwater targets for tasks such as inspection, localization, and docking. Given their often unstructured operating environments, vision offers enormous potential in underwater navigation over more traditional methods; however, reliable target segmentation often plagues these systems. This paper addresses robust vision-based target recognition by presenting a novel scale and rotationally invariant target design and recognition routine based on self-similar landmarks that enables robust target pose estimation with respect to a single camera. These algorithms are applied to an AUV with controllers developed for vision-based docking with the target. Experimental results show that the system performs exceptionally on limited processing power and demonstrates how the combined vision and controller system enables robust target identification and docking in a variety of operating conditions.

Automatic segmentation of choroidal thickness in optical coherence tomography

The assessment of choroidal thickness from optical coherence tomography (OCT) images of the human choroid is an important clinical and research task, since it provides valuable information regarding the eye’s normal anatomy and physiology, and changes associated with various eye diseases and the development of refractive error. Due to the time consuming and subjective nature of manual image analysis, there is a need for the development of reliable objective automated methods of image segmentation to derive choroidal thickness measures. However, the detection of the two boundaries which delineate the choroid is a complicated and challenging task, in particular the detection of the outer choroidal boundary, due to a number of issues including: (i) the vascular ocular tissue is non-uniform and rich in non-homogeneous features, and (ii) the boundary can have a low contrast. In this paper, an automatic segmentation technique based on graph-search theory is presented to segment the inner choroidal boundary (ICB) and the outer choroidal boundary (OCB) to obtain the choroid thickness profile from OCT images. Before the segmentation, the B-scan is pre-processed to enhance the two boundaries of interest and to minimize the artifacts produced by surrounding features. The algorithm to detect the ICB is based on a simple edge filter and a directional weighted map penalty, while the algorithm to detect the OCB is based on OCT image enhancement and a dual brightness probability gradient. The method was tested on a large data set of images from a pediatric (1083 B-scans) and an adult (90 B-scans) population, which were previously manually segmented by an experienced observer. The results demonstrate the proposed method provides robust detection of the boundaries of interest and is a useful tool to extract clinical data.

Dealing with shadows : capturing intrinsic scene appearance for image-based outdoor localisation

In outdoor environments shadows are common. These typically strong visual features cause considerable change in the appearance of a place, and therefore confound vision-based localisation approaches. In this paper we describe how to convert a colour image of the scene to a greyscale invariant image where pixel values are a function of underlying material property not lighting. We summarise the theory of shadow invariant images and discuss the modelling and calibration issues which are important for non-ideal off-the-shelf colour cameras. We evaluate the technique with a commonly used robotic camera and an autonomous car operating in an outdoor environment, and show that it can outperform the use of ordinary greyscale images for the task of visual localisation.

Transit passenger segmentation using travel regularity mined from Smart Card transactions data

Transit passenger market segmentation enables transit operators to target different classes of transit users to provide customized information and services. The Smart Card (SC) data, from Automated Fare Collection system, facilitates the understanding of multiday travel regularity of transit passengers, and can be used to segment them into identifiable classes of similar behaviors and needs. However, the use of SC data for market segmentation has attracted very limited attention in the literature. This paper proposes a novel methodology for mining spatial and temporal travel regularity from each individual passenger’s historical SC transactions and segments them into four segments of transit users. After reconstructing the travel itineraries from historical SC transactions, the paper adopts the Density-Based Spatial Clustering of Application with Noise (DBSCAN) algorithm to mine travel regularity of each SC user. The travel regularity is then used to segment SC users by an a priori market segmentation approach. The methodology proposed in this paper assists transit operators to understand their passengers and provide them oriented information and services.

Vision-based docking using an autonomous surface vehicle

This paper describes the development of a novel vision-based autonomous surface vehicle with the purpose of performing coordinated docking manoeuvres with a target, such as an autonomous underwater vehicle, at the water's surface. The system architecture integrates two small processor units; the first performs vehicle control and implements a virtual force based docking strategy, with the second performing vision-based target segmentation and tracking. Furthermore, the architecture utilises wireless sensor network technology allowing the vehicle to be observed by, and even integrated within an ad-hoc sensor network. Simulated and experimental results are presented demonstrating the autonomous vision- based docking strategy on a proof-of-concept vehicle.

Moving object detection in aerial video based on spatiotemporal saliency

In this paper, the problem of moving object detection in aerial video is addressed. While motion cues have been extensively exploited in the literature, how to use spatial information is still an open problem. To deal with this issue, we propose a novel hierarchical moving target detection method based on spatiotemporal saliency. Temporal saliency is used to get a coarse segmentation, and spatial saliency is extracted to obtain the object’s appearance details in candidate motion regions. Finally, by combining temporal and spatial saliency information, we can get refined detection results. Additionally, in order to give a full description of the object distribution, spatial saliency is detected in both pixel and region levels based on local contrast. Experiments conducted on the VIVID dataset show that the proposed method is efficient and accurate.