Video analytics for the detection of near-miss incidents on approach to railway level crossings

Recent modelling of socio-economic costs by the Australian railway industry in 2010 has estimated the cost of level crossing accidents to exceed AU$116 million annually. To better understand causal factors that contribute to these accidents, the Cooperative Research Centre for Rail Innovation is running a project entitled Baseline Level Crossing Video. The project aims to improve the recording of level crossing safety data by developing an intelligent system capable of detecting near-miss incidents and capturing quantitative data around these incidents. To detect near-miss events at railway level crossings a video analytics module is being developed to analyse video footage obtained from forward-facing cameras installed on trains. This paper presents a vision base approach for the detection of these near-miss events. The video analytics module is comprised of object detectors and a rail detection algorithm, allowing the distance between a detected object and the rail to be determined. An existing publicly available Histograms of Oriented Gradients (HOG) based object detector algorithm is used to detect various types of vehicles in each video frame. As vehicles are usually seen from a sideway view from the cabin’s perspective, the results of the vehicle detector are verified using an algorithm that can detect the wheels of each detected vehicle. Rail detection is facilitated using a projective transformation of the video, such that the forward-facing view becomes a bird’s eye view. Line Segment Detector is employed as the feature extractor and a sliding window approach is developed to track a pair of rails. Localisation of the vehicles is done by projecting the results of the vehicle and rail detectors on the ground plane allowing the distance between the vehicle and rail to be calculated. The resultant vehicle positions and distance are logged to a database for further analysis. We present preliminary results regarding the performance of a prototype video analytics module on a data set of videos containing more than 30 different railway level crossings. The video data is captured from a journey of a train that has passed through these level crossings.

V1-inspired features induce a weighted margin in SVMs

Image representations derived from simplified models of the primary visual cortex (V1), such as HOG and SIFT, elicit good performance in a myriad of visual classification tasks including object recognition/detection, pedestrian detection and facial expression classification. A central question in the vision, learning and neuroscience communities regards why these architectures perform so well. In this paper, we offer a unique perspective to this question by subsuming the role of V1-inspired features directly within a linear support vector machine (SVM). We demonstrate that a specific class of such features in conjunction with a linear SVM can be reinterpreted as inducing a weighted margin on the Kronecker basis expansion of an image. This new viewpoint on the role of V1-inspired features allows us to answer fundamental questions on the uniqueness and redundancies of these features, and offer substantial improvements in terms of computational and storage efficiency.

In the pursuit of effective affective computing : the relationship between features and registration

For facial expression recognition systems to be applicable in the real world, they need to be able to detect and track a previously unseen person's face and its facial movements accurately in realistic environments. A highly plausible solution involves performing a "dense" form of alignment, where 60-70 fiducial facial points are tracked with high accuracy. The problem is that, in practice, this type of dense alignment had so far been impossible to achieve in a generic sense, mainly due to poor reliability and robustness. Instead, many expression detection methods have opted for a "coarse" form of face alignment, followed by an application of a biologically inspired appearance descriptor such as the histogram of oriented gradients or Gabor magnitudes. Encouragingly, recent advances to a number of dense alignment algorithms have demonstrated both high reliability and accuracy for unseen subjects [e.g., constrained local models (CLMs)]. This begs the question: Aside from countering against illumination variation, what do these appearance descriptors do that standard pixel representations do not? In this paper, we show that, when close to perfect alignment is obtained, there is no real benefit in employing these different appearance-based representations (under consistent illumination conditions). In fact, when misalignment does occur, we show that these appearance descriptors do work well by encoding robustness to alignment error. For this work, we compared two popular methods for dense alignment-subject-dependent active appearance models versus subject-independent CLMs-on the task of action-unit detection. These comparisons were conducted through a battery of experiments across various publicly available data sets (i.e., CK+, Pain, M3, and GEMEP-FERA). We also report our performance in the recent 2011 Facial Expression Recognition and Analysis Challenge for the subject-independent task.

On Visual Detection of Highly-occluded Objects for Harvesting Automation in Horticulture

Developing accurate and reliable crop detection algorithms is an important step for harvesting automation in horticulture. This paper presents a novel approach to visual detection of highly-occluded fruits. We use a conditional random field (CRF) on multi-spectral image data (colour and Near-Infrared Reflectance, NIR) to model two classes: crop and background. To describe these two classes, we explore a range of visual-texture features including local binary pattern, histogram of oriented gradients, and learn auto-encoder features. The pro-posed methods are evaluated using hand-labelled images from a dataset captured on a commercial capsicum farm. Experimental results are presented, and performance is evaluated in terms of the Area Under the Curve (AUC) of the precision-recall curves.Our current results achieve a maximum performance of 0.81AUC when combining all of the texture features in conjunction with colour information.

Similarity-based birdcall retrieval from environmental audio

Automated digital recordings are useful for large-scale temporal and spatial environmental monitoring. An important research effort has been the automated classification of calling bird species. In this paper we examine a related task, retrieval of birdcalls from a database of audio recordings, similar to a user supplied query call. Such a retrieval task can sometimes be more useful than an automated classifier. We compare three approaches to similarity-based birdcall retrieval using spectral ridge features and two kinds of gradient features, structure tensor and the histogram of oriented gradients. The retrieval accuracy of our spectral ridge method is 94% compared to 82% for the structure tensor method and 90% for the histogram of gradients method. Additionally, this approach potentially offers a more compact representation and is more computationally efficient.

Numerical investigations of linear least squares methods for derivative estimation

The results of a numerical investigation into the errors for least squares estimates of function gradients are presented. The underlying algorithm is obtained by constructing a least squares problem using a truncated Taylor expansion. An error bound associated with this method contains in its numerator terms related to the Taylor series remainder, while its denominator contains the smallest singular value of the least squares matrix. Perhaps for this reason the error bounds are often found to be pessimistic by several orders of magnitude. The circumstance under which these poor estimates arise is elucidated and an empirical correction of the theoretical error bounds is conjectured and investigated numerically. This is followed by an indication of how the conjecture is supported by a rigorous argument.

Cell image classification using histograms, higher order statistics and adaboost

A cell classification algorithm that uses first, second and third order statistics of pixel intensity distributions over pre-defined regions is implemented and evaluated. A cell image is segmented into 6 regions extending from a boundary layer to an inner circle. First, second and third order statistical features are extracted from histograms of pixel intensities in these regions. Third order statistical features used are one-dimensional bispectral invariants. 108 features were considered as candidates for Adaboost based fusion. The best 10 stage fused classifier was selected for each class and a decision tree constructed for the 6-class problem. The classifier is robust, accurate and fast by design.

Automatic classification of human epithelial type 2 cell indirect immunofluorescence images using cell pyramid matching

This paper describes a novel system for automatic classification of images obtained from Anti-Nuclear Antibody (ANA) pathology tests on Human Epithelial type 2 (HEp-2) cells using the Indirect Immunofluorescence (IIF) protocol. The IIF protocol on HEp-2 cells has been the hallmark method to identify the presence of ANAs, due to its high sensitivity and the large range of antigens that can be detected. However, it suffers from numerous shortcomings, such as being subjective as well as time and labour intensive. Computer Aided Diagnostic (CAD) systems have been developed to address these problems, which automatically classify a HEp-2 cell image into one of its known patterns (eg. speckled, homogeneous). Most of the existing CAD systems use handpicked features to represent a HEp-2 cell image, which may only work in limited scenarios. We propose a novel automatic cell image classification method termed Cell Pyramid Matching (CPM), which is comprised of regional histograms of visual words coupled with the Multiple Kernel Learning framework. We present a study of several variations of generating histograms and show the efficacy of the system on two publicly available datasets: the ICPR HEp-2 cell classification contest dataset and the SNPHEp-2 dataset.

The assessment of ecological condition in south-east Queensland, Australia: An evaluation of reliability across variable environments and surrogate efficacy for biodiversity values

Multimetric ecological condition assessment has become an important biodiversity management tool. This study was the first to examine the reliability of these ecological surrogates across variable environments, and the implications for surrogate efficacy. It was demonstrated that through strategic application and design of the multimetric ecological condition index, the effects of environmental gradients and disturbance regimes can be mitigated, and that ecological condition assessment may serve as a scientifically rigorous approach for conservation planning.

Adaptive radiotherapy for virally mediated head and neck cancer : predicting which patients may benefit most

Background: Recent clinical studies have demonstrated an emerging subgroup of head and neck cancers that are virally mediated. This disease appears to be a distinct clinical entity with patients presenting younger and with more advanced nodal disease, having lower tobacco and alcohol exposure and highly radiosensitive tumours. This means they are living longer, often with the debilitating functional side effects of treatment. The primary objective of this study was to determine how virally mediated nasopharyngeal and oropharyngeal cancers respond to radiation therapy treatment. The aim was to determine risk categories and corresponding adaptive treatment management strategies to proactively manage these patients. Method/Results: 121 patients with virally mediated, node positive nasopharyngeal or oropharyngeal cancer who received radiotherapy treatment with curative intent between 2005 and 2010 were studied. Relevant patient demographics including age, gender, diagnosis, TNM stage, pre-treatment nodal size and dose delivered was recorded. Each patient’s treatment plan was reviewed to determine if another computed tomography (re-CT) scan was performed and at what time point (dose/fraction) this occurred. The justification for this re-CT was determined using four categories: tumour and/or nodal regression, weight loss, both or other. Patients who underwent a re-CT were further investigated to determine whether a new plan was calculated. If a re-plan was performed, the dosimetric effect was quantified by comparing dose volume histograms of planning target volumes and critical structures from the actual treatment delivered and the original treatment plan. Preliminary results demonstrated that 25/121 (20.7%) patients required a re-CT and that these re-CTs were performed between fractions 20 to 25 of treatment. The justification for these re-CTs consisted of a combination of tumour and/or nodal regression and weight loss. 16/25 (13.2%) patients had a replan calculated. 9 (7.4%) of these replans were implemented clinically due to the resultant dosimetric effect calculated. The data collected from this assessment was statistically analysed to identify the major determining factors for patients to undergo a re-CT and/or replan. Specific factors identified included nodal size and timing of the required intervention (i.e. how when a plan is to be adapted). This data was used to generate specific risk profiles that will form the basis of a biologically guided adaptive treatment management strategy for virally mediated head and neck cancer. Conclusion: Preliminary data indicates that virally mediated head and neck cancers respond significantly during radiation treatment (tumour and/or nodal regression and weight loss). Implications of this response are the potential underdosing or overdosing of tumour and/or surrounding critical structures. This could lead to sub-optimal patient outcomes and compromised quality of life. Consequently, the development of adaptive treatment strategies that improve organ sparing for this patient group is important to ensure delivery of the prescribed dose to the tumour volume whilst minimizing the dose received to surrounding critical structures. This could reduce side effects and improve overall patient quality of life. The risk profiles and associated adaptive treatment approaches developed in this study will be tested prospectively in the clinical setting in Phase 2 of this investigation.

Block models for improved earthwork allocation planning in linear infrastructure construction

Earthwork planning has been considered in this article and a generic block partitioning and modelling approach has been devised to provide strategic plans of various levels of detail. Conceptually this approach is more accurate and comprehensive than others, for instance those that are section based. In response to environmental concerns the metric for decision making was fuel consumption and emissions. Haulage distance and gradient are also included as they are important components of these metrics. Advantageously the fuel consumption metric is generic and captures the physical difficulties of travelling over inclines of different gradients, that is consistent across all hauling vehicles. For validation, the proposed models and techniques have been applied to a real world road project. The numerical investigations have demonstrated that the models can be solved with relatively little CPU time. The proposed block models also result in solutions of superior quality, i.e. they have reduced fuel consumption and cost. Furthermore the plans differ considerably from those based solely upon a distance based metric thus demonstrating a need for industry to reflect upon their current practices.

Compact features for birdcall retrieval from environmental acoustic recordings

Bioacoustic data can be used for monitoring animal species diversity. The deployment of acoustic sensors enables acoustic monitoring at large temporal and spatial scales. We describe a content-based birdcall retrieval algorithm for the exploration of large data bases of acoustic recordings. In the algorithm, an event-based searching scheme and compact features are developed. In detail, ridge events are detected from audio files using event detection on spectral ridges. Then event alignment is used to search through audio files to locate candidate instances. A similarity measure is then applied to dimension-reduced spectral ridge feature vectors. The event-based searching method processes a smaller list of instances for faster retrieval. The experimental results demonstrate that our features achieve better success rate than existing methods and the feature dimension is greatly reduced.

Investigation into Travel of Transit Oriented Development Residents’ of Kelvin Grove Urban Village

Travel surveys were conducted for collecting data related to residents’ travel at Kelvin Grove Urban Village (KGUV). Currently, KGUV has residents living in the affordable apartments, apartments, townhouses and student accommodation. As a part of data collection process, travel surveys were undertaken for residents living in apartments, affordable apartments and student accommodation. This document contains the questionnaire form used to collect the demographic and travel data related to residents at KGUV. A mail back survey technique was used to collect data for residents living in affordable apartment and apartments, and an intercept surveys was conducted for residents living in student accommodation.