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.

Scale adaptive tracking using mean shift and efficient feature matching

The mean shift tracker has achieved great success in visual object tracking due to its efficiency being nonparametric. However, it is still difficult for the tracker to handle scale changes of the object. In this paper, we associate a scale adaptive approach with the mean shift tracker. Firstly, the target in the current frame is located by the mean shift tracker. Then, a feature point matching procedure is employed to get the matched pairs of the feature point between target regions in the current frame and the previous frame. We employ FAST-9 corner detector and HOG descriptor for the feature matching. Finally, with the acquired matched pairs of the feature point, the affine transformation between target regions in the two frames is solved to obtain the current scale of the target. Experimental results show that the proposed tracker gives satisfying results when the scale of the target changes, with a good performance of efficiency.

Parts based representation for pedestrian using NMF with robustness to partial occlusion

Computer Vision has seen a resurgence in the parts-based representation for objects over the past few years. The parts are usually annotated beforehand for training. We present an annotation free parts-based representation for the pedestrian using Non-Negative Matrix Factorization (NMF). We show that NMF is able to capture the wide range of pose and clothing of the pedestrians. We use a modified form of NMF i.e. NMF with sparsity constraints on the factored matrices. We also make use of Riemannian distance metric for similarity measurements in NMF space as the basis vectors generated by NMF aren't orthogonal. We show that for 1% drop in accuracy as compared to the Histogram of Oriented Gradients (HOG) representation we can achieve robustness to partial occlusion.

Enzymatic synthesis of flavors in supercritical carbon dioxide

Commercially important flavor esters of isoamyl alcohol, catalyzed by crude hog pancreas lipase (HPL), were synthesized under solvent-free conditions and in supercritical carbon dioxide. The esters synthesized were isoamyl acetate, isoamyl propionate, isoamyl butyrate, and isoamyl octanoate. Very low yields (3-4%) of isoamyl acetate were obtained, but high yields for the other three esters were obtained under both supercritical and solvent-free conditions. The yields of esters of the even-carbon acids, isoamyl acetate, butyrate, and octanoate, increased with increasing chain length, whereas the yield of isoamyl propionate was higher than that of isoamyl butyrate. The optimum temperature of the reaction was higher under supercritical conditions (45 degreesC) than under solvent-free conditions (35-40 degreesC). The effects of other parameters such as alcohol concentration, water concentration, and enzyme loading were investigated. An increase in the water concentration decreased the conversion significantly in supercritical carbon dioxide but not under solvent-free conditions. The optimum ratio of alcohol to acid was dependent on the extent of inhibition by the acid. Although providing a higher apparent yield by being run in a highly concentrated medium, the overall conversion under solvent-free conditions was lower than that under supercritical conditions for similar enzyme concentrations, indicating that the synthesis of esters in supercritical carbon dioxide might be a viable option.

Detection of Construction Workers in Video Frames for Automatic Initialization of Vision Trackers

Vision based tracking can provide the spatial location of construction entities such as equipment, workers, and materials in large scale, congested construction sites. It tracks entities in video streams by inferring their locations based on the entities’ visual features and motion histories. To initiate the process, it is necessary to determine the pixel areas corresponding to the construction entities to be tracked in the following consecutive video frames. In order to fully automate the process, an automated way of initialization is needed. This paper presents the method for construction worker detection which can automatically recognize and localize construction workers in video frames. The method first finds the foreground areas of moving objects using a background subtraction method. Within these foreground areas, construction workers are recognized based on the histogram of oriented gradients (HOG) and histogram of the HSV colors. HOG’s have proved to work effectively for detection of people, and the histogram of HSV colors helps differentiate between pedestrians and construction workers wearing safety vests. Preliminary experiments show that the proposed method has the potential to automate the initialization process of vision based tracking.

Construction Worker Detection in Video Frames for Initializing Vision Trackers

Monitoring the location of resources on large scale, congested, outdoor sites can be performed more efficiently with vision tracking, as this approach does not require any pre-tagging of resources. However, the greatest impediment to the use of vision tracking in this case is the lack of detection methods that are needed to automatically mark the resources of interest and initiate the tracking. This paper presents such a novel method for construction worker detection that localizes construction workers in video frames. The proposed method exploits motion, shape, and color cues to narrow down the detection regions to moving objects, people, and finally construction workers, respectively. The three cues are characterized by using background subtraction, the histogram of oriented gradients (HOG), and the HSV color histogram. The method has been tested on videos taken in various environments. The results demonstrate its suitability for automatic initialization of vision trackers.

An alignment based similarity measure for hand detection in cluttered sign language video

Locating hands in sign language video is challenging due to a number of factors. Hand appearance varies widely across signers due to anthropometric variations and varying levels of signer proficiency. Video can be captured under varying illumination, camera resolutions, and levels of scene clutter, e.g., high-res video captured in a studio vs. low-res video gathered by a web cam in a user’s home. Moreover, the signers’ clothing varies, e.g., skin-toned clothing vs. contrasting clothing, short-sleeved vs. long-sleeved shirts, etc. In this work, the hand detection problem is addressed in an appearance matching framework. The Histogram of Oriented Gradient (HOG) based matching score function is reformulated to allow non-rigid alignment between pairs of images to account for hand shape variation. The resulting alignment score is used within a Support Vector Machine hand/not-hand classifier for hand detection. The new matching score function yields improved performance (in ROC area and hand detection rate) over the Vocabulary Guided Pyramid Match Kernel (VGPMK) and the traditional, rigid HOG distance on American Sign Language video gestured by expert signers. The proposed match score function is computationally less expensive (for training and testing), has fewer parameters and is less sensitive to parameter settings than VGPMK. The proposed detector works well on test sequences from an inexpert signer in a non-studio setting with cluttered background.

Phosphoramidates of 2'-beta-D-arabinouridine (AraU) as phosphate prodrugs; design, synthesis, in vitro activity and metabolism

2'-Beta-D-arabinouridine (AraU), the uridine analogue of the anticancer agent AraC, was synthesized and evaluated for antiviral activity and cytotoxicity. In addition, a series of AraU monophosphate prodrugs in the form of triester phosphoramidates (ProTides) were also synthesized and tested against a range of viruses, leukaemia and solid tumour cell lines. Unfortunately, neither the parent compound (AraU) nor any of its ProTides showed antiviral activity, nor potent inhibitory activity against any of the cancer cell lines. Therefore, the metabolism of AraU phosphoramidates to release AraU monophosphate was investigated. The results showed carboxypeptidase Y, hog liver esterase and crude CEM tumor cell extracts to hydrolyse the ester motif of phosphoramidates with subsequent loss of the aryl group, while molecular modelling studies suggested that the AraU l-alanine aminoacyl phosphate derivative might not be a good substrate for the phosphoramidase enzyme Hint-1. These findings are in agreement with the observed disappearance of intact prodrug and concomitant appearance of the corresponding phosphoramidate intermediate derivative in CEM cell extracts without measurable formation of araU monophosphate. These findings may explain the poor antiviral/cytostatic potential of the prodrugs.

Effects of modified LDL and HDL on retinal pigment epithelial cells: a role in diabetic retinopathy?

Aims/hypothesis: Blood–retina barrier leakage in diabetes results in extravasation of plasma lipoproteins. Intra-retinal modified LDLs have been implicated in diabetic retinopathy (DR), but their effects on retinal pigment epithelial (RPE) cells and the added effects of extravasated modified HDLs are unknown.

Methods: In human retinas from individuals with and without diabetes and DR, immunohistochemistry was used to detect ApoB, ApoA1 and endoplasmic reticulum (ER) stress markers. In cell culture, human RPE cells were treated with native LDL (N-LDL) or heavily-oxidised glycated LDL (HOG-LDL) with or without pretreatment with native HDL (N-HDL) or heavilyoxidised glycated HDL (HOG-HDL). Cell viability, oxidative stress, ER stress, apoptosis and autophagy were assessed by Cell Counting Kit-8 assay, dichlorofluorescein assay, western blotting, immunofluorescence and TUNEL assay. In separate
experiments, RPE cells were treated with lipid oxidation products, 7-ketocholesterol (7-KC, 5–40 µmol/l) or 4-hydroxynonenal (4-HNE, 5–80 µmol/l), with or without pretreatment with N-HDL or HOG-HDL.

Results: ApoB, ApoA1 staining and RPE ER stress were increased in the presence of DR. HOG-LDL but not N-LDL significantly decreased RPE cell viability and increased reactive oxygen species generation, ER stress, apoptosis and autophagy. Similarly, 4-HNE and 7-KC decreased viability and induced ER stress. Pretreatment with N-HDL mitigated these effects, whereas HOG-HDL was less effective by most, but not all, measures.

Conclusions/interpretation: In DR, extravascular modified LDL may promote RPE injury through oxidative stress, ER stress, autophagy and apoptosis. N-HDL has protective effects, but HOG-HDL is less effective. Extravasation and modification of HDL may modulate the injurious effects of extravasated modified LDL on the retinal pigment epithelium.

Mechanisms of modified LDL-induced pericyte loss and retinal injury in diabetic retinopathy

Aims/hypothesis: In previous studies we have shown that extravasated, modified LDL is associated with pericyte loss, an early feature of diabetic retinopathy (DR). Here we sought to determine detailed mechanisms of this LDLinduced pericyte loss.

Methods: Human retinal capillary pericytes (HRCP) were exposed to ‘highly-oxidised glycated’ LDL (HOG-LDL) (a model of extravasated and modified LDL) and to 4-hydroxynonenal or 7-ketocholesterol (components of oxidised LDL), or to native LDL for 1 to 24 h with or without 1 h of pretreatment with inhibitors of the following: (1) the scavenger receptor (polyinosinic acid); (2) oxidative stress (N-acetyl cysteine); (3) endoplasmic reticulum (ER) stress (4-phenyl butyric acid); and (4) mitochondrial dysfunction (cyclosporin A). Oxidative stress, ER stress, mitochondrial dysfunction, apoptosis and autophagy were assessed using techniques including western blotting, immunofluorescence, RT-PCR, flow cytometry and TUNEL assay. To assess the relevance of the results in vivo, immunohistochemistry was used to detect the ER stress chaperon, 78 kDa glucose-regulated protein, and the ER sensor, activating transcription factor 6, in retinas from a mouse model of DR that mimics exposure of the retina to elevated glucose and elevated LDL levels, and in retinas from human participants with and without diabetes and DR.

Results: Compared with native LDL, HOG-LDL activated oxidative and ER stress in HRCP, resulting in mitochondrial dysfunction, apoptosis and autophagy. In a mouse model of diabetes and hyperlipidaemia (vs mouse models of either condition alone), retinal ER stress was enhanced. ER stress was also enhanced in diabetic human retina and correlated with the severity of DR.

Conclusions/interpretation: Cell culture, animal, and human data suggest that oxidative stress and ER stress are induced by modified LDL, and are implicated in pericyte loss in DR.

'Latinising' Milton: Paradise Lost, Latinitas and the Long Eighteenth Century

This chapter traces the trajectory of Latin translations of Milton’s vernacular verse most capably encapsulated by Latin verse paraphrases of Paradise Lost by a certain J.C. (1686), William Hog (1690), Thomas Power (1691) and by such eighteenth-century renderings as that of William Dobson (1753). Situating its analysis in relation to early modern pedagogical practices, including the double translation system, and informed by current translational theory, the analysis considers the multifunctional aims and consequences of Latinising Milton: the elaboration and elucidation of a vernacular original via Latin exegesis and paraphrase; recourse to Latin as a means of facilitating a wider European readership. Integral to the discussion is an alertness to the contemporary and later reception of Milton’s work, and an assessment of ways in which Latinitas enabled the invocation of classical intertexts which in themselves offer a nuanced reading of Miltonic verse.

Tyrosine nitration of prostacyclin synthase is associated with enhanced retinal cell apoptosis in diabetes

The risk of diabetic retinopathy is associated with the presence of both oxidative stress and toxic eicosanoids. Whether oxidative stress actually causes diabetic retinopathy via the generation of toxic eicosanoids, however, remains unknown. The aim of the present study was to determine whether tyrosine nitration of prostacyclin synthase (PGIS) contributes to retinal cell death in vitro and in vivo. Exposure of human retinal pericytes to heavily oxidized and glycated LDL (HOG-LDL), but not native forms of LDL (N-LDL), for 24 hours significantly increased pericyte apoptosis, accompanied by increased tyrosine nitration of PGIS and decreased PGIS activity. Inhibition of the thromboxane receptor or cyclooxygenase-2 dramatically attenuated HOG-LDL-induced apoptosis without restoring PGIS activity. Administration of superoxide dismutase (to scavenge superoxide anions) or L-N(G)-nitroarginine methyl ester (L-NAME, a nonselective nitric oxide synthase inhibitor) restored PGIS activity and attenuated pericyte apoptosis. In Akita mouse retinas, diabetes increased intraretinal levels of oxidized LDL and glycated LDL, induced PGIS nitration, enhanced apoptotic cell death, and impaired blood-retinal barrier function. Chronic administration of tempol, a superoxide scavenger, reduced intraretinal oxidized LDL and glycated LDL levels, PGIS nitration, and retina cell apoptosis, thereby preserving the integrity of blood-retinal barriers. In conclusion, oxidized LDL-mediated PGIS nitration and associated thromboxane receptor stimulation might be important in the initiation and progression of diabetic retinopathy.

Activation of AMP-activated protein kinase inhibits oxidized LDL-triggered endoplasmic reticulum stress in vivo

The oxidation of LDLs is considered a key step in the development of atherosclerosis. How LDL oxidation contributes to atherosclerosis remains poorly defined. Here we report that oxidized and glycated LDL (HOG-LDL) causes aberrant endoplasmic reticulum (ER) stress and that the AMP-activated protein kinase (AMPK) suppressed HOG-LDL-triggered ER stress in vivo.

Apoptosis induction by oxidized glycated LDL in human retinal capillary pericytes is independent of activation of MAPK signaling pathways

Pericyte loss is a cardinal feature of early diabetic retinopathy. We previously reported that highly oxidized-glycated low density lipoprotein (HOG-LDL) induces pericyte apoptosis in vitro. In this study, we investigated the role of the mitogen-activated protein kinase (MAPK) signaling pathways in HOG-LDL-induced apoptosis in human pericytes.

Pigment epithelium-derived factor mitigates inflammation and oxidative stress in retinal pericytes exposed to oxidized low-density lipoprotein

Oxidized and/or glycated low-density lipoprotein (LDL) may mediate capillary injury in diabetic retinopathy. The mechanisms may involve pro-inflammatory and pro-oxidant effects on retinal capillary pericytes. In this study, these effects, and the protective effects of pigment epithelium-derived factor (PEDF), were defined in a primary human pericyte model. Human retinal pericytes were exposed to 100 microg/ml native LDL (N-LDL) or heavily oxidized glycated LDL (HOG-LDL) with or without PEDF at 10-160 nM for 24 h. To assess pro-inflammatory effects, monocyte chemoattractant protein-1 (MCP-1) secretion was measured by ELISA, and nuclear factor-kappaB (NF-kappaB) activation was detected by immunocytochemistry. Oxidative stress was determined by measuring intracellular reactive oxygen species (ROS), peroxynitrite (ONOO(-)) formation, inducible nitric oxide synthase (iNOS) expression, and nitric oxide (NO) production. The results showed that MCP-1 was significantly increased by HOG-LDL, and the effect was attenuated by PEDF in a dose-dependent manner. PEDF also attenuated the HOG-LDL-induced NF-kappaB activation, suggesting that the inhibitory effect of PEDF on MCP-1 was at least partially through the blockade of NF-kappaB activation. Further studies demonstrated that HOG-LDL, but not N-LDL, significantly increased ONOO(-) formation, NO production, and iNOS expression. These changes were also alleviated by PEDF. Moreover, PEDF significantly ameliorated HOG-LDL-induced ROS generation through up-regulation of superoxide dismutase 1 expression. Taken together, these results demonstrate pro-inflammatory and pro-oxidant effects of HOG-LDL on retinal pericytes, which were effectively ameliorated by PEDF. Suppressing MCP-1 production and thus inhibiting macrophage recruitment may represent a new mechanism for the salutary effect of PEDF in diabetic retinopathy and warrants more studies in future.