Nonrigid face alignment for unknown subject in video

Non-rigid face alignment is a very important task in a large range of applications but the existing tracking based non-rigid face alignment methods are either inaccurate or requiring person-specific model. This dissertation has developed simultaneous alignment algorithms that overcome these constraints and provide alignment with high accuracy, efficiency, robustness to varying image condition, and requirement of only generic model.

Clinical skin examination outcomes after a video-based behavioral intervention analysis from a randomized clinical trial

Importance Older men are at risk of dying of melanoma. Objective To assess attendance at and clinical outcomes of clinical skin examinations (CSEs) in older men exposed to a video-based behavioral intervention. Design, Setting, and Participants This was a behavioral randomized clinical trial of a video-based intervention in men aged at least 50 years. Between June 1 and August 31, 2008, men were recruited, completed baseline telephone interviews, and were than randomized to receive either a video-based intervention (n = 469) or brochures only (n = 461; overall response rate, 37.1%) and were again interviewed 7 months later (n = 870; 93.5% retention). Interventions Video on skin self-examination and skin awareness and written informational materials. The control group received written materials only. Main Outcomes and Measures Participants who reported a CSE were asked for the type of CSE (skin spot, partial body, or whole body), who initiated it, whether the physician noted any suspicious lesions, and, if so, how lesions were managed. Physicians completed a case report form that included the type of CSE, who initiated it, the number of suspicious lesions detected, how lesions were managed (excision, nonsurgical treatment, monitoring, or referral), and pathology reports after lesion excision or biopsy. Results Overall, 540 of 870 men (62.1%) self-reported a CSE since receiving intervention materials, and 321 of 540 (59.4%) consented for their physician to provide medical information (received for 266 of 321 [82.9%]). Attendance of any CSE was similar between groups (intervention group, 246 of 436 [56.4%]; control group, 229 of 434 [52.8%]), but men in the intervention group were more likely to self-report a whole-body CSE (154 of 436 [35.3%] vs 118 of 434 [27.2%] for control group; P = .01). Two melanomas, 29 squamous cell carcinomas, and 38 basal cell carcinomas were diagnosed, with a higher proportion of malignant lesions in the intervention group (60.0% vs 40.0% for controls; P = .03). Baseline attitudes, behaviors, and skin cancer history were associated with higher odds of CSE and skin cancer diagnosis. Conclusions and Relevance A video-based intervention may increase whole-body CSE and skin cancer diagnosis in older men. Trial Registration: anzctr.org.au Identifier: ACTRN12608000384358

Crowd monitoring using computer vision

Novel computer vision techniques have been developed for automatic monitoring of crowed environments such as airports, railway stations and shopping malls. Using video feeds from multiple cameras, the techniques enable crowd counting, crowd flow monitoring, queue monitoring and abnormal event detection. The outcome of the research is useful for surveillance applications and for obtaining operational metrics to improve business efficiency.

An evaluation of different features and learning models for anomalous event detection

The huge amount of CCTV footage available makes it very burdensome to process these videos manually through human operators. This has made automated processing of video footage through computer vision technologies necessary. During the past several years, there has been a large effort to detect abnormal activities through computer vision techniques. Typically, the problem is formulated as a novelty detection task where the system is trained on normal data and is required to detect events which do not fit the learned ‘normal’ model. There is no precise and exact definition for an abnormal activity; it is dependent on the context of the scene. Hence there is a requirement for different feature sets to detect different kinds of abnormal activities. In this work we evaluate the performance of different state of the art features to detect the presence of the abnormal objects in the scene. These include optical flow vectors to detect motion related anomalies, textures of optical flow and image textures to detect the presence of abnormal objects. These extracted features in different combinations are modeled using different state of the art models such as Gaussian mixture model(GMM) and Semi- 2D Hidden Markov model(HMM) to analyse the performances. Further we apply perspective normalization to the extracted features to compensate for perspective distortion due to the distance between the camera and objects of consideration. The proposed approach is evaluated using the publicly available UCSD datasets and we demonstrate improved performance compared to other state of the art methods.

Quality based frame selection for face clustering in news video

Clustering identities in a broadcast video is a useful task to aid in video annotation and retrieval. Quality based frame selection is a crucial task in video face clustering, to both improve the clustering performance and reduce the computational cost. We present a frame work that selects the highest quality frames available in a video to cluster the face. This frame selection technique is based on low level and high level features (face symmetry, sharpness, contrast and brightness) to select the highest quality facial images available in a face sequence for clustering. We also consider the temporal distribution of the faces to ensure that selected faces are taken at times distributed throughout the sequence. Normalized feature scores are fused and frames with high quality scores are used in a Local Gabor Binary Pattern Histogram Sequence based face clustering system. We present a news video database to evaluate the clustering system performance. Experiments on the newly created news database show that the proposed method selects the best quality face images in the video sequence, resulting in improved clustering performance.

Image segmentation and pose estimation of humans in video

This thesis introduces improved techniques towards automatically estimating the pose of humans from video. It examines a complete workflow to estimating pose, from the segmentation of the raw video stream to extract silhouettes, to using the silhouettes in order to determine the relative orientation of parts of the human body. The proposed segmentation algorithms have improved performance and reduced complexity, while the pose estimation shows superior accuracy during difficult cases of self occlusion.

Patron-driven acquisition of online video

Letting the patron choose ebooks has been a successful experience. Why not apply the same purchase model to other formats? This showcase outlines Queensland University of Technology’s experience with a trial of patron driven acquisition (PDA) for online video. The trial commencing in August 2012 provided access to over 700 online videos licensed from Kanopy across a number of discipline areas. As online video publishing is still in the early stages of development, and as the trial is only in the very early stages, it is too early to draw any firm conclusions about the likely suitability of this model for online video selection and acquisition. However, the trial provides some interesting initial comparisons with ebook PDA and existing online video purchase models and prompts further consideration of PDA as a method for online video selection and licensing.

Possible, inevitable or fait accompli? An analysis of streaming video acquisition, acceptance and use in higher education

This paper explores the potential for online video as a mechanism to transform the ways students learn, as measured by research, user experience and usage following surveys and trials of patron-driven acquisition collaboratively undertaken by Queensland University of Technology, La Trobe University and Kanopy.

Optimal camera planning under versatile user constraints in multi-camera image processing systems

The selection of optimal camera configurations (camera locations, orientations, etc.) for multi-camera networks remains an unsolved problem. Previous approaches largely focus on proposing various objective functions to achieve different tasks. Most of them, however, do not generalize well to large scale networks. To tackle this, we propose a statistical framework of the problem as well as propose a trans-dimensional simulated annealing algorithm to effectively deal with it. We compare our approach with a state-of-the-art method based on binary integer programming (BIP) and show that our approach offers similar performance on small scale problems. However, we also demonstrate the capability of our approach in dealing with large scale problems and show that our approach produces better results than two alternative heuristics designed to deal with the scalability issue of BIP. Last, we show the versatility of our approach using a number of specific scenarios.

‘Teachers flipping out’ beyond the online lecture : maximising the educational potential of video

While video is recognised as an important medium for teaching and learning in the digital age, many video resources are not as effective as they might be, because they do not adequately exploit the strengths of the medium. Presented here are some case studies of video learning resources produced for various courses in a university environment. This ongoing project attempts to identify pedagogic strategies for the use of video; learning situations in which video has the most efficacy; and what production techniques can be employed to make effective video learning resources.

Semi-binary based video features for activity representation

Efficient and effective feature detection and representation is an important consideration when processing videos, and a large number of applications such as motion analysis, 3D scene understanding, tracking etc. depend on this. Amongst several feature description methods, local features are becoming increasingly popular for representing videos because of their simplicity and efficiency. While they achieve state-of-the-art performance with low computational complexity, their performance is still too limited for real world applications. Furthermore, rapid increases in the uptake of mobile devices has increased the demand for algorithms that can run with reduced memory and computational requirements. In this paper we propose a semi binary based feature detectordescriptor based on the BRISK detector, which can detect and represent videos with significantly reduced computational requirements, while achieving comparable performance to the state of the art spatio-temporal feature descriptors. First, the BRISK feature detector is applied on a frame by frame basis to detect interest points, then the detected key points are compared against consecutive frames for significant motion. Key points with significant motion are encoded with the BRISK descriptor in the spatial domain and Motion Boundary Histogram in the temporal domain. This descriptor is not only lightweight but also has lower memory requirements because of the binary nature of the BRISK descriptor, allowing the possibility of applications using hand held devices.We evaluate the combination of detectordescriptor performance in the context of action classification with a standard, popular bag-of-features with SVM framework. Experiments are carried out on two popular datasets with varying complexity and we demonstrate comparable performance with other descriptors with reduced computational complexity.

Acceptability-based QoE models for mobile video

Quality of experience (QoE) measures the overall perceived quality of mobile video delivery from subjective user experience and objective system performance. Current QoE computing models have two main limitations: 1) insufficient consideration of the factors influencing QoE, and; 2) limited studies on QoE models for acceptability prediction. In this paper, a set of novel acceptability-based QoE models, denoted as A-QoE, is proposed based on the results of comprehensive user studies on subjective quality acceptance assessments. The models are able to predict users’ acceptability and pleasantness in various mobile video usage scenarios. Statistical regression analysis has been used to build the models with a group of influencing factors as independent predictors, including encoding parameters and bitrate, video content characteristics, and mobile device display resolution. The performance of the proposed A-QoE models has been compared with three well-known objective Video Quality Assessment metrics: PSNR, SSIM and VQM. The proposed A-QoE models have high prediction accuracy and usage flexibility. Future user-centred mobile video delivery systems can benefit from applying the proposed QoE-based management to optimize video coding and quality delivery decisions.

Real-time mobile 3D temperature mapping

The ability to measure surface temperature and represent it on a metrically accurate 3D model has proven applications in many areas such as medical imaging, building energy auditing, and search and rescue. A system is proposed that enables this task to be performed with a handheld sensor, and for the first time with results able to be visualized and analyzed in real-time. A device comprising a thermal-infrared camera and range sensor is calibrated geometrically and used for data capture. The device is localized using a combination of ICP and video-based pose estimation from the thermal-infrared video footage which is shown to reduce the occurrence of failure modes. Furthermore, the problem of misregistration which can introduce severe distortions in assigned surface temperatures is avoided through the use of a risk-averse neighborhood weighting mechanism. Results demonstrate that the system is more stable and accurate than previous approaches, and can be used to accurately model complex objects and environments for practical tasks.

Orchids : My Intersex Adventure

Orchids: My Intersex Adventure is a multi-award winning autobiographical documentary film. The film follows documentary filmmaker, Phoebe Hart, as she comes clean on her journey of self-discovery to embrace her future and reconcile the past shame and family secrecy surrounding her intersex condition. Despite her mother’s outright refusal to be in the film, Phoebe decides she must push on with her quest to resolve her life story and connect with other intersex people on camera. With the help of her sister Bonnie and support from her partner James, she hits the open road and reflects on her youth. Phoebe’s happy and carefree childhood came to an abrupt end at puberty when she was told she would never menstruate nor have children. But the reasons why were never discussed and the topic was taboo. At the age of 17, Phoebe’s mother felt she was old enough to understand the true nature of her body and the family secret was finally revealed. Phoebe then faced an orchidectomy, invasive surgery to remove her undescended testes, the emotional scars of which are still raw today. Phoebe’s road trip around Australia exposes her to the stories of other intersex people and holds a mirror to her own experience. She learns valuable lessons in resilience and healing but also sees the pervasive impact her condition has on all her relationships. At home, Phoebe and James want to start a family but dealing with infertility and the stress of the adoption process puts pressure on their marriage. Phoebe also starts to understand the difficult decisions her parents faced and is excited but apprehensive when they eventually agree to be interviewed. Will talking openly with her mother give Phoebe the answers she has been looking for? The film was produced and directed by Phoebe Hart and commissioned by the Australian Broadcasting Commission. The film premiered at the Brisbane International Film Festival in 2010 where it was voted the number one film of the festival by audiences. Orchids was broadcast on ABC1 in Australia in 2012, appeared in more than 50 film festivals internationally and has since been broadcast nationally in Switzerland, Sweden, Israel, Spain, France, Russia, Poland, Germany and the USA.

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.