Super-resolved faces for improved face recognition from surveillance video advances in biometrics

Characteristics of surveillance video generally include low resolution and poor quality due to environmental, storage and processing limitations. It is extremely difficult for computers and human operators to identify individuals from these videos. To overcome this problem, super-resolution can be used in conjunction with an automated face recognition system to enhance the spatial resolution of video frames containing the subject and narrow down the number of manual verifications performed by the human operator by presenting a list of most likely candidates from the database. As the super-resolution reconstruction process is ill-posed, visual artifacts are often generated as a result. These artifacts can be visually distracting to humans and/or affect machine recognition algorithms. While it is intuitive that higher resolution should lead to improved recognition accuracy, the effects of super-resolution and such artifacts on face recognition performance have not been systematically studied. This paper aims to address this gap while illustrating that super-resolution allows more accurate identification of individuals from low-resolution surveillance footage. The proposed optical flow-based super-resolution method is benchmarked against Baker et al.’s hallucination and Schultz et al.’s super-resolution techniques on images from the Terrascope and XM2VTS databases. Ground truth and interpolated images were also tested to provide a baseline for comparison. Results show that a suitable super-resolution system can improve the discriminability of surveillance video and enhance face recognition accuracy. The experiments also show that Schultz et al.’s method fails when dealing surveillance footage due to its assumption of rigid objects in the scene. The hallucination and optical flow-based methods performed comparably, with the optical flow-based method producing less visually distracting artifacts that interfered with human recognition.

Make-buy decisions in the face of technological change: does industry clockspeed matter?

Some evidence in the area of make-buy decisions for new technologies suggests that it is a good idea for a company to pursue a fairly rigorous ''make'' policy in the early days of a potentially disruptive innovation. Other studies prescribe exactly the opposite, promoting instead a ''buy'' strategy. This paper seeks to bridge the gap between these perspectives by suggesting that both strategies are valid, but that they are most successfully applied in different market environments. The ''make'' prescription may be more suited to either extremely fast or extremely slow rates of technological change, while a ''buy'' strategy might be more appropriate in market sectors where technologies evolve at a medium pace. This paper highlights the importance of industry clockspeed and supplier relationships in make-buy decisions for new technologies, and puts forward two new hypotheses that require empirical testing.

A multi-resolution image alignment technique based on direct methods for pose estimation of aerial vehicles

In this paper, we seek to expand the use of direct methods in real-time applications by proposing a vision-based strategy for pose estimation of aerial vehicles. The vast majority of approaches make use of features to estimate motion. Conversely, the strategy we propose is based on a MR (Multi- Resolution) implementation of an image registration technique (Inverse Compositional Image Alignment ICIA) using direct methods. An on-board camera in a downwards-looking configuration, and the assumption of planar scenes, are the bases of the algorithm. The motion between frames (rotation and translation) is recovered by decomposing the frame-to-frame homography obtained by the ICIA algorithm applied to a patch that covers around the 80% of the image. When the visual estimation is required (e.g. GPS drop-out), this motion is integrated with the previous known estimation of the vehicles’ state, obtained from the on-board sensors (GPS/IMU), and the subsequent estimations are based only on the vision-based motion estimations. The proposed strategy is tested with real flight data in representative stages of a flight: cruise, landing, and take-off, being two of those stages considered critical: take-off and landing. The performance of the pose estimation strategy is analyzed by comparing it with the GPS/IMU estimations. Results show correlation between the visual estimation obtained with the MR-ICIA and the GPS/IMU data, that demonstrate that the visual estimation can be used to provide a good approximation of the vehicle’s state when it is required (e.g. GPS drop-outs). In terms of performance, the proposed strategy is able to maintain an estimation of the vehicle’s state for more than one minute, at real-time frame rates based, only on visual information.

Sub-tropical high-density, low rise residential buildings: case study 3

The case study 3 team viewed the mitigation of noise and air pollution generated in the transport corridor that borders the study site to be a paramount driver of the urban design solution. These key urban planning strategies were adopted: * Spatial separation from transport corridor pollution source. A linear green zone and environmental buffer was proposed adjacent to the transport corridor to mitigate the environmental noise and air quality impacts of the corridor, and to offer residents opportunities for recreation * Open space forming the key structural principle for neighbourhood design. A significant open space system underpins the planning and manages surface water flows. * Urban blocks running on east-west axis. The open space rationale emphasises an east-west pattern for local streets. Street alignment allows for predominantly north-south facing terrace type buildings which both face the street and overlook the green courtyard formed by the perimeter buildings. The results of the ESD assessment of the typologies conclude that the design will achieve good outcomes through: * Lower than average construction costs compared with other similar projects * Thermal comfort; A good balance between daylight access and solar gains is achieved * The energy rating achieved for the units is 8.5 stars.

Face recognition across pose on video using eigen light-fields

We propose an approach to employ eigen light-fields for face recognition across pose on video. Faces of a subject are collected from video frames and combined based on the pose to obtain a set of probe light-fields. These probe data are then projected to the principal subspace of the eigen light-fields within which the classification takes place. We modify the original light-field projection and found that it is more robust in the proposed system. Evaluation on VidTIMIT dataset has demonstrated that the eigen light-fields method is able to take advantage of multiple observations contained in the video.

Feature-domain super-resolution framework for gabor-based face and iris recognition

The low resolution of images has been one of the major limitations in recognising humans from a distance using their biometric traits, such as face and iris. Superresolution has been employed to improve the resolution and the recognition performance simultaneously, however the majority of techniques employed operate in the pixel domain, such that the biometric feature vectors are extracted from a super-resolved input image. Feature-domain superresolution has been proposed for face and iris, and is shown to further improve recognition performance by capitalising on direct super-resolving the features which are used for recognition. However, current feature-domain superresolution approaches are limited to simple linear features such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), which are not the most discriminant features for biometrics. Gabor-based features have been shown to be one of the most discriminant features for biometrics including face and iris. This paper proposes a framework to conduct super-resolution in the non-linear Gabor feature domain to further improve the recognition performance of biometric systems. Experiments have confirmed the validity of the proposed approach, demonstrating superior performance to existing linear approaches for both face and iris biometrics.

Energy use, indoor temperature and possible adaptation strategies for air-conditioned office buildings in face of global warming

This paper discusses and summarises a recent systematic study on the implication of global warming on air conditioned office buildings in Australia. Four areas are covered, including analysis of historical weather data, generation of future weather data for the impact study of global warming, projection of building performance under various global warming scenarios, and evaluation of various adaptation strategies under 2070 high global warming conditions. Overall, it is found that depending on the assumed future climate scenarios and the location considered, the increase of total building energy use for the sample Australian office building may range from 0.4 to 15.1%. When the increase of annual average outdoor temperature exceeds 2 °C, the risk of overheating will increase significantly. However, the potential overheating problem could be completely eliminated if internal load density is significantly reduced.

Probabilistic matching of image sets for video-based face recognition

We address the problem of face recognition on video by employing the recently proposed probabilistic linear discrimi-nant analysis (PLDA). The PLDA has been shown to be robust against pose and expression in image-based face recognition. In this research, the method is extended and applied to video where image set to image set matching is performed. We investigate two approaches of computing similarities between image sets using the PLDA: the closest pair approach and the holistic sets approach. To better model face appearances in video, we also propose the heteroscedastic version of the PLDA which learns the within-class covariance of each individual separately. Our experi-ments on the VidTIMIT and Honda datasets show that the combination of the heteroscedastic PLDA and the closest pair approach achieves the best performance.

On the application of the probabilistic linear discriminant analysis to face recognition across expression

Facial expression is one of the main issues of face recognition in uncontrolled environments. In this paper, we apply the probabilistic linear discriminant analysis (PLDA) method to recognize faces across expressions. Several PLDA approaches are tested and cross-evaluated on the Cohn-Kanade and JAFFE databases. With less samples per gallery subject, high recognition rates comparable to previous works have been achieved indicating the robustness of the approaches. Among the approaches, the mixture of PLDAs has demonstrated better performances. The experimental results also indicate that facial regions around the cheeks, eyes, and eyebrows are more discriminative than regions around the mouth, jaw, chin, and nose.

Why the long face?

In this video, a male voice recites a script comprised entirely of jokes. Words flash on screen in time with the spoken words. Sometimes the two sets of words match, and sometimes they differ. This work examines processes of signification. It emphasizes disruption and disconnection as fundamental and generative operations in making meaning. Extending on post-structural and deconstructionist ideas, this work questions the relationship between written and spoken words. By deliberately confusing the signifying structures of jokes and narratives, it questions the sites and mechanisms of comprehension, humour and signification.

Evaluation of image resolution and super-resolution on face recognition performance

While researchers strive to improve automatic face recognition performance, the relationship between image resolution and face recognition performance has not received much attention. This relationship is examined systematically and a framework is developed such that results from super-resolution techniques can be compared. Three super-resolution techniques are compared with the Eigenface and Elastic Bunch Graph Matching face recognition engines. Parameter ranges over which these techniques provide better recognition performance than interpolated images is determined.

Life in the internet economy and the changing face of property use

Increased participation in the internet economy is actively encouraged and supported by all levels of government. Research to date clearly shows the positive impacts that increased internet access can bring, particularly for rural Australia. Meanwhile, for the most part, identification of any negative impacts of increased broadband access on existing and potential property uses is avoided. The aim of this article is to identify issues for property use arising as a consequence of increased engagement in the internet economy. The article commences by clarifying what is meant by the term ‘internet economy’ before highlighting current impacts of the internet. It concludes by suggesting potential impacts for property and property uses in the future.

Isotactics as a foundation for alignment and abstraction of behavioral models

There are many use cases in business process management that require the comparison of behavioral models. For instance, verifying equivalence is the basis for assessing whether a technical workflow correctly implements a business process, or whether a process realization conforms to a reference process. This paper proposes an equivalence relation for models that describe behaviors based on the concurrency semantics of net theory and for which an alignment relation has been defined. This equivalence, called isotactics, preserves the level of concurrency of aligned operations. Furthermore, we elaborate on the conditions under which an alignment relation can be classified as an abstraction. Finally, we show that alignment relations induced by structural refinements of behavioral models are indeed behavioral abstractions.

Engaging undergraduate nursing students in face-to-face tutorials

Chronic nursing shortages have placed increasing pressure on many nursing schools to recruit greater numbers of students with the consequence of larger class sizes. Larger class sizes have the potential to lead to student disengagement. This paper describes a case study that examined the strategies used by a group of nursing lecturers to engage students and to overcome passivity in a Bachelor of Nursing programme. A non-participant observer attended 20 tutorials to observe five academics deliver four tutorials each. Academics were interviewed both individually and as a group following the completion of all tutorial observations. All observations, field notes, interviews and focus groups were coded separately and major themes identified. From this analysis two broad categories emerged: getting students involved; and engagement as a struggle. Academics used a wide variety of techniques to interest and involve students. Additionally, academics desired an equal relationship with students. They believed that both they and the students had some power to influence the dynamics of tutorials and that neither party had ultimate power. The findings of this study serve to re-emphasise past literature which suggests that to engage students, the academics must also engage.