Elmedin Selmanovic

Complete Motion Control of a Serious Game against Obesity in Children

Childhood obesity is a major problem in most developed countries, with significant negative impacts on childrens health. A suggested method for reducing obesity, especially for children, are serious games. These could promote healthy eating and increased physical activity. Ideally, they should also increase energy expenditure during play, and not be a sedentary experience. In the preliminary work described here, we produced a demonstration serious game designed to combat childhood obesity. All user interaction for the game was supplied via movement using re-appropriated Wii input devices to maximize physical activity whilst playing. We describe the problems of implementing such an interface, in particular that of overlearning.

A high-fidelity virtual environment for the study of paranoia

Psychotic disorders carry social and economic costs for sufferers and society. Recent evidence highlights the risk posed by urban upbringing and social deprivation in the genesis of paranoia and psychosis. Evidence based psychological interventions are often not offered because of a lack of therapists. Virtual reality (VR) environments have been used to treat mental health problems. VR may be a way of understanding the aetiological processes in psychosis and increasing psychotherapeutic resources for its treatment. We developed a high-fidelity virtual reality scenario of an urban street scene to test the hypothesis that virtual urban exposure is able to generate paranoia to a comparable or greater extent than scenarios using indoor scenes. Participants (n = 32) entered the VR scenario for four minutes, after which time their degree of paranoid ideation was assessed. We demonstrated that the virtual reality scenario was able to elicit paranoia in a nonclinical, healthy group and that an urban scene was more likely to lead to higher levels of paranoia than a virtual indoor environment. We suggest that this study offers evidence to support the role of exposure to factors in the urban environment in the genesis and maintenance of psychotic experiences and symptoms. The realistic high-fidelity street scene scenario may offer a useful tool for therapists.

Optimal exposure compression for high dynamic range content

High dynamic range (HDR) imaging has become one of the foremost imaging methods capable of capturing and displaying the full range of lighting perceived by the human visual system in the real world. A number of HDR compression methods for both images and video have been developed to handle HDR data, but none of them has yet been adopted as the method of choice. In particular, the backwards-compatible methods that always maintain a stream/image that allow part of the content to be viewed on conventional displays make use of tone mapping operators which were developed to view HDR images on traditional displays. There are a large number of tone mappers, none of which is considered the best as the images produced could be deemed subjective. This work presents an alternative to tone mapping-based HDR content compression by identifying a single exposure that can reproduce the most information from the original HDR image. This single exposure can be adapted to fit within the bit depth of any traditional encoder. Any additional information that may be lost is stored as a residual. Results demonstrate quality is maintained as well, and better, than other traditional methods. Furthermore, the presented method is backwards-compatible, straightforward to implement, fast and does not require choosing tone mappers or settings.

Enabling stereoscopic high dynamic range video

Stereoscopic and high dynamic range (HDR) imaging are two methods that enhance video content by respectively improving depth perception and light representation. A large body of research has looked into each of these technologies independently, but very little work has attempted to combine them due to limitations in capture and display; HDR video capture (for a wide range of exposure values over 20 f-stops) is not yet commercially available and few prototype HDR video cameras exist. In this work we propose techniques which facilitate stereoscopic high dynamic range (SHDR) video capture by using an HDR and LDR camera pair. Three methods are proposed: one based on generating the missing HDR frame by warping the existing one using a disparity map; increasing the range of LDR video using a novel expansion operator; and a hybrid of the two where expansion is used for pixels within the LDR range and warping for the rest. Generated videos were compared to the ground truth SHDR video captured using two HDR video cameras. Results show little overall error and demonstrate that the hybrid method produces the least error of the presented methods.

Generating stereoscopic HDR images using HDR-LDR image pairs

A number of novel imaging technologies have been gaining popularity over the past few years. Foremost among these are stereoscopy and high dynamic range (HDR) Imaging. While a large body of research has looked into each of these imaging technologies independently, very little work has attempted to combine them. This is mostly due to the current limitations in capture and display. In this article, we mitigate problems of capturing Stereoscopic HDR (SHDR) that would potentially require two HDR cameras, by capturing an HDR and LDR pair and using it to generate 3D stereoscopic HDR content. We ran a detailed user study to compare four different methods of generating SHDR content. The methods investigated were the following: two based on expanding the luminance of the LDR image, and two utilizing stereo correspondence methods, which were adapted for our purposes. Results demonstrate that one of the stereo correspondence methods may be considered perceptually indistinguishable from the ground truth (image pair captured using two HDR cameras), while the other methods are all significantly distinct from the ground truth.

Backwards Compatible JPEG Stereoscopic High Dynamic Range Imaging

In this paper we introduce Stereoscopic High Dynamic Range (SHDR) Imagery which is a novel tecnique that combines high dynamic range imaging and stereoscopy. Stereoscopic imaging captures two images representing the views of both eyes and allows for better depth perception. High dynamic range (HDR) imaging is an emerging technology which allows the capture, storage and display of real world lighting as opposed to traditional imagery which only captures a restricted range of light due to limitation in hardware capture and displays. HDR provides better contrast and more natural looking scenes. One of the main challenges that needs to be overcome for SHDR to be successful is an efficient storage format that compresses the very large sizes obtained by SHDR if left uncompressed; stereoscopic imaging requires the storage of two images and uncompressed HDR requires the storage of a floating point value per colour channel per pixel. In this paper we present a number of SHDR compression methods that are backward compatible with traditional JPEG, stereo JPEG and JPEG-HDR. The proposed methods can encode SHDR content to little more than that of a traditional LDR image and the backward compatibility property encourages early adopters to adopt the format since their content will still be viewable by any of the legacy viewers.

Buffered Count-Min Sketch

In this paper, we present the preliminary work on the adaptation of Count-Min sketch (CMS) data structure to the external storage. CMS is a probabilistic, hashing-based data structure that is used to measure items’ frequencies using very compact space. CMS has broad applications in the streaming context, i.e., in measuring popularity (e.g., top k elements, heavy hitters, quantiles, range queries, etc.) CMS has two error parameters \(\epsilon \) and \(\delta \): on the input size N, it guarantees that the overestimate of the item frequency is within \(\epsilon N\) with probability at least \(1-\delta \). The error parameters are tunable and determine the size of the sketch. To maintain the same band of error, CMS grows linearly with the size of the dataset. Simply placing the CMS on SSD or a hard-drive results in very slow performance due to the random-write nature of UPDATE operations. We suggest two adaptations of the Count-Min sketch to alleviate this effect: Elevator Count-Min Sketch (ECMS) and Buffered Count-Min Sketch (BCMS). The two adaptations use buffering updates in RAM and hash localization, two methods similar to those used in [5] to alleviate similar issues with the Bloom filter. We show that operations on the ECMS and BCMS require asymptotically fewer I/Os than the traditional CMS placed on disk.