Summary form only given. To date, a large amount of research has been conducted using surveillance systems. In fact many conferences, journals, and research programmes are devoted entirely to this subject. However, Sousveillance [3], “watching from below” (or capturing image data from the perspective of a live observer), being a newer area of investigation currently has much less associated work. Since both research topics involve image pro-cessing, many similarities exist. Thus, much of the work which is done in surveillance may be “ported” to souveillance. One such example is that of colour constancy[1]. In particular, a problem that occurs when using multiple cameras for surveillance and associated tracking, is that colours can vary widely across cameras. An object and it's associated data that appears in one view and one system, may present completely difference data in another camera and system. New techniques have been developed to attempt to unify colours between cameras and systems. The same problem exists in the area of sousveillance. For example, an object observed by one cyborg may appear differently to another cyborg. Given that in the situation of souvellance, the camera control as well as the environment are largely in control of the wearcam operator/cyborg[2], colour constancy techniques which are used surveillance can actually be done more accurately in the case of souveillance. This discussion will present one method of mapping an existing method of colour constancy for multiple surveillance cameras to colour constancy for a group of cyborgs.

In this paper, we propose a framework to create a unique signature for a video. The framework aims to enable copy detection for online video sharing. This work improves on our earlier work by incorporating several features. First, we introduce a Singular Value Decomposition (SVD) method to detect shot changes and extract meaningful keyframes. Second, we incorporate a novel two-level bitmap structure for indexing the video signatures. Third, instead of Euclidean distance matching, a Boolean operation is used for video matching. The experimental result shows that the overall system performance improves as compared to previous work. In addition, the system is demonstrated to be effective and robust to several transformations such as color shift, brightness change, the addition of Gaussian noise as well as modified video with inserted text or logo.

In this paper, we propose a framework for detecting near duplicate copies of a video based on an ordinal method. The framework also incorporates a bitmap indexing structure instead of a typical indexing structure used in the previous published work. Using this method, two levels of indices are constructed. The first level of this process groups each input video (represented by their key frames) into k clusters. These clusters and the associated key frames are then used to construct the first level index. The second level of this process converts ordinal-based video signatures (generated using the technique developed in earlier work) into bitmap vectors. By adopting this two-level indexing scheme, query processing times are significantly reduced. This is because, the system is required to match only videos in the clusters that are relevant to the query and not all the videos in the database. Additionally, the technique implemented utilizes a bitmap structure for indexing, resulting in less storage space. Furthermore, we are able to employ low-cost Boolean operations such as AND, OR, and XOR in the matching process instead of Euclidean distance or other similar matching algorithms. This helps to reduce the computational time for video matching. The system has demonstrated to effectively reduce the space needed to store collections of video signatures in a database, as well as improving the overall system performance. In addition, initial results show that the system is effective and robust to several transformations such as changes in brightness, color, contrast, resolution (reduction) as well as the addition of noise.

In this paper, a method for detecting infringements or modifications of a video in real-time is proposed. The method first segments a video stream into shots, after which it extracts some reference frames as keyframes. This process is performed employing a Singular Value Decomposition (SVD) technique developed in this work. Next, for each input video (represented by its keyframes), ordinal-based signature and SIFT (Scale Invariant Feature Transform) descriptors are generated. The ordinal-based method employs a two-level bitmap indexing scheme to construct the index for each video signature. The first level clusters all input keyframes into k clusters while the second level converts the ordinal-based signatures into bitmap vectors. On the other hand, the SIFT-based method directly uses the descriptors as the index. Given a suspect video (being streamed or transferred on the Internet), we generate the signature (ordinal and SIFT descriptors) then we compute similarity between its signature and those signatures in the database based on ordinal signature and SIFT descriptors separately. For similarity measure, besides the Euclidean distance, Boolean operators are also utilized during the matching process. We have tested our system by performing several experiments on 50 videos (each about 1/2 hour in duration) obtained from the TRECVID 2006 data set. For experiments set up, we refer to the conditions provided by TRECVID 2009 on "Content-based copy detection" task. In addition, we also refer to the requirements issued in the call for proposals by MPEG standard on the similar task. Initial result shows that our framework is effective and robust. As compared to our previous work, on top of the achievement we obtained by reducing the storage space and time taken in the ordinal based method, by introducing the SIFT features, we could achieve an overall accuracy in F1 measure of about 96% (improved about 8%).

Abstract We present a system for interacting with 3D objects in a 3D virtual environment. Using the notion that a typical head‐mounted display (HMD) does not cover the user's entire face, we use a fiducial marker placed on the HMD to locate the user's exposed facial skin. Using this information, a skin model is built and combined with the depth information obtained from a stereo camera. The information when used in tandem allows the position of the user's hands to be detected and tracked in real time. Once both hands are located, our system allows the user to manipulate the object with five degrees of freedom (translation inx‐,y‐, andz‐ axis with roll and yaw rotations) in virtual three‐dimensional space using a series of intuitive hand gestures. Copyright © 2009 John Wiley & Sons, Ltd.

In this paper, we present a framework called ldquoWhat-you-seeis- what-I-see (WYSIWIS)rdquo. The framework describes a new trend for multimedia information (such as images and videos) sharing using an Eyetap device and a method to retrieve similar multimedia content. This Eyetap device is equipped with a video camera and networking capability. It can be used to capture an image or recording a video of a place being visited, sending it to the server to get the information about this place (through search mechanism), the captured image/video is then stored into the server for sharing. With this function, mobile users can also share the capturing video in real-time. This is similar to mobile phone equipped with video conference function. However, it is more convenient as users just wear this Eyetap device as normal glasses and performs their daily routine while stay connected.

We demonstrate a method in which gesture control is enabled through use of a stereo camera. Hard to use keyboard commands are effectively emulated using positional gestures. We describe the implementation and some results from user surveys based on user's trying the application at a public exposition. Along with outlining the implementation, we report the initial findings and show evidence as to why such a gesture interface is more effective as an interface as opposed to traditional gaming interfaces.

Global tone mapping operators (TMOs) are better in preserving the naturalness and relative illumination of the HDR scene compared to the local TMOs. However, they cannot preserve the details like the local TMOs. We propose a human visual system (HVS) based histogram method for global tone mapping, which can better preserve the details than the existing global TMOs. Our method can be incorporated to all histogram based global methods. We compare our results with traditional histogram adjustment by Ward et al. [Larson97] and photographic TMO [Reinhard2002], and in most of the cases our method is better in preserving the details of the input HDR images.

One of the long-term goals in human-computer interaction is to utilize more intuitive and natural methods such as speech and hand gestures that a user would employ for communication. In this paper, we present a robust method of hand tracking using a probability map computed from a joint probability function derived from both depth information and skin-tone information. The depth information is provided using a commercially available stereo camera, and the color information is found using calibrated and linearized color information. The work shows the effectiveness of this technique, in terms of both the quality of the results as well as the speed at which the computations may be performed. Due to the linearization of the color information and the use of stereo vision data, the technique is demonstrated to be largely invariant to illumination changes.

The paper proposes a method of compressing floating-point images of arbitrary precision. The concept of floating point images is used frequently in such areas as high dynamic range imaging, where pixel data stored as 8 or 12-bit integers are insufficient. The compression scheme presented in the paper organizes the floating point data in a manner such that already existing compression algorithms such as JPEG or Zlib compression may be used once the data re-organization has taken place. The paper compares the result to a popular (but restrictive) form of image compression, openEXR, and shows significant gains over this format. Furthermore, the compression scheme presented is scalable to deal with floating point images of arbitrary precision.

We propose a single figure-of-merit measure of resolution of a digital imaging system based on the work of Gabor in communication theory. Gabor's work was largely inspired by Heisenberg's developments in quantum theory, most notably his uncertainty theorem of quantum mechanics. Gabor's results look simultaneously at the frequency and spatial domain of a signal, making it ideal for the measure of the modulation transfer function and point-spread function of an imaging system. As opposed to the crude "megapixel" measure which is bantered about in the marketplace, we suggest a figure-of-merit which more accurately represents the resolution of the system. Given that the resolution measure we propose is condensed into a single number rather than a function such as the modulation transfer function or the point spread function, it is our intent to propose this scientific evaluation as a means for typical consumers to fairly judge the resolution of a camera. Finally, we use this measure to compare common digital SLR cameras with varying lenses

The paper demonstrates a method of simultaneously testing the spatial and tonal resolution of a camera. Unlike the modulation transfer function which has been used in the past, the measure proposed rates the resolution as a single number rather than a response over varied resolution, simplifying the measure and making it possible to compare the performance of different cameras easily. Previous work was subject to perturbations caused by aliasing at high frequencies. The measure proposed is immune to such perturbations, and is therefore appropriate for measuring a wide range of image sensing systems

When the user of a digital camera records an image, there is some presumption that when displayed, there is an accurate tonal representation. However, this is almost never the case. The paper shows how capture and tonal reproduction of an image rarely match, as well as a brief history as to why this is true. Techniques for calibrating digital cameras tonally as well as calibrating viewing devices are presented. The paper demonstrates a method of recovering camera response curves easily and with precision. Monitor calibration is demonstrated in a means that allows an accurate display of light-linear images. Ultimately, the paper shows how the proposed methods of calibration for digital cameras and display devices results in the accurate representation of images

We propose the use of a hand-held camera flash as a tangible user interface to a photographic lightpainting algorithm/ system. Our system includes a method of photographic multiple-exposure lighting using a single camera flash to obtain the results that would otherwise require complicated and more expensive professional multiple-light photographic studio setups. The system is simple in its approach, because it provides a direct metaphor-free interaction between the user, the camera, and the computer. The system mimics traditional multiple exposure photography by computationally combining images linearly to produce visual art works.

A robust method of camera response function estimation, using pictures taken by differently illuminating the same subject matter, is presented. The method solves for the response function directly using superposition constraints imposed by different combinations of two (or more) lights to illuminate the same subject matter. Previous methods of computing camera response functions typically used differing exposures of identical subject matter, leading to uniqueness problems (underconstrained due to comparametric periodicity or fractal ambiguity). The method used in this paper overcomes this problem. Finally, we compare the method of the paper to previous methods and find the new method outperforms the previous work.

For many years, the brightness constancy constraint equation (BCCE) has been used for optical flow and related computer vision computations. However, almost all cameras have some kind of automatic exposure feature such as automatic gain control (AGC), so that the overall exposure level of the image varies as the camera is aimed at brighter or darker portions of a scene. Moreover, because most cameras have some kind of unknown nonlinear response function, the change due to AGC cannot be captured by merely applying a multiplicative constant to the pixels of each image. We propose, therefore, a lightspace change constraint equation (LCCE) that accounts for exposure change (AGC) together with the nonlinear response function of the camera. The response function can be automatically "learned" by an intelligent image processing system presented with differently exposed captures of the same subject matter in overlapping regions of registered images. Most importantly, a logarithmic lightspace change constraint equation (LLCCE) is shown to have a very simple mathematical formulation. The LCCE (and log LCCE) is applied to the estimation of the projective coordinate transformation between pairs of images in a sequence, and is compared with examples where the BCCE fails.

When we ask the fundamental question "What does a camera measure?", we arrive at the concept of quantimetric imaging, which uses a new quantimetric unit, q, characteristic of a particular camera (e.g. each kind of camera defines its own quantimetric unit q based on its spectral response, etc.). Fluctuations in interframe exposures, along a sequence of images, give rise to a comparametric relationship between successive pairs of images. This allows us to estimate the response function of the camera (to derive the quantimetric unit q) as well as the relative differences in exposure. A new method of video image processing that exploits multiple differently exposed pictures (frames of the video sequence) of overlapping subject matter is thus possible. The method may be used whenever a video camera having automatic exposure captures multiple frames of video with the same subject matter appearing in regions of overlap between at least some of the successive video frames. Since almost all cameras have an automatic exposure feature, typically center weighted, when a light object falls in the center of the frame the exposure is automatically decreased, whereas the exposure is automatically increased when the camera swings around to point at a darker object. Such fluctuations in gain may be used to estimate the camera's response function, to estimate exposure differences, to do quantimetric processing, as well as to obtain images having both extended dynamic range and extended dynamic domain.