Corey Manders

An electrical muscle stimulation haptic feedback for mixed reality tennis game

We have developed a novel haptic interface for mixed reality applications. Specifically, we have constructed an electrical muscle stimulation system which is wirelessly controlled by a computer and generates electrical pulses with controlled amplitude, timing, and frequencies. The characteristics of the pulses are similar to the commercial electrical muscle stimulators used in medical applications. We apply these pulses through two electrode pads attached to the users forearms. Hence, the user can feel muscle contractions when pulses are activated.

Robust hand tracking using a skin tone and depth joint probability model

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.

Robust hand tracking using a simple color classification technique

Skin color is a strong cue in vision-based human tracking. Skin detection has been widely used in various applications, such as face and hand tracking, people detection in the video databases. In this paper, we propose and develop an effective hand tracking method based on a simple color classification. This method includes two major procedures: training and tracking. In the training procedure, the user specifies a region on a hand to obtain the training data. Based on the skin-color distribution, the training data will be classified into several color clusters using randomized list data structure. In the hand tracking procedure, the hand will be segmented in real-time from the background using the randomized lists that have been trained in the training procedure. The proposed method has two advantages: (1) It is fast because the image segmentation algorithm is automatically performed on a small region surrounding the hand; and (2) It is robust under different lighting conditions because the lighting factor is not employed in our effective color classification. Several experiments have been conducted to validate the performance of the proposed method. This proposed method has good potential in many real applications, such as virtual reality or augmented reality systems.

Eye HDR: gaze-adaptive system for displaying high-dynamic-range images

The human visual system (HVS) uses several methods to interactively adapt to the incredible real-world range of light intensities, continually changing to effectively perceive visual information. Eye HDR is a new approach to the problem of displaying high-dynamic-range (HDR) content on low-dynamic-range displays. Instead of creating a single static image, it uses a dynamic display system to naturally, interactively adapt to the users view, just as the HVS changes depending on the environment.

The effect of linearization of range in skin detection

There is a wide range of work detailing the effect of colorspace on the detection of skin tone pixels. However, one important consideration which has been overlooked is the effect of dynamic range compression. Specifically, many very commonly used file formats (JPEG, PNG, GIF, etc.) use dynamic range compression to compensate for the range expansion implicit in many display systems. When building a model for skin tone detection, this range compression can be detrimental to the performance of a skin classifier. In this paper, we demonstrate how linearization of the range can aid in the exposure invariance of building a skin model. Two common colorspaces used in the classification of skin pixels are HSV and normalized RGB. We show why linearization of the range is important before transformation into either of these spaces. Experimental results are shown for each colorspace used.

Interacting with 3D objects in a virtual environment using an intuitive gesture system

We present a system for interacting with 3D objects in a 3D virtual environment. Using the notion that a typical head-mounted display does not cover the users entire face, we use a fiducial marker placed on the HMD to locate the users 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 users 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 in x, y, and z axis with roll and yaw rotations) in virtual three-dimensional space using a series of intuitive hand gestures.

Video retrieval - evolution of video segmentation, indexing and search

This paper discusses the history and current trends of video retrieval, focusing mainly on video segmentation, indexing and search. The objective is to share with the readers how much we have done so far as well as the current trends in the field. Unlike text documents, video contains dynamic information such as audio, motion (object and/or camera motions), etc. Thus, indexing videos for future search still remains a difficult problem. In addition, one particular problem that remains with digital videos is that it is hard to deal with copyright issues. Thus, indexing videos needs to take this into consideration. In this paper, the history and some of the-state-of-art methods that help to solve these problems will be addressed.

HDR image tone mapping using histogram adjustment adapted to human visual system

Tone-mapping operators are used to produce low dynamic range versions of the high dynamic range images, while preserving as much details as possible. We have proposed a tone-mapping operator which is built on an existing histogram adjustment technique. It incorporates certain characteristics of the human visual system, to restrain the problem of extreme contrast enhancement of certain segments and intensive compression of others, associated with histogram equalization based techniques. Test results show significant improvement over traditional histogram adjustment. The proposed method also does quite well compared to the other state of the art tone-mapping operators.

A simplified ordinal-based method for video signature

In this paper, we propose an algorithm for video signature using music videos and news video for our study. The algorithm was developed based on our earlier work with an improvement (reducing the steps) on the process of generating video signature. Thus, revised process reduces the amount of processing time needed tremendously. In addition, besides color as a feature, we introduce the addition of a face feature to improve the system performance for video matching. For our experimental set up, most conditions met the requirements set forth by MPEG standardization on visual signature tools. Initial results show that the algorithm is effective and robust to several transformations such as color change, brightness change, the addition of Gaussian noise, and resolution reduction.

A fast and efficient framework for indexing and detection of modified copies in video

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.