Bor-Jiunn Hwang

An adaptive eye gaze tracker system in the integrated cloud computing and mobile device

This paper proposed an adaptive method for tracking eye gaze in the integrated cloud computing and mobile device environment. The task begins with extracting the eye position and the iris contour base on geometrical features. These local gaze features are calculate and integrated to train a neural network. And the estimated gaze point is outputted from the trained NN (Neural Network) in the cloud computing. A utility function is proposed to decide the functionality is performed in the cloud or mobile device adaptively based on device and network conditions. Besides, our proposed method can improve system performance as well as overcome the problem for limited resource of mobile device.

A modified mean shift algorithm for visual object tracking

The CamShift is an adaptive version of Mean Shift algorithm. It has received wide attention as an efficient and robust method for object tracking. However, it is often distracted or interfered by the other larger objects with similar colors. This paper presents a novel tracking algorithm based on the mean shift framework. Unlike the CamShift, which uses the probability density image determined by the color feature, the proposed algorithm employs the probability density image derived from both color and shape features. Experimental results indicate the proposed algorithm improves robustness without sacrificing computational cost, as compared to the conventional CamShift algorithm.

The integrated gaze, web and object tracking techniques for the web-based e-learning platform

Most web-based e-learning platforms for teaching and learning can record individual action history of the access to course materials and activities. In general, the click through rate (CTR) is recorded as the action to represent the history of people who review the course online. By analyzing CTR only would exclude the important information from the visual behaviors. This study proposed a different method for collecting navigation behaviors. A method uses a web-based camera with the techniques of analyzing the source codes and tracking the objects of web pages and puts people in a more natural and undisturbed environment.

A Vision-based System to Help Senior Citizens for Memory Recall of Object-placing

Human memory ability is gradually degenerated followed by the increasing of age. It is annoying for senior citizens to often forgetting and trying to recall the places of those objects commonly used in their daily lives. This paper presents a preliminary study for developing a vision-based system and helping senior citizens to recall the process of object-placing. In the initial stage, SURF (Speeded Up Robust Features) is adopted to extract feature points from the object image that are further used for the matching to its corresponding video clips in the video database. Experimental results have demonstrated that correct video clips can be retrieved from the database and played for the user to recall after the desired object image is provided. Although impressive results have been achieved, to increase the robustness of this system, more features and objects will be analyzed and used in the future.

Cluster Based Gaze Estimation and Data Visualization Supporting Diverse Environments

This paper proposes a method to explore the navigation of audience by estimating gaze points and labeling them to the objects of video or web content. The cluster based gaze estimation and statistics based labeling method are proposed to support the multiple user environments as well as improve the accuracy and usability. In addition, the number of feature clusters is accorded as the amount of areas of target screen. Additionally, statistics based labeling method is proposed to mapping the gaze points to target object by computing the probability. Moreover, this method can provide a good manner to estimate the attentive objects. The visualization of attentive blocks and the amount of probabilities are presented to illustrate the navigation of audience as attentive object. Therefore, this visualization method can exhibit the navigation behavior of audience more real, besides overcomes the problem of difficult labeling objects. The experimental results demonstrate the proposed method provide more robustness for long range as well as diversity environments.

The integrated gaze and object tracking techniques to explo re the user's navigation

This paper proposes a method to explore the users navigation foci and visual tracks by estimating gaze points and mapping them to the objects of video content. The tracking method for multiple objects is derived from the adaptive weight based feature with probability densities. It is able to track the target objects efficiently even when the target objects are lost. It continuously applies sequence scheme and mean scheme throughout to track objects while they are lost. The experimental results demonstrate the proposed method provide higher robustness under different conditions.

A multiple description coding method based on 3-D SPIHT for videos

This study presents a new multiple description coding method based on a three-dimensional set partitioning in hierarchical trees (3-D SPIHT) algorithm in WiMAX for videos. Applying a poly-phase sampling technique to sample an input video over its intra-frame or inter-frame, several independent and highly correlated descriptions are generated. Then, a 3-D SPIHT algorithm is applied to each of the produced descriptions. Finally, the coding results are transmitted via different channels. This proposed approach achieves high compression ratio, enhances transmission speed, and more importantly, attains acceptable video quality when channel congestion occurs. Experimental results are provided to demonstrate promising performance of the proposed method.