Sorry, you need to enable JavaScript to visit this website.

A robust, efficient video analytic tool is presented for detection and estimation of driver’s head position and orientation in the SHRP 2 NDS dataset. It is shown that by exploiting the temporal correlations between successive frames in a video, challenging conditions such as lighting variations, and lower resolutions, may be mitigated effectively. The Viola Jones frontal face detector provides initial results. Then, statistical inference methods for spurious faces elimination and missing driver’s head detection are developed.

Over the last few years, industry and academia have been shifting towards computer aided models for seismic interpretation because manual labeling and salt dome delineation is becoming very time consuming and labor intensive as the volume of seismic data is in the order of tera-bytes. In this paper, we have proposed an edge-based active contour with an arc length penalty using level set implementation for interpreter-assisted salt dome segmentation. We have designed an edge function and studied the effect of varying different active contour parameters on salt dome boundary detection.

The most efficient signal edge-preserving smoothing filters, e.g., for denoising, are non-linear. Thus, their acceleration is challenging and is often done in practice by tuning filters parameters, such as increasing the width of the local smoothing neighborhood, resulting in more aggressive smoothing of a single sweep at the cost of increased edge blurring. We propose an alternative technology, accelerating the original filters without tuning, by running them through a conjugate gradient method, not affecting their quality.

Presentation Slides for "Unsupervised Estimation Of Uncertainty For Video Saliency Detection Using Temporal Cues" at GlobalSIP 2015

Key-frame extraction has been a focused problem of human action recognition due to its effectiveness, efficiency and importance in action understanding. According to the characteristics of human motion perception, this paper proposes a new key-frame extraction framework based on motion change points. And in order to detect motion change points robustly, a hysteresis extrema seeking algorithm has been developed. Experimental results have demonstrated the good performance of the proposed methods.

We propose signal reconstruction algorithms which utilize a guiding subspace that represents desired properties of reconstructed signals. Optimal reconstructed signals are shown to belong to a convex bounded set, called the ``reconstruction'' set. Iterative reconstruction algorithms, based on conjugate gradient methods, are developed to approximate optimal reconstructions with low memory and computational costs. Effectiveness of the proposed method is demonstrated with an application to image magnification.