Approach to automatic video motion segmentation

A novel, fast automatic motion segmentation approach is presented. It differs from conventional pixel or edge based motion segmentation approaches in that the proposed method uses labelled regions (facets) to segment various video objects from the background. Facets are clustered into objects based on their motion and proximity details using Bayesian logic. Because the number of facets is usually much lower than the number of edges and points, using facets can greatly reduce the computational complexity of motion segmentation. The proposed method can tackle efficiently the complexity of video object motion tracking, and offers potential for real-time content-based video annotation.

Radiowave propagation from a tissue-implanted source at 418 MHz and 916.5 MHz

Tissue-implanted ultra-high frequency (UHF) radio devices are being employed in both humans and animals for telemetry and telecommand applications, This paper describes the experimental measurement and electromagnetic modeling of propagation from 418-MHz and 916.5-MHz sources placed in the human vagina. Whole-body homogeneous and semi-segmented software models were constructed using data from the Visible Human Project. Bodyworn radiation efficiencies for a vaginally placed 418-MHz source were calculated using finite-difference time-domain and ranged between 1.6% and 3.4% (corresponding to net body losses of between 14.7 and 18.0 dB), Greater losses were encountered at 916.5 MHz, with efficiencies between 0.36% and 0.46% (net body loss ranging between 23.4 and 24.4 dB), Practical measurements were in good agreement with simulations, to within 2 dB at 418 MHz and 3 dB at 916.5 MHz. The degree of tissue-segmentation for whole-body models was found to have a minimal effect on calculated azimuthal radiation patterns and bodyworn radiation efficiency, provided the region surrounding the implanted source was sufficiently detailed.

In situ measurement of UHF wearable antenna radiation efficiency using a reverberation chamber

The radiation efficiency and resonance frequency of five compact antennas worn by nine individual test subjects was measured at 2.45 GHz in a reverberation chamber. The results show that, despite significant differences in body mass, wearable antenna radiation efficiency had a standard deviation less than 0.6 dB and the resonance frequency shift was less than 1% between test subjects. Variability in the radiation efficiency and resonance frequency shift between antennas was largely dependant on body tissue coupling which is related to both antenna geometry and radiation characteristics. The reverberation chamber measurements were validated using a synthetic tissue phantom and compared with results obtained in a spherical near field chamber and finite-difference time-domain (FDTD) simulation.

Segmentation of optic disc in retinal images using an improved gradient vector flow algorithm

Image segmentation plays an important role in the analysis of retinal images as the extraction of the optic disk provides important cues for accurate diagnosis of various retinopathic diseases. In recent years, gradient vector flow (GVF) based algorithms have been used successfully to successfully segment a variety of medical imagery. However, due to the compromise of internal and external energy forces within the resulting partial differential equations, these methods can lead to less accurate segmentation results in certain cases. In this paper, we propose the use of a new mean shift-based GVF segmentation algorithm that drives the internal/external energies towards the correct direction. The proposed method incorporates a mean shift operation within the standard GVF cost function to arrive at a more accurate segmentation. Experimental results on a large dataset of retinal images demonstrate that the presented method optimally detects the border of the optic disc.