Domenico Vitulano

An Improvement of Kernel-Based Object Tracking Based on Human Perception

The objective of the paper is to embed perception rules into the kernel-based target tracking algorithm and to evaluate to what extent these rules are able to improve the original tracking algorithm, without any additional computational cost. To this aim, the target is represented through features that are related to its visual appearance; then, it is tracked in subsequent frames using a metric that, again, correlates well with the human visual perception (HVP). The use of HVP rules are twofold advantageous: it allows us to both increase tracking efficacy and considerably reduce the computational cost of the tracking process-thanks to the reduced size of the perceptual feature space. Various tests on video sequences have shown the stability and the robustness of the proposed framework, also in the presence of both other moving objects and partial or complete target occlusion in a limited number of subsequent frames.

Perceptual object tracking

This paper presents an improved kernel-based target tracking that uses new and effective features able to describe the target appearance. The key idea consists of adopting features that are related to the visual perception of the target in place of its color histogram. The change of the feature space is twofold advantageous. It allows us to faithfully follow the target and to considerably reduce the computational cost of the whole tracking algorithm thanks to the reduced dimension of the perceptual feature space. Preliminary tests on some video sequences are encouraging. The proposed tracker is able to follow the target even in case of complete occlusion for some consecutive frames. Moreover, it is more stable than the algorithm that uses just the luminance histogram as target feature. Finally, it is robust to the presence of other moving targets.

Non local means image denoising using noise-adaptive SSIM

This paper embeds SSIM in place of the L2 norm in a one step Non Local Means (NLM) scheme. This is possible thanks to a new form of SSIM that can be formally derived from the classical SSIM using the spreading error analysis. This approach has several advantages over L2 norm based NLM such as greater robustness to parameters setting, higher performance in terms of PSNR and SSIM, optimal subjective visual quality. In addition, it is possible to show that the cascade of the proposed pure visual approach and a second step based on L2 norm allows us to reach results close (slightly less) to the state of the art (BM3D) in terms of PSNR and SSIM.

An adaptive perception-based image preprocessing method

The aim of this paper is to introduce an adaptive preprocessing procedure based on human perception in order to increase the performance of some standard image processing techniques. Specifically, image frequency content has been weighted by the corresponding value of the contrast sensitivity function, in agreement with the sensitiveness of human eye to the different image frequencies and contrasts. The 2D Rational dilation wavelet transform has been employed for representing image frequencies. In fact, it provides an adaptive and flexible multiresolution framework, enabling an easy and straightforward adaptation to the image frequency content. Preliminary experimental results show that the proposed preprocessing allows us to increase the performance of some standard image enhancement algorithms in terms of visual quality and often also in terms of PSNR.

Automatic and Noninvasive Indoor Air Quality Control in HVAC Systems

This paper presents a methodology for assessing and monitoring the cleaning state of a heating, ventilation, and air conditioning (HVAC) system of a building. It consists of a noninvasive method for measuring the amount of dust in the whole ventilation system, that is, the set of filters and air ducts. Specifically, it defines the minimum amount of measurements, their time table, locations, and acquisition conditions. The proposed method promotes early intervention on the system and it guarantees high indoor air quality and proper HVAC working conditions. The effectiveness of the method is proved by some experimental results on different study cases.

Instantaneous frequency estimation of interfering FM signals through time-scale isolevel curves

This paper investigates the possibility of extracting information regarding two or more frequency modulated (FM) signals in almost complete interference. To this aim, a novel wavelet-based approach for the estimation of instantaneous frequency (IF) is presented. It is first proved that the modulus of the Analytic Wavelet Transform (referred to as scalogram) of one or more FM signals obeys a time-scale evolution law whose isolevel curves (ICs) depend on signal IF. Hence, it is shown that scalogram points not belonging to ridge can provide a more robust IF estimate in case of strong interference. Experimental results confirm that the proposed approach improves ridge-based IF estimation, even in presence of noise.

Instantaneous frequency detection via ridge neighbor tracking

This paper presents a novel approach to estimate chirp parameters in case of strong interference between two or more components in a 1D signal. In particular, it will proved that non ridge points provide a more robust parameters estimation in case of critical conditions. The proposed method has been tested on some synthetic signals and preliminary experimental results are very promising.

Phase-based Motion Estimation for Noisy Sequences

This paper presents a novel approach for estimating affine motion in noisy image sequences. It exploits Fourier phase information by comparing the averaging of a group of frames and the convolution of the reference one with a Dirac comb function. A study of the estimation error in case of Gaussian noise is also offered. The proposed approach outperforms available techniques in terms of quality and computational effort.