Zobrazeno 1 - 10
of 66
pro vyhledávání: '"James W. Pitton"'
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems. 17:3602-3612
This paper proposes a robust ground-moving-platform-based human tracking system, which effectively integrates visual simultaneous localization and mapping (V-SLAM), human detection, ground plane estimation, and kernel-based tracking techniques. The p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c760d7c3059e7dbeb321a6b0c97d35f9
https://doi.org/10.1109/tits.2016.2557763
https://doi.org/10.1109/tits.2016.2557763
Publikováno v:
Journal of Signal Processing Systems. 86:27-39
In this paper, we attempt to solve the challenging task of precise and robust human tracking from a moving camera. We propose an innovative human tracking approach, which efficiently integrates the deformable part model (DPM) into multiple-kernel tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4e11774779f077f81f9d6da63fe1dc79
https://doi.org/10.1007/s11265-015-1097-y
https://doi.org/10.1007/s11265-015-1097-y
Publikováno v:
ICASSP
Historically, sparse methods and neural networks, particularly modern deep learning methods, have been relatively disparate areas. Sparse methods are typically used for signal enhancement, compression, and recovery, usually in an unsupervised framewo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6d96e07ff597dcf6196f8853e92f02c5
https://doi.org/10.1109/icassp.2017.7952977
https://doi.org/10.1109/icassp.2017.7952977
Publikováno v:
WASPAA
In this paper, we propose a novel recurrent neural network architecture for speech separation. This architecture is constructed by unfolding the iterations of a sequential iterative soft-thresholding algorithm (ISTA) that solves the optimization prob
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fd5ff7c1748f08ef732d5d6e639f2b44
Publikováno v:
ACSSC
Conventional statistical signal processing of nonstationary signals uses circular complex Gaussian distributions to model the complex-valued short-time Fourier transform. In this paper, we show how noncircular complex Gaussian distributions can provi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::973e21aac3362b37c8a9cf0127943d76
https://doi.org/10.1109/acssc.2016.7869102
https://doi.org/10.1109/acssc.2016.7869102
Publikováno v:
SAM
Natural signals are typically nonstationary. The complex-valued frequency spectra of nonstationary signals do not have zero spectral correlation, as is assumed for wide-sense stationary processes. Instead, these spectra have non-zero second-order non
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d84bbf17f2b8f6d66737d487d4fdb0d2
https://doi.org/10.1109/sam.2016.7569672
https://doi.org/10.1109/sam.2016.7569672
Publikováno v:
ICASSP
In this paper, we propose an innovative human tracking algorithm, which efficiently integrates the deformable part model (DPM) into the multiple-kernel based tracking using a moving camera. By representing each part model of a DPM detected human as a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4ae20601d9bf385d28f1b94fc5a1d192
https://doi.org/10.1109/icassp.2015.7178371
https://doi.org/10.1109/icassp.2015.7178371
Publikováno v:
ICASSP
Many voice activity detection (VAD) systems use the magnitude of complex-valued spectral representations. However, using only the magnitude often does not fully characterize the statistical behavior of the complex values. We present two novel methods
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ea53e59fa78ae1f7ca231bbf7c33318c
https://doi.org/10.1109/icassp.2015.7178823
https://doi.org/10.1109/icassp.2015.7178823
Publikováno v:
IEEE Transactions on Signal Processing. 52:3023-3035
For nonstationary signal classification, e.g., speech or music, features are traditionally extracted from a time-shifted, yet short data window. For many applications, these short-term features do not efficiently capture or represent longer term sign
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ebb8c2640e94116a24860b8eea4d8e2c
https://doi.org/10.1109/tsp.2004.833861
https://doi.org/10.1109/tsp.2004.833861
Publikováno v:
ACSSC
This paper describes an improved detector for nonstationary harmonic signals. The performance improvement is accomplished by using a novel method for extending the coherence time of such signals. This method applies a transformation to a noisy signal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0830ab941f4d825be6a2b2636ed08ed2
https://doi.org/10.1109/acssc.2014.7094774
https://doi.org/10.1109/acssc.2014.7094774