RESUMO
We propose new techniques for joint recognition, segmentation and pose estimation of infrared (IR) targets. The problem is formulated in a probabilistic level set framework where a shape constrained generative model is used to provide a multi-class and multi-view shape prior and where the shape model involves a couplet of view and identity manifolds (CVIM). A level set energy function is then iteratively optimized under the shape constraints provided by the CVIM. Since both the view and identity variables are expressed explicitly in the objective function, this approach naturally accomplishes recognition, segmentation and pose estimation as joint products of the optimization process. For realistic target chips, we solve the resulting multi-modal optimization problem by adopting a particle swarm optimization (PSO) algorithm and then improve the computational efficiency by implementing a gradient-boosted PSO (GB-PSO). Evaluation was performed using the Military Sensing Information Analysis Center (SENSIAC) ATR database, and experimental results show that both of the PSO algorithms reduce the cost of shape matching during CVIM-based shape inference. Particularly, GB-PSO outperforms other recent ATR algorithms, which require intensive shape matching, either explicitly (with pre-segmentation) or implicitly (without pre-segmentation).
RESUMO
We propose a new integrated target tracking, recognition and segmentation algorithm, called ATR-Seg, for infrared imagery. ATR-Seg is formulated in a probabilistic shape-aware level set framework that incorporates a joint view-identity manifold (JVIM) for target shape modeling. As a shape generative model, JVIM features a unified manifold structure in the latent space that is embedded with one view-independent identity manifold and infinite identity-dependent view manifolds. In the ATR-Seg algorithm, the ATR problem formulated as a sequential level-set optimization process over the latent space of JVIM, so that tracking and recognition can be jointly optimized via implicit shape matching where target segmentation is achieved as a by-product without any pre-processing or feature extraction. Experimental results on the recently released SENSIAC ATR database demonstrate the advantages and effectiveness of ATR-Seg over two recent ATR algorithms that involve explicit shape matching.
RESUMO
Facial expressions are described traditionally as monolithic or unitary entities. However, humans have the capacity to produce facial blends of emotion in which the upper and lower face simultaneously display different expressions. Recent neuroanatomical studies in monkeys have demonstrated that there are separate cortical motor areas for controlling the upper and lower face in each hemisphere that, presumably, also occur in humans. Using high-speed videography, we began measuring the movement dynamics of spontaneous facial expressions, including facial blends, to develop a more complete understanding of the neurophysiology underlying facial expressions. In our part 1 publication in Cortex (2016), we found that hemispheric motor control of the upper and lower face is overwhelmingly independent; 242 (99%) of the expressions were classified as demonstrating independent hemispheric motor control whereas only 3 (1%) were classified as demonstrating dependent hemispheric motor control. In this companion paper (part 2), 251 unitary facial expressions that occurred on either the upper or lower face were analyzed. 164 (65%) expressions demonstrated dependent hemispheric motor control whereas 87 (35%) expressions demonstrated independent or dual hemispheric motor control, indicating that some expressions represent facial blends of emotion that occur across the vertical facial axis. These findings also support the concepts that 1) spontaneous facial expressions are organized predominantly across the horizontal facial axis and secondarily across the vertical facial axis and 2) facial expressions are complex, multi-component, motoric events. Based on the Emotion-type hypothesis of cerebral lateralization, we propose that facial expressions modulated by a primary-emotional response to an environmental event are initiated by the right hemisphere on the left side of the face whereas facial expressions modulated by a social-emotional response to an environmental event are initiated by the left hemisphere on the right side of the face.
Assuntos
Face/fisiologia , Expressão Facial , Lateralidade Funcional/fisiologia , Córtex Motor/fisiologia , Adolescente , Adulto , Emoções/fisiologia , Feminino , Humanos , Masculino , Adulto JovemRESUMO
BACKGROUND: Haemopoietic stem-cell transplantation (HSCT) eradicates host haemopoiesis before venous infusion of haemopoietic stem cells (HSCs). The pathway to cellular recovery has been difficult to study in human beings because of risks associated with interventions during aplasia. We investigated whether 18F-fluorothymidine (18F-FLT) imaging was safe during allogenic HSCT and allowed visualisation of early cellular proliferation and detection of patterns of cellular engraftment after HSCT. METHODS: Eligible patients were aged 18-55 years, had high-risk haematological malignancies. All patients underwent myeloablation followed by HSCT. The imaging primary endpoint was detection of early subclinical engraftment after HSCT with 18F-FLT PET or CT. Imaging was done 1 day before and 5 or 9, and 28 days, and 1 year after HSCT. This study is registered with ClinicalTrials.gov, number NCT01338987. FINDINGS: Between April 1, 2014, and Dec 31, 2015, 23 patients were enrolled and assessable for toxic effects after completing accrual. 18F-FLT was not associated with any adverse events or delayed engraftment. 18F-FLT imaging objectively identified subclinical bone-marrow recovery within 5 days of HSC infusion, which was up to 20 days before engraftment became clinically evident. Quantitatively, 18F-FLT intensity differed significantly between myeloablative infusion before HSCT and subclinical HSC recovery (p=0·00031). 18F-FLT biodistribution over time revealed a previously unknown path of cellular recovery of haemopoiesis in vivo that mirrored fetal ontogeny. INTERPRETATION: 18F-FLT allowed quantification and tracking of subclinical bone-marrow repopulation in human beings and revealed new insights into the biology of HSC recovery after HSCT. FUNDING: National Institutes of Health, Ben's Run/Ben's Gift, Albert and Elizabeth Tucker Foundation, Mex Frates Leukemia Fund, Jones Family fund, and Oklahoma Center for Adult Stem Cell Research.
Assuntos
Neoplasias Hematológicas/diagnóstico por imagem , Neoplasias Hematológicas/cirurgia , Transplante de Células-Tronco Hematopoéticas , Tomografia por Emissão de Pósitrons , Tomografia Computadorizada por Raios X , Adulto , Didesoxinucleosídeos/farmacocinética , Feminino , Humanos , Masculino , Projetos Piloto , Estudos Prospectivos , Distribuição TecidualRESUMO
Facial expressions are described traditionally as monolithic entities. However, humans have the capacity to produce facial blends, in which the upper and lower face simultaneously display different emotional expressions. This, in turn, has led to the Component Theory of facial expressions. Recent neuroanatomical studies in monkeys have demonstrated that there are separate cortical motor areas for controlling the upper and lower face that, presumably, also occur in humans. The lower face is represented on the posterior ventrolateral surface of the frontal lobes in the primary motor and premotor cortices and the upper face is represented on the medial surface of the posterior frontal lobes in the supplementary motor and anterior cingulate cortices. Our laboratory has been engaged in a series of studies exploring the perception and production of facial blends. Using high-speed videography, we began measuring the temporal aspects of facial expressions to develop a more complete understanding of the neurophysiology underlying facial expressions and facial blends. The goal of the research presented here was to determine if spontaneous facial expressions in adults are predominantly monolithic or exhibit independent motor control of the upper and lower face. We found that spontaneous facial expressions are very complex and that the motor control of the upper and lower face is overwhelmingly independent, thus robustly supporting the Component Theory of facial expressions. Seemingly monolithic expressions, be they full facial or facial blends, are most likely the result of a timing coincident rather than a synchronous coordination between the ventrolateral and medial cortical motor areas responsible for controlling the lower and upper face, respectively. In addition, we found evidence that the right and left face may also exhibit independent motor control, thus supporting the concept that spontaneous facial expressions are organized predominantly across the horizontal facial axis and secondarily across the vertical axis.
Assuntos
Comportamento/fisiologia , Emoções/fisiologia , Face/fisiologia , Expressão Facial , Lateralidade Funcional/fisiologia , Córtex Motor/fisiologia , Adolescente , Adulto , Feminino , Humanos , Masculino , Adulto JovemRESUMO
Clinical assessment of bone marrow is limited by an inability to evaluate the marrow space comprehensively and dynamically and there is no current method for automatically assessing hematopoietic activity within the medullary space. Evaluating the hematopoietic space in its entirety could be applicable in blood disorders, malignancies, infections, and medication toxicity. In this paper, we introduce a CT/PET 3D automatic framework for measurement of the hematopoietic compartment proliferation within osseous sites. We first perform a full-body bone structure segmentation using 3D graph-cut on the CT volume. The vertebrae are segmented by detecting the discs between adjacent vertebrae. Finally, we register the bone marrow CT volume with its corresponding PET volume and capture the spinal bone marrow volume. The proposed framework was tested on 17 patients, achieving an average accuracy of 86.37% and a worst case accuracy of 82.3% in automatically extracting the aggregate volume of the spinal marrow cavities.
RESUMO
Targets of interest in video acquired from imaging infrared sensors often exhibit profound appearance variations due to a variety of factors, including complex target maneuvers, ego-motion of the sensor platform, background clutter, etc., making it difficult to maintain a reliable detection process and track lock over extended time periods. Two key issues in overcoming this problem are how to represent the target and how to learn its appearance online. In this paper, we adopt a recent appearance model that estimates the pixel intensity histograms as well as the distribution of local standard deviations in both the foreground and background regions for robust target representation. Appearance learning is then cast as an adaptive Kalman filtering problem where the process and measurement noise variances are both unknown. We formulate this problem using both covariance matching and, for the first time in a visual tracking application, the recent autocovariance least-squares (ALS) method. Although convergence of the ALS algorithm is guaranteed only for the case of globally wide sense stationary process and measurement noises, we demonstrate for the first time that the technique can often be applied with great effectiveness under the much weaker assumption of piecewise stationarity. The performance advantages of the ALS method relative to the classical covariance matching are illustrated by means of simulated stationary and nonstationary systems. Against real data, our results show that the ALS-based algorithm outperforms the covariance matching as well as the traditional histogram similarity-based methods, achieving sub-pixel tracking accuracy against the well-known AMCOM closure sequences and the recent SENSIAC automatic target recognition dataset.
RESUMO
The spectrum of the convolution of two continuous functions can be determined as the continuous Fourier transform of the cross-correlation function. The same can be said about the spectrum of the convolution of two infinite discrete sequences, which can be determined as the discrete time Fourier transform of the cross-correlation function of the two sequences. In current digital signal processing, the spectrum of the contiuous Fourier transform and the discrete time Fourier transform are approximately determined by numerical integration or by densely taking the discrete Fourier transform. It has been shown that all three transforms share many analogous properties. In this paper we will show another useful property of determining the spectrum terms of the convolution of two finite length sequences by determining the discrete Fourier transform of the modified cross-correlation function. In addition, two properties of the magnitude terms of orthogonal wavelet scaling functions are developed. These properties are used as constraints for an exhaustive search to determine an robust lower bound on conjoint localization of orthogonal scaling functions.