Skovgaardcalhoun0437

We consider visual tracking in numerous applications of computer vision and seek to achieve optimal tracking accuracy and robustness based on various evaluation criteria for applications in intelligent monitoring during disaster recovery activities. We propose a novel framework to integrate a Kalman filter (KF) with spatial-temporal regularized correlation filters (STRCF) for visual tracking to overcome the instability problem due to large-scale application variation. To solve the problem of target loss caused by sudden acceleration and steering, we present a stride length control method to limit the maximum amplitude of the output state of the framework, which provides a reasonable constraint based on the laws of motion of objects in real-world scenarios. Moreover, we analyze the attributes influencing the performance of the proposed framework in large-scale experiments. The experimental results illustrate that the proposed framework outperforms STRCF on OTB-2013, OTB-2015 and Temple-Color datasets for some specific attributes and achieves optimal visual tracking for computer vision. Compared with STRCF, our framework achieves AUC gains of 2.8%, 2%, 1.8%, 1.3%, and 2.4% for the background clutter, illumination variation, occlusion, out-of-plane rotation, and out-of-view attributes on the OTB-2015 datasets, respectively. For sporting events, our framework presents much better performance and greater robustness than its competitors.Dual-frequency capacitive micromachined ultrasonic transducers (CMUTs) are introduced for multiscale imaging applications, where a single array transducer can be used for both deep low-resolution imaging and shallow high-resolution imaging. These transducers consist of low- and high-frequency membranes interlaced within each subarray element. They are fabricated using a modified sacrificial release process. Successful performance is demonstrated using wafer-level vibrometer testing, as well as acoustic testing on wirebonded dies consisting of arrays of 2- and 9-MHz elements of up to 64 elements for each subarray. The arrays are demonstrated to provide multiscale, multiresolution imaging using wire phantoms and can span frequencies from 2 MHz up to as high as 17 MHz. Peak transmit sensitivities of 27 and 7.5 kPa/V are achieved with the low- and high-frequency subarrays, respectively. At 16-mm imaging depth, lateral spatial resolution achieved is 0.84 and 0.33 mm for low- and high-frequency subarrays, respectively. The signal-to-noise ratio of the low-frequency subarray is significantly higher for deep targets compared to the high-frequency subarray. The array achieves multiband imaging capabilities difficult to achieve with current transducer technologies and may have applications to multipurpose probes and novel contrast agent imaging schemes.We developed a new method, called the tangent plane method (TPM), for more efficiently and accurately estimating 2-D shear wave speed (SWS) from any direction of wave propagation. In this technique, we estimate SWS by solving the Eikonal equation because this approach is more robust to noise. To further enhance the performance, we computed the tangent plane of the arrival time surface. To evaluate the approach, we performed simulations and also conducted phantom studies. Simulation studies showed that TPM was more robust to noise than the conventional methods such as 2-D cross correlation (CC) and the distance method. The contrast/CNR for an inclusion (69 kPa; manufacturer provided stiffness) of a phantom is 0.54/4.17, 0.54/1.82, and 0.46/1.22. SWS results [mean and standard deviation (SD)] were 4.41 ± 0.49, 4.62 ± 0.85, and 3.66 ± 0.99 m/s, respectively, while the manufacturer's reported value (mean and range) is 4.81 ± 0.49 m/s. This shows that TPM has the higher CNR and lower SD than other methods. To increase the computation speed, an iterative version of TPM (ITPM) was also developed, which calculated the time-of-flight iteratively. ITPM reduced the computation time to 3.6%, i.e., from 748 to 27 s. In vivo case analysis demonstrated the feasibility of using the conventional ultrasound scanner for the proposed 2-D SWS algorithms.In study, we developed a positron emission tomography (PET) insert for simultaneous brain imaging within 7-Tesla (7T) magnetic resonance (MR) imaging scanners. The PET insert has 18 sectors, and each sector is assembled with two-layer depth-of-interaction (DOI)-capable high-resolution block detectors. The PET scanner features a 16.7-cm-long axial field-of-view (FOV) to provide entire human brain images without bed movement. The PET scanner early digitizes a large number of block detector signals at a front-end data acquisition (DAQ) board using a novel field-programmable gate array (FPGA)-only signal digitization method. All the digitized PET data from the front-end DAQ boards are transferred using gigabit transceivers via non-magnetic high-definition multimedia interface (HDMI) cables. A back-end DAQ system provides a common clock and synchronization signal for FPGAs over the HDMI cables. An active cooling system using copper heat pipes is applied for thermal regulation. All the 2.17-mm-pitch crystals with two-layer DOI information were clearly identified in the block detectors, exhibiting a system-level energy resolution of 12.6%. The PET scanner yielded clear hot-rod and Hoffman brain phantom images and demonstrated 3D PET imaging capability without bed movement. We also performed a pilot simultaneous PET/MR imaging study of a brain phantom. The PET scanner achieved a spatial resolution of 2.5 mm at the center FOV (NU 4) and a sensitivity of 18.9 kcps/MBq (NU 2) and 6.19% (NU 4) in accordance with the National Electrical Manufacturers Association (NEMA) standards.In supervised learning for medical image analysis, sample selection methodologies are fundamental to attain optimum system performance promptly and with minimal expert interactions (e.g. label querying in an active learning setup). In this article we propose a novel sample selection methodology based on deep features leveraging information contained in interpretability saliency maps. In the absence of ground truth labels for informative samples, we use a novel self supervised learning based approach for training a classifier that learns to identify the most informative sample in a given batch of images. We demonstrate the benefits of the proposed approach, termed Interpretability-Driven Sample Selection (IDEAL), in an active learning setup aimed at lung disease classification and histopathology image segmentation. We analyze three different approaches to determine sample informativeness from interpretability saliency maps (i) an observational model stemming from findings on previous uncertainty-based sample selection approaches, (ii) a radiomics-based model, and (iii) a novel data-driven self-supervised approach. We compare IDEAL to other baselines using the publicly available NIH chest X-ray dataset for lung disease classification, and a public histopathology segmentation dataset (GLaS), demonstrating the potential of using interpretability information for sample selection in active learning systems. Results show our proposed self supervised approach outperforms other approaches in selecting informative samples leading to state of the art performance with fewer samples.Recently, automatic diagnostic approaches have been widely used to classify ocular diseases. Most of these approaches are based on a single imaging modality (e.g., fundus photography or optical coherence tomography (OCT)), which usually only reflect the oculopathy to a certain extent, and neglect the modality-specific information among different imaging modalities. This paper proposes a novel modality-specific attention network (MSAN) for multi-modal retinal image classification, which can effectively utilize the modality-specific diagnostic features from fundus and OCT images. read more The MSAN comprises two attention modules to extract the modality-specific features from fundus and OCT images, respectively. Specifically, for the fundus image, ophthalmologists need to observe local and global pathologies at multiple scales (e.g., from microaneurysms at the micrometer level, optic disc at millimeter level to blood vessels through the whole eye). Therefore, we propose a multi-scale attention module to extract both the local and global features from fundus images. Moreover, large background regions exist in the OCT image, which is meaningless for diagnosis. Thus, a region-guided attention module is proposed to encode the retinal layer-related features and ignore the background in OCT images. Finally, we fuse the modality-specific features to form a multi-modal feature and train the multi-modal retinal image classification network. The fusion of modality-specific features allows the model to combine the advantages of fundus and OCT modality for a more accurate diagnosis. Experimental results on a clinically acquired multi-modal retinal image (fundus and OCT) dataset demonstrate that our MSAN outperforms other well-known single-modal and multi-modal retinal image classification methods.Remarkable gains in deep learning usually benefit from large-scale supervised data. Ensuring the intra-class modality diversity in training set is critical for generalization capability of cutting-edge deep models, but it burdens human with heavy manual labor on data collection and annotation. In addition, some rare or unexpected modalities are new for the current model, causing reduced performance under such emerging modalities. Inspired by the achievements in speech recognition, psychology and behavioristics, we present a practical solution, self-reinforcing unsupervised matching (SUM), to annotate the images with 2D structure-preserving property in an emerging modality by cross-modality matching. Specifically, we propose a dynamic programming algorithm, dynamic position warping (DPW), to reveal the underlying element correspondence relationship between two matrix-form data in an order-preserving fashion, and devise a local feature adapter (LoFA) to allow for cross-modality similarity measurement. On these bases, we develop a two-tier self-reinforcing learning mechanism on both feature level and image level to optimize the LoFA. The proposed SUM framework requires no any supervision in emerging modality and only one template in seen modality, providing a promising route towards incremental learning and continual learning. Extensive experimental evaluation on two proposed challenging one-template visual matching tasks demonstrate its efficiency and superiority.Most state-of-the-art methods of object detection suffer from poor generalization ability when the training and test data are from different domains. To address this problem, previous methods mainly explore to align distribution between source and target domains, which may neglect the impact of the domain-specific information existing in the aligned features. Besides, when transferring detection ability across different domains, it is important to extract the instance-level features that are domain-invariant. To this end, we explore to extract instance-invariant features by disentangling the domain-invariant features from the domain-specific features. Particularly, a progressive disentangled mechanism is proposed to decompose domain-invariant and domain-specific features, which consists of a base disentangled layer and a progressive disentangled layer. Then, with the help of Region Proposal Network (RPN), the instance-invariant features are extracted based on the output of the progressive disentangled layer. Finally, to enhance the disentangled ability, we design a detached optimization to train our model in an end-to-end fashion.