In this paper, we present a fusion approach to solve the nonrigid shape recovery problem, which takes advantage of both the appearance information and the local features. We have two major contributions. First, we pro...
详细信息
In this paper, we present a fusion approach to solve the nonrigid shape recovery problem, which takes advantage of both the appearance information and the local features. We have two major contributions. First, we propose a novel progressive finite Newton optimization scheme for the feature-based nonrigid surface detection problem, which is reduced to only solving a set of linear equations. The key is to formulate the nonrigid surface detection as an unconstrained quadratic optimization problem that has a closed-form solution for a given set of observations. Second, we propose a deformable Lucas-Kanade algorithm that triangulates the template image into small patches and constrains the deformation through the second-order derivatives of the mesh vertices. We formulate it into a sparse regularized least squares problem, which is able to reduce the computational cost and the memory requirement. The inverse compositional algorithm is applied to efficiently solve the optimization problem. We have conducted extensive experiments for performance evaluation on various environments, whose promising results show that the proposed algorithm is both efficient and effective.
We present the VROnSite platform that supports immersive training of first responder units' on-site squad leaders. Our training platform is fully immersive, entirely untethered to ease use and provides two means o...
详细信息
We present the VROnSite platform that supports immersive training of first responder units' on-site squad leaders. Our training platform is fully immersive, entirely untethered to ease use and provides two means of navigation-abstract and natural walking-to simulate stress and exhaustion, two important factors for decision making. With the platform's capabilities, we close a gap in prior art for first responder training. Our research is closely interlocked with stakeholders from multiple fire brigades to gather early feedback in an iterative design process. In this paper, we present the system's design rationale, provide insight into the process of training scenario development and present results of a user study with 41 squad leaders from the firefighting domain. Virtual disaster environments with two different navigation types were evaluated using quantitative and qualitative measures. Participants considered our platform highly suitable for training of decision making in complex first responder scenarios and results show the importance of the provided navigation technologies in this context.
This paper introduces a texture representation suitable for recognizing images of textured surfaces under a wide range of transformations, including viewpoint changes and nonrigid deformations. At the feature extracti...
详细信息
This paper introduces a texture representation suitable for recognizing images of textured surfaces under a wide range of transformations, including viewpoint changes and nonrigid deformations. At the feature extraction stage, a sparse set of affine Harris and Laplacian regions is found in the image. Each of these regions can be thought of as a texture element having a characteristic elliptic shape and a distinctive appearance pattern. This pattern is captured in an affine-invariant fashion via a process of shape normalization followed by the computation of two novel descriptors, the spin image and the RIFT descriptor. When affine invariance is not required, the original elliptical shape serves as an additional discriminative feature for texture recognition. The proposed approach is evaluated in retrieval and classification tasks using the entire Brodatz database and a publicly available collection of 1,000 photographs of textured surfaces taken from different viewpoints.
We introduce a technique to synthetically increase the framerate of semi-repetitive videos (i.e., videos of motion that repeats but not in an identical fashion) to aid in visualization. By reordering and combining fra...
详细信息
We introduce a technique to synthetically increase the framerate of semi-repetitive videos (i.e., videos of motion that repeats but not in an identical fashion) to aid in visualization. By reordering and combining frames from all repetitions, we produce a single non-repetitive sequence with much higher temporal resolution. Then, we use a novel frame warping technique based on a dense corrective flow to counteract differences between repetitions. The resulting video maintains smoothness of motion and additionally allows for seamless, infinite looping. We demonstrate the effectiveness of the proposed solution both quantitatively, by measuring the improvement over existing methods, and qualitatively, by performing a user evaluation and providing several examples in the article and accompanying video.
Convolutional neural networks (CNNs) are widely used in machine learning (ML) applications such as imageprocessing. CNN requires heavy computations to provide significant accuracy for many ML tasks. Therefore, the ef...
详细信息
Convolutional neural networks (CNNs) are widely used in machine learning (ML) applications such as imageprocessing. CNN requires heavy computations to provide significant accuracy for many ML tasks. Therefore, the efficient implementations of CNNs to improve performance using limited resources without accuracy reduction is a challenge for ML systems. One of the architectures for the efficient execution of CNNs is the array-based accelerator, that consists of an array of similar processing elements (PEs). The array accelerators are popular as high-performance architecture using the features of parallel computing and data reuse. These accelerators are optimized for a set of CNN layers, not for individual layers. Using the same accelerator dimension size to compute all CNN layers with varying shapes and sizes leads to the resource underutilization problem. We propose a flexible and scalable architecture for array-based accelerator that increases resource utilization by resizing PEs to better match the different shapes of CNN layers. The low-cost partial reconfiguration improves resource utilization and performance, resulting in a 23.2% reduction in computational times of GoogLeNet compared to the state-of-the-art accelerators. The proposed architecture decreases the on-chip memory access rate by 26.5% with no accuracy loss.
We develop a mathematical framework for quantifying and understanding multidimensional frequency modulations in digital images. We begin with the widely accepted definition of the instantaneous frequency vector ( IF) ...
详细信息
We develop a mathematical framework for quantifying and understanding multidimensional frequency modulations in digital images. We begin with the widely accepted definition of the instantaneous frequency vector ( IF) as the gradient of the phase and define the instantaneous frequency gradient tensor ( IFGT) as the tensor of component derivatives of the IF vector. Frequency modulation bounds are derived and interpreted in terms of the eigendecomposition of the IFGT. Using the IFGT, we derive the ordinary differential equations ( ODEs) that describe image flowlines. We study the diagonalization of the ODEs of multidimensional frequency modulation on the IFGT eigenvector coordinate system and suggest that separable transforms can be computed along these coordinates. We illustrate these new methods of image pattern analysis on textured and fingerprint images. We envision that this work will find value in applications involving the analysis of image textures that are nonstationary yet exhibit local regularity. Examples of such textures abound in nature.
Two online meetings of the JRTIP editorial board were held in 2021 and based on the discussions at these meetings, several steps were taken to shorten the review cycle time to one month for the first round of reviews ...
详细信息
Two online meetings of the JRTIP editorial board were held in 2021 and based on the discussions at these meetings, several steps were taken to shorten the review cycle time to one month for the first round of reviews and two weeks for the second round of reviews.
A new publication model is being considered and discussed with Springer for Volume 19 in 2022 which is called Continuous Article Publishing (or CAP).
Furthermore, since the new impact factor computational approach now includes online papers with DOIs, impact factor would not get affected by adopting the CAP model.
暂无评论