The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The strong abilities of deep learning models have been shown in the area of text detection in natural scene images. In this paper, we introduce a new method called deep metric learning for scene text detection. We use the triplet loss [1] to replace the traditional loss function (Softmax) and learn a mapping from image regions to a compact Euclidean space where distances correspond to a measure of...
Science of Neural Networks, and even much more so computing applications, have undergone developments beyond any predictions since McCullock-Pitts artificial neuron (1943) up via Hopfield's neurons (1982, 1984) to Kasabov spiking-neurons neucube (2014) and evolving connectionist systems (2003). Still computational functionality of all kinds of neural network implies guaranteed operating steady-state...
This paper presents a model for the deviation of distances measured by radar and by optical sensors (3D point clouds). The measured 3D point clouds are typically clustered to objects and the cluster centers are then associated with the radar targets. However, the physical extent and the object geometry cause a divergence of the measured radar range from the cluster centers of the 3D point cloud. Existing...
In this paper we introduce the TorontoCity benchmark, which covers the full greater Toronto area (GTA) with 712.5km2 of land, 8439km of road and around 400, 000 buildings. Our benchmark provides different perspectives of the world captured from airplanes, drones and cars driving around the city. Manually labeling such a large scale dataset is infeasible. Instead, we propose to utilize different sources...
In this paper, a low-complexity robust adaptive beamforming method is proposed to against array steering vector (ASV) mismatch and effects of low snapshots. The robustness of proposed method depends on two aspects: the non-uniform diagonal loading which prevent the beamformer weight vector from converging to the noise components and variable diagonal loading factor can be changed adaptively when the...
The robustness of adaptive beamforming is relate to the input signal-to-noise ratio (SNR). In order to further improve the performance of input SNR estimation, a modified method of input SNR estimation for robust adaptive beamforming is proposed. Comparatively accurate value of the input SNR can be obtained by the proposed method, especially when the input SNR exceeds 0 dB. When the proposed method...
In this paper, a novel quality-monitor method of inkjet-printed electronics based on terahertz (THz) sensing is presented. Specifically, two different approaches, namely THz reflection spectroscopy and THz near-field scanning, are proposed.
Neural networks have demonstrated promising results for a wide range of applications. The proposed techniques employ different architectures and objective functions to adapt to the application while enabling a feasible implementation. Commonly used objective functions for network optimization are based on the cross entropy between the empirical distribution of the training data and the model distribution...
Surface registration is an inevitable step for solving the correspondence problem in statistical shape modeling and useful for automatic 3D segmentation of objects of a certain shape. Common techniques for a pairwise surface registration rely either on a point-based or a mesh-based representation of the source (moving) and the target (fixed) surface. Iterative closest point (ICP) algorithms operate...
Despite the widespread installation of access control systems in all places where authorized users to enter, access control systems are still not immature due to the limited technology of convenience, security and low latency. Existing biological method based systems are relatively reliable, such as fingerprint identification, face perception and iris recognition. However, these techniques require...
Multi-carrier (MC) multiple-input multiple-output (MIMO) radar offers an additional degree of freedom in the array optimization through the carrier frequencies. In this paper, we study the MC-MIMO array optimization with respect to the direction of arrival (DOA) estimation based on the Cramer-Rao bound (CRB). In particular, we choose the transmit and receive antenna positions as well as the carrier...
We present in this work a novel approach for the reconstruction of wired network topologies from reflection measurements. Existing approaches state the network reconstruction as discrete optimization problem, which is difficult to solve. The (discrete) topology is optimized while the cable lengths are a secondary result. The contribution of this paper is the formulation of the topology reconstruction...
Automatic segmentation of distinct muscles is a crucial step for quantitative analysis of muscle's tissue properties. Magnetic resonance (MR) imaging provides a superior soft tissue contrast and noninvasive means for assessing muscular characteristics. However, automatic segmentation of muscles using common morphological MR imaging is very challenging as the intensities and textures of adjacent muscles...
Supervised event-based NILM systems usually require a large set of labeled training data to achieve high classification accuracies. To minimize the cost of labeling a sufficient amount of events, active learning can be employed. By using only a small set of labeled samples for initial training followed by selecting only the most informative samples to be labeled, the total number of labeled training...
A comparative analysis of the plug-in fuel cell vehicles (PFCV) is studied regarding different topologies, drive cycles and control strategies. To improve the performance of the PFCV, an optimization strategy is proposed at first by regulating the power distribution between the battery and the PEMFC system. Then, a direct multiple shooting (DMS) algorithm is used to solve this nonlinear programming...
Nonlinear spectral unmixing based on the bilinear mixture models has received much attention recently. In this paper, an abundance estimation algorithm based on the geometric characteristics of bilinear mixture models is proposed. By representing the models' bilinear terms as the linear contribution of an extra vertex that concentrates the common nonlinear mixing effect, solving the complex bilinear...
Nonnegative matrix factorization (NMF) is often used for unsupervised spectral unmixing in recent years. In this paper, a constrained NMF algorithm based on the bilinear mixture models for unsupervised nonlinear spectral unmixing is proposed. By using a distance measure without dimension reduction, data's projection on a group of constructed hyperplanes representing the nonlinearity are obtained so...
Change detection in multitemporal hyperspectral images (HSI) can be regarded as a classification task, consisting of two steps: change feature extraction and identification. To extract clean change features from heavily corrupted spectral change vectors (SCV) of multitemporal HSI, this paper proposes a novel spectrally-spatially regularized low-rank and sparse decomposition model (LRSDSS). It exploits...
Nonnegative Matrix Factorization (NMF) has been applied to hyperspectral unmixing for a few years. To relieve the non-convex problem, different constraints are imposed on NMF. But these constraints are added only on endmember or abundance. Simultaneously imposing constraints on endmember and abundance has not been tried yet. In this paper, we impose constraints on endmember and abundance at the same...
A technique called active disturbance rejection control is proposed to realize the acceleration/deceleration process of aero-engine in a more flexible manner. According to the requirements of response time for acceleration/deceleration state, tracking differentiator is utilized to arrange the expected transition trajectories. An extended nonlinear state observer is introduced to estimate the rotor...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.