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.
Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in their building modules. In this work, we introduce two new modules to enhance the transformation modeling capability of CNNs, namely, deformable convolution and deformable RoI pooling. Both are based on the idea of augmenting the spatial sampling locations in the...
To predict a set of diverse and informative proposals with enriched representations, this paper introduces a differentiable Determinantal Point Process (DPP) layer that is able to augment the object detection architectures. Most modern object detection architectures, such as Faster R-CNN, learn to localize objects by minimizing deviations from the ground truth, but ignore correlation between multiple...
In dynamic object detection, it is challenging to construct an effective model to sufficiently characterize the spatial-temporal properties of the background. This paper proposes a new Spatio-Temporal Self-Organizing Map (STSOM) deep network to detect dynamic objects in complex scenarios. The proposed approach has several contributions: First, a novel STSOM shared by all pixels in a video frame is...
Automatic target generation process (ATGP) has been widely used for unsupervised hyperspectral target detection. It implements a succession of orthogonal subspace projections (OSPs) to extract targets of interest without prior knowledge. This paper extends ATGP to a kernel version of ATGP, called kernel ATGP (KATGP) to further deal with linear non-separation problem. It introduces nonlinear kernels...
This paper proposes a target detector based on kernel sparse and spatial constraint for hyperspectral imagery (HSI). Due to the nonlinear and structural features of HSI data, sparse representation and spatial constraint are taken into consideration. Firstly, we construct a dictionary to represent the target pixels within a small neighborhood by a linear combination of samples. Then, these targets...
Deep learning is becoming increasingly popular for a wide variety of applications including object detection, classification, semantic segmentation and natural language processing. Convolutional neural networks (CNNs) are a type of deep neural network that achieve high accuracy for these tasks. CNNs are hierarchical mathematical models comprising billions of operations to produce an output. The high...
Infrared polarization imaging detection can be used to obtain not only the polarization state but also the radiation of target. With this method, the target that traditional photometry cannot detect can be settled. The degree and angle of polarization that used in polarization detection reflect different physical properties, and it is seriously redundancy along with intensity of images. A target detection...
The given work describes a new technique of image segmentation, in particular for building detection on radar or infrared Earth-observation images. The method is based on property of most man-made objects which consist in straight edges and mostly right angles. The developed 2D adaptive image filter assists to detect straight edges even if given image fragment has a low contrast and has been extremely...
The manual process for privacy setting could be very time-consuming and challenging for common users. By assuming that there are hidden correlations between the visual properties of images (i.e., visual features) or object classes and the privacy settings for image sharing, an effective algorithm is developed in this paper to achieve automatic prediction of image privacy, so that the best-matching...
Deep Convolutional Neural Networks based object detection has made significant progress recent years. However, detecting small scale objects is still a challenging task. This paper addresses the problem and proposes a unified deep neural network building upon the prominent Faster R-CNN framework. This paper has two main contributions. Firstly, an Atrous Region Proposal Network (ARPN) is proposed to...
Diffusion maps, when applied to large datasets, are typically constructed by a process of sampling and out-of-sample function extension. However, the performance of anomaly detection in large data when using diffusion maps is sensitive to the chosen samples. In this paper we propose an iterative data-driven approach to improve the sample set and diffusion maps representation. By updating the sample...
Deep Learning (DL), especially Convolutional Neural Networks (CNN), has become the state-of-the-art for a variety of pattern recognition issues. Technological developments have allowed the use of high-end General Purpose Graphic Processor Units (GPGPU) for accelerating numerical problem solving. They resort no only to lower computational time, but also allow considering much larger networks. Hence,...
Target detection is a hard real-time task for video and image processing. This task has recently been accomplished through the feedforward process of convolutional neural net-works (CNN), which is usually accelerated by general-purpose graphic units (GPUs). However, there is a challenge for this task. The running speed remains to be improved. In this paper, we present an efficient image combination...
Segmenting moving objects from the background is an important step in intelligent video applications, such as intelligent video surveillance. Many approaches use optimal threshold for the separation of moving object from a background. However they suffer from two limitations: It is not only difficult to compute an optimal threshold, but also ignore the correlation that exists between the intensity...
Automated Dial Reading (ADR) using image processing is a challenging task that has to deal with the dynamics of real time environment. Literature contains limited research work for ADR that is based on background subtraction, object tracking, and pattern recognition. These methods suffer from dynamic environment such as: varying light intensity, poor resolution, and vibrations in capturing device...
Separating the foreground objects from the complex background in a static image is one of the research hot spots in computer vision. Due to lack of motion information, most of the current approaches only explore local object cues in the segment-level which easily suffer from not only the view and illumination changes, but also deformation and occlusion. This paper proposed a new multi-class object...
This paper presents a statistical treatment of background modeling for use in target detection, where the global information and local information is added into the statistical framework to construct a robust background model to achieve accurate object detection results. Specifically, a novel self-adaptive Gaussian mixture model is proposed to construct a statistical background model based on the...
Artificial awareness is an interesting way of realizing artificial intelligent perception for machines. Since the foreground object can provide more useful information for perception and informative description of the environment than background regions, the informative saliency characteristics of the foreground object can be treated as a important cue of the objectness property. Thus, a sparse reconstruction...
Various active learning methods have been proposed for image classification problems, while very little work addresses object detection. Measuring the informativeness of an image based on its object windows is a key problem in active learning for object detection. In this paper, an image selection method to select the most representative images is proposed based on measuring their object window distributions...
This paper surveys the learning algorithms of visual features representation and the computational modelling approaches proposed with the aim of developing better artificial object recognition systems. It turns out that most of the learning theories and schemas have been developed either in the spirit of understanding biological facts of vision or designing machines that provide better or competitive...
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.