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.
Underwater image formation is degraded by several factors, which causes the ocean to be a challenging environment for image processing. This paper aims to improve the visual servoing capability of an autonomous underwater vehicle by using pre-processing algorithms to improve the image quality. We used artificial fiducial markers to feed the visual controller. Therefore, three different methods for...
In this paper, we present the first multilevel implementation of the Harris-Stephens corner detector and the ORB feature extractor running on FPGA hardware, for computer vision and robotics applications. ORB is a fundamental component of many robotics applications, and requires significant computation. The design has been validated both in behavioural simulation and in implementation on an Arria V...
This paper presents a low-cost silicon-based terahertz computed tomography system for industrial volumetric imaging. The THz-CT scanner comprises a single radiator and detector at 490 GHz and a PTFE-lens based optical train that is fixed inside a portable cage system. It features a 2.5 mm resolution limited by the effective lens aperture and offers up to 62 dB SNR in chopped and 38 dB in a continuous-wave...
Spectral imaging is useful in a wide range of applications for non-invasive detection and classification. However, the massive amount of involved data increases its processing and storing costs. In contrast, compressive spectral imaging (CSI) establishes that the three-dimensional data cube can be recovered from a small set of projections, that are generally captured in 2-dimensional detectors. Furthermore,...
Automatic image cropping techniques have been developed recently to address the mismatch between the native display and image characteristics, such as resolution, aspect ratio, etc. These techniques usually rely on determining the importance of various regions in the image, or the aesthetic appeal of the final cropped image. In this work, we present a cropping method that combines bottom-up visual...
We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. First we propose various improvements to the YOLO detection method, both novel and drawn from prior work. The improved model, YOLOv2, is state-of-the-art on standard detection tasks like PASCAL VOC and COCO. Using a novel, multi-scale training method the same YOLOv2 model can run...
Edge detection had made significant progress with the help of deep Convolutional Networks (ConvNet). ConvNet based edge detectors approached human level performance on standard benchmarks. We provide a systematical study of these detector outputs, and show that they failed to accurately localize edges, which can be adversarial for tasks that require crisp edge inputs. In addition, we propose a novel...
Though tremendous strides have been made in object recognition, one of the remaining open challenges is detecting small objects. We explore three aspects of the problem in the context of finding small faces: the role of scale invariance, image resolution, and contextual reasoning. While most recognition approaches aim to be scale-invariant, the cues for recognizing a 3px tall face are fundamentally...
The detection and extraction of buildings using high resolution synthetic aperture radar (SAR) images has been the topic of recent discussions. In this paper, a framework for building extraction and classification is proposed. Buildings are classified into three kinds: commercial architecture, residential building and Industrial building, by the fusion of structure features (point-like, linear and...
In this paper, an improvement of fast image scaling algorithm, which produces image with wellpreserved edge, is proposed. The edge of the original image is detected by using four Sobel spatial operators. And the direction of edge is then measured by using two newly proposed edge detectors employing two threshold values. Based on these, pixels are interpolated adaptively, where edge pixels are interpolated...
Information on icebergs and ice islands is important for climate science and for various marine operations in Arctic and Antarctic. This work investigates capabilities of RADARSAT-2 polarimetric data for detection of icebergs in sea ice. Several iceberg detectors were analyzed with the full polarimetric data acquired in Fine Quad and Fine Quad Wide modes. The results of iceberg detection were validated...
A single pixel Holoscopy for 3D high resolution optical imaging acquisition method is proposed. By using compressive sensing theory in holoscopy, we fully reconstruct the wave field from a single hologram with only 10% sampling ratio.
Light scattering on diffuse rough surfaces was long assumed to destroy geometry and photometry information about hidden (non line of sight) objects making ‘looking around the corner’ (LATC) and ‘non line of sight’ (NLOS) imaging impractical. Recent work pioneered by Kirmani et al. [1], Velten et al. [2] demonstrated that transient information (time of flight information) from these scattered third...
This paper proposes a novel method to optimize bandwidth usage for object detection in critical communication scenarios. We develop two operating models of active information seeking. The first model identifies promising regions in low resolution imagery and progressively requests higher resolution regions on which to perform recognition of higher semantic quality. The second model identifies promising...
This paper deals with a design of specific marker detector and tracker for semiautonomous convoy purpose. The solution is based on computer vision. The detectors main requirement is the specific marker recognition ability for various environments. The next part of this paper deals with tracking of marker by KLT algorithm. This solution was primary designed for a semi-autonomous convoy task, where...
In this work, two enhancement methods are proposed to speed up junction detection performed by the JUDOCA detector. The first enhancement method minimizes the number of junction candidates on which the circular kernel is applied. This is achieved by introducing a suppression technique that takes both the thin and thick edge images into consideration. The second method works on relaxing the step of...
In this paper, a method for unknown object tracking in output images from 360-degree cameras called Modified Training-Learning-Detection (MTLD) is presented. The proposed method is based on the recently introduced Training-Learning-Detection (TLD) scheme in the literature. The flaws of the TLD approach have been detected and significant modifications are proposed to enhance and to elaborate the scheme...
Pedestrian detection from in-vehicle camera images for the purpose of advanced driver assistance systems is of particular importance in cases of low-resolution pedestrians, because it is desirable to detect the pedestrian as far from the vehicle as possible to effectively provide safe driving support for the driver. Most previous studies on pedestrian detection, however, have focused on pedestrians...
To solve the problem that there is few invariant features, which can be extracted from both images, to be matched for large changes of view, an efficient invariant image matching approach is presented. The proposed approach consists of two main steps. In the first step, we use the multi-resolution strategy to detect maximally stable extremal regions (MSERs) and obtain the geometric transformation...
Finding correspondences between two images of the same scene or object, taken from different viewpoints and in different conditions, is a challenging task. Furthermore, in the analysis of scientific imagery, it must be possible in terms of human perception to appreciate detected local features, thus making the task even more complex. A renowned generic feature detector, Maximally Stable Extremal Regions...
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.