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 imaging has become a staple tool used by scientists exploring the deep ocean. Advanced camera systems are able to combine quantitative measurements from in-situ sensors with qualitative imaging to provide high fidelity multi-dimensional datasets which can be used to support a wide range of science questions. This includes benthic characterization and mapping, identification of biota and...
Consumer-grade RGB-D cameras capture RGB images along with per-pixel depth information, and because of their limited cost and ability to measure distances at a high frame rate, have been used in robotics and computer vision application. However, drawbacks include the repeatability and accuracy of RGB-D cameras for object detection and localization. This paper investigates and compares RGB-D cameras'...
Stereo matching systems that generate dense, accurate, robust and real-time disparity maps are quite attractive for a variety of applications. Most of the existing stereo matching systems that fulfill to all of these requirements adopt the Semi-Global Matching (SOM) technique. This work proposes a scalable architecture based on a systolic array, fully pipeline. The design builds on a combination of...
One of the solutions of depth imaging of moving scene is to project a static pattern on the object and use just a single image for reconstruction. However, if the motion of the object is too fast with respect to the exposure time of the image sensor, patterns on the captured image are blurred and reconstruction fails. In this paper, we impose multiple projection patterns into each single captured...
Smartphones are a popular device class for mobile Augmented Reality but suffer from a limited input space. Around-device interaction techniques aim at extending this input space using various sensing modalities. In this paper we present our work towards extending the input area of mobile devices using front-facing device-centered cameras that capture reflections in the cornea. As current generation...
Exploiting camera sensors to conduct intruder detection has attracted a lot of research attention. Different from the traditional sensor with omni-directional sensing model, a camera sensor usually has a specified direction with a fixed sensing angle of sensing area. The sensing quality of coverage is critical to the application of coverage scheme. In this paper, we first investigate the complete...
For augmented reality (AR), computer-generated virtual objects are overlapped on the image of a real world. Since a disturbing real object (e.g, a moving human) on the display of an AR device reduces the immersion to AR experiences, the virtual objects need to be augmented after eliminating the disturbing object. From this motivation, this paper presents mediated reality (MR) photography, where the...
Intruder detection in a protected zone can be performed by the physical protection which acts within the object's perimeter and survey's it (patrols, monitoring screens of CCTV systems, etc.), but intruder detection can be also done using active protection elements. Active protection elements include alarm systems (electronic safety and distress alarm systems, CCTV security systems, system for control...
3D images of moving objects can be achieved with a surveillance camera and four white light-emitting diodes. With these simple components, an imaging rate of 15 Hz is possible, limited by the camera framerate.
High-accuracy remote position measurements are regarded in applications where different systems or components need to be placed in precise configurations. There are some cases in which it is impossible to define an absolute, precise reference frame and the application should rely only on relative measurements. In recent years, fiducial markers began to provide an interesting alternative to standard...
The complete plenoptic function records radiance of rays from every location, at every angle, for every wavelength and at every time. The signal is multi-dimensional and has long relied on multi-modal sensing such as hybrid light field camera arrays. In this paper, we present a single camera hyperspectral light field imaging solution that we call Snapshot Plenoptic Imager (SPI). SPI uses spectral...
Researchers have developed excellent feed-forward models that learn to map images to desired outputs, such as to the images’ latent factors, or to other images, using supervised learning. Learning such mappings from unlabelled data, or improving upon supervised models by exploiting unlabelled data, remains elusive. We argue that there are two important parts to learning without annotations: (i) matching...
In practical CCTV applications, there are problems of the camera with low resolution, camera fields of view, and lighting environments. These could degrade the image quality and it is difficult to extract useful information for further processing. Super-resolution techniques have been proposed widely by the researchers. However, many approaches are complex and are difficult to use in practical scenarios...
The ability to identify, follow, approach, and intercept a non-stationary target is a desirable capability of autonomous micro aerial vehicles (MAV) and puts high demands on reliable target perception, fast trajectory planning, and stable control. We present a fully autonomous MAV that lands on a planar platform mounted on a ground vehicle, relying only on onboard sensing and computing. We evaluate...
Autonomous vehicles, as people all know, will have great impact to human transportation in the near future. In the vision system of autonomous vehicles, the lane detection has always been an important part. This paper describes an algorithm which can make the lane detection process faster and more applicable. The algorithm is mainly based on lane mark detection and Reduced Resolution lane detection...
EUS is performed with radial imaging perpendicular to the endoscope shaft, and lateral imaging parallel to the shaft and biopsy channel. Radial imaging is preferred for some diagnostic and staging purpose because of ease of use as well as the production of a full 360-degree field of view. For operation smoothly and safety, the smaller external diameter (less than 11mm), the higher optical and ultrasonic...
The paper presents an approach to localize human body joints in 3D coordinates based on a single low resolution depth image. First a framework to generate a database of 80k realistic depth images from a 3D body model is described. Then data preprocessing and normalization procedure, and DNN and MLP artificial neural networks architectures and training are presented. The robustness against camera distance...
Face based deception detection systems are non-invasive and are more convenient than other deception detection systems as the facial images can be captured and analyzed without the knowledge of the subject being analysed. Deception detection research studies show that blink rate is an indicator of deception. Some studies concluded that blink rate increases during deception, whereas some other researchers...
This paper presents a novel terahertz reflection imaging set-up, where a plenoptic camera is used in lieu of a single pixel detector in a direct projection mode. This configuration allows for post-process adjustments to the optical alignment, field-of-view and sensor directivity, all of which influence the final image quality. The optimal image synthesis is demonstrated with a highly directive and...
In this paper, a new multi-resolution CMOS imager sensor with trapezoid pixel array, called TZOID, is presented. It was designed for traffic monitoring to detect the speed and location vehicles approaching a signized intersection. It composes of significantly less number of pixels than a comparable image sensor used in similar application. The unique trapezoid image sensor design eliminates computationally...
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.