Steerable Camera Research Articles

AcTrak: Controlling a Steerable Surveillance Camera using Reinforcement Learning

Steerable cameras that can be controlled via a network, to retrieve telemetries of interest have become popular. In this paper, we develop a framework called AcTrak , to automate a camera’s motion to appropriately switch between (a) zoom ins on existing targets in a scene to track their activities, and (b) zoom out to search for new targets arriving to the area of interest. Specifically, we seek to achieve a good trade-off between the two tasks, i.e., we want to ensure that new targets are observed by the camera before they leave the scene, while also zooming in on existing targets frequently enough to monitor their activities. There exist prior control algorithms for steering cameras to optimize certain objectives; however, to the best of our knowledge, none have considered this problem, and do not perform well when target activity tracking is required. AcTrak automatically controls the camera’s PTZ configurations using reinforcement learning (RL ), to select the best camera position given the current state. Via simulations using real datasets, we show that AcTrak detects newly arriving targets 30% faster than a non-adaptive baseline and rarely misses targets, unlike the baseline which can miss up to 5% of the targets. We also implement AcTrak to control a real camera and demonstrate that in comparison with the baseline, it acquires about 2× more high resolution images of targets.

Flying Chameleons: A New Concept for Minimum-Deployment, Multiple-Target Tracking Drones.

In this paper, we aim to open up new perspectives in the field of autonomous aerial surveillance and target tracking systems, by exploring an alternative that, surprisingly, and to the best of the authors’ knowledge, has not been addressed in that context by the research community thus far. It can be summarized by the following two questions. Under the scope of such applications, what are the implications and possibilities offered by mounting several steerable cameras onboard of each aerial agent? Second, how can optimization algorithms benefit from this new framework, in their attempt to provide more efficient and cost-effective solutions on these areas? The paper presents the idea as an additional degree of freedom to be exploited, which can enable more efficient alternatives in the deployment of such applications. As an initial approach, the problem of the optimal positioning with respect to a set of targets of one single agent, equipped with several onboard tracking cameras with different or variable focal lengths, is addressed. As a consequence of this allowed heterogeneity in focal lengths, the notion of distance needs to be adapted into a notion of optical range, as the agent can trade longer Euclidean distances for correspondingly longer focal lengths. Moreover, the proposed optimization indices try to balance, in an optimal way, the verticality of the viewpoints along with the optical range to the targets. Under these premises, several positioning strategies are proposed and comparatively evaluated.

Challenge and Advantage of Materials in Design and Fabrication of Composite UAV

Unmanned Aerial Vehicles (UAVs) is constructed with composite materials, including its aerodynamic surfaces wings, horizontal stabilizer, and rudder. Three main constituents of our model is Kevlar 49, carbon fibre, glass fibre. KALPANA-1 is a pusher type, tail dragger, fixed wing radio controlled medium range remotely operated composite aircraft. This is designed for Aerial surveillance & reconnaissance. It is a kind of drone which has capability of carrying 2kg of operational payload as surveillance camera and its gimbal mount unit. It can be equipped with on-board sensors for weather monitoring as civilian use of UAV. It has a carbon frame body which makes it hassle to work in all-weather environment, protecting its electronics and payload from external entities. KEVLAR-49 is reinforced at the bottom part of the fuselage to overcome hard landing & impacts. The main disadvantage of using carbon fibre is that it partially shelled the RC signals so we fixed our receiver outside of the fuselage. For camera mounting purpose a duct made in front side of fuselage. It can use as other diplomatic mission as mounting camera and robotic arm for weight lifting mechanism. Some further upgrading two semi ducts at two side of the front face of the fuselage for steerable camera mounting. Aircraft using single electrical propulsive system and large wings which helps it for a long range, good endurance and smooth steady flight. Composite materials don’t break easily, but that makes it hard to analyses if the interior structure has been damaged at all. In contrast, aluminum bends and dents easily, making it easy to detect structural damage; the same damage is much harder to detect with composite structures. Repairs can also be more difficult when a composite surface is damaged. Finally, composite materials can be expensive, but the high initial costs are typically offset by long-term cost savings and life cycle more compare to cost of material.

A remote‐controlled observatory for behavioural and ecological research: A case study on emperor penguins

Abstract Long‐term photographic recordings of animal populations provide unique insights into ecological and evolutionary processes. However, image acquisition at remote locations under harsh climatic conditions is highly challenging. We present a robust, energetically self‐sufficient and remote‐controlled observatory designed to operate year‐round in the Antarctic at temperatures below −50°C and wind speeds above 150 km/h. The observatory is equipped with multiple overview cameras and a high resolution steerable camera with a telephoto lens for capturing images with high spatial and temporal resolution. Our observatory has been in operation since 2013 to investigate an emperor penguin (Aptenodytes forsteri) colony at Atka Bay near the German Neumayer III research station. Data recorded by this observatory give novel biological insights in animal life cycle and demographic trends, but also in collective and individual behaviour. As an example, we present data showing how wind speed and direction influence movements of the entire colony and of individual penguins. We also estimate daily fluctuations in the total number of individuals present at the breeding site. Our results demonstrate that remote‐controlled observation systems can bridge the gap between remote sensing, simple time‐lapse recording setups, and on‐site observations by human investigators to collect unique biological datasets of undisturbed animal populations.

4-mm-diameter three-dimensional imaging endoscope with steerable camera for minimally invasive surgery (3-D-MARVEL).

High-resolution three-dimensional (3-D) imaging (stereo imaging) by endoscopes in minimally invasive surgery, especially in space-constrained applications such as brain surgery, is one of the most desired capabilities. Such capability exists at larger than 4-mm overall diameters. We report the development of a stereo imaging endoscope of 4-mm maximum diameter, called Multiangle, Rear-Viewing Endoscopic Tool (MARVEL) that uses a single-lens system with complementary multibandpass filter (CMBF) technology to achieve 3-D imaging. In addition, the system is endowed with the capability to pan from side-to-side over an angle of [Formula: see text], which is another unique aspect of MARVEL for such a class of endoscopes. The design and construction of a single-lens, CMBF aperture camera with integrated illumination to generate 3-D images, and the actuation mechanism built into it is summarized.

The axial continuous-flow blood pump: Bench evaluation of changes in flow associated with changes of inflow cannula angle

Changes in the geometry of the HeartMate II (HMII) inflow cannula have been implicated in device thrombosis post-implant. The purpose of this in vitro study was to evaluate what effects changing the angle of the cannula in relation to the pump may have on pump flow and arterial pressure, under simulated inflow conditions. The HMII with an inflow cannula was mounted on a mock loop consisting of a pulsatile pneumatic ventricle to simulate the native ventricle. The angles of the HMII in relation to the inflow cannula were adjusted by separate fixed gooseneck holders. A custom-made miniature steerable camera was introduced into a flexible portion of the HMII inflow cannula. Endoscopic views of various types of inflow cannula constriction (bending, squeezing, stretching and twisting) were recorded, and pump flow and systemic arterial pressure (AoP) were assessed during each simulation. Baseline mean pump flow (3.5 liters/min) and mean AoP (91.5 mm Hg) were unchanged by bending maximally in 2 different directions, twisting up to 30°, stretching (compression or extension), or occluding the inflow graft <90%. However, mean pump flow and mean AoP decreased substantially when the inflow graft became occluded by ≥90% by sliding or squeezing. "Less-than-critical" obstruction (what we define here as <90%) of the HMII inflow cannula did not reveal substantial changes in pump flow or AoP. Data suggest that a major alteration to inflow cannula geometry is required to achieve clinically relevant hemodynamic changes. These data confirm that minor changes in angulation of the inflow cannula have no impact on flow through the device.

Sanovas Micro CMOS (Complementary Metal Oxide Semiconductor) Steerable Camera and Guide-Sheath System: Novel Imaging Role in Flexible Bronchoscopy

Sanovas Micro CMOS (Complementary Metal Oxide Semiconductor) Steerable Camera and Guide-Sheath System: Novel Imaging Role in Flexible Bronchoscopy

Online Diarization of Streaming Audio-Visual Data for Smart Environments

For an environment to be perceived as being smart, contextual information has to be gathered to adapt the system's behavior and its interface towards the user. Being a rich source of context information speech can be acquired unobtrusively by microphone arrays and then processed to extract information about the user and his environment. In this paper, a system for joint temporal segmentation, speaker localization, and identification is presented, which is supported by face identification from video data obtained from a steerable camera. Special attention is paid to latency aspects and online processing capabilities, as they are important for the application under investigation, namely ambient communication. It describes the vision of terminal-less, session-less and multi-modal telecommunication with remote partners, where the user can move freely within his home while the communication follows him. The speaker diarization serves as a context source, which has been integrated in a service-oriented middleware architecture and provided to the application to select the most appropriate I/O device and to steer the camera towards the speaker during ambient communication.

A camera-based support system with augmented reality functions for manual tasks in radioactive production environments

This paper presents a support system dedicated to the improvement of the often unfavorable working conditions for manual tasks in radioactive production environments. Its main goals are to increase operational safety and comfort, to diminish costly mistakes and to improve the radiation protection for the operators, thus to reduce the permanent threat of nuclear radiation. The support system consists of a steerable camera system with intuitive control in combination with the information technology augmented reality that supplies the user with necessary data, required details and working instructions. Additionally to its ability to ease the adverse operating conditions, the support system offers a variety of additional features that create further benefit, like the possibility to have a closer look on tiny parts due to the zoom function, the excellent quality of the view and helpful extra information superimposed directly into the view of the operator.

From virtual slides to virtual pathology institution: the future of tissue-based diagnosis?

In this paper, we describe an augmented reality tool for collaborative work called the MagicBoard. The MagicBoard is based on an ordinary white board which has been enhanced by a video-projector and a steerable camera. A supervisor coordinates the cooperation of several modules including gesture recognition, finger tracking and white board scanning for digitalisation of the content. The gesture recognition module uses an approach based on local spatio-temporal appearance of activities. The tracking module is designed for use with cluttered backgrounds and variable lighting conditions. The white board scanner eliminates global luminosity differences by adaptive thresholding and the result can serve to digitise the content of the board. The supervisor is based on a rule-based architecture and is easily extendable. The selected modules fit together to a compact system, that largely increases the functionality of a white board and makes it a useful tool in the future office environments.

The role of emerging technologies in imagery for disaster monitoring and disaster relief assistance

Emerging technologies enable new concepts in low-cost Earth observing constellations. In this paper we posit an architecture that addresses a largely unmet need for real-time disaster monitoring and disaster relief assistance. A satellite based system capable of being controlled from, and downlinking data to, a relatively primitive ground site would be invaluable for focusing disaster relief efforts. In this concept, real-time continuous high resolution imagery from a system capable of selecting wavelength bands for specific needs would be implemented. The system is comprised of elements at geosynchronous and L1 altitudes. From geosynchronous altitude, focused high-value imagery is provided by steerable cameras with a 250m resolution. At L1, full disk imagery provides context for mesoscale high resolution imagery.

MagicBoard: A contribution to an intelligent office environment

In this paper, we describe an augmented reality tool for collaborative work called the MagicBoard. The MagicBoard is based on an ordinary white board which has been enhanced by a video-projector and a steerable camera. A supervisor coordinates the cooperation of several modules including gesture recognition, finger tracking and white board scanning for digitalisation of the content. The gesture recognition module uses an approach based on local spatio-temporal appearance of activities. The tracking module is designed for use with cluttered backgrounds and variable lighting conditions. The white board scanner eliminates global luminosity differences by adaptive thresholding and the result can serve to digitise the content of the board. The supervisor is based on a rule-based architecture and is easily extendable. The selected modules fit together to a compact system, that largely increases the functionality of a white board and makes it a useful tool in the future office environments.