Active Camera Research Articles

Implementation Mapping of the Collaborative University of California Teleophthalmology Initiative (CUTI): A Qualitative Study Using the Exploration, Preparation, Implementation, and Sustainment (EPIS) Framework.

Background This study aimed to investigate the rationale, barriers, and facilitators of teleretinal camera implementation in primary care and endocrinology clinics for diabetic retinopathy (DR) screening across University of California (UC) health systems utilizing the Exploration, Preparation, Implementation, and Sustainment (EPIS) framework. Methodology Institutional representatives from UC Los Angeles, San Diego, San Francisco, and Davis participated in a series of focus group meetings to elicit implementation facilitators and barriers for teleophthalmology programs within their campuses. Site representatives also completed a survey regarding their program's performance over the calendar year 2022 in the following areas: DR screening camera sites, payment sources and coding, screening workflows including clinical, information technology (IT), reading, results, pathologic findings, and follow-up, including patient outreach for abnormal results. Focus group and survey results were mapped to the EPIS framework to gain insights into the implementation process of these programs and identify areas for optimization. Results Four UC campuses with 20 active camera sites screened 7,450 patients in the calendar year 2022. The average DR screening rate across the four campuses was 55%. Variations between sources of payment, turn-around time, image-grading structure, image-report characteristics, IT infrastructure, and patient outreach strategies were identified between sites. Closing gaps in IT integration between data systems, ensuring the financial sustainability of the program, and optimizing patient outreach remain primary challenges across sites and serve as good opportunities for cross-institutional learning. Conclusions Despite the potential for long-term cost savings and improving access to care, numerous obstacles continue to hinder the widespread implementation of teleretinal DR screening. Implementation science approaches can identify strategies for addressing these challenges and optimizing implementation.

IoT-Integrated Smart Attendance and Attention Monitoring System For Primary and Secondary School Classroom Management

The monitoring of student attendance is a crucial aspect of the assessment of academic performance. The conventional methods for monitoring student attendance have inherent limitations in terms of both time efficiency and accuracy. Consequently, there is a clear need for a more expedient and precise attendance system. The objective of this research is to present the design of a real-time attendance recording and monitoring system for students from elementary school to senior high school, which will be implemented using the concept of the Internet of Things (IoT). The proposed system employs biometric technology in the form of face recognition. The methodology commences with the capture of images of students who leave the classroom during the instructional period via an active camera positioned on the classroom door. The system employs a Convolutional Neural Network (CNN) algorithm and a powerful computer vision tool, OpenCV, to perform real-time face recognition. Teachers will be informed of student absences and returns, as well as at the 15th and 30th minutes. An absence exceeding 30 minutes is classified as truancy. The integration of sophisticated technologies, such as machine learning and image processing, not only enhances the precision of attendance records but also equips educators with an efficient and automated system for streamlining classroom attendance management. This not only optimizes the learning environment but also facilitates more advanced and efficient pedagogical practices.

Active gas camera mass flow quantification (qOGI): Application in a biogas plant and comparison to state-of-the-art gas cams.

Gas cameras are primarily used to detect gas leaks, but their use has been increasingly extended to mass flow quantification (qOGI). We employ the previously published active illuminated gas camera [Bergau etal. "Real-time active-gas imaging of small gas leaks," J. Sens. Sens. Syst. 12, 61-68 (2023) and Bergau etal. "Flow rate quantification of small methane leaks using laser spectroscopy and deep learning," Process Saf. Environ. Prot. 182, 752-759 (2024)] in a real-world application for quantification, enhancing the camera with two new features: sensitivity adaptation and camera-gas distance detection. This technology was applied to a gas leak found in the pressure swing adsorption room of a biogas plant in Germany. We compare its performance with state-of-the-art quantification gas cameras (qOGI), such as Sensia Mileva 33. Such a comparison between active and passive gas cameras is possible for the first time due to the introduced sensitivity tuning. Additionally, we enclosed the gas leak and measure the methane concentration with a flame ionization detector, providing a gold standard for comparison. Our findings revealed relative offsets to our gold standard of -57% and +319% for the DAS-camera and the Sensia, respectively, suggesting that the accuracy of mass flow quantification could be improved through the use of active gas cameras.

Human Detection in Flood Using Drone

Drowning people in India approximately around 38000 peoples per year leads to dead finally because of, we have insufficient water rescue or timely emergency response to search and rescue team during emergency, also the lack of information to the rescue team about the drowning people place. We should believe that a few seconds' difference could have saved a person’s life. The timely information conveyed to the rescue team is also an important criterion for drowning to dead rate being very higher At first, we make a dataset, which contains many human targets at sea. Then, we improve the algorithm In the feature extraction network, we use the residual module with channel attention mechanism. Finally, on the settings of the raspberry pi Pico with GPS and GSM, we use a linear transformation method to deal with the python generated by clustering algorithm. The detection accuracy of the improved algorithm for human targets at sea is improved, which has a good detection effect. The drone with detecting and alerting with voice message to the Rescue Team at remote end with required all details about the drowning people make sense for faster rescue and save as the highest accuracy. The camera detection of the rescue Drone had a proper in that the range of the active camera and the speed of the video with Wi-Fi to the control room also optimal for the detection to work properly.

Optimizing Camera Motion with MCTS and Target Motion Modeling in Multi-Target Active Object Tracking

In this work, we are dedicated to multi-target active object tracking (AOT), where the goal is to achieve continuous tracking of targets through real-time control of camera. This form of active camera control can be applied to unmanned aerial vehicles (UAV), intelligent robots, and sports events. Our work is conducted in an environment featuring multiple cameras and targets, where our goal is to maximize target coverage. Contrasting with previous research, our work introduces additional degrees of freedom for the cameras, allowing them not only to rotate but also to move along boundary lines. In addition, we model the motion of target to predict the future position of the target in environment. With target’s future position, we use Monte Carlo Tree Search (MCTS) method to find the optimal action of camera. Since the action space is large, we propose to leverage the action selection from multi-agent reinforcement learning (MARL) network to prune the search tree of Monte Carlo Tree Search method, so as to find the optimal action more efficiently. We establish a multi-target 2D environment to simulate several sports games, and experimental results demonstrate that our method can effectively improve the target coverage. The code is available at: http://github.com/HopeChanger/ActiveObjectTracking .

Formation Tracking of Mobile Robots Under Obstacles Using Only an Active RGB-D Camera

This paper attempts to achieve leader-follower formation tracking for mobile robots under obstacles with only one RGB-D camera on the follower. In contrast, most existing research employs at least two sensors, including a camera and a LiDAR. However, the limited field-of-view (FOV) of RGB-D cameras introduces three significant challenges: intermittent observation of the leader, partial detection of obstacles, and conflicting observations of the leader and obstacles. To overcome these difficulties, we first propose a controller that enables the follower to achieve continuous observation and formation tracking of the leader without obstacles and depth images. To address the partial detection of obstacles, we design a rotating device that allows the camera to actively extend its observation range and resolve conflicts with leader detection. Based on camera feedback and the proposed controller, a multi-objective controller is presented that enables the follower to achieve formation tracking and obstacle avoidance simultaneously, without requiring communication or leader velocity. Simulations and experiments are conducted to demonstrate the feasibility of our methods.

An EEG Dataset of Subject Pairs during Collaboration and Competition Tasks in Face-to-Face and Online Modalities

This dataset was acquired during collaboration and competition tasks performed by sixteen subject pairs (N = 32) of one female and one male under different (face-to-face and online) modalities. The collaborative task corresponds to cooperating to put together a 100-piece puzzle, while the competition task refers to playing against each other in a one-on-one classic 28-piece dominoes game. In the face-to-face modality, all interactions between the pair occurred in person. On the other hand, in the online modality, participants were physically separated, and interaction was only allowed through Zoom software with an active microphone and camera. Electroencephalography data of the two subjects were acquired simultaneously while performing the tasks. This article describes the experimental setup, the process of the data streams acquired during the tasks, and the assessment of data quality.

A novel camera calibration method based on known rotations and translations

It is often difficult to align the camera optical center with the rotation center of the motion mechanism during active vision calibration, and this dis-alignment could lead to inaccuracy of the constraint equations and calibration results. To circumvent such issues, this paper proposes a novel method for active vision camera calibration and facilitates its real-world implementation. In this method, the rotational motion axis is assumed not necessarily to pass through the camera’s optical center, and the constraint equations are established by correlating image matched points before and after camera motions. The displacements caused by rotation are incorporated into the constraint equations to improve the accuracy of calibration. Numerical simulation and experiments are conducted. The feasibility of this proposed method is justified by using both synthetic and experimental data, and the results show that this method could estimate camera intrinsic parameters with high accuracy. Furthermore, it is found that small rotation angles can better the calibration accuracy even under the influence of external noises. This study suggests that this novel method has great potential for visual and image applications.

Predation of the endangered Ae'o (Hawaiian Stilt) by a native raptor, the Pueo (Hawaiian Short-eared Owl) on the island of O'ahu, Hawai'i, USA.

While the impact of introduced predators is a widely acknowledged issue and key component of conservation considerations for endemic waterbird populations in the Hawaiian Islands, the impact of native predators on endemic, endangered waterbirds is not as frequently discussed or factored into recovery models. The Pueo (Hawaiian Short-eared Owl; Asio flammeus sandwichensis) is a subspecies of Short-eared Owl endemic to the Hawaiian Islands and is State-listed as Endangered on the island of O'ahu. The Ae'o (Hawaiian Stilt; Himantopus mexicanus knudensi) is a subspecies of the Black-necked Stilt endemic to Hawai'i and is federally listed as Endangered throughout its range. A variety of non-native predators are confirmed to consume Ae'o eggs, chicks, and adults, including invasive mammals (e.g., feral cats), birds (e.g., Barn Owls), and amphibians (e.g., bullfrogs). While predation by native predators was suspected, there are no cases documented in the literature to date describing Pueo preying upon Ae'o. Here, we describe four events that provide evidence of Pueo predating Ae'o during the 2019-2021 breeding seasons in a wetland area on the island of O'ahu: (1) confirmed Pueo predating an Ae'o chick, (2) a suspected predation attempt of a Pueo chasing adult Ae'o, and (3) two suspected predation events based on (a) 10 adult-sized Ae'o carcasses and remains found near an active Pueo nest and (b) game camera photos of Pueo visiting two Ae'o nests. To our knowledge, these novel observations are the first published accounts of predator-prey interactions between these two subspecies.

When Two Cameras Are a Crowd

Understanding and handling interference across multiple active cameras.

IoVT-based efficient solution for optimal active smart camera selection in a tracking mission

Nowadays, to ensure people’s and property’s safety, cities have dozens of cameras installed on almost every corner. However, the haphazard deployment of these cameras often results in overlapping fields of view, leading to redundant processing of the same events by multiple cameras. This situation requires more power, huge bandwidth, and more storage capacity for collecting, processing and distributing multimedia data over the network. To overcome these challenges, we propose a novel Internet of Video Things-based system that efficiently reduces the number of cameras involved in processing redundant events. The proposed system operates through a two-step process. Firstly, a leader is elected from a group of cameras based on the degree of overlap in their fields of view, serving as the coordinator. Secondly, the system intelligently selects suitable assistants from neighboring cameras to complement the leader’s vision when it becomes inadequate for effective object tracking. Consequently, only the leader and its assistants remain active, while other neighboring cameras remain in an inactive state. The evaluation demonstrates that our IoVT-based solution offers an efficient approach by minimizing redundancy, optimizing resource utilization and overcoming the challenges posed by the random installation of cameras in urban environments.

Marker-Based Localization System Using an Active PTZ Camera and CNN-Based Ellipse Detection

Localization in GPS-denied environments is challenging, and many existing solutions have infrastructural and on-site calibration requirements. This article tackles these challenges by proposing a localization system that is infrastructure free and does not require on-site calibration, using a single active pan–tilt–zoom camera to detect, track, and localize a circular LED marker. We propose to use a convolutional neural network (CNN) trained using only synthetic images to detect the LED marker as an ellipse and show that our approach is more robust than using traditional ellipse detection without requiring tuning of parameters for feature extraction. We also propose to leverage the predicted elliptical angle as a measure of uncertainty of the CNN's predictions and show how it can be used in a filter to improve marker range estimation and 3-D localization. We evaluate our system's performance through localization of a unmanned aerial vehicle in real-world flight experiments and show that it can outperform alternative methods for localization in GPS-denied environments. We also demonstrate our system's performance in indoor and outdoor environments.

Non-line-of-sight snapshots and background mapping with an active corner camera

The ability to form reconstructions beyond line-of-sight view could be transformative in a variety of fields, including search and rescue, autonomous vehicle navigation, and reconnaissance. Most existing active non-line-of-sight (NLOS) imaging methods use data collection steps in which a pulsed laser is directed at several points on a relay surface, one at a time. The prevailing approaches include raster scanning of a rectangular grid on a vertical wall opposite the volume of interest to generate a collection of confocal measurements. These and a recent method that uses a horizontal relay surface are inherently limited by the need for laser scanning. Methods that avoid laser scanning to operate in a snapshot mode are limited to treating the hidden scene of interest as one or two point targets. In this work, based on more complete optical response modeling yet still without multiple illumination positions, we demonstrate accurate reconstructions of foreground objects while also introducing the capability of mapping the stationary scenery behind moving objects. The ability to count, localize, and characterize the sizes of hidden objects, combined with mapping of the stationary hidden scene, could greatly improve indoor situational awareness in a variety of applications.

Photonics Large-Survey Telescope Internal Motion Metrology System

Large survey telescopes are vital for mapping dark energy and dark matter in the deep universe. This study presents a fiber-linked internal motion metrology system that aligns the mirrors and large lenses in the telescopes to enhance alignment accuracy by improving the image quality at a lower weight, volume, power, and cost. The internal motion system comprises a photonic laser beam projector capable of projecting multiple Gaussian beams onto the detector of the telescope. The specific spatial frequency aberration component is determined by combining Gaussian beam location and the geometry model of the telescope. Furthermore, integrating the proposed system with the curvature-sensing wavefront system enables more precise alignment and camera sensing. In the experimental tests, the location precision was within 10 μm, and the rotation precision improved to 5 arcsecs, fulfilling the alignment and motion monitoring requirements of large survey telescopes. The results of this study can be used as a reference to improve the performance of closed-loop bandwidth systems and active camera optics.

Perception-Motion Coupling in Active Telepresence: Human Behavior and Teleoperation Interface Design

Teleoperation enables complex robot platforms to perform tasks beyond the scope of the current state-of-the-art robot autonomy by imparting human intelligence and critical thinking to these operations. For seamless control of robot platforms, it is essential to facilitate optimal situational awareness of the workspace for the operator through active telepresence cameras. However, the control of these active telepresence cameras adds an additional degree of complexity to the task of teleoperation. In this paper we present our results from the user study that investigates: (1) how the teleoperator learns or adapts to performing the tasks via active cameras modeled after camera placements on the TRINA humanoid robot; (2) the perception-action coupling operators implement to control active telepresence cameras, and (3) the camera preferences for performing the tasks. These findings from the human motion analysis and post-study survey will help us determine desired design features for robot teleoperation interfaces and assistive autonomy.

CW coherent detection lidar for micro-Doppler sensing and raster-scan imaging of drones.

We demonstrate a continuous-wave (CW) coherent detection lidar (CDL) capable of detecting micro-Doppler (propeller) signatures and acquiring raster-scan images of small unmanned aerial systems/vehicles (UAS/UAV). The system uses a narrow-linewidth 1550 nm CW laser and takes advantage of mature and low-cost fiber-optics components from the telecommunications industry. Using either collimated or focused probe beam geometry, lidar based detection of characteristic periodic motions of drone propellers up to a remote distance of 500 m has been achieved. Furthermore, by raster scanning a focused CDL beam with a galvo-resonant mirror beamscanner, two-dimensional images of flying UAVs up to 70 m range were obtained. Each pixel of the raster-scan images provides both lidar return signal amplitude and target radial speed information. The raster-scan images obtained up to 5 frames per second make it possible to discriminate various UAV types based on their profile and even resolve the presence of payloads. With feasible improvements, the anti-drone lidar is a promising alternative to expensive EO/IR and active SWIR cameras used in counter-UAV systems.

Monocular depth estimation network with single-pixel depth guidance.

Due to the scale ambiguity problem, the performance of monocular depth estimation (MDE) is inherently restricted. Multi-camera systems, especially those equipped with active depth cameras, have addressed this problem at the expense of increased hardware costs and space. In this Letter, we adopt a similar but cost-effective solution using only single-pixel depth guidance with a single-photon avalanche diode. To this end, we design a single-pixel guidance module (SPGM) that combines the global information from the single-pixel depth guidance with the spatial information from the image at the feature level. By integrating SPGMs into an MDE network, we introduce PhoMoNet, the first, to the best of our knowledge, end-to-end MDE network with single-pixel depth guidance. Experimental results show the effectiveness and superiority of PhoMoNet over state-of-the-art MDE networks on synthetic and real-world datasets.

Reflection Removal With NIR and RGB Image Feature Fusion

Removing undesirable reflections in photographs benefits both human perceptions and downstream computer vision tasks, but it is a highly ill-posed problem based on a single RGB image. Different from RGB images, near-infrared (NIR) images captured by an active NIR camera are less likely to be affected by reflections when glass and camera planes form certain angles, while textures on objects could “vanish” in some situations. Based on this observation, we propose a cascaded reflection removal network with an image feature fusion strategy to utilize auxiliary information in active NIR images. To tackle the insufficiency of training data, we propose a data generation pipeline to approximate perceptual properties and the reflection-suppressing nature of active NIR images. We further build a dataset with synthetic and real images to facilitate the research. Experimental results show that the proposed method outperforms state-of-the-art reflection removal methods in both quantitative metrics and visual quality.

Robotic Endoscope Control - State of the Art of Voice Control and Other Options for Laparoscopic Camera Robot Guidance.

In video-based surgery (VBS), the surgeon is no longer the master of his or her view. Visualization of the surgical field is mediated by a video camera guided by an assistant. The separation of visualization and surgical activities leads to significant drawbacks. Early in the history of VBS, active camera holders controlled directly by the surgeon were introduced to replace the human camera assistant. However, despite remarkable technological advances over the past 25 years, robotic camera guidance systems (RCGS) still play only a marginal role. This is less due to inadequate mechanical designs or kinematics, and mainly due to inadequate human-machine interaction. In most cases, a simple task-shift is required that increases the surgeon's mental workload instead of reducing it. The current state of the art in robotic camera guidance, as represented by the SOLOASSIST II RCGS (AKTORmed, Neutraubling, Germany), includes a sophisticated combination of direct manual control, joystick navigation and high-quality voice control that provides the most intuitive surgeon-machine interaction currently available. An in-depth analysis of further clinical needs and promising developments in operating room integration suggests that the addition of context sensitivity could actually enhance the assistive effect of RCGS, making them potentially superior to the average human camera guidance.

Fast and robust active camera relocalization in the wild for fine-grained change detection

Active camera relocalization (ACR) is an important and challenging task, whose feasibility and success highly depend on illumination consistency and convergence speed. If under varied lighting conditions in outdoor scenes, however, both the convergence and accuracy of ACR cannot be guaranteed. In this paper, we propose a fast and robust ACR scheme, namely rACR, that works well under highly varied illuminations. To achieve robustness to lighting variations, rather than using 2D feature matching, we rely on 3D point clouds, acquired by a visual SLAM engine (VSE), to register the current and reference camera coordinate frames. We present a scale-aware point cloud matching function that is minimized by a two-stage coarse-to-fine method, i.e., fast alignment considering only geometric error at first, followed by fine-grained alignment optimizing both geometric, photometric errors and the poses of VSE keyframes. The two aligned point clouds with equalized scales help to bridge current and reference observations, avoiding 2D feature matching that are sensitive to large lighting variances, and can directly generate effective camera pose adjustments. Moreover, to achieve fast convergence speed, we implement the above algorithm with a parallel scheme, which is specifically composed of an initialization procedure and three parallel threads, i.e., VSE thread, pose alignment thread, and pose adjustment thread. Extensive experiments show that, rACR has much higher robustness to lighting variations and 5× faster convergence rate over state-of-the-art methods, thus significantly improves its feasibility in real-world fine-grained change detection tasks in the wild.