Articles tagged with Cameras
A pilot study found that an examiner-worn, neck-mounted camera can supplement the observation and review of clinical skills during OSCE assessments. The results showed moderate to strong agreement between live and video-based assessments, with the wearable camera enabling more observations to be evaluated than the fixed camera.
Researchers developed SpiderCam, a highly energy-efficient 3D camera inspired by jumping spiders. It captures two images with different focus settings and analyzes the differences in sharpness to produce real-time 3D maps while consuming less than a watt of power.
A new framework combines a custom-built training dataset with transfer learning to improve the detection accuracy of small and distant objects in omnidirectional videos. The proposed model achieved an overall accuracy of 90%, significantly higher than conventional models for small moving objects.
A new approach enables computers and machines to capture images at higher resolution and faster speed, making it impervious to reflective surfaces. The technology uses a virtual screen created by repurposing the surroundings of specular objects.
A new single-chip camera captures ultraviolet, near-infrared and visible images using a compact design inspired by the multiwavelength vision capability of the mantis shrimp. The camera helps surgeons identify cancer-linked lymph nodes during surgery, making cancer treatment safer and less invasive.
Researchers at the University of Washington developed a system that integrates tiny cameras in wireless earbuds with an AI model, allowing users to ask questions about the scene in front of them. The system achieved high accuracy rates for translation and object recognition, making it a promising technology for future applications.
A biologically inspired event camera measures vibrations accurately without expensive equipment, providing a cost-effective alternative to laser-based systems. The camera captures high-speed vibrations by recording brightness changes independently at each pixel, enabling precise amplitude, phase, and frequency estimation.
A new method analyzes nearby vehicle motion to estimate road's trajectory and vanishing point, capturing distant road areas and enhancing safety. The system outperformed conventional and deep learning-based techniques in tests under day and night conditions, reducing intersection-related accidents.
The Art of Science competition celebrates creativity through photography and video, highlighting FAU's rise as a hub for innovation. Chelsea Bennice wins with her captivating underwater octopus image, while Gabriella Carvajal's 'Sea Turtle Beginning' showcases embryonic development, shedding light on climate change impacts.
The device integrates new software and AI technologies to enhance optics in small areas with limited light, providing a super vision for surgeons. The team hopes to expand its scope to areas like the brain, enabling more complicated surgeries with high-quality results.
Researchers at FAU Engineering have developed foot-mounted wearable sensors and a 3D depth camera that accurately measure how people walk, even in busy clinical environments. The study findings reveal that these technologies match the accuracy of traditional tools but are more scalable, remote, and cost-effective.
Researchers at Champalimaud Centre for the Unknown used machine learning techniques to show that mice's facial movements reflect their hidden thoughts. This discovery could offer unprecedented insight into brain function and potential new research tools.
Researchers have developed a high-performance mid-infrared imaging system without lenses, capturing clear pictures over large distances and in low light. The system uses an optical pinhole inside a nonlinear crystal to form an image, which is then converted into visible light, allowing for distortion-free and large-depth imaging.
Researchers used an experimental technique called annealing to rescue a damaged camera on NASA's Juno spacecraft, offering lessons for other space systems that experience high radiation.
The PUNCH mission has successfully imaged a huge solar eruption, providing unprecedented views of coronal mass ejections and the solar wind. The spacecraft constellation is enabling scientists to better understand and predict space weather events that can disrupt communications and endanger satellites.
The PUNCH mission has successfully collected its first images of the solar corona using four small spacecraft that act as a single virtual instrument. The images show the outer atmosphere of the Sun in stunning detail, with scientists aiming to remove background light and preserve the faint signal of the solar wind.
A new method using free software and a drone with a low-cost camera has been developed to select drought-tolerant corn plants. The approach allows for optimized data collection, faster processing, and reduced costs compared to conventional methods.
The study tracked over 1,800 cameras across school zones from 2019 to 2021 and found that most cameras achieve their safety purpose within six months. Effectiveness patterns vary geographically across the city, with some areas experiencing a significant reduction in speeding behaviors, while others show marginal impact.
Researchers at TUM integrate 60 camera pixels into a single detector, achieving unprecedented resolution of up to 3840 MPixels. This technology enables the observation of tiny shifts due to gravity in antihydrogen beams and has broader applications in experiments requiring high position resolution.
University of Missouri researchers developed a method using lidar and AI to analyze pedestrian, cyclist, and vehicle interactions at traffic signals. The approach aims to enhance driver awareness, reduce accidents, and improve mobility.
The NRL-developed Narrow Field Imager is a compact coronagraph that will image the transition of the Sun's atmosphere to the solar wind, gaining insights into space plasma environments. The PUNCH mission aims to improve prediction and mitigation of space weather events like coronal mass ejections.
Researchers developed a portable system using AI to spot cognitive impairment by measuring subtle differences in motor function. The device accurately identified 83% of participants with mild cognitive impairment (MCI), offering potential for early intervention and improved outcomes.
Researchers at the University of Adelaide used quantum-sensitive cameras to image embryos, capturing biological processes in their natural state. The sensitive detection of photons allows for gentle illumination and minimizes damage from light, enabling researchers to study live cells and developing specimens.
The PUNCH spacecraft will study the solar corona and track space weather events in three dimensions for the first time. The constellation includes four small suitcase-sized spacecraft that will provide a clear view of the Sun's outer atmosphere, allowing scientists to discern the exact trajectory and speed of coronal mass ejections.
The MultiX project aims to revolutionize 6G communication networks by integrating multisensory perception, allowing them to interact with the environment in real-time. This innovation has potential applications in healthcare, such as recognizing falls in elderly people or monitoring vital signs at home.
A new method of biometric authentication has been developed using hyperspectral imaging and AI to identify individuals through the unique patterns in their blood vessels on the palm of their hand. The technology shows great promise for secure personal identification and could potentially be used as a key to unlock homes.
The PUNCH mission will study the solar corona and its impact on the solar wind, improving space weather forecasting capabilities. The four small spacecraft, launched by NASA's Small Explorers program, will create a virtual instrument to image the Sun's corona, revealing previously invisible phenomena.
The release of a unique Type Ia Supernovae dataset has significant implications for cosmologists measuring the universe's expansion history. The dataset, comprising 3628 supernovae, provides unprecedented precision and accuracy in exploring the properties of these events.
A new study by Northeastern University's Crime Prevention Lab found that CCTV cameras in Newark, NJ, were associated with reduced auto thefts three to four years after installation. The study highlights the importance of longer-term evaluations to understand the persistence and potential increase of crime prevention effects.
The KeyScope is a low-cost, robust laparoscope priced at approximately $1,000, making it accessible in low- and middle-income countries. It offers high-resolution images, color accuracy, and low distortion, comparable to standard laparoscopes.
Lauren Berger, a Texas A&M University doctoral student, has been awarded a prestigious FINESST grant from NASA to study Martian dunes. She aims to analyze the shapes and patterns of compound dunes on Mars using high-resolution images, comparing them to similar dunes on Earth.
Researchers developed a new technique to estimate prey size and energy content from animal-borne camera footage, providing insights into predator-prey interactions and foraging strategies. This study on Humboldt, King and Tawaki/Fiordland penguins sheds light on the feeding behavior of marine wildlife.
A team of scientists introduced a novel technique to refine prey size estimation from animal-borne camera footage, enhancing understanding of predator-prey interactions. The correction factors developed allow accurate measurements directly from video footage, providing unprecedented insight into wildlife feeding behavior.
Researchers discovered organic molecules on Ceres' surface but found no evidence of volcanic or tectonic activity. The deposits are thought to have originated from impacts by outer asteroid belt bodies, which could have introduced building blocks of life.
Researchers are developing a software framework for crowd-sourced 3D map generation and visual localization from camera data to improve real-time updates and low-cost visual localization. This technology aims to advance self-driving vehicles and enable fully automated transportation
The researchers developed a novel camera-based system that adapts to traffic flow in real-time, ensuring efficient monitoring and resource use. The system's two approaches, the Random-Value-Camera-Level Algorithm and the ALL-Random-With-Weight Algorithm, optimize camera usage and save energy while maintaining reliable surveillance.
A Mount Sinai-led team has developed an automated machine learning method that analyzes video recordings of clinical sleep tests to detect REM sleep behavior disorder (RBD) with nearly 92% accuracy. RBD is a sleep condition that causes abnormal movements during REM sleep and is often an early sign of Parkinson's disease or dementia.
Researchers at Osaka Metropolitan University developed a simple method to measure deformations in thin membrane materials using photogrammetry and a single camera. This technology can accurately detect wrinkle size and wavelength, enabling more efficient spacecraft operations.
Researchers at University of Washington developed IRIS, a smart ring that allows users to control smart devices by aiming the ring's small camera at the device and clicking a built-in button. The prototype Bluetooth ring controls devices up to two seconds faster than voice commands.
Researchers at CAMERA have developed an open-source markerless motion capture system using computer vision and deep learning methods. The system estimates joint positions from regular 2D image data, providing unobtrusive analysis of body movements.
A novel physical reservoir computing device uses a dye-sensitized solar cell to mimic human synaptic elements, enabling efficient time-series data processing and low power consumption. The device achieved high computational performance in tasks such as human motion classification with over 90% accuracy.
Researchers at Seoul National University's Optical Engineering and Quantum Electronics Laboratory developed an optical design technology that dramatically reduces the volume of cameras with a folded lens system utilizing metasurfaces. The new lens system achieves a thickness of 0.7mm, making it suitable for ultra-compact devices such a...
Researchers developed a system that uses machine learning to recognize touching on the skin, achieving over 96% accuracy. The EgoTouch tool can detect various types of touch, including force and gesture, and has potential applications for skin-based interfaces and virtual reality.
The collaboration aims to detect red tide occurrences early and provide information to fisheries stakeholders to prevent damage to marine environments. The system will also be used for broader environmental monitoring of forests and oceans, improving accuracy through repeated validation.
Researchers from DTU have discovered a neutron star that rotates at an astonishing 716 times per second, making it one of the fastest-spinning objects ever observed. The neutron star is part of an X-ray binary star system and is located in the Sagittarius constellation.
A computer model uses camera pose estimation and phototourism data to reconstruct the 3D scene of Antarctic penguin colonies, allowing for their identification and tracking. This innovative approach enables researchers to study and monitor penguin populations more effectively.
A meta-imaging camera has been developed for aberration-robust monocular passive depth sensing, outperforming traditional light-field cameras in depth estimation precision and robustness. The camera's capability to overcome spatial resolution and angular resolution trade-offs enables accurate depth sensing even in the presence of optic...
A research team, led by Francesco Ferretti, located signs of white sharks at four sites in the Sicilian Channel, a stronghold of the endangered species. The team used improved methods and technologies, including eDNA sampling and camera traps, to detect the presence of the sharks.
Researchers at GIST developed a cat's eye-inspired vision system that filters out unnecessary light and improves visibility in low-light conditions. The system promises to elevate the precision of drones, security robots, and self-driving vehicles, enabling them to navigate intricate environments with unparalleled accuracy.
A team of researchers from USC and Caltech developed a new noninvasive tool to measure brain blood pressure, assessing stroke risk through changes in blood flow and volume during a stress test. The affordable, portable device has the potential to transform stroke care by providing more reliable data than existing questionnaires.
Researchers used body-worn camera footage to study changes in police behavior after procedural justice training, finding a significant increase in respectful communication techniques with drivers of all races. Post-training stops were twice as likely to use formal titles and express concern for the driver's safety.
A study by Dr. Shunichi Kasahara found that levels of identification with one's face remain consistent regardless of agency or control over facial movements. The results suggest that a sense of agency does not significantly impact our ability to judge our facial identity, even in scenarios like deepfakes.
Researchers developed DeepLens design method based on curriculum learning to optimize complex lens designs. The approach considers key parameters like resolution, aperture, and field of view, providing optimal solutions without human intervention.
A new method to measure continuous light spectrum improves thermal imaging accuracy without direct contact. It eliminates wavelength and temperature dependence, revealing higher surface temperatures of photothermal catalysts than previous methods.
A new handheld device enables rapid non-invasive detection of harmful chemicals and biological molecules using a Raman spectrometer and cellphone camera. This technology reduces analysis time from days to minutes, making it ideal for remote areas where laboratory spectrometers are impractical.
A new camera system called PrivacyLens can replace people in images with generic stick figures, protecting their identities and reducing unnecessary surveillance. This technology could prevent embarrassing photos from being shared online and make patients more comfortable using cameras for chronic health monitoring.
Researchers at Kaunas University of Technology developed an end-to-end system to eliminate visual distractions caused by overlapping camera angles in live football broadcasts. The system uses YOLOv8 object detection and video inpainting technology to remove unwanted objects, such as cameramen, from frames.
The University of Maryland team created a camera mechanism that mimics the involuntary movements of the human eye, resulting in sharper and more accurate images. The Artificial Microsaccade-Enhanced Event Camera (AMI-EV) has implications for robotics, national defense, and industries relying on accurate image capture.
Researchers developed a technique called Multi-View Attentive Contextualization (MvACon) to improve AI's ability to map 3D spaces using 2D images from multiple cameras. MvACon significantly improved the performance of vision transformers in locating objects and detecting speed and orientation.
Researchers have developed a compact, palm-sized light field camera that simultaneously captures 3D spatial and spectral information in a single snapshot. The camera uses inkjet printing to create its key optical components, enabling efficient manufacturing and customization.