Articles tagged with Cameras
Researchers developed a new hand gesture recognition algorithm that surpasses current methods in accuracy, complexity, and applicability. The algorithm combines adaptive hand type classification and a shortcut feature for efficient real-time recognition.
A new COVID-19 mobile robot detects social distancing breaches in crowds and encourages people to move apart using a novel system that employs Deep Reinforcement Learning and Frozone algorithm. The robot also incorporates a thermal camera for contact-tracing efforts, ensuring privacy protection and de-identification.
Researchers at Duke University developed a holographic system that can image and analyze tens of thousands of cells per minute to spot signs of disease. The technique distinguished between healthy samples and cancerous or pre-cancerous cells with nearly 100% accuracy, using just four basic cellular physical parameters.
The new system can produce high-quality images comparable to those of conventional cameras, with a compact design suitable for minimally invasive endoscopy and full-scene sensing. This breakthrough could revolutionize medical imaging and robotics with size and weight constraints.
A new imaging method measures individual photons, greatly reducing interference and improving spatial resolution by three times. The technology could also reduce radiation exposure during x-ray imaging, making it ideal for medical applications.
Researchers at Northwestern University developed a new high-resolution camera that can see hidden objects by indirectly scattering coherent light. The device overcomes limitations of existing NLoS imaging technologies with high spatial and temporal resolution, small probing area, and large angular field of view.
Researchers developed a technology that accurately detects lies by analyzing facial muscle contractions, achieving a success rate of 73%. The study identified two distinct groups of 'liars' based on cheek muscle and eyebrow activation, with potential implications for real-life deception detection.
A new imaging technique called single-shot photoluminescence lifetime imaging thermometry (SPLIT) measures temperature in 2D, without contact, and in real-time. This technology could improve photothermal therapy and help detect skin cancers.
Researchers tracked black-tailed deer before, during, and after the Mendocino Complex Fire, finding that all 18 deer survived. Despite burned areas with no vegetation, most deer returned home within hours, potentially due to their loyalty to habitat. However, some deer's body condition declined as they expanded their range.
A new rapid screening test for glaucoma uses infra-red sensors to monitor eye movement, providing accurate results within seconds. The test could help advance early detection of the disease, a leading cause of irreversible blindness, and make it more accessible for national screening programs.
A new buoy-borne underwater dark field imaging system has been developed to expand marine plankton monitoring capabilities. The system features a high-quality imager with embedded computer and cloud computing-based deep learning algorithms for object detection and quantification.
Researchers at MIT develop RFusion, a robotic system that uses data from a camera and radio frequency antenna to locate and retrieve lost items. The system relies on RFID tags and machine learning algorithms to optimize the robot's trajectory and grasp the object.
Researchers create a novel framework for generating and detecting Lamb waves in transparent materials without damaging the sample. They use laser-induced plasma shock waves and high-speed polarization cameras to spot microscopic scratches, demonstrating potential for non-contact damage detection.
A team of researchers at Kennedy Krieger Institute developed a new method to diagnose Autism Spectrum Disorder (ASD) using a single 2D camera. The Computer Assessment of Motor Imitation (CAMI) method provides greater access to patients and shows accurate assessment with 2D technology.
A team of astronomers used dashcam footage to track a fireball over Slovenia, recovering three space rocks and tracing their origins in the Solar System. The fragments provide insights into the history of our Solar System and potential hazards like Near Earth Objects.
A Dartmouth research team has been selected to present their abstract on a new advancement in Cherenkov imaging at the ASTRO Annual Meeting. The work, which involves designing a color-sensitive camera to image Cherenkov emission from patients, allows for more accurate quantification of radiation delivery and safe treatment.
A newly improved robotic cane, funded by NIH/National Eye Institute, uses a color 3D camera, inertial measurement sensor, and onboard computer to guide users to desired locations while avoiding obstacles. The device can provide accurate navigation assistance in large spaces with sensory and auditory cues.
A study by University of Plymouth researchers found that seabed habitats and species recover more quickly following extreme storms than from the impacts of bottom-towed fishing. The research examined the impact of the 2013/14 winter storms on the Lyme Bay Marine Protected Area, off southern England's coast.
Scientists at Nara Institute of Science and Technology create a projected touchscreen system using just one camera and projector, eliminating the need for additional detectors. The system uses slope disparity gating to capture touch data with high efficiency, enabling portable projection systems for large interactive displays.
Engineers at MIT and the University of Twente study water jet impacts on droplets to inform needle-free injection systems. They developed a model predicting fluid jet behavior in human skin, aiming to minimize damage.
Researchers developed a new method to analyze video segments from live streams and estimate the prevalence of mask wearing. The protocol was successfully learned in under an hour and found reliable estimates of mask-compliance, with the potential to provide useful results for decision-makers within 48 hours.
A new study using video recordings from animal-towed cameras reveals the secret life of basking sharks in Scottish waters. The research shows that the sharks engage in feeding, courtship and social behaviors, challenging previous assumptions about their solitary nature.
A new algorithm has been developed that can guide a quadrotor drone through a series of waypoints on a circuit, beating the fastest lap of two world-class human pilots. The algorithm generates time-optimal trajectories that fully consider the drones' limitations, resulting in faster and more consistent flight times.
Researchers at the University of California, Irvine have created a new type of camera technology that can visualize various materials and structures with detailed chemical information. The technology uses nonlinear optical effects in silicon to capture depth-resolved images on a camera in one shot, allowing for faster inspection of obj...
Researchers studied protein bubbles and discovered they pop like blooming flowers when deflated with a needle due to viscoelastic properties. High-speed cameras captured the phenomenon at 20,000 frames per second, revealing unique mechanisms of rupture.
Researchers use ultrafast electron diffraction to observe an electronic device as it operates, discovering a new intermediate state that enables fast and energy-efficient switching. The study paves the way for next-generation electronic devices that can meet the world's growing needs for data-intensive computing.
Researchers developed an open-source camera to capture mice's view in their natural environments. The study reveals that mice have adapted to perceive colors in the green and ultraviolet regions to aid survival and reproduction.
Researchers found that Asian elephants produce high-pitched squeaks through lip vibration, contradicting previous assumptions that the sound comes from the trunk. The technique is unique in the animal kingdom and may be learned, suggesting flexibility in sound production.
A new study using near-infrared (NIR) spectrum cameras has shown that these small, mobile cameras can help detect more snakes and could lead to an automated python tracker. By utilizing NIR cameras, pythons can be detected 20% farther away than with visible cameras.
Researchers from uOttawa propose a new optical element called spaceplate, which simulates light spreading in a small device, enabling the miniaturization of optical systems. This technology has potential applications in fields like healthcare, where thin cameras or endoscopes could be used to visualize internal organs.
Researchers developed a near-infrared camera system that can detect Burmese pythons up to 1.3 times farther away than traditional visible-wavelength cameras, providing a new tool for removal efforts and expanding detection capabilities day and night.
Researchers at Carnegie Mellon University developed a model that enables drones to capture videos evoking specific emotions, such as excitement or calmness, through camera angles and flight paths.
Researchers developed an infrared thermal imaging camera to assess filarial lymphoedema status. The tool helps monitor disease progression and detect sub-clinical cases, improving diagnosis and care for those affected by this devastating tropical disease.
Researchers developed a dual hybrid camera system that enables 360-degree monitoring while capturing high-resolution images, addressing the trade-off between field-of-view and resolution. The system uses an omnidirectional camera and a separate pan-tilt camera to capture highly accurate object identification.
A new algorithm corrects motion blur in single-photon images, allowing for high-quality pictures even with multiple objects moving independently. The approach accurately estimates individual object motion and groups pixels by similar motion, enabling deblurring of each region independently.
Researchers at CoReLS have realized the highest laser intensity ever reached, exceeding 1023 W/cm2. This achievement allows for the exploration of extreme physical conditions and novel physical phenomena, such as Compton scattering and photon-photon scattering in nonlinear regimes.
Researchers developed a camera inspired by the mantis shrimp to visualize cancer cells during surgery, combining it with tumor-targeted drugs for enhanced accuracy. The technology aims to prevent cancer recurrence and improve patient recovery.
Scientists at Texas A&M developed a cellphone extension that detects chemicals, drugs, and biological molecules using fluorescence and Raman spectroscopy. The system's sensitivity is comparable to industrial Raman spectrometers but can be improved with HDR applications.
Researchers discover that mantis shrimp larvae can unleash powerful punches as little as 9 days after hatching, with limb accelerations reaching blistering speeds. The tiny creatures' appendages operate similarly to those of adult mantis shrimp, but scaled down, and can hurl the limb at rotational speeds of ~16,500deg/s.
Researchers at NIST measured moon dust particles as small as 400 nanometers, revealing a strong link between particle shape and light scattering. The study uses X-ray nano computed tomography to analyze particle shapes and improve satellite tracking of weather patterns.
Researchers found virtual reality (VR) effective in assessing balance and improving postural control in older adults. VR systems can differentiate healthy from balance-impaired individuals and provide a more natural and relevant testing environment.
A team of researchers has developed a webcam that mimics the movements of a human eye, raising questions about its potential effects on human interaction. The device's anthropomorphic design aims to encourage people to think about their relationship with sensing devices.
Researchers found that Parkinson's patients exhibit 53% lower step length synergy while crossing obstacles compared to healthy subjects. This impairment affects gait timing and foot positioning, making it difficult for patients to navigate obstacles safely, increasing the risk of falls.
A University of Washington-led team has developed a system that uses machine learning to capture subtle changes in facial light reflection to estimate pulse and respiration rates from smartphone videos. The system outperforms previous versions on diverse datasets, including those with darker skin tones.
Researchers have developed a robot that combines radio wave sensing with computer vision to locate and grasp occluded objects. RF-Grasp uses radio waves to sense objects even when they're fully blocked from view, enabling efficient fulfillment in warehouses or retrieving lost items.
Researchers at UMD have developed a new camera allowing for the imaging of wetland soil activity in real time, enabling the calculation of iron reduction rates. This technology opens up new research avenues in soil science, providing a better understanding of wetland soil behavior and its potential applications.
Researchers used trail cameras to study wildlife behavior during the pandemic, gathering data on animal populations and identifying unique research opportunities. The cameras allowed scientists to monitor individual animals passively over a large area without the need for manual trapping or processing.
Researchers attached an omnidirectional camera to a humpback whale to study its resting behavior. The whale was found to be inactive for half the recorded period, with active behavior in the latter half, suggesting it may have been recovering from foraging.
A new algorithm, C2FIV, uses facial motion to verify identities, providing an additional layer of security. With a success rate of over 90% accuracy in its preliminary study, the technology has broader applications beyond smartphone access, including workplace and online banking security.
Researchers from Eindhoven University of Technology used a high-speed camera and 2176 microphones to measure the precise origin of the hummingbird's sound. The team found that the wing's pressure difference generates the hum, which is essential for lift-off and hovering.
Researchers at Duke University and other institutions are developing a 'super camera' capable of capturing all types of information carried by light, including polarization, depth, phase, coherence, and incidence angle. The project aims to create an imaging system that can handle sensing and processing simultaneously, streamlining size...
Researchers have shown that three-layered surgical masks are most effective at stopping large cough droplets from getting atomized into smaller aerosols. This is crucial since these smaller droplets can linger in the air, spreading to people at larger distances.
A large-scale citizen science project in NC captured over 2.2 million wildlife photos, increasing verified mammal records by a factor of five. The project trained 580 volunteers to take candid animal photos and gathered data on wildlife abundance, reproduction, and behavior.
A team of researchers from NYU Tandon School of Engineering discovered that popular machine-learning frameworks for protecting sensitive data can be subverted, allowing secret information to be extracted. The study highlights the inadequacy of current privacy checks and warns against relying on untrusted third-party tools.
A team of researchers at Tokyo Tech has designed a flexible and free-standing terahertz sensor array that can image irregularly shaped objects. The camera patch sheet can be easily cut into smaller sensors for better coverage, showcasing its potential in industrial applications such as quality control operations.
Researchers have created an angle-insensitive 3D-printed miniature spectrometer that can be fabricated directly on a miniature image sensor. This innovation enables complex measurement systems in medical engineering and precision farming, with potential applications in hyperspectral imaging.
Researchers at Cornell University have developed a low-cost method for soft robots to detect human touch without relying on physical contact. The ShadowSense technology uses a USB camera to capture shadow movements of hand gestures on the robot's skin, classifying them with machine-learning software.
A hybrid approach combining hardware- and computer vision-based tracking improves the accuracy of laparoscopic ultrasound imaging. By using a custom tracking mount with EM sensors and CV markers, the system can track the transducer's pose with high accuracy.
Researchers developed a novel camera-based system for automated drone landing using 2D symbol detection, allowing drones to safely land on uneven terrain. The system consists of a commercial flight controller, Raspberry Pi module, and image-processing algorithm that detects a distinctive landing symbol in real-time.
Researchers have discovered a method to produce silicon at room temperature using electrical currents instead of extreme heat, which could slash energy use and cost in the industry. This technique replaces thermochemical processes with electrochemical processes, converting clean electricity into chemical energy.