Articles tagged with Cameras
Researchers at Incheon National University have developed an IoT-enabled, real-time object detection system for autonomous vehicles. The YOLOv3-based model achieved high accuracy (>96%) in detecting 2D and 3D objects, outperforming other state-of-the-art detection models.
A new type of active pixel sensor using a novel 2D material reduces energy use while enabling ultra-sharp cellphone photos in low light. The sensor's dynamic range and image processing capabilities improve photography in adverse conditions, such as night or foggy days.
Researchers analyzed 2.3 million camera-trap photos of tropical mammals, revealing consistent daily activity patterns across continents. Body size and diet are key factors influencing activity, with larger animals active during the day and smaller ones at night.
Researchers at University of South Australia have developed a non-contact system to accurately measure systolic and diastolic blood pressure using AI algorithms and a camera. The system achieved 90% accuracy in readings, outperforming existing methods.
A study by the Leibniz Institute for Zoo and Wildlife Research found that cheetah marking trees serve as hotspots for communication among multiple mammalian species. These trees were visited more frequently by some species, such as black-backed jackals and warthogs, suggesting they gain important information from the scent marks. In co...
University of Missouri engineers are working on a collaborative human-robot order picking system to speed up the online delivery process. The proposed model aims to optimize key decisions in warehouse operations, allowing robots to navigate efficiently and collaborate with humans to increase efficiency.
A new study using artificial intelligence has found that a simple eye test can accurately predict the risk of heart disease. The researchers developed an algorithm that can analyze retinal images to assess cardiovascular health, providing a non-invasive alternative to traditional risk scores.
ICFO researchers successfully demonstrate transport of two-photon quantum states through a phase-separated Anderson localization optical fiber, showing maintained spatial anti-correlation. The phase-separated fiber enables efficient transmission of quantum information via Corning's optical fiber.
Researchers used satellites with radar imaging sensors to map flooding and assess flood impacts in Queensland. The technique combines images from optical satellites with information from imaging radar satellites, providing faster update times and more accurate data.
Researchers have developed a new miniature robot called Joey that can explore real pipe networks completely on its own, weighing just 70g. The robots are small enough to fit in the palm of your hand and are equipped with energy-efficient sensors to navigate through narrow sections and obstacles.
Researchers from Tokyo Metropolitan University developed a VR system that enables users to share their visual and sensory experiences on Segways with remote collaborators. The system reduced VR sickness by 54% and improved user experience, promising new possibilities for remote collaboration.
Researchers from the University of Tokyo's Interactive Intelligent Systems Laboratory developed a new system called LookHere that incorporates natural hand gestures into the teaching process. This approach eliminates extraneous details and provides better input data for machines to create models, resulting in improved efficiency and ac...
A University of Washington-led study found that even low levels of human activity in protected areas can alter wildlife behavior. Wildlife activity dropped to zero when outdoor recreation levels reached around 40 visitors per week in Glacier Bay National Park.
MIT researchers create a low-power, sound-harvesting camera that captures color photos and transmits data wirelessly. The autonomous device can run for weeks without power, enabling scientists to explore remote oceans and monitor climate change impacts.
Researchers have developed an algorithm that uses smartphone camera and flash to detect low blood oxygen levels. The method produced accurate results in 80% of the participants, showing promise for remote monitoring and early detection of conditions like COVID-19.
Researchers developed a lensless camera that captures 3D information with a single exposure using a thin microlens array and new image processing algorithms. The camera can produce 3D images in real-time, enabling applications such as industrial part inspection, gesture recognition, and 3D display systems.
The new photodetector design combines long-range transport of optical energy with long-range conversion to electrical current, mimicking the photosynthetic complexes found in plants. The device can gather light from areas of about 0.01 mm² and achieve conversion of light to electrical current over exceptionally long distances of 0.1 nm.
Researchers developed a silicon photodiode array for in-sensor processing, allowing for real-time image filtering and extraction of relevant visual information. The technology has potential applications in machine vision, bio-inspired systems, and intelligent imaging devices.
Researchers have developed highly sensitive and mass producible organic photodetectors that can detect weak signals. The new photodetectors exhibited a detectivity comparable to those of conventional silicon photodiodes, operating stably under temperatures above 150 °C.
Researchers at WVU are using robots to analyze potential hazards and provide walkability maps in retail environments, aiming to reduce occupational injuries. The team plans to test the robots after hours in an actual retail space, combining camera data with wheel speed measurements to estimate slip risks.
Researchers at the University of Vienna have discovered that Asian elephants emit low-frequency rumbles through both their trunk and mouth, a finding that challenges existing knowledge on animal communication. This novel discovery suggests that mammals may be more flexible in their vocalizations than previously thought.
A team of researchers uses mirrors to gather more light and views of an object from different angles, allowing them to reconstruct a three-dimensional model of an atom cloud. This technique enables 'light-field imaging', capturing not just intensity but also direction of light rays.
Researchers developed a novel biologically-inspired intraoral camera with a wide-angle insect eye structure, increasing field of view and resolving optical aberrations. The device provides multifunctional dental imaging, including high dynamic range, 3D depth, and autofluorescence, without discomfort or image blur.
The project empowers Indigenous youth to create films about locally available foods and other concerns, raising awareness of nutritional deficiencies and gender discriminatory norms. The initiative aims to improve dietary diversity and promote transformative change through self-expression and participation.
Researchers have developed a novel computational imaging framework, Compact Light-field Photography (CLIP), allowing the camera system to acquire wide and deep panoramic views. The technology enables the detection of hidden objects around occlusions and has potential applications in autonomous vehicles and medical imaging.
A new study reveals sponges have a unique mechanism to clear their water channels: a sneeze-like process. Sponges release a type of mucus that is consumed by other animals, providing a food source inaccessible to most sea creatures.
University of Arizona students developed a comprehensive study to track and characterize the brightness of satellites. The team's work could help astronomers adapt by closing their telescopes' shutters during incoming bright satellites.
Researchers from GIST have developed an amphibious artificial vision system with a panoramic field-of-view based on the Fiddler crab's eye structure. The system overcomes limitations of current artificial visions, enabling imaging in both aquatic and terrestrial environments.
A Rutgers study suggests that using automated traffic safety cameras as a tool to limit racially divisive interactions with the police can increase public support. The research found that emphasizing the technology's role in reducing racial profiling and minimizing police-driver interactions can broaden support for the cameras, particu...
A new study takes inspiration from the 'waggle dance' of honeybees to devise a way for robots to communicate effectively in situations with unreliable network communications. Researchers designed a visual communication system using on-board cameras, allowing robots to interpret gestures and convey complex information.
Researchers developed a lidar-based system for smart cars to recognize objects more accurately than cameras. The system uses a grid map to divide the field of view into regions containing individual objects.
Hawks use a unique flight path to slow down to a safe speed while minimizing the distance from the perch at which they stall. This allows them to control their landings effectively, even when slowing down risks stall, leading to sudden loss of flight control.
The Biofinder instrument has successfully detected bio-residue in ancient fish fossils from the Green River formation, confirming that biological residues can survive millions of years. The device's capabilities make it an ideal tool for future NASA missions to detect signs of past life on other planetary bodies.
A Rutgers team created an AI-powered framework that detects trespassing events, differentiates violators, and generates video clips of infractions. The system analyzed 1,632 hours of archival footage and found nearly 70% of trespassers were men, with most incidents occurring on Saturdays around 5 p.m.
Computer scientists have developed a system to analyse noise produced by individual cameras, linking videos or images to specific cameras. The tool extracts camera-specific noise from video frames, achieving high accuracy rates and potential practical use for law enforcement.
A new camera system developed by Carnegie Mellon University researchers can reconstruct sound vibrations with extraordinary accuracy, capturing isolated audio without inference or a microphone. The dual-shutter vibration-sensing system uses two cameras and a laser to detect high-speed, low-amplitude surface vibrations.
The device can instantly recognize what it sees, like automatic descriptions of pictures taken by a camera or phone, and outperforms the eye in the number of wavelengths it can see. It's uniqueness comes from its ability to integrate three different operations into one, making it many times faster than current technology.
A Washington State University research team developed a system using cameras and small drones to detect and deter pest birds. The system successfully reduced bird counts by four-fold in vineyards, resulting in a 50% reduction in damaged fruits. Further refinement and industry partnerships are needed for commercialization.
Researchers at Lancaster University have created a camera-like device that captures images of mini whirlpools in quantum liquids for the first time. The camera uses particle-like disturbances to take pictures of collections of vortices, which are unpredictable and form in specific patterns above a vibrating wire.
Researchers use AI software to identify invasive species and native trees threatened by disease from photos taken by on-train cameras. This technology enables railway workers to take action to better manage lineside vegetation and achieve biodiversity net gain by 2035.
Researchers from the University of Helsinki used new techniques to observe tree hyraxes in Kenya's Taita Hills, finding that they are social animals with specific habitat preferences. The study estimated a population size of no more than 2,000–4,000 individuals, shedding light on the behavior and conservation of these unique mammals.
Snap Inc has endowed a professorship at TU Graz to develop visionary software methods in camera technology and explore new approaches to visual information processing. The professorship will pursue new application ideas for mixed reality, including the fusion of photos with computer-generated content.
A new study examining body-worn camera use in Phoenix found that departmental policy is a crucial factor in determining activation rates. The study revealed that policies confining, structuring, and checking officer discretion significantly impact decisions on turning on the cameras.
Researchers at UC San Diego have developed a smartphone app that uses near-infrared camera technology to track pupil size changes, which can indicate cognitive conditions. The app is designed to be user-friendly for older adults and has shown comparable results to traditional pupillometry devices.
Researchers have developed a novel image reconstruction method using Vision Transformer (ViT) architecture to overcome limitations of conventional methods. The proposed algorithm enables the acquisition of high-quality images in a short computing time, suitable for real-time capture and various applications.
A Dartmouth study using advanced recording technology reveals that females prefer lower frequency songs with low variance, while males time their songs to follow neighbors. The research shows how chorus composition and individual songs impact mating in wood frogs.
Researchers at Samsung have developed a novel approach to inspect critical dimensions of semiconductor devices, improving speed and resolution. The new 'line-scan hyperspectral imaging' (LHSI) technique offers faster measurements with high spatial resolution, outperforming existing methods.
The new eye detection system allows for clear iris image capture from 2m away and can process over 700 frames per second, enabling real-time biometric identification. This innovation has the potential to revolutionize security and access control in various settings.
Researchers at Stanford University have developed a new approach to enable standard image sensors to capture light in three dimensions. The system uses acoustic resonance and piezoelectric properties of lithium niobate to modulate light, allowing for high-performance lidar capabilities in compact devices.
Researchers developed a metasurface attachment that can turn any camera into a polarization camera, capturing light's polarization at every pixel. This innovation benefits various fields like face recognition, self-driving cars and remote sensing, revealing hidden details and features.
Researchers at Duke University have demonstrated a new attack strategy that can deceive industry-standard autonomous vehicle sensors into believing nearby objects are closer or further than they appear. This vulnerability highlights the need for additional redundancy and data sharing between vehicles to protect against such attacks.
The microsatellite will fly at a Very Low Earth Orbit (VLEO), collecting data for commercial VLEO satellites with multiple applications. The satellite is designed to be sustainable, de-orbiting within days of its operational life.
A team of scientists has developed a pioneering approach to combine advances in computer vision with ecological expertise to analyze wildlife populations. By leveraging AI and machine learning algorithms, researchers can extract key features from images and videos to quickly classify species, count individuals, and track behavior.
KAUST researchers have found that even low-speed solid-liquid impacts can cause cavitation and generate damaging shock waves. This challenges previous assumptions about the effects of such impacts. The team used high-speed cameras to study the impact of a flat-bottomed cylinder on a pool of liquid, observing that pressures below a cert...
Researchers developed MonoCon, a new AI technique that enables accurate identification of 3D objects in 2D images. By incorporating auxiliary context, the method improves object detection and estimation accuracy, paving the way for safer and more robust autonomous vehicles.
The researchers developed an eye-like adaptive liquid lens that can be used to diverge or converge light by changing the shape of the DBA liquid. The lens exhibits high optical performance with good stability and can be used in various applications such as mobile phone cameras, endoscopes, and machine vision.
A new study from the University of Otago found that children are exposed to 554 brands per 10-hour day, or nearly a brand a minute. The majority of these exposures occurred in school, at home, and in-store, with most coming from brand labels, product packaging, and commercial signage.
A Washington State University study found that people's attitudes toward virtual meetings depend on their public self-consciousness. Those low in this trait tend to have more positive attitudes when their own faces are visible, while highly self-conscious individuals experience worse attitudes.
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.