Articles tagged with Cameras
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.
Researchers have developed a new perovskite-based camera inspired by the structures and functions of bird's eyes, specializing in object detection. The camera features an artificial fovea and multispectral image sensor that detects UV and RGB light, providing greater motion detection capabilities than conventional cameras.
Researchers have developed a system combining bio-inspired cameras with AI to quickly detect obstacles around cars, using less computational power. The hybrid system detects objects up to one hundred times faster than current systems while reducing data transmission and processing needs.
Researchers at Delft University of Technology developed a drone that flies autonomously using neuromorphic image processing and control based on the workings of animal brains. The drone's deep neural network processes data up to 64 times faster and consumes three times less energy than when running on a GPU.
A new approach uses artificial intelligence to turn low-quality images into high-quality ones, enhancing the image quality of metalens cameras. This technology could make these cameras viable for intricate microscopy applications and mobile devices.
Researchers from GIST and MIT CSAIL develop a MultiSenseBadmpton dataset to enhance badminton performance analysis and AI-based coaching. The dataset captures joint movements, muscle signals, and gaze movements of badminton players.
Scientists at Harvard John A. Paulson School of Engineering and Applied Sciences have developed a compact, single-shot polarization imaging system that can provide a complete picture of polarization. The system uses two thin metasurfaces to capture the most complete polarization response of an object in real-time.
Researchers at the University of Sydney and Queensland University of Technology have developed a new approach to designing cameras that process and scramble visual information. The approach, known as 'sighted systems,' creates distorted images that can still be used by robots to complete tasks but do not compromise privacy.
Researchers at Kennedy Krieger Institute and Johns Hopkins Medicine developed a new method for analyzing walking and gait using free software and cellphone videos. This approach is more accessible and quicker than current state-of-the-art methods, enabling clinicians to assess patients' walking abilities more conveniently.
Researchers propose using coordinated multi-swarm drones to quell forest fires, leveraging AI-enabled fire detection and autonomous decision-making. The approach could lead to more efficient fire suppression and reduced response times.
Researchers developed a custom-built, low-cost mesoscope that can adapt to different neuroimaging experiments in live mice and rats. The system offers excellent spatial and temporal resolutions, achieved through its reversible tandem lens configuration, which enables flexible experimentation.
A study published in BMC Geriatrics uses in-vehicle sensors to detect anomalous driving behavior indicative of cognitive impairment in older adults. The system analyzes driving patterns, facial expressions, and eye movement to identify early signs of dementia.
A new AI-powered system has been shown to detect 40% more polyps during colonoscopies, a crucial step in preventing colorectal cancer. This breakthrough technology uses artificial intelligence to examine every pixel in the image and alert doctors to potential issues, allowing for more accurate diagnoses.
Researchers at Simon Fraser University have developed an AI approach to intrinsic decomposition, separating images into lighting effects and true colours of objects. This innovation enables a range of applications, including image compositing and augmented reality, making it accessible to content creators and post-production artists.
Researchers developed a way for robots to recognize objects even when partially obscured, using a visual perception system and topology. The THOR (Teaching Humans Object Recognition) method outperforms current state-of-the-art models in cluttered spaces, including warehouses and homes.
Researchers developed a compact facial recognition system that uses metasurfaces to create high-resolution images. The new technology recognized Michelangelo's David with similar accuracy as existing smartphone systems, using significantly less power and space.
A new study published in Frontiers in Sports and Active Living found that resistance training before basketball practice has minimal to no effect on shooting performance. In fact, the only scenario where accuracy decreased was after upper-body training, but this decrease disappeared 30 minutes post-exercise completion.
A Japanese research team developed a four-meter-long, remotely controllable flying firehose robot called the Dragon Firefighter. It can safely and efficiently extinguish fires by directly approaching flames. The robot will be deployed in real-world firefighting scenarios after approximately 10 more years of development.
A computer vision system developed by University of Malaga engineers estimates vehicle speeds in real time using a single camera, reducing complexity and costs. The algorithm, published in Neurocomputing, aims to improve vehicle safety and has potential applications in autonomous driving and driver assistance.
Scientists use new photography technique to observe interaction between biological cell and shock wave, revealing high-speed phenomena. The technology has potential applications in science, medicine, and industry.
Researchers develop a versatile imaging system for targeted spectroscopy in the eye fundus, allowing for continuous color imaging and spectral measurements. The system enables users to select targets and move them to any location within the eye fundus region without realignment or fixation changes.
Researchers from RMIT University found that Australians aged 20 to 40 years old take more selfies than teenagers and older Australians. Older participants used their smartphones for functional purposes like capturing information at work, whereas teenage participants preferred taking photos during exciting events or with friends.
A new study found that anti-bias training significantly improved police performance scores and reduced discrimination-based complaints. Officers who received the training had a small but significant increase in performance scores and a 50% reduction in complaints compared to those who did not receive training.
A recent study published in the Proceedings of the National Academy of Sciences found that AI's deep convolutional neural networks can identify faces but struggle to capture other important information like emotional state and trustworthiness. Brain activity scans revealed a weak correlation between AI's codes and human brain represent...
Researchers at NIST built a superconducting camera containing 400,000 pixels to capture weak light signals. The new device enables applications in science and biomedical research by having more pixels than any other device of its type.
A smartphone attachment developed by UC San Diego engineers can screen for neurological conditions like Alzheimer's disease and traumatic brain injury at low cost, accurately regardless of skin tone. The technology uses far-red light to enhance visibility of the pupil, making it easier to track changes in eye movement.
A team of researchers proposes a novel approach to generate three-dimensional holograms directly from regular 2D color images captured using ordinary cameras. This approach utilizes deep learning to transform the image into data that can be used to display a 3D scene or object as a hologram.
A study found that participants rated women's bodies as slimmer when viewed in selfie photographs compared to external perspectives. The researchers also discovered a link between self-viewing and disordered eating thoughts, suggesting potential harm from social media consumption.
Researchers developed MonoXiver, a new method to help AI extract 3D information from 2D images, making cameras more useful tools for emerging technologies. The method significantly improves accuracy when used in conjunction with existing techniques, such as MonoCon.
A team from Université de Genève and University of Teacher Education, State of Vaud conducted an innovative field study on pedagogical authority. They found that 'double addressing' strategies, combining direct and indirect communication, are particularly effective in exercising teaching authority. This approach allows teachers to prev...
Researchers developed a new diffraction-gated real-time ultrahigh-speed mapping (DRUM) camera that captures dynamic events in a single exposure at 4.8 million frames per second. The camera uses off-the-shelf components and is fast enough to capture highly dynamic biomedical processes or enable high-speed lidar systems.
A new study from the University of Kansas used motion capture technology to analyze the biomechanics of proficient free-throw shooters. Proficient shooters exhibited lower knee and center of mass peak and mean angular velocities, greater release height, and less forward trunk lean compared to nonproficient shooters.
Researchers have developed a new measurement technique that uses the Kramers-Kronig relation to untangle complex helical light patterns from camera intensity measurements. This allows for single-shot retrieval of orbital angular momentum spectrum information, accelerating and simplifying the process compared to conventional on-axis int...
Quantum ghost imaging allows 3D imaging on a single photon level, enabling the lowest photon dose possible. The technique can be applied to image materials and tissues sensitive to light or drugs without risk of damage.
A study by Ohio State University researchers uses mobile cameras installed on campus buses to count vehicles, detect objects in the road, and track movements. The AI-powered YOLOv4 model provides accurate measurements with high spatial and temporal coverage, which could enhance current traffic systems and improve efficiency.
Lancaster University researchers have developed a novel scanning thermal microscopy approach to directly measure the heat conductivity of two-dimensional materials. This breakthrough enables the creation of efficient waste heat scavengers generating cheap electricity, new compact fridges, and advanced optical and microwave sensors and ...
Researchers have developed flexible photodetectors that can detect visible to long-wave infrared radiation, covering the full spectrum of greenhouse gases without complex optical components. The new detectors are simple and cost-effective to make, with production at room temperature.
A University of Massachusetts Amherst researcher has updated the Pregnancy Physical Activity Questionnaire (PPAQ), a widely used tool for measuring prenatal physical activity. The new PPAQ is considered reliable and valid, providing estimates of physical activity and sedentary behavior in pregnant women.
A recent study published in the Proceedings of the National Academy of Sciences found that officers' first 45 words during a vehicle stop with a Black driver can indicate how the stop will end. The study discovered a unique 'linguistic signature' that characterizes escalated stops, where officers give an order without stating the reaso...
The INRS team developed a single-shot ultrafast terahertz photography system that captures ultrashort events in optically opaque scenarios. The system uses an electro-optic sampling technique and achieves sub-picosecond resolution, allowing researchers to study complex dynamics inaccessible by conventional optical frequencies.
A new camera technology developed by Aarhus University and Newtec Engineering A/S aims to make it easier to recycle plastic materials. The technology uses hyperspectral imaging to analyze the chemical composition of plastic waste, allowing for the removal of unwanted additives that may be banned or harmful.
Researchers from Aston University and the University of York discovered new insights into how the human brain makes perceptual judgments of the external world. They found that humans can exploit 'defocus blur' to infer perceptual scale, but this process is crude and more heuristic than metrical analysis.
Researchers develop innovative data compression scheme to facilitate multispeckle diffuse correlation spectroscopy with high pixel resolutions, enabling non-invasive measurement of brain blood flow. The scheme uses field-programmable gate array compression to alleviate computational burdens and expand the use of SPAD cameras in biomedi...
A POSTECH research team has successfully mass-produced metalenses for visible light, overcoming previous limitations in fabrication and efficiency. By combining photolithography and nanoimprint lithography, the team achieved high-speed production of high-performance lenses with improved efficiency up to 90%.
Researchers have developed a novel registration method to identify plant traits in close-up photos by correcting illumination effects. The approach uses artificial intelligence and combines data from multiple sensors to generate high-quality point clouds of plants.
The City University of Hong Kong has developed a novel electron microscope that combines scanning and transmission electron microscope modes in a compact format. The device can produce high-resolution images in five minutes, enabling the study of atom dynamics and beam-sensitive materials.
Researchers at University of California - San Diego found that vertebrates acquired a special protein from bacteria more than 500 million years ago. This discovery reveals a new piece of genetic material introduced from foreign bacterial genes, leading to unique functionality in vertebrate eyes.
A new camera design allows for cheaper and more efficient long-term volcano monitoring, enabling researchers to track gas emissions and predict eruptions. The camera's affordability and user-friendliness make it accessible to more volcanologists, facilitating new research opportunities.
Researchers developed a robotic finger with high-resolution sensors that capture data along the entire length of each finger. The three-fingered robotic hand can identify objects after just one grasp, with 85% accuracy, using tactile sensing and machine-learning algorithms.
Research highlights centuries-old manipulation of photos and videos, raising questions about the social problems behind deepfakes, including the objectification of women and dehumanization of marginalized groups. Dr. Joshua Habgood-Coote argues for media reform and institutional change to combat these issues.
Researchers discovered that even in the absence of predators, escape events occur frequently but rarely spread to many fish. The study suggests that this robustness to false alarms is due to dynamic adjustments in sensitivity to socially acquired information.
Researchers developed a novel design for the chip using a crossbar layout, outperforming state-of-the-art photonic counterparts in terms of scalability and technical versatility. The synergy of powerful photonics with the novel crossbar architecture enables next generation neuromorphic computing engines.
Researchers have developed a high-speed, 3D gigapixel microscope that stitches together dozens of cameras to capture life in unprecedented detail. The device enables the recording of differences in pitch and depth, allowing scientists to study zebrafish behavior and developmental biology without harming the animals.
Brazilian researchers used a high-speed camera to capture an image of lightning rods trying to connect to nearby buildings, revealing details of the connections. The image shows that even with multiple lightning rods in place, the strike connected to a smokestack on top of one building, highlighting the importance of proper installation.
Researchers found that increasing melanin levels in human skin reduces Cherenkov emission intensity, while blood concentration affects different color channels. The study suggests using multispectral signatures to correct attenuated signals based on patient's blood volume or skin color.
Researchers developed a new AI-driven method to detect and predict defects in 3D printed metals, enabling rapid improvements in additive manufacturing. The method uses X-ray imaging and machine learning to identify pore generation in real-time with near-perfect accuracy.
Researchers have developed a robotic system called AngleNet that measures leaf angles on corn plants, providing plant breeders with accurate data more quickly. The technology uses stereo vision and deep convolutional neural networks to capture images of leaves at different heights, enabling 3D modeling and precise measurements.
The DART mission successfully deflected the orbit of asteroid Dimorphos by 33 minutes. The team's calculations showed that the momentum transferred to Dimorphos was significantly enhanced by the recoil created from streams of particles produced by the impact, exceeding initial expectations.
Scientists at IISc develop neuromorphic camera that uses machine learning to pinpoint objects smaller than 50 nanometers in size, enabling nanoscale precision in biological processes, chemistry, and physics. The technique combines optical microscopy with the neuromorphic camera and machine learning algorithms.