Stanford researchers have developed a hierarchical event readout method that solves a major latency problem in event-based image sensors. Event-based sensors output data only when pixels change, enabling fast and efficient sensing.
The Satellite Hardware-In-the-loop Rendezvous Trajectory (SHIRT) dataset consists of images and pose labels associated with two rendezvous trajectory scenarios (ROE1 and ROE2) in Low Earth Orbit (LEO) created from two different sources.
SPEED+ is an advanced dataset for vision-based spacecraft pose estimation with specific emphasis on evaluating the robustness of Machine Learning (ML) models across the domain gap.
Stanford inventors have developed TrueImage, a machine learning algorithm to assess the quality of patient images sent in for telemedicine appointments.
Artificial intelligence can be leveraged to evaluate how facial expressions will be perceived by others. A deep learning neural network is used to generate facial vectors for each image of a person.
Engineers in the Solgaard lab have developed a high-speed, random access grating light valve (GLV) for phase modulation to steer and focus light in LIDAR and 3D imaging applications.
Stanford researchers have created the first large-scale dataset of aerial videos from multiple classes of targets interacting in complex outdoor spaces.
Stanford inventors have developed a deep learning framework that is able to label individual points from 3D Point Clouds that are acquired by various sensors (RGBD sensors, LIDAR sensors, etc.). This framework obtains a point-level fine-grained labeling of 3D Scenes.
Stanford researchers have developed a method that allows for 3D semantic parsing of indoor spaces. It receives a 3D point cloud input which is parsed into individual spaces and specific components, such as structural and furniture.