7 terms
Camera calibration estimates a camera's intrinsic, distortion and extrinsic parameters so a robot can turn image pixels into accurate geometric measurements.
Object recognition in robotics is the perception task of identifying which known objects appear in sensor data and where they are, so a robot can act…
A point cloud is a set of 3D points sampled from surfaces, which robots use in perception to map scenes, detect obstacles and locate objects.
Sensor fusion combines data from several robot sensors into one estimate of state or surroundings that is more accurate and reliable than any single source.
SLAM, simultaneous localization and mapping, lets a robot build a map of an unknown environment while estimating its own position within that map.
Stereo vision recovers depth from two cameras a known distance apart by matching points and measuring disparity, a core technique in robot perception.
Visual odometry is a robot perception method that estimates how a camera moves through space by tracking changes between consecutive camera images.