Paper 3 Terms Flashcards
Bundle Adjustment
Enhances the accuracy and reliability of 3D scene reconstructions from multiple images and camera views
Computer Vision
A field of AI enabling computers to derive info from images, videos, and other inputs
Dead Reckoning Data
Method used to estimate the robot’s current position based on a known starting point, estimated speed, moving direction, and amount of moving time
Edge Computing
Distributed computing framework that brings enterprise applications closer to data sources such as IoT devices or local edge servers
Global Map Optimization
A process of improving the accuracy and consistency of a map that a robot has created of its environment
Global Positioning System (GPS) Signal
A satellite constellation supporting highly accurate positioning, navigation, and timing (PNT) measurements worldwide
GPS-Degraded Environment
Refers to any situation or location where the GPS signals are unreliable, weak, or completely unavailable. Could be due to urban areas, indoor locations, forested areas, underground/underwater, mountainous terrain, interference or jamming
GPS-Denied Environment
A location or situation where the GPS signals aren’t available aren’t available at all. This could be due to indoor locations, underground/underwater locations, jamming/spoofing, or space between the signal and destination
Human Pose Estimation
A task in computer vision designed to recognize and accurately track specific points on the human body
Inertial Measurement Unit
A device that can measure and report specific gravity and angular rate of an object to which it is attached
Keyframe Selection
Selecting certain frames of images or scans of surroundings, and using the new/important information in those frames to create a map of it’s environment and track its position more efficiently
Key Points/Pairs
Used to align images with one another & reconstruct 3D structure and camera movement from a series of 2D images
Light Detection and Ranging (LIDAR)
A remote sensing method that uses light in the form of a pulsed laser to measure ranges to the Earth
Object Occlusion
The event where a part or all of an object in the scene is hidden from view by some other object in the scene
Odometry Sensor
A device used to estimate the change in position over time of a vehicle, like a car or robot, based on data from its own sensors
Optimization
The method of obtaining the most effective/efficient solution to a given problem
Rigid Pose Estimation (RPE)
A concept in computer vision and robotics that involves determining the position and orientation of an object that doesn’t deform or change shape
Relocalization
The ability of a robot to determine its current location in a map that it previously built or in a known environment, particularly after it has lost track of its position due to an error, disturbance, or after it has been manually moved
Robot Drift
Refers to the accumulated error in a robot’s estimated position and orientation over time
Simultaneous Localization and Mapping (SLAM)
A methos used for autonomous vehicles that lets you build a map and localize your vehicle at the time same. These algorithms allow the vehicle to map out unknown environments
Sensor Fusion Model
The process of merging data from multiple sensors to reduce the amount of uncertainty that may be involved in a robot navigation motion or task performing
Visual Simultaneous Localization and Mapping (vSLAM)
The process of calculating the position and orientation of a camera, with respect to its surroundings, while simultaneously mapping the environment. This process uses only visual inputs from the camera
vSLAM Initialization
Refers to the process of setting up initial conditions / starting point for the algorithm
