IB COMP SCI CASE STUDY (BOTPRO) 2024

a computer vision technique used to refine a 3D reconstruction by minimizing the reprojection error between observed image points and predicted (projected) 3D points

algorithms and techniques that allow computers to analyze, interpret, and makes sense of digital images or videos

Method for estimating sensor/object position (localization) and digitally constructing an unknown environment (mapping)

estimation of current position made using dead reckoning

Data processing takes place at local devices (i.e. robots), rather than relying on a centralized server

the process of enforcing visual consistency across a whole map (using bundle adjustment + other processes, but on a larger scale)

refers to the radio frequency signal transmitted by satellites in the Global Positioning System (GPS); used to determine the receiver's location, velocity, and time

situation where GPS signals are weakened; still available, but quality, accuracy, and acquisition time degraded

with no signal available

used to identify key points on inanimate objects

Device that combines 3 sensors to measure acceleration, rotation, and magnetic field orientation

the process of identifying and selecting significant frames from a video sequence to build a sparse map of the environment and estimate the camera's trajectory accurately

distinctive and identifiable locations or regions within an image or a video frame

sensing system used in vSLAM that utilizes lasers to create detailed 3D representations of the surroundings and measure distances

situation in which objects or parts of objects in a scene are partially or completely obstructed from view by another object (s)

provides information about the movement and position of robots by measuring - the rotation of wheels and/or other moving parts

of the process of refining the estimated camera poses and 3D point positions to improve the accuracy and consistency of the 3D reconstruction and camera position

the process of re-establishing a camera’s position and orientation in a known environment

situation where a cumulative error in dead reckoning leads to significant deviation of calculated position from the true position

Method for estimating sensor/object position (localization) and digitally constructing an unknown environment (mapping)

paradigm in which information from multiple sensors is combined to get a better understanding of the surrounding environment

the initial capture of visual data in a rescue site

The usage of the vSLAM “process” to build a 3D Map loop closure - The usage of instances where the camera (on the robot) revisits a location or previous scene to improve the 3D map

the process of re-establishing a camera’s position and orientation in a known environment

The tracking of visual features across frames for purposes of localization