Image (mathematics)

Related papers: 20

About

In mathematics and computer vision, an **image** refers to the output of a function mapping an input domain (such as a 2D sensor array) to a range of values representing measurements like intensity, color, or depth. In robotics and AI, images serve as the primary sensory input for perceiving and interpreting the environment — captured by cameras, depth sensors, or LiDAR systems and processed to extract meaningful information about objects, scenes, and spatial relationships. Images underpin a vast range of robotic capabilities: autonomous vehicles use them for obstacle detection and lane following, manipulators rely on them for object recognition and grasp planning, and SLAM systems use image sequences to build maps and estimate pose. Techniques such as convolutional neural networks, feature descriptors, and point cloud processing all operate on image-derived data to enable tasks like 3D reconstruction, action recognition, and 6D pose estimation. Images matter because they provide rich, high-bandwidth environmental information that enables robots and AI systems to operate intelligently in complex, unstructured real-world settings — making image understanding foundational to nearly every modern perception pipeline.

Top Cited Papers

Are we ready for autonomous driving? The KITTI vision benchmark suite

Andreas Geiger, P Lenz, R. Urtasun

Citations: 14348 • 2012

Vision meets robotics: The KITTI dataset

Andreas Geiger, Philip Lenz, Christoph Stiller, Raquel Urtasun

Citations: 9681 • 2013

Color indexing

Michael J. Swain, Dana H. Ballard

Citations: 5591 • 1991

Computer and Robot Vision

Robert M. Haralock, Linda G. Shapiro

Citations: 3952 • 1991

Robot Vision

Berthold K. P. Horn

Citations: 3635 • 1986

The vector field histogram-fast obstacle avoidance for mobile robots

J. Borenstein, Yoram Koren

Citations: 2278 • 1991

Temporal Convolutional Networks for Action Segmentation and Detection

Colin Lea, M. D. Flynn, Renè Vidal, Austin Reiter, Gregory D. Hager

Citations: 2028 • 2017

Potential field methods and their inherent limitations for mobile robot navigation

Yoram Koren, J. Borenstein

Citations: 1552 • 2002

Derivative Dynamic Time Warping

Eamonn Keogh, Michael J. Pazzani

Citations: 1124 • 2001

Ultrafast machine vision with 2D material neural network image sensors

Lukas Mennel, Joanna Symonowicz, Stefan Wachter, Dmitry K. Polyushkin, Aday J. Molina‐Mendoza, Thomas Mueller

Citations: 1105 • 2020

DeepFruits: A Fruit Detection System Using Deep Neural Networks

Inkyu Sa, Zongyuan Ge, Feras Dayoub, Ben Upcroft, Tristán Pérez, Chris McCool

Citations: 1079 • 2016

Towards 3D Point cloud based object maps for household environments

Radu Bogdan Rusu, Zoltán-Csaba Márton, Nico Blodow, Mihai Dolha, Michael Beetz

Citations: 1078 • 2008

PCN: Point Completion Network

Wentao Yuan, Tejas Khot, David Held, Christoph Mertz, Martial Hebert

Citations: 955 • 2018

Robotic Grasping of Novel Objects using Vision

Ashutosh Saxena, Justin Driemeyer, Andrew Y. Ng

Citations: 948 • 2008

DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes

Berta Bescos, José M. Fácil, Javier Civera, José Neira

Citations: 924 • 2018

Designing Responsive Buckled Surfaces by Halftone Gel Lithography

Jungwook Kim, James Hanna, Myunghwan Byun, Christian D. Santangelo, Ryan C. Hayward

Citations: 872 • 2012

Fast 3D recognition and pose using the Viewpoint Feature Histogram

Radu Bogdan Rusu, Gary Bradski, R. Thibaux, JJ Hsu

Citations: 859 • 2010

ARTag, a Fiducial Marker System Using Digital Techniques

Mark A. Fiala

Citations: 853 • 2005

Scan registration for autonomous mining vehicles using 3D‐NDT

Martin Magnusson, Achim J. Lilienthal, Tom Duckett

Citations: 767 • 2007

Handbook of pattern recognition and image processing

Citations: 766 • 1986