Feature (linguistics)

Related papers: 20

About

In robotics and AI, a **feature** refers to a measurable, distinctive property or descriptor extracted from raw sensor data — such as images, point clouds, or audio — that captures meaningful structure useful for perception and decision-making. Borrowed from linguistics, where features describe categorical properties of language units, the term in robotics broadly denotes any compact representation that encodes relevant information about the environment. Features may be geometric (e.g., edges, corners, surface normals), appearance-based (e.g., SIFT descriptors, color histograms), or learned (e.g., neural network activations). In practice, robots use features for tasks like simultaneous localization and mapping (SLAM), object detection, visual odometry, and gesture recognition — extracting stable, discriminative descriptors from sensor streams and matching them across views or time steps. Features matter because raw sensor data is high-dimensional and noisy; compact feature representations reduce computational cost, improve robustness to viewpoint and lighting changes, and enable reliable correspondence across observations. Whether hand-crafted or learned end-to-end, features form the perceptual backbone of nearly every robotic vision and navigation system.

Top Cited Papers

3D is here: Point Cloud Library (PCL)

Radu Bogdan Rusu, Steve Cousins

Citations: 4825 • 2011

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

Yin Zhou, Oncel Tuzel

Citations: 4542 • 2018

Simultaneous localization and mapping: part I

Hugh Durrant‐Whyte, T. Bailey

Citations: 4107 • 2006

Computer and Robot Vision

Robert M. Haralock, Linda G. Shapiro

Citations: 3952 • 1991

MonoSLAM: Real-Time Single Camera SLAM

Andrew J. Davison, Ian Reid, Nicholas Molton, Olivier Stasse

Citations: 3909 • 2007

Convolutional networks and applications in vision

Yann LeCun, Koray Kavukcuoglu, Clément Farabet

Citations: 2163 • 2010

Real-time simultaneous localisation and mapping with a single camera

Davison

Citations: 1718 • 2003

Learning Rich Features from RGB-D Images for Object Detection and Segmentation

Saurabh Gupta, Ross Girshick, Pablo Arbeláez, Jitendra Malik

Citations: 1531 • 2014

Target-driven visual navigation in indoor scenes using deep reinforcement learning

Yuke Zhu, Roozbeh Mottaghi, Eric Kolve, Joseph J. Lim, Abhinav Gupta, Li Fei-Fei, Ali Farhadi

Citations: 1507 • 2017

StereoScan: Dense 3d reconstruction in real-time

Andreas Geiger, Julius Ziegler, Christoph Stiller

Citations: 1102 • 2011

SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights

Michael Milford, Gordon Wyeth

Citations: 970 • 2012

Fast 3D recognition and pose using the Viewpoint Feature Histogram

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

Citations: 859 • 2010

3-D Mapping With an RGB-D Camera

Felix Endres, Jürgen Hess, Jürgen Sturm, Daniel Cremers, Wolfram Burgard

Citations: 822 • 2013

Dynamic sensor-based control of robots with visual feedback

L.E. Weiss, Arthur C. Sanderson, Charles P. Neuman

Citations: 822 • 1987

Socially aware motion planning with deep reinforcement learning

Yu Fan Chen, Michael Everett, Miao Liu, Jonathan P. How

Citations: 715 • 2017

Kalman filter-based algorithms for estimating depth from image sequences

Larry Matthies, Takeo Kanade, Richard Szeliski

Citations: 712 • 1989

Visual SLAM algorithms: a survey from 2010 to 2016

Takafumi Taketomi, Hideaki Uchiyama, Sei Ikeda

Citations: 700 • 2017

Max-pooling convolutional neural networks for vision-based hand gesture recognition

Jawad Nagi, Frederick Ducatelle, Gianni A. Di, Dan Cireşan, Ueli Meier, Alessandro Giusti, Farrukh Nagi, Jürgen Schmidhuber, Luca Maria Gambardella

Citations: 648 • 2011

Adaptive Fuzzy Neural Network Control for a Constrained Robot Using Impedance Learning

Wei He, Yiting Dong

Citations: 638 • 2017

Model-based recognition in robot vision

R.T. Chin, Charles R. Dyer

Citations: 565 • 1986