Cognitive neuroscience of visual object recognition
Related papers: 20
About
Visual object recognition in the context of robotics and AI refers to the computational processes by which machines identify, classify, and localize objects within visual data, drawing inspiration from how the human brain processes and interprets visual scenes. Rooted in cognitive neuroscience, this field informs the design of algorithms that extract hierarchical features from images — from low-level edges to high-level semantic categories — mirroring the ventral visual pathway in biological brains. In robotics, these principles underpin systems that process RGB, depth (RGB-D), LiDAR, and point cloud data to recognize objects for tasks such as grasping, navigation, and scene understanding. Techniques range from classical template matching and model-based methods to modern deep convolutional neural networks trained on large-scale datasets. The field matters because robust object recognition is foundational to autonomous robot operation in unstructured real-world environments — enabling capabilities like manipulation, place recognition, and semantic mapping. Understanding the neuroscientific basis of vision continues to inspire more generalizable, efficient, and human-like machine perception systems.
Top Researchers
Top Cited Papers
VoxNet: A 3D Convolutional Neural Network for real-time object recognition
Daniel Maturana, Sebastian Scherer
Citations: 3579 • 2015
Convolutional networks and applications in vision
Yann LeCun, Koray Kavukcuoglu, Clément Farabet
Citations: 2163 • 2010
A large-scale hierarchical multi-view RGB-D object dataset
Kevin Lai, Liefeng Bo, Xiaofeng Ren, Dieter Fox
Citations: 1322 • 2011
Visual Place Recognition: A Survey
Stephanie Lowry, Niko Sünderhauf, Paul Newman, John J. Leonard, David Cox, Peter Corke, Michael Milford
Citations: 1071 • 2015
A Perspective on Range Finding Techniques for Computer Vision
R.A. Jarvis
Citations: 782 • 1983
A Study on CNN Transfer Learning for Image Classification
Mahbub Hussain, Jordan J. Bird, Diego R. Faria
Citations: 607 • 2018
Model-based recognition in robot vision
R.T. Chin, Charles R. Dyer
Citations: 565 • 1986
Template Matching Techniques in Computer Vision: Theory and Practice
Roberto Brunelli
Citations: 543 • 2009
Invariant surface characteristics for 3D object recognition in range images
Paul J. Besl, Ramesh Jain
Citations: 513 • 1986
Application of Deep Learning for Object Detection
Ajeet Ram Pathak, Manjusha Pandey, Siddharth Swarup Rautaray
Citations: 505 • 2018
HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects
Nicholas Ayache, Olivier D. Faugeras
Citations: 492 • 1986
The MOPED framework: Object recognition and pose estimation for manipulation
Alvaro Collet, Manuel Martínez, Siddhartha S Srinivasa
Citations: 443 • 2011
Robotic tactile perception of object properties: A review
Shan Luo, João Bimbo, Ravinder Dahiya, Hongbin Liu
Citations: 407 • 2017
Active vision in robotic systems: A survey of recent developments
Shengyong Chen, Youfu Li
Citations: 403 • 2011
Semantic Labeling of 3D Point Clouds for Indoor Scenes
Hema Swetha Koppula, Abhishek Anand, Thorsten Joachims, Ashutosh Saxena
Citations: 331 • 2011
RGB-D object recognition and pose estimation based on pre-trained convolutional neural network features
Max Schwarz, Hannes Schulz, Sven Behnke
Citations: 321 • 2015
Detect-SLAM: Making Object Detection and SLAM Mutually Beneficial
Fangwei Zhong, Sheng Wang, Ziqi Zhang, China Chen, Yizhou Wang
Citations: 304 • 2018
Object Detection Using Convolutional Neural Networks
Reagan L. Galvez, Argel A. Bandala, Elmer P. Dadios, Ryan Rhay P. Vicerra, Jose Martin Z. Maningo
Citations: 303 • 2018
Comparison of surface normal estimation methods for range sensing applications
Klaas Klasing, Daniel Althoff, Dirk Wollherr, Martin Buss
Citations: 296 • 2009
SoftPOSIT: Simultaneous Pose and Correspondence Determination
Philip David, Daniel DeMenthon, Ramani Duraiswami, Hanan Samet
Citations: 237 • 2004