A Survey on Deep Learning Methods for Robot Vision

Abstract

Deep learning has allowed a paradigm shift in pattern recognition, from using hand-crafted features together with statistical classifiers to using general-purpose learning procedures for learning data-driven representations, features, and classifiers together. The application of this new paradigm has been particularly successful in computer vision, in which the development of deep learning methods for vision applications has become a hot research topic. Given that deep learning has already attracted the attention of the robot vision community, the main purpose of this survey is to address the use of deep learning in robot vision. To achieve this, a comprehensive overview of deep learning and its usage in computer vision is given, that includes a description of the most frequently used neural models and their main application areas. Then, the standard methodology and tools used for designing deep-learning based vision systems are presented. Afterwards, a review of the principal work using deep learning in robot vision is presented, as well as current and future trends related to the use of deep learning in robotics. This survey is intended to be a guide for the developers of robot vision systems.

References in corpus (45)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning in Neural Networks: An Overview
• Rethinking Atrous Convolution for Semantic Image Segmentation
• LSTM: A Search Space Odyssey
• Improving neural networks by preventing co-adaptation of feature detectors
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Densely Connected Convolutional Networks
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• Stacked Hourglass Networks for Human Pose Estimation
• Feature Pyramid Networks for Object Detection
• Fractional Max-Pooling
• Beyond Skip Connections: Top-Down Modulation for Object Detection
• Residual Attention Network for Image Classification
• Pyramid Scene Parsing Network
• Fast Training of Convolutional Networks through FFTs
• Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books
• XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
• Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
• Deep convolutional neural networks for pedestrian detection
• Sample Efficient Actor-Critic with Experience Replay
• Identity Mappings in Deep Residual Networks
• Pylearn2: a machine learning research library
• Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
• Speed/accuracy trade-offs for modern convolutional object detectors
• Learning Spatiotemporal Features with 3D Convolutional Networks
• Blocks and Fuel: Frameworks for deep learning
• Comparative Study of Deep Learning Software Frameworks
• Stacked Deconvolutional Network for Semantic Segmentation
• Contextual Action Recognition with R*CNN
• Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
• Training a Convolutional Neural Network for Appearance-Invariant Place Recognition
• RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints
• Accurate Single Stage Detector Using Recurrent Rolling Convolution
• Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
• Crafting GBD-Net for Object Detection
• Object Recognition Using Deep Neural Networks: A Survey
• Convolutional Neural Network-Based Image Representation for Visual Loop Closure Detection
• Robobarista: Learning to Manipulate Novel Objects via Deep Multimodal Embedding
• Real-world Object Recognition with Off-the-shelf Deep Conv Nets: How Many Objects can iCub Learn?
• What you need to know about the state-of-the-art computational models of object-vision: A tour through the models
• Object Recognition from Short Videos for Robotic Perception
• Learning Rich Features from RGB-D Images for Object Detection and Segmentation
• What Can I Do Around Here? Deep Functional Scene Understanding for Cognitive Robots

Cited by in corpus (2)

• An Overview of Federated Learning at the Edge and Distributed Ledger Technologies for Robotic and Autonomous Systems
• A Multisensory Learning Architecture for Rotation-invariant Object Recognition