Deep EndoVO: A Recurrent Convolutional Neural Network (RCNN) based Visual Odometry Approach for Endoscopic Capsule Robots
arXiv:1708.06822 · doi:10.1016/j.neucom.2017.10.014
Abstract
Ingestible wireless capsule endoscopy is an emerging minimally invasive diagnostic technology for inspection of the GI tract and diagnosis of a wide range of diseases and pathologies. Medical device companies and many research groups have recently made substantial progresses in converting passive capsule endoscopes to active capsule robots, enabling more accurate, precise, and intuitive detection of the location and size of the diseased areas. Since a reliable real time pose estimation functionality is crucial for actively controlled endoscopic capsule robots, in this study, we propose a monocular visual odometry (VO) method for endoscopic capsule robot operations. Our method lies on the application of the deep Recurrent Convolutional Neural Networks (RCNNs) for the visual odometry task, where Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are used for the feature extraction and inference of dynamics across the frames, respectively. Detailed analyses and evaluations made on a real pig stomach dataset proves that our system achieves high translational and rotational accuracies for different types of endoscopic capsule robot trajectories.
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- ORB-SLAM: a Versatile and Accurate Monocular SLAM System
- DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks
- On the Performance of ConvNet Features for Place Recognition
- A Non-Rigid Map Fusion-Based RGB-Depth SLAM Method for Endoscopic Capsule Robots
- Sparse-then-Dense Alignment based 3D Map Reconstruction Method for Endoscopic Capsule Robots
- A Deep Learning Based 6 Degree-of-Freedom Localization Method for Endoscopic Capsule Robots
- A fully dense and globally consistent 3D map reconstruction approach for GI tract to enhance therapeutic relevance of the endoscopic capsule robot
- Image-based localization using LSTMs for structured feature correlation
- Magnetic-Visual Sensor Fusion based Medical SLAM for Endoscopic Capsule Robot
Cited by in corpus (22)
- GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks
- Artificial Intelligence and its Role in Near Future
- Bimodal Camera Pose Prediction for Endoscopy
- An Improvement of Data Classification Using Random Multimodel Deep Learning (RMDL)
- Sparse-then-Dense Alignment based 3D Map Reconstruction Method for Endoscopic Capsule Robots
- Motion-based Camera Localization System in Colonoscopy Videos
- A Survey of Deep Learning Techniques for Mobile Robot Applications
- Endo-VMFuseNet: Deep Visual-Magnetic Sensor Fusion Approach for Uncalibrated, Unsynchronized and Asymmetric Endoscopic Capsule Robot Localization Data
- Image Based Camera Localization: an Overview
- Gender Detection on Social Networks using Ensemble Deep Learning
- EndoSLAM Dataset and An Unsupervised Monocular Visual Odometry and Depth Estimation Approach for Endoscopic Videos: Endo-SfMLearner
- RGB-Depth SLAM Review
- On Machine Learning and Structure for Mobile Robots
- Bayesian dense inverse searching algorithm for real-time stereo matching in minimally invasive surgery
- Reachability Analysis of Convolutional Neural Networks
- Combining Deep Learning with Geometric Features for Image based Localization in the Gastrointestinal Tract
- Design, fabrication and 3-DOF control of legless capsule robot
- Magnetically Guided Capsule Endoscopy
- Distance Metric-Based Learning with Interpolated Latent Features for Location Classification in Endoscopy Image and Video
- Hybrid Feature Based SLAM Prototype
- Diagnosis and Analysis of Celiac Disease and Environmental Enteropathy on Biopsy Images using Deep Learning Approaches
- Deep Visual Odometry Methods for Mobile Robots