Cited 1 time in webofscience Cited 4 time in scopus

Real-time Tracking of Guidewire Robot Tips using Deep Convolutional Neural Networks on Successive Localized Frames

Title
Real-time Tracking of Guidewire Robot Tips using Deep Convolutional Neural Networks on Successive Localized Frames
Authors
Ullah, IhsanChikontwe, PhilipPark, Sang Hyun
DGIST Authors
Ullah, Ihsan; Chikontwe, Philip; Park, Sang Hyun
Issue Date
2019-10
Citation
IEEE Access, 7, 159743-159753
Type
Article
Article Type
Article
Author Keywords
CathetersTrackingImage segmentationReal-time systemsMotion segmentationFeature extractionConvolutional neural networksmicro-robot trackingguidewire trackingpatch-wise segmentation
Keywords
NAVIGATION
ISSN
2169-3536
Abstract
Studies are proceeded to stabilize cardiac surgery using thin micro-guidewires and catheter robots. To control the robot to a desired position and pose, it is necessary to accurately track the robot tip in real time but tracking and accurately delineating the thin and small tip is challenging. To address this problem, a novel image analysis-based tracking method using deep convolutional neural networks (CNN) has been proposed in this paper. The proposed tracker consists of two parts; (1) a detection network for rough detection of the tip position and (2) a segmentation network for accurate tip delineation near the tip position. To learn a robust real-time tracker, we extract small image patches, including the tip in successive frames and then learn the informative spatial and motion features for the segmentation network. During inference, the tip bounding box is first estimated in the initial frame via the detection network, thereafter tip delineation is consecutively performed through the segmentation network in the following frames. The proposed method enables accurate delineation of the tip in real time and automatically restarts tracking via the detection network when tracking fails in challenging frames. Experimental results show that the proposed method achieves better tracking accuracy than existing methods, with a considerable real-time speed of 19ms.
URI
http://hdl.handle.net/20.500.11750/10958
DOI
10.1109/ACCESS.2019.2950263
Publisher
Institute of Electrical and Electronics Engineers Inc.
Related Researcher
  • Author Park, Sang Hyun Medical Image & Signal Processing Lab
  • Research Interests 컴퓨터비전, 인공지능, 의료영상처리
Files:
Collection:
Department of Robotics EngineeringMedical Image & Signal Processing Lab1. Journal Articles


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE