The Centre has a long history of developing new techniques for medical imaging (particularly in magnetic resonance imaging), transforming them from a primarily diagnostic modality into an interventional and therapeutic platform. This is facilitated by the Centre's strong engineering background in practical imaging and image analysis platform development, as well as advances in minimal access and robotic assisted surgery. Hamlyn has a strong tradition in pursuing basic sciences and theoretical research, with a clear focus on clinical translation.

In response to the current paradigm shift and clinical demand in bringing cellular and molecular imaging modalities to an in vivo – in situ setting during surgical intervention, our recent research has also been focussed on novel biophotonics platforms that can be used for real-time tissue characterisation, functional assessment, and intraoperative guidance during minimally invasive surgery. This includes, for example, SMART confocal laser endomicroscopy, time-resolved fluorescence spectroscopy and flexible FLIM catheters.


BibTex format

author = {Guo, Y and Deligianni, F and Gu, X and Yang, G-Z},
doi = {10.1109/LRA.2019.2928775},
journal = {IEEE Robotics and Automation Letters},
pages = {3617--3624},
title = {3-D Canonical pose estimation and abnormal gait recognition with a single RGB-D camera},
url = {},
volume = {4},
year = {2019}

RIS format (EndNote, RefMan)

AB - Assistive robots play an important role in improvingthe quality of life of patients at home. Among all the monitoringtasks, gait disorders are prevalent in elderly and people with neurological conditions and this increases the risk of fall. Therefore,the development of mobile systems for gait monitoring at home innormal living conditions is important. Here, we present a mobilesystem that is able to track humans and analyze their gait incanonical coordinates based on a single RGB-D camera. First,view-invariant three-dimensional (3-D) lower limb pose estimationis achieved by fusing information from depth images along with2-D joints derived in RGB images. Next, both the 6-D camerapose and the 3-D lower limb skeleton are real-time tracked in acanonical coordinate system based on simultaneously localizationand mapping (SLAM). A mask-based strategy is exploited to improve the re-localization of the SLAM in dynamic environments.Abnormal gait is detected by using the support vector machine andthe bidirectional long-short term memory network with respect toa set of extracted gait features. To evaluate the robustness of thesystem, we collected multi-cameras, ground truth data from 16healthy volunteers performing 6 gait patterns that mimic commongait abnormalities. The experiment results demonstrate that ourproposed system can achieve good lower limb pose estimation andsuperior recognition accuracy compared to previous abnormal gaitdetection methods.
AU - Guo,Y
AU - Deligianni,F
AU - Gu,X
AU - Yang,G-Z
DO - 10.1109/LRA.2019.2928775
EP - 3624
PY - 2019///
SN - 2377-3766
SP - 3617
TI - 3-D Canonical pose estimation and abnormal gait recognition with a single RGB-D camera
T2 - IEEE Robotics and Automation Letters
UR -
UR -
UR -
VL - 4
ER -