Abstract
Human motion analysis provides useful information for the diagnosis and recovery assessment of people suffering from pathologies, such as those affecting the way of walking, i.e., gait. With recent developments in deep learning, state-of-the-art performance can now be achieved using a single 2D-RGB-camera-based gait analysis system, offering an objective assessment of gait-related pathologies. Such systems provide a valuable complement/alternative to the current standard practice of subjective assessment. Most 2D-RGB-camera-based gait analysis approaches rely on compact gait representations, such as the gait energy image, which summarize the characteristics of a walking sequence into one single image. However, such compact representations do not fully capture the temporal information and dependencies between successive gait movements. This limitation is addressed by proposing a spatiotemporal deep learning approach that uses a selection of key frames to represent a gait cycle. Convolutional and recurrent deep neural networks were combined, processing each gait cycle as a collection of silhouette key frames, allowing the system to learn temporal patterns among the spatial features extracted at individual time instants. Trained with gait sequences from the GAIT-IT dataset, the proposed system is able to improve gait pathology classification accuracy, outperforming state-of-the-art solutions and achieving improved generalization on cross-dataset tests.
Highlights
Gait can be defined as a sequence of limb movements that produces locomotion.Its analysis has a wide range of application in the fields of surveillance, forensics, and medicine
The recurrent neural network architecture considered to process the temporal information was the Long Short-Term Memory (LSTM) network [35], since it addresses the limitation of Recurrent Neural Networks (RNNs) to store long-term dependencies and it regulates the information that flows through the network
The acquisition of the gait data for GAIT-IT was performed on two different days, with prior training offered through videos, live demos, and practice sessions
Summary
Gait can be defined as a sequence of limb movements that produces locomotion.Its analysis has a wide range of application in the fields of surveillance, forensics, and medicine. Among the camera-based approaches, the use of markers still represents the goldstandard Solutions, such as the one reported in [13], are typically based on the application of these markers on key body parts and use multiple optical sensors to obtain kinematic features from the observed motion. This type of approach often relies on controlled environments and specialized personnel, as well as setup and calibration processes that can be very time-consuming and impractical in less constrained environments
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have