Hand tremor detection in videos with cluttered background using neural network based approaches

Abstract

With the increasing prevalence of neurodegenerative diseases, including Parkinson's disease, hand tremor detection has become a popular research topic because it helps with the diagnosis and tracking of disease progression. Conventional hand tremor detection algorithms involved wearable sensors. A non-invasive hand tremor detection algorithm using videos as input is desirable but the existing video-based algorithms are sensitive to environmental conditions. An algorithm, with the capability of detecting hand tremor from videos with a cluttered background, would allow the videos recorded in a non-research environment to be used. Clinicians and researchers could use videos collected from patients and participants in their own home environment or standard clinical settings. Neural network based machine learning architectures provide high accuracy classification results in related fields including hand gesture recognition and body movement detection systems. We thus investigated the accuracy of advanced neural network architectures to automatically detect hand tremor in videos with a cluttered background. We examined configurations with different sets of features and neural network based classification models. We compared the performance of different combinations of features and classification models and then selected the combination which provided the highest accuracy of hand tremor detection. We used cross validation to test the accuracy of the trained model predictions. The highest classification accuracy for automatically detecting tremor (vs non tremor) was 80.6% and this was obtained using Convolutional Neural Network-Long Short-Term Memory and features based on measures of frequency and amplitude change.

Assessing the Usability of an Instagram Filter in Monitoring Essential Tremor: A Proof‐of‐Concept Study

“…11 Earlier attempts of using smartphone apps in monitoring ET had shown promising results. 8,12,13 Although most of these videobased tremor detection tools provide excellent characterization of tremor, they have been used only in research settings, and specialized equipment and certain professional knowledge are usually needed. 13,14 Furthermore, these sensor-based tools were found to be partially inefficient in detecting tremor fluctuation and disease progression in addition to the lack of a standardized definition and protocol for using these tools in tremor assessment.…”

Real-Time Image-Based Vibration Extraction with Memory-Efficient Optical Flow and Block-Based Adaptive Filter

“…Various research works have been carried out to date on tremor attenuation from a wide range of aspects [1]- [10]. For isolating the vibration component of tremor from voluntary motion without phase delay, which is an essential part of active tremor canceling, Riviere et al proposed an adaptive algorithm called the weighted frequency Fourier linear combiner (WFLC) [1].…”

“…For example, Uhrikova et al implemented an image-based system for measuring the frequency of tremor [7]. Soran et al developed a tremor detection system using a support vector machine (SVM) in the frequency domain [9], and Wang et al proposed a hand tremor detection system based on neuralnetwork-based approaches [10], both of which detect the presence of tremor. These are useful for diagnosis purposes, but not directly applicable to real-time tremor canceling.…”

Video-Based Hand Movement Analysis of Parkinson Patients before and after Medication Using High-Frame-Rate Videos and MediaPipe

“…Contactless measurements provide more comfortable diagnostics for patients [ 16 ], are more hygienic, and are easier to set up. Research on how to utilize video recordings to monitor PD motor symptoms has been performed in several works [ 17 , 18 , 19 , 20 , 21 ].…”