Publications

@inproceedings{Shi2024ICIEA,

title = {Combining old school autoencoder with Cotracker for improved skin feature tracking},

author = {Wei-Pei Shi and Torbjörn E M Nordling},

year  = {2024},

date = {2024-08-01},

urldate = {2024-08-01},

booktitle = {The 19th IEEE Conference on Industrial Electronics and Applications (ICIEA 2024)},

publisher = {IEEE},

address = {Kristiansand, Norway},

series = {IEEE Conference on Industrial Electronics and Applications (ICIEA 2024)},

abstract = {Abstract—Background: Skin feature tracking enables quantification of human 

 motion in an explainable way, making it suitable for clinical assessments. 

 Accuracy is crucial, but no study has investigated state-of-the-art deep neural 

 network-based point tracking models such as Cotracker. Cotracker jointly tracks 

 points and has been shown to have better 3-pixel accuracy than five other 

 state-of-the-art deep learning methods on the two most commonly used datasets 

 for evaluation of single target point tracking. In 2021, Chang and Nordling 

 introduced the Deep Feature Encoder (DFE) and demonstrated skin feature tracking 

 so accurate that the errors cannot be excluded to stem from the manual labeling 

 of the videos based on a χ2-test. 

 Problem: How accurately can different methods track skin features and how to avoid 

 the intrinsic weaknesses of the methods? 

 Methods: We use videos of the Unified Parkinson’s Disease Rating Scale postural 

 tremor test recorded at two hospitals for benchmarking. DFE utilizes the encoder 

 part of an autoencoder consisting of a five-layer convolutional neural network 

 trained to reproduce skin crops without supervision. The residual squared error 

 of the latent features of the encoder is then compared with crops to obtain a 

 predicted position. We also propose Cotracker DFE, using Cotracker to obtain an 

 approximate position and subsequently cropping a small area that is fed to DFE 

 to obtain a position predicted with a lower mean pixel error. 

 Results: The mean Euclidean distance errors of Cotracker, DFE, and Cotracker-DFE 

 are 1.2, 0.8, and 0.8 pixels, respectively. DFE requires time-consuming computations, 

 making it 35 times slower than Cotracker. 

 Conclusion: The old school DFE provided more accurate skin feature tracking, while 

 combining DFE with Cotracker provides the best overall performance, circumventing 

 the lack of labeled data and computational resources required to fine-tune Cotracker.},

howpublished = {The 19th IEEE Conference on Industrial Electronics and Applications (ICIEA 2024),  in Kristiansand, Norway 05-08 August 2024},

keywords = {autoencoder, Convolutional neural network, Cotracker, Deep feature encoder, human motion assessment, Skin feature tracking, Transformer},

pubstate = {published},

tppubtype = {inproceedings}

}