Application of Superpixels to Segment Several Landmarks in Running Rodents

TL;DR

This paper presents a superpixels-based image segmentation method to efficiently identify landmarks in running rodents, improving the speed and accuracy of kinematic analysis in neuroscience research.

Contribution

It introduces a novel segmentation approach using superpixels with spatial and color information, optimized for analyzing high-speed rodent locomotion.

Findings

RGB images slightly outperform hue in segmentation accuracy

Hue representation better captures relevant color features for merging and classification

Method reduces manual effort in landmark tracking

Abstract

Examining locomotion has improved our basic understanding of motor control and aided in treating motor impairment. Mice and rats are the model system of choice for basic neuroscience studies of human disease. High frame rates are needed to quantify the kinematics of running rodents, due to their high stride frequency. Manual tracking, especially for multiple body landmarks, becomes extremely time-consuming. To overcome these limitations, we proposed the use of superpixels based image segmentation as superpixels utilized both spatial and color information for segmentation. We segmented some parts of body and tested the success of segmentation as a function of color space and SLIC segment size. We used a simple merging function to connect the segmented regions considered as neighbor and having the same intensity value range. In addition, 28 features were extracted, and t-SNE was used to demonstrate how much the methods are capable to differentiate the regions. Finally, we compared the segmented regions to a manually outlined region. The results showed for segmentation, using the RGB image was slightly better compared to the hue channel. For merg- ing and classification, however, the hue representation was better as it captures the relevant color information in a single channel.