PyMiceTracking: An Open-Source Toolbox for Real-Time Behavioral Neuroscience Experiments

Richardson Menezes, Aron de Miranda, Helton Maia; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 21459-21465

The development of computational tools allows the advancement of research in behavioral neuroscience and elevates the limits of experiment design. Many behavioral experiments need to determine the animal's position from its tracking, which is crucial for real-time decision-making and further analysis of experimental data. Modern experimental designs usually generate the recording of a large amount of data, requiring the development of automatic computational tools and intelligent algorithms for timely data acquisition and processing. The proposed tool in this study initially operates with the acquisition of images. Then the animal tracking step begins with background subtraction, followed by the animal contour detection and morphological operations to remove noise in the detected shapes. Finally, in the final stage of the algorithm, the principal components analysis (PCA) is applied in the obtained shape, resulting in the animal's gaze direction.