Noninvasive Tracking of Every Individual in Unmarked Mouse Groups Using Multi-Camera Fusion and Deep Learning / 神经科学通报·英文版

Accurate and efficient methods for identifying and tracking each animal in a group are needed to study complex behaviors and social interactions. Traditional tracking methods (e.g., marking each animal with dye or surgically implanting microchips) can be invasive and may have an impact on the social behavior being measured. To overcome these shortcomings, video-based methods for tracking unmarked animals, such as fruit flies and zebrafish, have been developed. However, tracking individual mice in a group remains a challenging problem because of their flexible body and complicated interaction patterns. In this study, we report the development of a multi-object tracker for mice that uses the Faster region-based convolutional neural network (R-CNN) deep learning algorithm with geometric transformations in combination with multi-camera/multi-image fusion technology. The system successfully tracked every individual in groups of unmarked mice and was applied to investigate chasing behavior. The proposed system constitutes a step forward in the noninvasive tracking of individual mice engaged in social behavior.

Deformation Characteristics of Hand Movement During Grasping / 医用生物力学

Objective Based on the multi-camera digital image correlation (DIC) method, the dynamic deformation characteristics of human hand during grasping were studied. Methods A continuous four-camera DIC system was established to measure surface strain of the skin on the back of the hand during grasping process, and then through the connection between skin, joints, bones and muscles, the regular pattern of muscle deformation could be known indirectly. Results Four grasping postures (medium cylinder, lateral pinch, index finger extension, power sphere) were measured. It was found that the increases of strain magnitude were different at different positions on back surface of the hand under different grasping postures, and the maximum principal strains were between 0.1 and 0.3. The movement characteristics for each muscle group of the hand under different grasping postures were obtained through analysis. Conclusions This method has the characteristics of non-contact, full field, intuitive results, which provides a new way for in vivo measurement of dynamic deformation during grasping.