Towards real-time whisker tracking in rodents for studying sensorimotor disorders
The rodent whisker system is a prominent experimental subject for the study of sensorimotor integration and active sensing. As a result of improved video-recording technology and progressively better neurophysiological methods, there is now the prospect of precisely analyzing the intact vibrissal sensori-motor system. The vibrissae and snout analyzer (ViSA), a widely used algorithm based on computer vision and image processing, has been proven successful for tracking and quantifying rodent sensorimotor behavior, but at a great cost in processing time. In order to accelerate this offline algorithm and eventually employ it for online whisker tracking (less than 1 ms/frame latency), we have explored various optimizations and acceleration platforms, including OpenMP multithreading, NVidia GPUs and Maxeler Dataflow Engines. Our experimental results indicate that the optimal solution for an offline implementation of ViSA is currently the OpenMP-based CPU execution. By using 16 CPU threads, we achieve more than 4,500x speedup compared to the original Matlab serial version, resulting in an average processing latency of 1.2 ms/frame, which is a solid step towards real-time (and online) tracking. Analysis shows that running the algorithm on a 32-thread-enabled machine can reduce this number to 0.72 ms/frame, thereby enabling real-time performance. This will allow direct interaction with the whisker system during behavioral experiments. In conclusion, our approach shows that a combination of software optimizations and the careful selection of hardware platform yields the best performance increase.
|17th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS 2017|
|Organisation||Department of Neuroscience|
Ma, Y, Geethakumari, P.R. (Prajith Ramakrishnan), Smaragdos, G, Lindeman, S, Romano, V, Negrello, M, … Strydis, C. (2018). Towards real-time whisker tracking in rodents for studying sensorimotor disorders. In Proceedings - 2017 17th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS 2017 (pp. 137–145). doi:10.1109/SAMOS.2017.8344621