Resource efficient machine learning for driver safety
| Reference number | |
| Coordinator | RISE Research Institutes of Sweden AB |
| Funding from Vinnova | SEK 500 000 |
| Project duration | April 2022 - December 2022 |
| Status | Completed |
| Venture | Electronics, software and communication - FFI |
| Call | Electronics, software and communication - FFI - December 2021 |
| End-of-project report | 2021-05046eng.pdf (pdf, 265 kB) |
Important results from the project
This feasibility study aims to reduce traffic accidents by enabling energy-efficient and low-cost driver monitoring systems based on machine learning.
Expected long term effects
We have shown that convolution operations, which account for 90-95% of the computational cost in the type of machine learning models that can be used in driver monitoring systems, can be made significantly more efficient using pruning on the type of computational platforms used in the automotive industry. This can be exploited to extend the use of deep convolutional networks for driver monitoring as well as other functions that require image recognition.
Approach and implementation
We worked experimentally by studying convolution operations from a popular image processing network, resnet50. We developed sparse algorithms for convolution and adapted them to the type of processors used in the automotive industry and we compared the performance with similarly adapted non-sparse operations.