Rapid Deployment of Domain-specific Hyperspectral Image Processors with Application to Autonomous Driving
This work addresses the problem of efficient on-board processing for autonomous driving systems, but it is incremental as it adapts existing methods to new hardware constraints.
The paper tackled deploying hyperspectral image segmentation for autonomous driving on low-cost hardware by adapting a lightweight fully convolutional network to a System-On-Module, using quantization techniques to reduce computation and storage while maintaining accuracy.
The article discusses the use of low cost System-On-Module (SOM) platforms for the implementation of efficient hyperspectral imaging (HSI) processors for application in autonomous driving. The work addresses the challenges of shaping and deploying multiple layer fully convolutional networks (FCN) for low-latency, on-board image semantic segmentation using resource- and power-constrained processing devices. The paper describes in detail the steps followed to redesign and customize a successfully trained HSI segmentation lightweight FCN that was previously tested on a high-end heterogeneous multiprocessing system-on-chip (MPSoC) to accommodate it to the constraints imposed by a low-cost SOM. This SOM features a lower-end but much cheaper MPSoC suitable for the deployment of automatic driving systems (ADS). In particular the article reports the data- and hardware-specific quantization techniques utilized to fit the FCN into a commercial fixed-point programmable AI coprocessor IP, and proposes a full customized post-training quantization scheme to reduce computation and storage costs without compromising segmentation accuracy.