Red grape detection with accelerated artificial neural networks in the FPGA's programmable logic
This work addresses speed constraints in robotic object detection, but it is incremental as it applies existing methods (FINN architecture and quantized models) to a new dataset.
The paper tackled the problem of slow object detection in robots by deploying quantized artificial neural networks on FPGAs, achieving a success rate of 98% and an inference speed of 6611 FPS with MobileNet v1.
Robots usually slow down for canning to detect objects while moving. Additionally, the robot's camera is configured with a low framerate to track the velocity of the detection algorithms. This would be constrained while executing tasks and exploring, making robots increase the task execution time. AMD has developed the Vitis-AI framework to deploy detection algorithms into FPGAs. However, this tool does not fully use the FPGAs' PL. In this work, we use the FINN architecture to deploy three ANNs, MobileNet v1 with 4-bit quantisation, CNV with 2-bit quantisation, and CNV with 1-bit quantisation (BNN), inside an FPGA's PL. The models were trained on the RG2C dataset. This is a self-acquired dataset released in open access. MobileNet v1 performed better, reaching a success rate of 98 % and an inference speed of 6611 FPS. In this work, we proved that we can use FPGAs to speed up ANNs and make them suitable for attention mechanisms.