Object Detection based on LIDAR Temporal Pulses using Spiking Neural Networks
This addresses computational overhead and latency in autonomous driving by enabling direct processing of raw LIDAR data, though it is incremental as it applies SNNs to a new data type.
The paper tackled object detection from raw LIDAR temporal pulses using Spiking Neural Networks (SNN), achieving 99.83% accuracy with 10% noise and an average recognition delay of 265 ns.
Neural networks has been successfully used in the processing of Lidar data, especially in the scenario of autonomous driving. However, existing methods heavily rely on pre-processing of the pulse signals derived from Lidar sensors and therefore result in high computational overhead and considerable latency. In this paper, we proposed an approach utilizing Spiking Neural Network (SNN) to address the object recognition problem directly with raw temporal pulses. To help with the evaluation and benchmarking, a comprehensive temporal pulses data-set was created to simulate Lidar reflection in different road scenarios. Being tested with regard to recognition accuracy and time efficiency under different noise conditions, our proposed method shows remarkable performance with the inference accuracy up to 99.83% (with 10% noise) and the average recognition delay as low as 265 ns. It highlights the potential of SNN in autonomous driving and some related applications. In particular, to our best knowledge, this is the first attempt to use SNN to directly perform object recognition on raw Lidar temporal pulses.