🤖 AI Summary
This work addresses the high energy consumption and deployment challenges of conventional deep learning models in autonomous driving perception by proposing an efficient multi-object detection and tracking method based on spiking neural networks (SNNs) and neuromorphic computing. Leveraging transfer learning and a novel SpikeYOLO architecture, the approach achieves mAP scores of 0.937 and 0.771 and HOTA metrics of 0.701 and 0.445 on the KITTI and BDD100K MOT2020 datasets, respectively—performance comparable to traditional models while significantly reducing energy usage. This study presents the first comprehensive evaluation of SNNs for multi-object detection and tracking in real-world autonomous driving scenarios, demonstrating their potential for jointly optimizing accuracy and energy efficiency.
📝 Abstract
Deep learning algorithms are notorious for their high carbon footprint and computational demands that limit their deployment on edge devices and raise concerns about their long-term sustainability. Neuromorphic computing and Spiking Neural Networks (SNNs) offer a promising alternative to traditional Von Neumann architectures, providing energy-efficient performance, massively parallel computation, and on-chip learning capabilities. Autonomous machines represent a critical application domain where these advantages are particularly valuable. We present the first comprehensive evaluation of SNNs for real-world automotive multi-object detection and tracking. Using transfer learning with the SpikeYOLO architecture, we achieve mean Average Precision of 0.937 on the KITTI dataset and 0.771 on BDD100K MOT2020 dataset for object detection and a Higher Order Tracking Accuracy score of 0.701 (KITTI) and 0.445 (BDD100K MOT2020) for object tracking--results competitive with conventional deep learning methods. Our results demonstrate that SNNs can deliver high-performance object detection and tracking in an energy efficient manner, establishing their viability for perception in real-world autonomous systems.