Self-Configurable Stabilized Real-Time Detection Learning for Autonomous Driving Applications
This work addresses the critical need for reliable and efficient object detection in autonomous vehicles, though it is incremental as it builds on existing detection and optical flow networks.
The paper tackles the trade-off between real-time performance and accuracy in object detection for autonomous driving by proposing a self-configurable framework that uses optical flow and Lyapunov optimization to adaptively switch between detection modes, resulting in improvements of 3.02% in accuracy and 59.6% in the number of detected objects while ensuring queue stability.
Guaranteeing real-time and accurate object detection simultaneously is paramount in autonomous driving environments. However, the existing object detection neural network systems are characterized by a tradeoff between computation time and accuracy, making it essential to optimize such a tradeoff. Fortunately, in many autonomous driving environments, images come in a continuous form, providing an opportunity to use optical flow. In this paper, we improve the performance of an object detection neural network utilizing optical flow estimation. In addition, we propose a Lyapunov optimization framework for time-average performance maximization subject to stability. It adaptively determines whether to use optical flow to suit the dynamic vehicle environment, thereby ensuring the vehicle's queue stability and the time-average maximum performance simultaneously. To verify the key ideas, we conduct numerical experiments with various object detection neural networks and optical flow estimation networks. In addition, we demonstrate the self-configurable stabilized detection with YOLOv3-tiny and FlowNet2-S, which are the real-time object detection network and an optical flow estimation network, respectively. In the demonstration, our proposed framework improves the accuracy by 3.02%, the number of detected objects by 59.6%, and the queue stability for computing capabilities.