arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.14525cs.CVcs.SYeess.SY
收藏

用于自动驾驶应用的自配置稳定实时的检测学习

Self-Configurable Stabilized Real-Time Detection Learning for Autonomous Driving Applications

Korea University(高丽大学);University of Central Florida(中佛罗里达大学)

Won Joon Yun, Soohyun Park, Joongheon Kim, David Mohaisen

摘要:

在自动驾驶环境中,同时保证实时的【形】和准确的目标检测至关重要。然而,现有的目标检测神经网络系统的特征在于计算时间和准确性之间的权衡,使得优化这样的权衡是必要的。幸运的是,在许多自动驾驶环境中,图像以连续的形式出现,这为使用光流提供了机会。在本文中,我们提高性能的目标检测神经网络利用光流估计。此外,我们提出了一个李雅普诺夫优化框架的时间平均性能最大化的稳定性。该算法自适应地确定是否使用光流来适应动态车辆环境,从而在保证车辆排队稳定性的同时保证车辆时均性能最大化。为了验证的关键思想,我们进行了各种目标检测神经网络和光流估计网络的数值实验。此外,我们展示了自配置的稳定检测与YOLOv 3-tiny和FlowNet 2-S,这是实时的【形】目标检测网络和光流估计网络,分别。在演示中,我们提出的框架提高了3.02%的准确性,检测到的对象的数量由59.6%,和计算能力的队列稳定性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑