arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1904.02074cs.CVcs.RO
收藏

基于视觉神经网络的汽车碰撞鲁棒感知

A Visual Neural Network for Robust Collision Perception in Vehicle Driving Scenarios

University of Lincoln(林肯大学);Guangzhou University(广州大学);Newcastle University(纽卡斯尔大学)

Qinbing Fu, Nicola Bellotto, Huatian Wang, F. Claire Rind, Hongxin Wang, Shigang Yue

摘要:

本研究解决了在非常复杂和动态的真实物理场景中,特别是车辆驾驶场景中的视觉碰撞检测的挑战性问题。这项研究的灵感来自于一个大视野隐约可见的敏感神经元,即,蝗虫视觉通路中的小叶巨型运动探测器(LGMD),它代表了快速接近物体的高尖峰频率。在我们以前的模型的基础上,在本文中,我们提出了一种新的抑制机制,能够适应不同层次的背景复杂性。这种自适应机制有效地调节了局部抑制强度,并调节了到达LGMD神经元的局部兴奋的时间延迟。结果表明,该模型能有效地从复杂的动态视觉场景中提取碰撞线索。我们测试了所提出的方法,使用一系列的刺激,包括模拟运动光栅背景和自然全景场景的转移,以及车辆碰撞视频序列。实验结果表明,该方法是可行的快速碰撞感知在现实世界的情况下,在未来的自动驾驶汽车的潜在应用。

英文摘要:

This research addresses the challenging problem of visual collision detection in very complex and dynamic real physical scenes, specifically, the vehicle driving scenarios. This research takes inspiration from a large-field looming sensitive neuron, i.e., the lobula giant movement detector (LGMD) in the locust's visual pathways, which represents high spike frequency to rapid approaching objects. Building upon our previous models, in this paper we propose a novel inhibition mechanism that is capable of adapting to different levels of background complexity. This adaptive mechanism works effectively to mediate the local inhibition strength and tune the temporal latency of local excitation reaching the LGMD neuron. As a result, the proposed model is effective to extract colliding cues from complex dynamic visual scenes. We tested the proposed method using a range of stimuli including simulated movements in grating backgrounds and shifting of a natural panoramic scene, as well as vehicle crash video sequences. The experimental results demonstrate the proposed method is feasible for fast collision perception in real-world situations with potential applications in future autonomous vehicles.

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。

↑