当前位置: X-MOL 学术Comput. Commun. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A novel visibility semantic feature-aided pedestrian detection scheme for autonomous vehicles
Computer Communications ( IF 6 ) Pub Date : 2021-07-08 , DOI: 10.1016/j.comcom.2021.06.009
Mingzhi Sha 1 , Azzedine Boukerche 1
Affiliation  

Intelligent transportation systems (ITS) have become a popular method for enhancing transportation safety and efficiency. As essential participants of ITS, autonomous vehicles need to detect pedestrians accurately. In this paper, we propose a one-stage anchor-free pedestrian detection model named Bi-Center Network (BCNet), which is aided by the semantic features of pedestrians’ visible parts. We perform an ablation study to discover how visibility features could benefit the detector’s performance, including introducing two hyper-parameters and adopting three different attention mechanisms, respectively. The experimental results indicate that the performance of pedestrian detection could be significantly improved, since the visibility semantic could prompt stronger responses on the heatmap. We compare our BCNet variants with state-of-the-art models on the CityPersons dataset and ETH dataset; results indicate that our detector is effective and achieves a promising performance.



中文翻译:

一种新颖的自动驾驶汽车可见性语义特征辅助行人检测方案

智能交通系统 (ITS) 已成为提高交通安全和效率的流行方法。作为 ITS 的重要参与者,自动驾驶汽车需要准确检测行人。在本文中,我们提出了一种名为 Bi-Center Network (BCNet) 的单阶段无锚行人检测模型,该模型借助行人可见部分的语义特征进行辅助。我们进行了一项消融研究,以发现可见性特征如何使检测器的性能受益,包括分别引入两个超参数和采用三种不同的注意机制。实验结果表明,行人检测的性能可以得到显着提高,因为可见性语义可以在热图上提示更强的响应。我们在 CityPersons 数据集和 ETH 数据集上将我们的 BCNet 变体与最先进的模型进行比较;结果表明我们的检测器是有效的并取得了有希望的性能。

更新日期:2021-08-03
down
wechat
bug