Lightweight network and parallel computing for fast pedestrian detection,International Journal of Circuit Theory and Applications

当前位置： X-MOL 学术 › Int. J. Circ. Theory Appl. › 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.)

Lightweight network and parallel computing for fast pedestrian detection
International Journal of Circuit Theory and Applications ( IF 1.8 ) Pub Date : 2020-11-04 , DOI: 10.1002/cta.2903
Jianpeng Wu ₁ , Yao Men ₁ , DeSheng Chen ₁

Affiliation

In recent years, researchers have made great efforts in computer vision task (e.g., object detection) with the widely use of convolutional neural networks (CNNs). However, object detection algorithms based on CNNs suffer from high computation cost even on the high‐performance computers. In addition, with the development of high‐resolution videos, the deployment of object detection algorithms becomes more and more difficult because of the large amount of data, let alone the portable platforms, such as unmanned aerial vehicles (UAVs). In this paper, we research a lightweight network on portable platform for outdoor tiny pedestrian detection. Concretely, we first set up a training dataset manually for lack of tiny pedestrian samples in common datasets. We provide a lightweight network, and then, parallel computing is introduced to make the most of the advantage of GPU. Finally, our method can achieve real‐time performance on Jetson TX2. Experimental results verify that the proposed model has promising performance in tiny pedestrian detection designed for portable GPU platforms.

中文翻译：

轻量级网络和并行计算，可快速检测行人

近年来，随着卷积神经网络（CNN）的广泛使用，研究人员在计算机视觉任务（例如，对象检测）上做出了巨大的努力。但是，即使在高性能计算机上，基于CNN的目标检测算法也要承受较高的计算成本。此外，随着高分辨率视频的发展，由于数据量大，对象检测算法的部署变得越来越困难，更不用说便携式平台（例如无人机）了。在本文中，我们研究了便携式平台上的轻型网络，用于室外微小行人检测。具体而言，我们首先手动建立了一个训练数据集，以解决常见数据集中缺少微小的行人样本的问题。我们提供了一个轻量级的网络，然后，引入并行计算以充分利用GPU的优势。最后，我们的方法可以在Jetson TX2上实现实时性能。实验结果证明，该模型在为便携式GPU平台设计的微小行人检测中具有良好的性能。

更新日期：2020-11-04

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11