首页> 美国卫生研究院文献>Heliyon >A multi-branch separable convolution neural network for pedestrian attribute recognition
【2h】

A multi-branch separable convolution neural network for pedestrian attribute recognition

机译:用于行人属性识别的多分支可分离卷积神经网络

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

Video surveillance applications have made great strides in making the world a safer place. Extracting visual attributes from a scene, such as the type of shoes, the type of clothing, carrying any object or not, or wearing any accessory etc., is a challenging problem and an efficient solution holds the key to a great number of applications. In this paper, we present a multi-branch convolutional neural network that uses epthwise eparable onvolution (DSC) layers to solve the pedestrian attribute recognition problem. Researchers have proposed various solutions over the years making use of convolutional neural networks (CNN), however, we introduce DSC layers to the CNN for the problem of pedestrian attribute recognition. In addition, we make a novel use of the different color spaces and create a 3-branch CNN, denoted as 3bCNN, that is efficient, especially with smaller datasets. We experiment on two benchmark datasets and show results with improvement over the state of the art.
机译:视频监控应用在使世界更安全的过程中取得了长足的进步。从场景中提取视觉属性,例如鞋子的类型,衣服的类型,是否携带任何物体或穿着任何附件等,是一个具有挑战性的问题,有效的解决方案是许多应用程序的关键。在本文中,我们提出了一种多分支卷积神经网络,该网络使用逐层可扩展卷积(DSC)层来解决行人属性识别问题。多年来,研究人员提出了各种使用卷积神经网络(CNN)的解决方案,但是,针对行人属性识别问题,我们将DSC层引入了CNN。另外,我们新颖地利用了不同的色彩空间,并创建了一个高效的3分支CNN(称为3bCNN),尤其是对于较小的数据集。我们对两个基准数据集进行了实验,并显示了与现有技术相比有所改进的结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号