BriefGPT.xyz
Jul, 2014
使用空间池化特征加强行人检测效果
Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features
HTML
PDF
Sakrapee Paisitkriangkrai, Chunhua Shen, Anton van den Hengel
TL;DR
本研究提出一种简单而有效的行人检测方法，其基于低级视觉特征和空间池化，将部分ROC曲线下面积直接优化，表现出色优于当前所有竞争方法，平均错误率最低达到了11％，与多个基准数据集相比，取得了最先进的结果。
Abstract
We propose a simple yet effective approach to the problem of
pedestrian detection
which outperforms the current state-of-the-art. Our new features are built on the basis of
low-level visual features
and
→