The objective of this paper is to provide an overview of the current state of the art from both methodologicaland experimental perspectives. The first part of the paper consists of a survey. We cover the main components of a pedestrian detection syst

通过fisher对hog特征降维，并用于物体检测-We present a method for object detection that combines AdaBoost learning with local histogram features. On the side of learning we improve the performance by designing a weak learner for multi-valued features based on Weighte

通过改进基于Haar-like特征和Adaboost的级联分类器，提出一种融合Haar-like特征和 HOG特征的道路车辆检测方法-By improving based on Haar-like features and Adaboost cascade classifier, presents a fusion of Haar-like features and characteristics of HOG road vehicle detection method

ICCV2013： 简 称UDN算法，从文中描述的检测效果来看，该方法是所有方法中最好的，并且，效果远超过其他方法。经过对论文和该算法源码的研究，该算法是与作者另外一篇 论文的方法 ，另外的论文算法做图片扫描，得到矩形框，然后用该方法对矩形框进行进一步确认，以及降低误警率和漏警率。另外的论文是：Multi-Stage Contextual Deep Learning for Pedestrian Detection 说得难听一点，这篇文章对行人检测没有多大的贡献。仅仅是用深度学习