基于差异性区域预测的行人与骑车人联合检测

本文中针对自动驾驶车辆在环境感知过程中易将行人与骑车人混淆的问题,提出一种有效区分行人与骑车人的联合检测方法,并基于快速区域卷积神经网络Faster R-CNN进行改进。首先,通过增加一个子网络提取图像形状特征通道,将其与主干网络生成的特征图进行聚合,额外的形状语义通道用以辅助检测器区分行人与骑车人的特征;接着,通过构建差异性区域预测单元,以区分行人与骑车人差异部位,将建议区域划分为多个部件并计算其置信度,根据该置信度对部件特征进行加权;最后,将主体特征与加权后的部件特征聚合后送至分类器进行分类。在本文中构建的行人-骑车人数据集和公开的Caltech数据集中进行测试的结果表明,改进后的检测方法能有效减少将骑车人误检为行人的情况,具有较高的检测精度。

Joint Detection of Pedestrian and Rider Based on Diversity Region Prediction

Aiming at the problem that autonomous vehicles tend to confuse pedestrians and riders in the process of environmental perception,a joint detection method to effectively distinguish pedestrians and riders is pro?posed in this paper,with an improvement made based on faster region convolutional neural networks.Firstly,a sub?network is added to extract the shape feature channel of images,which is then aggregated with the feature map gen?erated by the backbone network,and the additional shape semantic channels are used for assisting the detector to distinguish the pedestrian and rider features.Then,a diversity region prediction unit is constructed to distinguish the distinct parts between pedestrians and riders and the suggested regions are divided into several parts with their confidence calculated,which is then used to determine the weight of part feature.Finally,the part features are ag?gregated with main?body feature and are sent to classifier for classification.The results of test on both pedestrian-rider data set built in this paper and open Caltech data set show that the improved detection method has relatively high detection accuracy,and the situations of the rider being mis?detected as pedestrian are effectively reduced.