级联式多尺度行人检测算法研究

Study on multi-scale pedestrian detection algorithm based on cascade convolution network

针对多尺度行人检测精度不够高的问题,提出了一种级联式多尺度行人检测算法,使用矩形卷积核提取行人特征,根据行人轮廓特征设计候选区域宽高比例;并提出自适应损失函数,使网络聚焦于困难样本,有效缓解了长尾效应在训练网络时带来的不利因素,提高了网络泛化能力。实验结果表明:所提算法对于Caltech数据集中的大尺度行人,漏检率比Adapt Faster Rcnn算法降低了1.36%;对于中小尺度行人,漏检率比Adapt Faster Rcnn算法下降8.82%。

Aiming at the problem that precision of multi-scale pedestrian detection algorithm is not high,a multi-scale pedestrian detection algorithm based on cascade convolutional neural network is proposed.The rectangular convolution kernel is used to extract pedestrian features,and the ratio of width to height of proposals are designed according to pedestrian contour features and the self-adaptive loss function is proposed,which makes the network focus on hard samples and effectively alleviate adverse factors brought by the long tail effect in training network and improves the network generalization ability.Compared with Adapt Faster RCNN,the miss rate of the proposed algorithm declines by 1.36%in large-scale pedestrians of Caltech data set and that decreases by 8.82%in small and medium-sized.