基于RetinaNet及优化损失函数的夜间车辆检测方法

A Method of Vehicle Detection at Night Based on RetinaNet and Optimized Loss Functions

为解决智能驾驶系统中夜间车辆检测误检多、远处小目标检测效果差的问题,在RetinaNet的基础上对损失函数进行全面优化。在分类损失函数方面,分析了负样本与正样本交并比的产生机理和对训练的影响,构造了关联交并比的分类损失函数,利用负样本交并比使网络注重于训练难分类负样本,同时利用正样本交并比提高了检测框的定位精度;在定位损失函数方面,改进了传统L1损失的归一化方式,提高了小目标检测能力。此外,针对夜间场景中的车辆特征对网络结构进行了优化设计,并在夜间车辆数据集上进行了测试验证,结果表明模型优化后的平均检测精度提升了14.6%。

In view of the high false detection rate and poor detection results for distant small target in vehi⁃cle detection at night for intelligent driving system,the loss functions are comprehensively optimized based on Reti⁃naNet.For classification loss function,both the generation mechanism and the influence on training results of the IoUs of negative and positive samples are analyzed,the classification loss function of correlated IoU is constructed,the IoU of negative sample is used to make network lay emphasis on the training of negative samples,which are hard to classify,meanwhile the IoU of positive sample is used to enhance the locating accuracy of detection frame.For lo⁃cating loss function,the normalization way of traditional L1 loss is improved and the ability of small target detection is enhanced.In addition,a design optimization is conducted on network structure for the vehicle features in night scene,and a test verification is performed on vehicle data at night.The results show that the average detection accu⁃racy of the model optimized increases by 14.6 percentage point.