激光与光电子学进展, 2021, 58 (4): 0415009, 网络出版: 2021-02-22
基于改进残差网络的道口车辆分类方法 下载: 852次
Classification Method of Crossing Vehicle Based on Improved Residual Network
图 & 表
图 2. 改进对比。(a)原始残差块;(b)改进残差块
Fig. 2. Improve comparison. (a) Original residual block; (b) improved residual block
图 6. 不同模型处理的热力图。(a)原图;(b)原始模型ResNet;(c)增加注意力机制后的模型
Fig. 6. Heat maps processed by different models. (a) Original map; (b) original model ResNet; (c) model with attention mechanism
表 1不同模型在Stanford Cars数据集中的准确率
Table1. Accuracy of different models on Stanford Cars dataset
|
表 2消融实验结果
Table2. Results of ablation experiment
|
李宇昕, 杨帆, 刘钊, 司亚中. 基于改进残差网络的道口车辆分类方法[J]. 激光与光电子学进展, 2021, 58(4): 0415009. Yuxin Li, Fan Yang, Zhao Liu, Yazhong Si. Classification Method of Crossing Vehicle Based on Improved Residual Network[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0415009.