梁继然,陈 壮,董国军,陈 琦,许延雷.结合注意力机制和密集连接网络的车辆检测方法[J].电子测量与仪器学报,2022,36(3):210-216 |
结合注意力机制和密集连接网络的车辆检测方法 |
Vehicle detection method combining attentionmechanism and dense connection network |
|
DOI: |
中文关键词: 车辆检测 密集连接网络 注意力机制 SoftPool |
英文关键词:vehicle detection densely connected network attention mechanism SoftPool |
基金项目:天津市科技重大专项与工程(19ZXZNGX00060)项目资助 |
|
|
摘要点击次数: 732 |
全文下载次数: 950 |
中文摘要: |
为提高算法对车辆检测的准确性,解决原有算法在复杂交通场景下对车辆检测效果不佳的问题,提出一种基于注意力
机制和改进密集连接网络结构的车辆检测方法。 首先在过渡层中使用 SoftPool 整合密集块之间的特征信息;其次通过轻量化
通道注意力机制加强有效通道特征的表达,将其作为 Darknet-53 的深层特征提取层;引入 CIOU 损失作为模型的边界框位置预
测损失项,使用深度可分离卷积缩减模型体积;与原算法相比 mAP 值提高 2. 6%,模型体积缩减为原来的 42%,实验证明本算法
在复杂交通场景下具有良好的检测性能。 |
英文摘要: |
To improve the accuracy of the algorithm for vehicle detection and solve the problem that the original algorithm is not effective
in the complex traffic scene, a vehicle detection method based on attention mechanism and improved densely connection network
structure was proposed. Firstly, SoftPool was used in the transition layer to consolidate the characteristic information between the dense
blocks. Secondly, the expression of effective channel features was enhanced by the lightweight channel attention mechanism, it was used
as the deep feature extraction layer of Darknet-53. The CIOU loss was used as the prediction loss term of the bounding box position of the
model, and reduce the model volume using deep separable convolution. Compared with the original algorithm, the mAP value is
increased by 2. 6%, and the model volume is reduced to 42%. Experimental results show that the algorithm has good detection
performance in complex traffic scene. |
查看全文 查看/发表评论 下载PDF阅读器 |