基于改进 Faster R-CNN 的瓶装饮料商品目标检测方法
Target Detection Method of Bottled Drinks Based on Improved Faster R-CNN
-
摘要: 该文以无人售货机售卖瓶装饮料商品为研究场景, 提出一种基于改进 Faster R-CNN 算法的瓶装饮料商品目标检测方法。首先, 采用残差网络 ResNet-50 进行特征提取, 加深网络对目标特征的提取和学习的深度；然后, 根据瓶装饮料商品形态学特征, 增加区域建议网络(Regional Proposal Network) 的锚框数量和样式；最后, 基于所提出的多维特征图融合网络, 增强了网络对小目标的检测性能。实验结果表明, 模型训练迭代 10 000 次后的损失值趋于收敛, 10 个类别的瓶装饮料商品平均精度值均在 90% 以上, 综合检测识别率平均精度均值(MAP)为 93.26%, 较改进前的模型测试精度提升 20%, 取得良好检测效果。Abstract: This paper presents an improved faster R-CNN algorithm based on the application of unmanned vending machine selling bottled drinks. Firstly, the residual network ResNet-50 is used as the feature extraction network to deepen the depth of target feature extraction and learning. Then, the number and style of anchor frame in regional proposal network (RPN) is improved according to the morphological characteristics of bottled beverage products. Finally, a multi-dimensional feature map fusion network is proposed to enhance the detection performance of small targets. The experimental results showed that, the loss value tends to converge after 10 000 iterations of model training. Average precision values of 10 categories of bottled beverage products are all larger than 90%. And the comprehensive detection recognition rate mean average precision value is 93.26%, which is improved 20% compared with the original model.
下载: