基于改进型Faster R-CNN的仓储环境物体识别技术研究 |
点此下载全文 |
引用本文:周诗捷1,王玉槐1,沈思橙1,陈在娥1,韩江涛1,陈昱臻2.基于改进型Faster R-CNN的仓储环境物体识别技术研究[J].计算技术与自动化,2024,(2):187-191 |
摘要点击次数: 182 |
全文下载次数: 0 |
|
|
中文摘要:为解决传统目标检测精确度不高、有效性差、难以适应仓储环境下多目标识别应用场景的问题,提出了一种改进型Faster R-CNN目标检测算法。首先,采用ResNet50替换VGG16作为特征提取网络,以提高模型的检测精度;同时,为兼顾多尺度及小目标物体的检测,引入了特征金字塔网络,形成了残差金字塔特征提取网络ResFPN;其次,引入了注意力机制,提高输入特征的空间和通道有效信息利用率;最后,使用RoI Align代替原有的RoI Pooling,以消除因量化取整而产生的预测框回归误差。在经图像增广处理的自建数据集上进行实验测试,结果表明,提出的改进型Faster R-CNN算法在仓储环境下能满足对人员、叉车和托盘的目标检测需求,其平均检测精确度能达到90.2%。 |
中文关键词:仓储环境 目标检测 注意力机制 Faster R-CNN |
|
Research on Object Recognition in Warehouse Environment Based on Improved Faster R-CNN |
|
|
Abstract:In order to solve the problem of low accuracy and poor effectiveness of traditional target detection, which is difficult to adapt to the application scenarios of multi-target recognition in warehouse environment, an improved Faster R-CNN target detection algorithm is proposed. Firstly, ResNet50 is used to replace VGG16 as the feature extraction network to improve the detection accuracy of the model. At the same time, in order to take into account the detection of multi-scale and small target objects, a feature pyramid network is introduced to form a residual pyramid feature extraction network called ResFPN. Secondly, attention mechanism is introduced to improve the effective information utilization rate of the input feature space and channels. Finally, ROI Align is used to replace the original ROI Pooling to eliminate the prediction box regression error caused by quantization rounding. The experimental tests were conducted on the self-built data set with data augmentation. The experimental results show that the improved Faster R-CNN algorithm proposed in this paper can meet the detection requirements of targets such as people, forklifts and pallets in the warehouse environment with an average detection accuracy of 90.2%. |
keywords:warehouse environment object detection attention mechanism Faster R-CNN |
查看全文 查看/发表评论 下载pdf阅读器 |