计算机工程 ›› 2018, Vol. 44 ›› Issue (6): 176-181.doi: 10.19678/j.issn.1000-3428.0047321

• 图形图像处理 • 上一篇    下一篇

卷积神经网络物体检测算法在物流仓库中的应用

李天剑  1,黄斌  2,刘江玉  1,金秋  1   

  1. 1.北京信息科技大学 机电工程学院,北京 100192; 2.北京航空航天大学 自动化科学与电气工程学院,北京 100191
  • 收稿日期:2017-05-23 出版日期:2018-06-15 发布日期:2018-06-15
  • 作者简介:李天剑(1969—),男,副教授、博士,主研方向为图形图像处理、机器人技术、计算机视觉;黄斌,博士研究生;刘江玉、金秋,硕士研究生。
  • 基金项目:
    北京市科技计划项目(Z171100000817006)。

Application of Convolution Neural Network Object Detection Algorithm in Logistics Warehouse

LI Tianjian  1 , HUANG Bin  2  ,LIU Jiangyu  1,JIN Qiu  1   

  1. 1.School of Mechanical and Electrical Engineering,Beijing Information Science and Technology University,Beijing 100192,China; 2.School of Automation Science and Electrical Engineering,Beihang University,Beijing 100191,China
  • Received:2017-05-23 Online:2018-06-15 Published:2018-06-15

摘要: 针对传统物体检测算法在复杂环境下检测准确率较低的问题,提出一种新的托盘检测算法。采集真实仓库中包括人和托盘的大量图片进行标注,构建物流仓库的托盘数据库,并将单次多箱探测器检测算法中的基础网络改进为DenseNet网络,利用所标注的托盘数据库进行训练和测试。在测试阶段,结合不同分辨率的多尺度特征图,以增强网络对被检测物体的适应能力,并使用单一网络实现检测任务。实验结果表明,与YOLO算法相比,该算法检测准确率提高了6.1%。

关键词: 物体检测, 托盘检测, 卷积神经网路, 深度学习, 稠密连接卷积神经网络

Abstract: In complex environments,the accuracies of traditional object detection algorithms is too low.A new pallet detection algorithm is proposed.A large number of pictures containing people and pallets in real warehouses are collected and annotated to building the pallets dataset for training.In the paper,the based network of the improved algorithm based on Single Shot MultiBox Detector(SSD) pipeline is adapted with DenseNet.In the experiments,the real pallets dataset is used for training and testing.In the testing phase,multi-scale feature maps of different resolutions are utilized for enhancing the network’s ability to adapt to detected objects,and the detection task is employing with single network.The experiment results show that the accuracy of the improved algorithm increased by 6.1% compared with YOLO algorithm.

Key words: object detection, pallet detection, Convolution Neural Betwork(CNN), deep learning, densely connected convolutional neural network

中图分类号: