Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (1): 88-97.DOI: 10.11772/j.issn.1001-9081.2021101838

• Artificial intelligence • Previous Articles     Next Articles

Arthropod object detection method based on improved Faster RCNN

GUO Zihao, DONG Lele, QU Zhijian   

  1. School of Computer Science and Technology, Shandong University of Technology, Zibo Shandong 255000, China
  • Received:2021-10-28 Revised:2022-01-06 Online:2022-03-04
  • Contact: QU Zhijian, born in 1980, Ph. D., associate professor. His research interests include machine learning, evolutionary algorithm.
  • About author:GUO Zihao, born in 1997, M. S. candidate. His research interests include machine learning, computer vision;DONG Lele, born in 1998, M. S. candidate. Her research interests include machine learning, process mining;
  • Supported by:
    This work is partially supported by Outstanding Youth Innovation Teams in Higher Education of Shandong Province (2019KJN048).

基于改进Faster RCNN的节肢动物目标检测方法

郭子豪, 董乐乐, 曲志坚   

  1. 山东理工大学 计算机科学与技术学院,山东 淄博 255000
  • 作者简介:郭子豪(1997—),男,山东临沂人,硕士研究生,CCF会员,主要研究方向:机器学习、计算机视觉;董乐乐(1998—),女,山东聊城人,硕士研究生,主要研究方向:机器学习、过程挖掘;曲志坚(1980—),男,山东青岛人,副教授,博士,CCF会员,主要研究方向:机器学习、进化算法。;
  • 基金资助:

Abstract: Arthropod object detection in natural environment has characteristics of complex object background, large scale difference, and dense objects,resulting in poor object detection accuracy and precision. Therefore, an arthropod object detection method was proposed based on the improved Faster RCNN model, namely AROD RCNN (ARthropod Object Detection RCNN). Firstly, a Supervised Parallel mechanism with Spatial and Channel ATtention modules (SPSCAT) was designed to improve the accuracy of arthropod object detection in the environment with complex background. Then, the second-generation deformable convolution was introduced to reconstruct the convolutional layer with C1~C5 blocks in ResNet50, and the Feature Pyramid Network (FPN) was adopted to perform feature fusion on the C2~C6 blocks in ResNet50 to solve the problem that large difference in object scale affected detection accuracy. Finally, the Dense Local Regression (DLR) method was used to improve the regression stage, thereby improving the accuracy of the model regression. Experimental results show that on ArTaxOr (Arthropod Taxonomy Orders Object Detection) dataset, the proposed method has the mean Average Precision (mAP) of 0.717, which is 0.453 higher than that of the original model, and has the recall reached 0.787. It can be seen that the proposed method can effectively solve the problems of object occlusion and complex background, and performs well in the detection of dense arthropod objects and small arthropod objects.

Key words: object detection, attention mechanism, deformable convolution, Feature Pyramid Network (FPN), Dense Local Regression (DLR), arthropod

摘要: 自然生态环境下的节肢动物目标检测存在目标背景复杂、尺度差异大以及目标密集等特点,导致目标检测精度和准确率不高。为此,提出一种基于改进Faster RCNN模型的节肢动物目标检测方法AROD RCNN。首先,设计一种有监督的并行空间与通道注意力(SPSCAT)机制,以提高复杂背景环境下节肢动物目标检测的准确率;然后,引入第二代可变形卷积重塑ResNet50中C1~C5块卷积层,并使用特征金字塔网络(FPN)对ResNet50中C2~C6块进行特征融合以解决目标尺度差异较大影响检测精度的问题;最后,通过密集局部回归(DLR)方法对回归阶段进行改进,从而提高模型回归的准确性。实验结果表明,该方法在ArTaxOr数据集上的各类别平均精度(mAP)达到了0.717,较原始Faster RCNN模型提高了0.453,而召回率达到了0.787。可见该方法能够有效解决目标遮挡和复杂背景等问题,在节肢动物密集目标与小目标检测中表现良好。

关键词: 目标检测, 注意力机制, 可变形卷积, 特征金字塔网络, 密集局部回归, 节肢动物

CLC Number: