Multi feature fusion-based water occlusion object detection algorithm

被引：0
|
作者：
Feng H. [1 ,2 ]
Jiang C. [2 ]
Xu H. [1 ,2 ]
Xie L. [3 ]
机构：
[1] Key Laboratory of High Performance Ship Technology of Ministry of Education, Wuhan University of Technology, Wuhan
[2] School of Naval Architecture,Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan
[3] Intelligent Transportation Systems Research Center, Wuhan University of Technology, Wuhan
来源：
Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) | 2024年 / 52卷 / 04期
关键词：
data resampling; hybrid attention mechanism; intelligent ships; multi-scale feature fusion structure; occlusion detection;
D O I：
10.13245/j.hust.240555
中图分类号：
学科分类号：
摘要：
Aiming at the problem that the object detection accuracy was affected by the mutual occlusion of ships that often occured when intelligent ships navigated in inland waterways,a water surface occlusion object detection algorithm based on multi-feature aggregation was proposed.First,a multi-scale sensory field feature fusion structure was set up in the backbone network to fuse the visible area of the occluded ship with the surrounding environment features.Second,a hybrid attention mechanism was added to the backbone network and the feature splicing part of the network to enhance the long-range dependence of the network,and to aggregate the features of the ship's bow and stern.Then,a data resampling strategy was designed to adaptively adjust the sample frequency according to the number of ship categories during the training process to alleviate the serious unevenness of the number of ships in the dataset.Finally,the algorithm was validated.Results show that the algorithm can effectively improve the detection accuracy of surface targets under visual occlusion by aggregating multi-scale features such as the visible area of the occluded ship and the surrounding environment,and by aggregating the long-range features of the bow and the stern of the ship,with an accuracy increase of 3.3% compared with the original algorithm. © 2024 Huazhong University of Science and Technology. All rights reserved.
引用
收藏
页码：76 / 81
页数：5
相关论文
共 21 条
  • [1] DALAL N, TRIGGS B., Histograms of oriented gradients for human detection, Proc of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 886-893, (2005)
  • [2] (2017)
  • [3] 42, 1, pp. 58-64, (2019)
  • [4] GIRSHICK R, DONAHUE J, DARRELL T, Et al., Rich feature hierarchies for accurate object detection and semantic segmentation, Proc of IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, (2014)
  • [5] GIRSHICK R., FAST R-CNN, Proc of IEEE International Conference on Computer Vision, pp. 1440-1448, (2015)
  • [6] REN S, HE K, GIRSHICK R, Et al., Faster r-cnn:towards real-time object detection with region proposal networks[J], Advances in Neural Information Processing Systems, 28, pp. 91-99, (2015)
  • [7] LIU W, ANGUELOV D, ERHAN D, Et al., SSD: single shot multibox detector, Proc of European Conference on Computer Vision, pp. 21-37, (2016)
  • [8] REDMON J, DIVVALA S, GIRSHICK R, Et al., You only look once:unified,real-time object detection[C], Proc of IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, (2016)
  • [9] REDMON J, FARHADI A., YOLO9000:better,faster,stronger, Proc of IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263-7271, (2017)
  • [10] REDMON J, FARHADI A., Yolov3: an incremental improvement
123