One-stage CNN detector-based benthonic organisms detection with limited training dataset. (December 2021)

• Record Type: Journal Article
• Authors: Chen, Tingkai; Wang, Ning; Wang, Rongfeng; Zhao, Hong; Zhang, Guichen
• Is Part Of: Neural networks. Volume 144(2021)
• Page Start: 247
• Page End: 259
• Publication Date: 2021-12
• Subjects: Benthonic organisms detection -- One-stage CNN detector -- Generalized intersection over union -- Benthonic organisms anchor boxes -- Data augmentation; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2021.08.014
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: In this paper, focusing on the challenges in unique shape dimension and limited training dataset of benthonic organisms, an one-stage CNN detector-based benthonic organisms detection (OSCD-BOD) scheme is proposed. Main contributions are as follows: (1) The regression loss between the predicted bounding box and ground truth box is innovatively measured by the generalized intersection over union (GIoU), such that localization accuracy of benthonic organisms is dramatically enhanced. (2) By devising K-means-based dimension clustering, multiple benthonic organisms anchor boxes (BOAB) sufficiently exploring a priori dimension information can be finely derived from limited training dataset, and thereby significantly promoting the recall ability. (3) Geometric and color transformations (GCT)-based data augmentation technique is further resorted to not only efficiently prevent over-fitting training but also to significantly enhance detection generalization in complex and changeable underwater environments. (4) The OSCD-BOD scheme is eventually established in a modular manner by integrating GIoU, BOAB and GCT functionals. Comprehensive experiments and comparisons sufficiently demonstrate that the proposed OSCD-BOD scheme outperforms typical approaches including Faster R-CNN, SSD, YOLOv2, YOLOv3 and CenterNet in terms of mean average precision by 6.88%, 10.92%, 12.44%, 3.05% and 1.09%, respectively.