arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.05032cs.CV
收藏

使用基于 DETR 和 YOLO 的深度网络进行牲畜鱼苗计数

Livestock Fish Larvae Counting using DETR and YOLO based Deep Networks

Universidade Católica Dom Bosco(多姆博斯科天主教大学);Agropeixe Ltda.(阿格罗佩克萨有限公司);Universidade Federal de Mato Grosso do Sul(南马托格罗索联邦大学)

Daniel Ortega de Carvalho, Luiz Felipe Teodoro Monteiro, Fernanda Marques Bazilio, Gabriel Toshio Hirokawa Higa, Hemerson Pistori

AI总结:

本文构建低采集需求的鱼苗标注数据集,并评估多种 CNN 与 transformer 检测架构,结合图像分块使 DETR 与 YOLOv8 均实现低 MAPE 计数。

摘要:

计数鱼苗是水产养殖中一项重要但要求高且耗时的任务。为了解决这一问题,本工作评估了四种神经网络架构,包括卷积神经网络和 transformer,具有不同规模,用于鱼苗计数任务。为进行评估,我们提出了一个新的带标注图像数据集,其数据采集需求低于以往工作,包含斑短平口鲶和 dourado 鱼苗图像。通过使用图像分块技术,我们使用超大型实时检测 transformer 取得了 4.46%(±4.70)的 MAPE,并使用中型 YOLOv8 取得了 4.71%(±4.98)的 MAPE。

英文摘要:

Counting fish larvae is an important, yet demanding and time consuming, task in aquaculture. In order to address this problem, in this work, we evaluate four neural network architectures, including convolutional neural networks and transformers, in different sizes, in the task of fish larvae counting. For the evaluation, we present a new annotated image dataset with less data collection requirements than preceding works, with images of spotted sorubim and dourado larvae. By using image tiling techniques, we achieve a MAPE of 4.46% ($\pm 4.70$) with an extra large real time detection transformer, and 4.71% ($\pm 4.98$) with a medium-sized YOLOv8.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑