arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.17488cs.CVcs.LG
收藏

用于昆虫分类的低成本机器视觉

Low Cost Machine Vision for Insect Classification

Berliner Hochschule fuer Technik(柏林技术应用大学);UBZ Listhof e.V.(利斯特霍夫环境教育中心)

Danja Brandt, Martin Tschaikner, Teodor Chiaburu, Henning Schmidt, Ilona Schrimpf, Alexandra Stadel, Ingeborg E. Beckers, Frank Haußer

AI总结:

本研究提出一种低成本、可扩展的开源多传感器成像系统,通过优化照明与分辨率并采用ResNet50等CNN架构,在16种昆虫数据集上实现了超过96%的分类准确率。

摘要:

保护昆虫的数量和多样性是社会在环境可持续性领域最重要的目标之一。其前提是进行系统化和规模化的监测,以发现相关性并制定应对措施。因此,使用活体诱捕器进行自动化监测非常重要,但迄今为止,尚无系统能够提供包含足够详细信息的图像数据以供昆虫学分类使用。在本研究中,我们提出了一种成像方法,作为多传感器系统的一部分。该系统被开发为低成本、可扩展的开源系统,能够适应传统诱捕器类型。图像质量满足了分类学树中进行分类所需的要求。为此,我们优化了照明和分辨率,并抑制了运动伪影。该系统在一个包含16种昆虫的数据集上进行了示例性评估,这些昆虫属于相同或不同的属、科和目。我们证明,像 ResNet50(在 iNaturalist 数据上预训练)或 MobileNet 这样的标准 CNN 架构在重新训练后,在预测任务中表现非常出色。较小的定制 CNN 也取得了有前景的结果。分类准确率已达到 >96%。此外,研究还证明,对昆虫进行图像裁剪对于具有高类间相似性的物种分类是必要的。

英文摘要:

Preserving the number and diversity of insects is one of our society's most important goals in the area of environmental sustainability. A prerequisite for this is a systematic and up-scaled monitoring in order to detect correlations and identify countermeasures. Therefore, automatized monitoring using live traps is important, but so far there is no system that provides image data of sufficient detailed information for entomological classification. In this work, we present an imaging method as part of a multisensor system developed as a low-cost, scalable, open-source system that is adaptable to classical trap types. The image quality meets the requirements needed for classification in the taxonomic tree. Therefore, illumination and resolution have been optimized and motion artefacts have been suppressed. The system is evaluated exemplarily on a dataset consisting of 16 insect species of the same as well as different genus, family and order. We demonstrate that standard CNN-architectures like ResNet50 (pretrained on iNaturalist data) or MobileNet perform very well for the prediction task after re-training. Smaller custom made CNNs also lead to promising results. Classification accuracy of $>96\%$ has been achieved. Moreover, it was proved that image cropping of insects is necessary for classification of species with high inter-class similarity.

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。

↑