arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.13487cs.CVcs.LGcs.RO
收藏

基于点标记的超像素水下图像多物种分割

Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery

Queensland University of Technology(昆士兰科技大学);Data61, CSIRO(联邦科学与工业研究组织数据61研究所)

Scarlett Raine, Ross Marchant, Brano Kusy, Frederic Maire, Tobias Fischer

摘要:

使用水下航行器监测珊瑚礁,通过收集大量图像,扩大了海洋调查的范围和历史生态数据的可用性。可以使用经过训练以执行语义分割的模型来自动分析该图像,但是密集地标记图像以用于训练监督模型太昂贵和耗时。在这封信中,我们利用照片样方图像标记的生态学家与稀疏的点标签。我们提出了一种点标签感知方法,用于在超像素区域内传播标签,以获得用于训练语义分割模型的增强地面实况。我们的点标签感知超像素方法利用稀疏的点标签,并使用学习到的特征对像素进行聚类,以准确地在杂乱复杂的珊瑚图像中生成单物种片段。我们的方法在UCSD Mosaics数据集上的像素准确度和标签传播任务的平均IoU分别比之前的方法高出3.62%和8.35%,同时将之前方法报告的计算时间减少了76%。我们训练了DeepLabv3+架构,并在UCSD Mosaics数据集上的像素准确度和平均IoU分别为2.91%和9.65%,在Eilat数据集上的像素准确度和平均IoU分别为4.19%和14.32%,优于最先进的语义分割。

英文摘要:

Monitoring coral reefs using underwater vehicles increases the range of marine surveys and availability of historical ecological data by collecting significant quantities of images. Analysis of this imagery can be automated using a model trained to perform semantic segmentation, however it is too costly and time-consuming to densely label images for training supervised models. In this letter, we leverage photo-quadrat imagery labeled by ecologists with sparse point labels. We propose a point label aware method for propagating labels within superpixel regions to obtain augmented ground truth for training a semantic segmentation model. Our point label aware superpixel method utilizes the sparse point labels, and clusters pixels using learned features to accurately generate single-species segments in cluttered, complex coral images. Our method outperforms prior methods on the UCSD Mosaics dataset by 3.62% for pixel accuracy and 8.35% for mean IoU for the label propagation task, while reducing computation time reported by previous approaches by 76%. We train a DeepLabv3+ architecture and outperform state-of-the-art for semantic segmentation by 2.91% for pixel accuracy and 9.65% for mean IoU on the UCSD Mosaics dataset and by 4.19% for pixel accuracy and 14.32% mean IoU for the Eilat dataset.

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。

↑