Promoting Usage of Deep Learning Object Detection in Ecology by Improving Performance and Accessibility

The inability of object detectors to generalise to domains beyond those included in labelled training data is limited when the training data has high intra-dataset similarity. This dataset aims to address this by providing data characterised by high intra-dataset variability. Highly variable images were scraped from FlickR and iNaturalist using python scripts available at https://github.com/ashep29/infusion for the following animals: Sus scrofa, striped hyena, and rhinoceros. These were supplemented with location specific camera trap images from WCS Camera Traps (WCS_striped_hyena and WCS_rhino), Snapshot Serengeti (SS_striped_hyena and SS_rhino), Missouri Camera Traps (EU_pig) and North American Camera Trap Images (NA_pig) which are publicly available on www.lila.science. The high intra-dataset variability of these subsets was ensured by removing all images with an SSIM score greater than 0.8 (where 1.0 represents identical images). All these images were then annotated in PASCAL VOC format with bounding boxes to allow for object detector training.

当带标注训练数据的数据集内部相似度较高时，目标检测器（object detector）难以泛化至训练数据覆盖领域之外的场景这一局限会更为凸显。本数据集旨在解决该问题，其核心特点为具备极高的数据集内变异性。研究人员通过https://github.com/ashep29/infusion处公开的Python脚本，从Flickr和iNaturalist平台爬取了以下三类动物的高多样性图像：野猪（Sus scrofa）、条纹鬣狗以及犀牛。此外还补充了来自WCS相机陷阱数据集（WCS_striped_hyena与WCS_rhino）、塞伦盖蒂快照数据集（SS_striped_hyena与SS_rhino）、密苏里相机陷阱数据集（EU_pig）以及北美相机陷阱图像数据集（NA_pig）的特定位置相机陷阱图像，上述数据集均在www.lila.science平台公开可获取。为确保各子集具备较高的数据集内变异性，研究人员移除了所有结构相似性指数（SSIM，Structural Similarity Index）得分高于0.8的图像（得分1.0代表两幅图像完全一致）。随后，所有图像均以PASCAL VOC格式标注了边界框（bounding boxes），以支持目标检测器的训练工作。

搜集汇总

背景与挑战

背景概述

该数据集旨在提升深度学习目标检测在生态学领域的应用，通过提供具有高内部变异性的图像数据来增强模型的泛化能力。数据包括从FlickR和iNaturalist爬取的动物图像以及公开的相机陷阱图像，经过筛选和PASCAL VOC格式标注，适用于目标检测训练。