Hughes Benjamin, Burghardt Tilo
1Save Our Seas Foundation, Rue Philippe Plantamour 20, CH-1201 Geneva, Switzerland.
2Department of Computer Science, University of Bristol, Bristol, BS8 1UB UK.
Int J Comput Vis. 2017;122(3):542-557. doi: 10.1007/s11263-016-0961-y. Epub 2016 Oct 13.
This paper discusses the automated visual identification of individual great white sharks from dorsal fin imagery. We propose a computer vision photo ID system and report recognition results over a database of thousands of unconstrained fin images. To the best of our knowledge this line of work establishes the first contour-based visual ID system in the field of animal biometrics. The approach put forward appreciates shark fins as textureless, flexible and partially occluded objects with an individually characteristic shape. In order to recover animal identities from an image we first introduce an open contour stroke model, which extends multi-scale region segmentation to achieve robust fin detection. Secondly, we show that combinatorial, scale-space selective fingerprinting can successfully encode fin individuality. We then measure the species-specific distribution of visual individuality along the fin contour via an embedding into a global 'fin space'. Exploiting this domain, we finally propose a non-linear model for individual animal recognition and combine all approaches into a fine-grained multi-instance framework. We provide a system evaluation, compare results to prior work, and report performance and properties in detail.
本文讨论了从背鳍图像中自动视觉识别大白鲨个体的方法。我们提出了一种计算机视觉照片识别系统,并报告了在包含数千张无约束鳍图像的数据库上的识别结果。据我们所知,这一系列工作在动物生物识别领域建立了首个基于轮廓的视觉识别系统。所提出的方法将鲨鱼鳍视为无纹理、灵活且部分遮挡的具有个体特征形状的物体。为了从图像中恢复动物身份,我们首先引入了一种开放轮廓笔画模型,该模型扩展了多尺度区域分割以实现稳健的鳍检测。其次,我们表明组合式、尺度空间选择性指纹识别能够成功编码鳍的个体特征。然后,我们通过嵌入到全局“鳍空间”中来测量沿鳍轮廓的视觉个体特征的物种特异性分布。利用这个领域,我们最终提出了一种用于个体动物识别的非线性模型,并将所有方法整合到一个细粒度的多实例框架中。我们提供了系统评估,将结果与先前的工作进行比较,并详细报告了性能和特性。