贝叶斯融合主动轮廓模型与卷积网络先验用于站立枯木分割
Bayesian Fusion of Active Contour Models and ConvNet Priors for Standing Dead Tree Segmentation
AI总结：
针对自然资源监测影像中枯木实例分割，提出贝叶斯最大后验推断框架，融合CNN先验与GAN深度形状模型，驱动主动轮廓水平集演化，在树冠轮廓重建上显著优于Mask R-CNN和K-net。
摘要：
实例分割是一项核心计算机视觉任务，具有重要的实际意义。近期，由大规模基准数据集推动的进展，已产生了良好的通用型卷积神经网络（CNN）方法。自然资源监测（NRM）利用遥感影像，这些影像通常具有已知尺度，并包含同一类别的多个重叠实例，其中物体轮廓呈锯齿状且高度不规则。这与经典基准数据集中发现的规则人造物体形成鲜明对比。我们解决这一问题，并提出一种面向NRM影像的新型实例分割方法。我们将问题表述为贝叶斯最大后验推断，在学习各个物体轮廓时，融合了来自最先进CNN架构的形状、位置和姿态先验，驱动多个物体轮廓的同时水平集演化。我们采用提供先验的CNN与主动轮廓过程之间的松散耦合，允许新网络架构的即插即用替换。此外，我们引入了一种新颖的轮廓形状先验，即基于生成对抗网络（GAN）架构的一类深度形状模型。这些深度形状模型本质上是经典特征形状公式的非线性推广。在实验中，我们处理了具有挑战性的现实世界问题：分割单个枯死树冠并描绘精确轮廓。我们将我们的方法与两种领先的通用实例分割方法——Mask R-CNN和K-net——在彩色红外航空影像上进行比较。结果表明，在树冠轮廓重建质量方面，我们的方法显著优于这两种方法。此外，使用基于GAN的深度形状模型先验，相比原始特征形状先验，所有结果均获得显著提升。
英文摘要：
Instance segmentation is a core computer vision task with great practical significance. Recent advances, driven by large-scale benchmark datasets, have yielded good general-purpose Convolutional Neural Network (CNN)-based methods. Natural Resource Monitoring (NRM) utilizes remote sensing imagery with generally known scale and containing multiple overlapping instances of the same class, wherein the object contours are jagged and highly irregular. This is in stark contrast with the regular man-made objects found in classic benchmark datasets. We address this problem and propose a novel instance segmentation method geared towards NRM imagery. We formulate the problem as Bayesian maximum a posteriori inference which, in learning the individual object contours, incorporates shape, location, and position priors from state-of-the-art CNN architectures, driving a simultaneous level-set evolution of multiple object contours. We employ loose coupling between the CNNs that supply the priors and the active contour process, allowing a drop-in replacement of new network architectures. Moreover, we introduce a novel prior for contour shape, namely, a class of Deep Shape Models based on architectures from Generative Adversarial Networks (GANs). These Deep Shape Models are in essence a non-linear generalization of the classic Eigenshape formulation. In experiments, we tackle the challenging, real-world problem of segmenting individual dead tree crowns and delineating precise contours. We compare our method to two leading general-purpose instance segmentation methods - Mask R-CNN and K-net - on color infrared aerial imagery. Results show our approach to significantly outperform both methods in terms of reconstruction quality of tree crown contours. Furthermore, use of the GAN-based deep shape model prior yields significant improvement of all results over the vanilla Eigenshape prior.
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。
