Tree Instance Segmentation with Temporal Contour Graph
Tree Instance Segmentation with Temporal Contour Graph
复制标题
DOI：
10.1109/cvpr52729.2023.00218
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
A. Firoze;Cameron Wingren;Raymond A. Yeh;Bedrich Benes;Daniel G. Aliaga
中科院分区：
文献类型：
--
作者：
A. Firoze;Cameron Wingren;Raymond A. Yeh;Bedrich Benes;Daniel G. Aliaga
提出了一种利用俯视RGB图像序列对密集自相似树进行实例分割和计数的新方法。我们提出了一种利用像素内容、形状和自遮挡的解决方案。首先，我们对图像序列进行初始过分割，并将结构特征聚集到包含时间信息的等高线图中。其次，利用图卷积网络及其固有的局部消息传递能力，将相邻的树冠块合并成最终的树冠集。通过各种研究和比较，我们的方法在高精度的实例分割和计数方面优于所有已有的方法和结果，尽管树被紧密地堆积在一起。最后，我们提供了各种森林图像序列数据集，适用于后续在不同海拔和树叶条件下捕获的基准和评估。
We present a novel approach to perform instance segmentation and counting for densely packed self-similar trees using a top-view RGB image sequence. We propose a solution that leverages pixel content, shape, and self-occlusion. First, we perform an initial over-segmentation of the image sequence and aggregate structural characteristics into a contour graph with temporal information incorporated. Second, using a graph convolutional network and its inherent local messaging passing abilities, we merge adjacent tree crown patches into a final set of tree crowns. Per various studies and comparisons, our method is superior to all prior methods and results in high-accuracy instance segmentation and counting despite the trees being tightly packed. Finally, we provide various forest image sequence datasets suitable for subsequent benchmarking and evaluation captured at different altitudes and leaf conditions.