This paper proposes a novel framework for fluorescence plant video processing. Biologists are interested in the leaf level photosynthetic analysis within a plant. A prerequisite for such analysis is to segment all leaves, estimate their structures and track them over time. We treat this as a joint multi-leaf segmentation, alignment, and tracking problem. First, leaf segmentation and alignment are applied on the last frame of a plant video to find a number of well-aligned leaf candidates. Second, leaf tracking is applied on the remaining frames with leaf candidate transformation from the previous frame. We form two optimization problems with shared terms in their objective functions for leaf alignment and tracking respectively. Gradient descent is used to solve the proposed optimization problems. A quantitative evaluation framework is formulated to evaluate the performance of our algorithm with three metrics. Two models are learned to predict the alignment accuracy and detect tracking failure respectively. We also study the limitation of our proposed alignment and tracking framework. Experimental results show the effectiveness, efficiency, and robustness of the proposed method.

本文提出了一种用于植物视频处理的新型框架，旨在实现基于叶片水平的光合分析，解决了多叶片分割、对齐和跟踪问题，提出了两个优化问题来实现叶片对齐和跟踪，并提出了两个模型来为后续植物生物学分析提供指导。实验结果表明，该方法具有高效性、鲁棒性和有效性。

来自荧光植物视频的联合多叶分割、对齐和跟踪