SheepInst: A High-Performance Instance Segmentation of Sheep Images Based on Deep Learning

文献类型： 外文期刊

第一作者： Zhao, Hongke

作者： Zhao, Hongke;Mao, Rui;Li, Mei;Wang, Meili;Zhao, Hongke;Wang, Meili;Zhao, Hongke;Wang, Meili;Li, Bin

作者机构：

关键词： precision livestock farming; deep learning; sheep instance segmentation; attention mechanism; computer vision

期刊名称：ANIMALS （ 影响因子：3.0； 五年影响因子：3.2 ）

ISSN： 2076-2615

年卷期： 2023 年 13 卷 8 期

页码：

收录情况： SCI

摘要： Simple Summary With the development of computer vision, more work is applied to promote precision livestock farming. Due to the high overlap and irregular contours of sheep, it poses a challenge to computer vision tasks. Instance segmentation can simultaneously locate and segment individuals in a sheep flock, which can effectively solve the above problems. This paper proposed a two-stage high-performance instance segmentation model, which can accurately locate and segment sheep. Under the topic of precision livestock farming, this study can provide technical support for the implementation of sheep intelligent management based on deep learning. Sheep detection and segmentation will play a crucial role in promoting the implementation of precision livestock farming in the future. In sheep farms, the characteristics of sheep that have the tendency to congregate and irregular contours cause difficulties for computer vision tasks, such as individual identification, behavior recognition, and weight estimation of sheep. Sheep instance segmentation is one of the methods that can mitigate the difficulties associated with locating and extracting different individuals from the same category. To improve the accuracy of extracting individual sheep locations and contours in the case of multiple sheep overlap, this paper proposed two-stage sheep instance segmentation SheepInst based on the Mask R-CNN framework, more specifically, RefineMask. Firstly, an improved backbone network ConvNeXt-E was proposed to extract sheep features. Secondly, we improved the structure of the two-stage object detector Dynamic R-CNN to precisely locate highly overlapping sheep. Finally, we enhanced the segmentation network of RefineMask by adding spatial attention modules to accurately segment irregular contours of sheep. SheepInst achieves 89.1%, 91.3%, and 79.5% in box AP, mask AP, and boundary AP metric on the test set, respectively. The extensive experiments show that SheepInst is more suitable for sheep instance segmentation and has excellent performance.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序