基于关键点和单眼深度估计的姿势估计,用于预测牛的体重和部高度
Guilherme L Menezes1, Alyssa Seitz1, Enrico Casella2
1Department of Animal and Dairy Sciences, University of Wisconsin-Madison, Madison, WI, 53703, United States.
Journal of animal science
|February 18, 2026
概括
通过使用具有姿势估计和单眼深度估计 (MDE) 的二维图像,可以预测牛的体重和部高度. 这种计算机视觉方法为畜牧监测3D系统提供了一种经济有效的替代方案.
科学领域:
- 农业工程 农业工程
- 计算机视觉 计算机视觉
- 动物科学动物科学
背景情况:
- 传统的计算机视觉系统 (CVS) 用于预测牛的体重 (BW) 和部高度 (HH),通常依赖于昂贵的3D成像或不切实际的侧视2D摄像头.
- 顶向下视图2D成像与姿势估计相结合,为提取生物识别特征提供了潜在的解决方案.
- 单眼深度估计 (MDE) 可以从二维图像中生成深度信息,进一步增强生物识别分析.
研究的目的:
- 开发BW和HH的预测模型,使用身体姿势关键点的特征和MDE生成的深度图像从上下2D红外图像.
- 将这些模型的预测性能与使用3D成像系统特征的模型进行比较.
主要方法:
- 采集了395个由上向下视图视频,使用红外和深度传感器对肉牛和奶牛杂交.
- 利用姿势估计模型确定了七个关键的解剖学地标.
- 应用零射击MDE将2D红外图像转换为3D表示和提取的特征 (体积,面积等). ) 的情况.
- 从使用相同特征提取管道的3D成像系统处理深度图像.
- 评估随机森林,部分最小平方回归 (PLS) 和支持矢量回归模型,使用离开一个块的交叉验证.
主要成果:
- 使用关键点衍生特征的PLS模型实现了BW的R2为0.90,HH的R2为0.77.
- 使用MDE衍生深度特征的PLS模型表现出卓越的性能,BW (RMSE 24.2公斤) 的R2为0.95,HH的R2为0.95,HH的结果相似.
- 使用2D衍生功能的预测性能与3D成像系统的性能相当.
结论:
- 从上下2D图像中提取的生物特征,包括通过MDE生成的生物特征,为牛的BW和HH提供了有效和可比的预测.
- 这种方法为传统的3D成像系统提供了一种具有成本效益和实用的替代方案,用于牲畜监测和管理.
更多相关视频
06:52An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field
Published on: May 26, 2020
8.7K
14:14Quantification of Strain in a Porcine Model of Skin Expansion Using Multi-View Stereo and Isogeometric Kinematics
Published on: April 16, 2017
12.0K
相关概念视频
Estimation of the Physical Quantities
8.1K
On many occasions, physicists, other scientists, and engineers need to make estimates of a particular quantity. These are sometimes referred to as guesstimates, order-of-magnitude approximations, back-of-the-envelope calculations, or Fermi calculations. The physicist Enrico Fermi was famous for his ability to estimate various kinds of data with surprising precision. Estimating does not mean guessing a number or a formula at random. Instead, estimation means using prior experience and sound...
8.1K
Depth Perception and Spatial Vision
2.2K
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
2.2K
What are Estimates?
8.9K
It isn't easy to measure a parameter such as the mean height or the mean weight of a population. So, we draw samples from the population and calculate the mean height or mean weight of the individuals in the sample. This sample data acts as a representative measure of the population parameter. These sample statistics are known as estimates.
The estimate for the mean of a sample is denoted by ͞x, whereas the mean of the population is designated as μ. Further, parameters such...
The estimate for the mean of a sample is denoted by ͞x, whereas the mean of the population is designated as μ. Further, parameters such...
8.9K
