期刊
COMPUTERS AND ELECTRONICS IN AGRICULTURE
卷 187, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.compag.2021.106299
关键词
Pigs weight measurement; Image processing; Deep learning; Regression network
资金
- National Natural Science Foundation of China [61871142]
- Research and Implementation of Multi-sensor Information Fusion and Decision-making System Based on Artificial Intelligence Architecture [KY10800180032]
- Fundamental Research Funds for the Central Universities of Ministy of Education of China [3072020CFT0830]
Measuring pig weight based on depth images can avoid the time-consuming and stressful process of weighing with scales. By designing preprocessing algorithms and a regression network based on BotNet, we achieve good accuracy in predicting pig weight.
Weighing pigs with scales takes a lot of time and makes pigs stressful easily. It can be avoided by measuring weight based on the depth images. We design a series of preprocessing algorithms including instance segmentation, distance independence, noise reduction, rotation correction. These algorithms are used to eliminate the influence of the surrounding environment and other factors. In order to predict the weight precisely, we build a regression network based on BotNet. Dual branch of 3 x 3 convolution and MHSA replaces single 3 x 3 convolution of the fourth block in ResNet. At the end of the network, we use multiple fully connection layers in parallel, then concat them to predict weight. After training on 122736 images, MAE of our network is 6.366 on 5326 test images.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据