排
苗木
杂草
偏移量(计算机科学)
高斯分布
数学
水田
人工智能
模式识别(心理学)
像素
稳健性(进化)
计算机科学
农学
生物
生物化学
物理
量子力学
数据库
基因
程序设计语言
作者
Rongru He,Xiwen Luo,Zhigang Zhang,Wenyu Zhang,Chunyu Jiang,Bingxuan Yuan
出处
期刊:Agriculture
[MDPI AG]
日期:2022-10-20
卷期号:12 (10): 1736-1736
被引量:3
标识
DOI:10.3390/agriculture12101736
摘要
The identification method of rice seedling rows based on machine vision is affected by environmental factors that decrease the accuracy and the robustness of the rice seedling row identification algorithm (e.g., ambient light transformation, similarity of weed and rice features, and lack of seedlings in rice rows). To solve the problem of the above environmental factors, a Gaussian Heatmap-based method is proposed for rice seedling row identification in this study. The proposed method is a CNN model that comprises the High-Resolution Convolution Module of the feature extraction model and the Gaussian Heatmap of the regression module of key points. The CNN model is guided using Gaussian Heatmap generated by the continuity of rice row growth and the distribution characteristics of rice in rice rows to learn the distribution characteristics of rice seedling rows in the training process, and the positions of the coordinates of the respective key point are accurately returned through the regression module. For the three rice scenarios (including normal scene, missing seedling scene and weed scene), the PCK and average pixel offset of the model were 94.33%, 91.48%, 94.36% and 3.09, 3.13 and 3.05 pixels, respectively, for the proposed method, and the forward inference speed of the model reached 22 FPS, which can meet the real-time requirements and accuracy of agricultural machinery in field management.
科研通智能强力驱动
Strongly Powered by AbleSci AI