Plant identification drawing method and system based on unmanned aerial vehicle image deep learning

• Main Authors: XIONG YONGZHU, CHEN YANKUI, ZENG XIAOFENG, ZHU MINGYONG, LIAO WENJIA, LAI WEIQIAN
• Format: Patent
• Language: Chinese; English
• Published: 05.08.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses a plant identification drawing method and system based on unmanned aerial vehicle image deep learning. A to-be-tested plant remote sensing image is collected through an unmanned aerial vehicle; acquiring a single plant remote sensing image data set; the Faster RCNN deep learning target recognition framework model is optimized, a FruitNet deep learning target recognition model is obtained and trained, single plant recognition prediction is carried out on the FruitNet deep learning target recognition model, and a single plant recognition prediction result is obtained; and obtaining a plant spatial distribution thematic map based on the single plant identification prediction result. According to the method, errors of artificial investigation and statistics are effectively solved, the precision and efficiency of plant investigation identification and positioning are improved, the complexity of a traditional plant investigation and statistics method is reduced, important scientific and tech