【背景和目的】烟叶成熟度的准确判定和适时采收是提高烟叶质量的关键,为提高烟叶成熟度判定的准确性。【方法】以翠碧一号(CB-1)的鲜烟叶为研究对象,采用手机拍摄上、中、下3个部位5个成熟度(M1~M5)烟叶图像,利用labelimg软件从原始的...【背景和目的】烟叶成熟度的准确判定和适时采收是提高烟叶质量的关键,为提高烟叶成熟度判定的准确性。【方法】以翠碧一号(CB-1)的鲜烟叶为研究对象,采用手机拍摄上、中、下3个部位5个成熟度(M1~M5)烟叶图像,利用labelimg软件从原始的图像中获取目标烟叶图像二维坐标信息,通过轻量级网络You Only Look Once(YOLO)v5进行数据训练,构建烟叶5个成熟度识别模型。【结果】CB-1的上、中、下3个部位模型中的m AP值均达到0.9以上,平均准确率分别为93.6%,92.8%,95.2%。进一步将模型部署到云服务器、并配套开发了基于Android端的烟草成熟度智能识别应用程序,实现在大田环境下响应式的鲜烟叶成熟度等级判断。【结论】基于YOLOv5模型的智能识熟APP可有效、准确地判定鲜烟叶成熟度。本研究结果可为鲜烟叶成熟度的智能识别提供理论基础和技术支撑。展开更多
[ Objective] This study was to understend the optimized combination of planting density, duration of disclosing plastic film and nitrogen fertilization under no-tillage cultivation. [ Method] Quadratic polynomial regr...[ Objective] This study was to understend the optimized combination of planting density, duration of disclosing plastic film and nitrogen fertilization under no-tillage cultivation. [ Method] Quadratic polynomial regression and saturated D-optimal design were employed to investigate the effects of planting density, duration of disclosing plastic film and nitrogen fertilization on the dynamics growth of rapeseed under no-tillage cultivation.[ Result] Within the experimental range, the growth dynamics of no-tillage cultivated rapeseed assumed a rise-fall tend. For the effects to the growth dynamics of no-tillage cultivated rapeseed, nitrogen application amount was higher than planting density and duration of disclosing plastic film. The interaction effect between planting density and duration of disclosing plastic film was higher than that between nitrogen application amount and planting density, and between nitrogen application amount and duration of disclosing plastic film. [ Conclusion] The optimized combination of these factors for dynamic growth of rapeseed under no-tillage cultivation was determined to be： planting density of per hectare 154 925 individuals, duration of disclosing plastic film of 110 d, nitrogen application amount of 315 kg/hm^2.展开更多
文摘【背景和目的】烟叶成熟度的准确判定和适时采收是提高烟叶质量的关键,为提高烟叶成熟度判定的准确性。【方法】以翠碧一号(CB-1)的鲜烟叶为研究对象,采用手机拍摄上、中、下3个部位5个成熟度(M1~M5)烟叶图像,利用labelimg软件从原始的图像中获取目标烟叶图像二维坐标信息,通过轻量级网络You Only Look Once(YOLO)v5进行数据训练,构建烟叶5个成熟度识别模型。【结果】CB-1的上、中、下3个部位模型中的m AP值均达到0.9以上,平均准确率分别为93.6%,92.8%,95.2%。进一步将模型部署到云服务器、并配套开发了基于Android端的烟草成熟度智能识别应用程序,实现在大田环境下响应式的鲜烟叶成熟度等级判断。【结论】基于YOLOv5模型的智能识熟APP可有效、准确地判定鲜烟叶成熟度。本研究结果可为鲜烟叶成熟度的智能识别提供理论基础和技术支撑。
基金Supported by Key Agricultural R&D Program in Guizhou Province dur-ing the Eleventh Five-year Plan[NZ(2005)3001]~~
文摘[ Objective] This study was to understend the optimized combination of planting density, duration of disclosing plastic film and nitrogen fertilization under no-tillage cultivation. [ Method] Quadratic polynomial regression and saturated D-optimal design were employed to investigate the effects of planting density, duration of disclosing plastic film and nitrogen fertilization on the dynamics growth of rapeseed under no-tillage cultivation.[ Result] Within the experimental range, the growth dynamics of no-tillage cultivated rapeseed assumed a rise-fall tend. For the effects to the growth dynamics of no-tillage cultivated rapeseed, nitrogen application amount was higher than planting density and duration of disclosing plastic film. The interaction effect between planting density and duration of disclosing plastic film was higher than that between nitrogen application amount and planting density, and between nitrogen application amount and duration of disclosing plastic film. [ Conclusion] The optimized combination of these factors for dynamic growth of rapeseed under no-tillage cultivation was determined to be： planting density of per hectare 154 925 individuals, duration of disclosing plastic film of 110 d, nitrogen application amount of 315 kg/hm^2.
