On the current breeding goose farm,the detection of individual egg laying mainly depends on some judgement experiences of farm workers.At present,there have been some egg laying detection systems developed with images...On the current breeding goose farm,the detection of individual egg laying mainly depends on some judgement experiences of farm workers.At present,there have been some egg laying detection systems developed with images and weighing sensors,which only signal the eggs being laid,but no egg position being achieved.Meanwhile,the detection rate of the system is not high due to environment limitations like dim light of the goose barn.Therefore,to solve these problems mentioned above,an intelligent detection and positioning system is pro-posed by integrating technologies of the Radio Frequency(RF)and photoelectric sensors,together with the geometric calculation principle.In this research,individual egg laying information of breeding geese in a non-cage state was examined to improve the level of auto-matic detection and positioning in the field of breeder egg production.The results showed that an accurate detection and positioning of an egg in a nest filled with the artificial turf could be achieved under some conditions:the height of sensor is 3.5 cm from the bottom plate of the egg laying nest,the spacing of the photoresistor module is 5 cm,and the external light intensity is less than 110 LUX.It also shown that the error of the goose egg position recognition is 0.443 cm with a suitable level of straw in the nest.Therefore,the monitoring system and positioningmethod that was developed in this research could provide a reference for the analysis of individual egg laying behavior,and could result in an improvement in the automatic egg collection for the breeding geese production.展开更多
马岗鹅的行为与其生长状况和福利状况密切相关,马岗鹅关键行为监测对评估其生长性能具有重要的现实意义。为了实现对群养栏马岗鹅关键行为高效率精准监测,该研究探索一种基于YoloX的群养马岗鹅关键行为监测算法(Magang geese behavior m...马岗鹅的行为与其生长状况和福利状况密切相关,马岗鹅关键行为监测对评估其生长性能具有重要的现实意义。为了实现对群养栏马岗鹅关键行为高效率精准监测,该研究探索一种基于YoloX的群养马岗鹅关键行为监测算法(Magang geese behavior monitoring of based on Double Head-YoloX,MGBM-DH-YoloX),该算法通过减少YoloX的头部数量提升检测效率、使用损失函数减少前景背景干扰、使用迁移训练方式提高网络训练效率等技术对马岗鹅采食、饮水、休息和应激等关键行为及其规律进行分析。MGBM-DH-YoloX首先用Mosaic和Mixup对马岗鹅图像进行数据增强,然后使用增强后的数据集训练模型,并且利用模型检测马岗鹅的关键行为,最后累计得出马岗鹅关键行为的发生时长和行为节律;试验训练集为1400幅、验证集200幅和测试集为400幅,连续活动视频10 d。结果表明,MGBM-DH-YoloX算法的平均精度为98.98%、检测速度达到81帧/s、内存消耗为2520.04 MB。对马岗鹅的10 d养殖数据分析发现,MGBM-DH-YoloX能有效观察到马岗鹅随着日龄增长采食次数逐渐减少;试验鹅每日采食与饮水行为同时出现的比例为83.74%,呈现整体相伴趋势,但也从90.78%降低到74.57%,说明马岗鹅采食与饮水行为随着日龄增加呈现出逐渐分离趋势;试验鹅随着日龄增长休息时间逐渐加多,呈现出肉鸭对笼养的适应性逐步增强;应激行为随机性很强,突发性明显,发现人员随机走动等不规范饲喂带来的应激行为占据很大比例。该研究显示MGBM-DH-YoloX算法能利用监控视频对马岗鹅的关键行为进行智能提取,可为家禽智能养殖监管提供技术支撑。展开更多
基金This work was supported by the Key Area Research Program of Universities in Guangdong Province(Nature science),China(2020ZDZX1041).I would like to express my gratitude to all those who helped me during the writing of this thesis.
文摘On the current breeding goose farm,the detection of individual egg laying mainly depends on some judgement experiences of farm workers.At present,there have been some egg laying detection systems developed with images and weighing sensors,which only signal the eggs being laid,but no egg position being achieved.Meanwhile,the detection rate of the system is not high due to environment limitations like dim light of the goose barn.Therefore,to solve these problems mentioned above,an intelligent detection and positioning system is pro-posed by integrating technologies of the Radio Frequency(RF)and photoelectric sensors,together with the geometric calculation principle.In this research,individual egg laying information of breeding geese in a non-cage state was examined to improve the level of auto-matic detection and positioning in the field of breeder egg production.The results showed that an accurate detection and positioning of an egg in a nest filled with the artificial turf could be achieved under some conditions:the height of sensor is 3.5 cm from the bottom plate of the egg laying nest,the spacing of the photoresistor module is 5 cm,and the external light intensity is less than 110 LUX.It also shown that the error of the goose egg position recognition is 0.443 cm with a suitable level of straw in the nest.Therefore,the monitoring system and positioningmethod that was developed in this research could provide a reference for the analysis of individual egg laying behavior,and could result in an improvement in the automatic egg collection for the breeding geese production.
文摘马岗鹅的行为与其生长状况和福利状况密切相关,马岗鹅关键行为监测对评估其生长性能具有重要的现实意义。为了实现对群养栏马岗鹅关键行为高效率精准监测,该研究探索一种基于YoloX的群养马岗鹅关键行为监测算法(Magang geese behavior monitoring of based on Double Head-YoloX,MGBM-DH-YoloX),该算法通过减少YoloX的头部数量提升检测效率、使用损失函数减少前景背景干扰、使用迁移训练方式提高网络训练效率等技术对马岗鹅采食、饮水、休息和应激等关键行为及其规律进行分析。MGBM-DH-YoloX首先用Mosaic和Mixup对马岗鹅图像进行数据增强,然后使用增强后的数据集训练模型,并且利用模型检测马岗鹅的关键行为,最后累计得出马岗鹅关键行为的发生时长和行为节律;试验训练集为1400幅、验证集200幅和测试集为400幅,连续活动视频10 d。结果表明,MGBM-DH-YoloX算法的平均精度为98.98%、检测速度达到81帧/s、内存消耗为2520.04 MB。对马岗鹅的10 d养殖数据分析发现,MGBM-DH-YoloX能有效观察到马岗鹅随着日龄增长采食次数逐渐减少;试验鹅每日采食与饮水行为同时出现的比例为83.74%,呈现整体相伴趋势,但也从90.78%降低到74.57%,说明马岗鹅采食与饮水行为随着日龄增加呈现出逐渐分离趋势;试验鹅随着日龄增长休息时间逐渐加多,呈现出肉鸭对笼养的适应性逐步增强;应激行为随机性很强,突发性明显,发现人员随机走动等不规范饲喂带来的应激行为占据很大比例。该研究显示MGBM-DH-YoloX算法能利用监控视频对马岗鹅的关键行为进行智能提取,可为家禽智能养殖监管提供技术支撑。
