A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
The invention discloses an automatic green belt watering method and system based on a watering cart, a terminal and a medium, and belongs to the field of artificial intelligence, and the method comprises the steps: inputting an original image into a pre-trained target detection model, so as to obtain a visual perception result including a pedestrian target; wherein the target detection model is obtained by training image samples subjected to category labeling based on a deep learning network; fusing the radar sensing result and the visual sensing result to obtain a current distance between the pedestrian target and the target watering cart; and under the condition that the current distance is smaller than or equal to the preset water sprinkling range of the target water sprinkling vehicle, a closing instruction is generated, and the closing instruction is used for controlling the target water sprinkling vehicle to close a water sprinkling system. The technical problems that in the prior art, when a watering cart works, the labor intensity of workers is large, and water spraying is not stopped in time, so that water is easily sprayed to roadside pedestrians are solved.
本发明公开了一种基于洒水车的绿化带自动化洒水方法、系统、终端和介质，本发明属于人工智能领域，所述方法包括：将所述原始图像输入预先训练的目标检测模型，以得到包括行人目标的视觉感知结果；其中，所述目标检测模型是基于深度学习网络利用类别标注后的图像样本进行训练得到的；将所述雷达感知结果和所述视觉感知结果进行融合，以得到所述行人目标与所述目标洒水车的当前距离；在所述当前距离小于或等于所述目标洒水车的预设洒水范围的情况下，生成关闭指令，所述关闭指令用于控制所述目标洒水机关闭洒水系统。解决了有技术中洒水车作业时工作人员劳动强度较大，喷水关闭不及时而导致的容易喷洒到路边行人的技术问题。
The invention discloses an automatic green belt watering method and system based on a watering cart, a terminal and a medium, and belongs to the field of artificial intelligence, and the method comprises the steps: inputting an original image into a pre-trained target detection model, so as to obtain a visual perception result including a pedestrian target; wherein the target detection model is obtained by training image samples subjected to category labeling based on a deep learning network; fusing the radar sensing result and the visual sensing result to obtain a current distance between the pedestrian target and the target watering cart; and under the condition that the current distance is smaller than or equal to the preset water sprinkling range of the target water sprinkling vehicle, a closing instruction is generated, and the closing instruction is used for controlling the target water sprinkling vehicle to close a water sprinkling system. The technical problems that in the prior art, when a watering cart works, the labor intensity of workers is large, and water spraying is not stopped in time, so that water is easily sprayed to roadside pedestrians are solved.
本发明公开了一种基于洒水车的绿化带自动化洒水方法、系统、终端和介质，本发明属于人工智能领域，所述方法包括：将所述原始图像输入预先训练的目标检测模型，以得到包括行人目标的视觉感知结果；其中，所述目标检测模型是基于深度学习网络利用类别标注后的图像样本进行训练得到的；将所述雷达感知结果和所述视觉感知结果进行融合，以得到所述行人目标与所述目标洒水车的当前距离；在所述当前距离小于或等于所述目标洒水车的预设洒水范围的情况下，生成关闭指令，所述关闭指令用于控制所述目标洒水机关闭洒水系统。解决了有技术中洒水车作业时工作人员劳动强度较大，喷水关闭不及时而导致的容易喷洒到路边行人的技术问题。
Automatic green belt watering method and system based on watering cart, terminal and medium
基于洒水车的绿化带自动化洒水方法、系统、终端和介质
LIU CHAO (author)
2023-07-14
Patent
Electronic Resource
Chinese
| European Patent Office | 2020
Watering cart capable of automatically watering and automatic watering method
| European Patent Office | 2021
Power system for watering cart, watering cart and control method
| European Patent Office | 2024