Dynamic weed control using selective laser application with object tracking and target scheduling
Selective laser application for weed control is emerging as one of the most sustainable practices for various crops. The system targets weeds using a laser beam with specific time and intensity settings to eliminate undesired plants through thermal damage. However, this process — commonly known as s...
| Autores: | ; ; ; |
|---|---|
| Tipo de documento: | Artículo |
| Estado: | Published version |
| Fecha de publicación: | 2025 |
| País: | Chile |
| Institución: | Pontificia Universidad Católica de Chile |
| Repositorio: | Pontificia Universidad Católica de Chile |
| OAI Identifier: | oai:repositorio.uc.cl:11534/105859 |
| Acceso en línea: | https://doi.org/10.1016/j.compag.2025.111004 https://repositorio.uc.cl/handle/11534/105859 |
| Nivel de acceso: | Acceso abierto |
| Palabra clave: | Weed detection Machine learning Hyperweed selection Laser 550 Ciencias de la tierra 15 Life on land 15 Vida de ecosistemas terrestres |
| _version_ | 1879187922118246400 |
|---|---|
| author | Vargas Fernández, Juan Ignacio |
| author2 | Wane, Sam Arévalo Ramírez, Tito Auat Cheein, Fernando |
| author2_role | author author author |
| author_browse | Arévalo Ramírez, Tito Auat Cheein, Fernando Vargas Fernández, Juan Ignacio Wane, Sam |
| author_facet | Vargas Fernández, Juan Ignacio Wane, Sam Arévalo Ramírez, Tito Auat Cheein, Fernando |
| author_role | author |
| bitstream_url_str_mv | https://repositorio.uc.cl/dspace/bitstreams/43a98625-59e1-463e-bcdd-b57667a62a07/download |
| collection | Pontificia Universidad Católica de Chile |
| description | Selective laser application for weed control is emerging as one of the most sustainable practices for various crops. The system targets weeds using a laser beam with specific time and intensity settings to eliminate undesired plants through thermal damage. However, this process — commonly known as static weed laser treatment — reduces machinery efficiency, as the platform must remain stationary until all visible weeds are treated. To address this limitation, the current work proposes a dynamic laser weeding approach that predicts weed positions while the platform is in motion, thereby improving operational efficiency. Several deep learning architectures (e.g., YOLO series for weed detection and DeepSORT for weed tracking) are evaluated to identify the most effective models for detecting and tracking multiple weeds in RGB images. In addition, a time-constrained scheduling strategy is implemented to determine the order in which weeds are treated, minimizing the number of missed targets. We find that receding horizon control offers the best performance, particularly under strict time and energy constraints. Field deployment results show that YOLOv7 achieves the highest precision, recall, and mean Average Precision (mAP) for weed detection. The dynamic laser weeding system significantly outperforms the static counterpart, enabling up to 2.8 times faster movement while successfully treating 90% of detected weeds. This work presents a proof of concept for dynamic weeding, laying the foundation for future developments in intelligent, autonomous crop protection systems. |
| eu_rights_str_mv | openAccess |
| format | article |
| id | CL_839914db661b612f5a3eeb367d55aa01 |
| identifier_str_mv | 10.1016/j.compag.2025.111004 |
| institution | Pontificia Universidad Católica de Chile |
| instname_str | Pontificia Universidad Católica de Chile |
| network_acronym_str | CL |
| network_name_str | Chile |
| oai_identifier_str | oai:repositorio.uc.cl:11534/105859 |
| publishDate | 2025 |
| publishDateSort | 2025 |
| reponame_str | Pontificia Universidad Católica de Chile |
| spelling | Dynamic weed control using selective laser application with object tracking and target scheduling Vargas Fernández, Juan Ignacio Wane, Sam Arévalo Ramírez, Tito Auat Cheein, Fernando Weed detection Machine learning Hyperweed selection Laser 550 Ciencias de la tierra 15 Life on land 15 Vida de ecosistemas terrestres Selective laser application for weed control is emerging as one of the most sustainable practices for various crops. The system targets weeds using a laser beam with specific time and intensity settings to eliminate undesired plants through thermal damage. However, this process — commonly known as static weed laser treatment — reduces machinery efficiency, as the platform must remain stationary until all visible weeds are treated. To address this limitation, the current work proposes a dynamic laser weeding approach that predicts weed positions while the platform is in motion, thereby improving operational efficiency. Several deep learning architectures (e.g., YOLO series for weed detection and DeepSORT for weed tracking) are evaluated to identify the most effective models for detecting and tracking multiple weeds in RGB images. In addition, a time-constrained scheduling strategy is implemented to determine the order in which weeds are treated, minimizing the number of missed targets. We find that receding horizon control offers the best performance, particularly under strict time and energy constraints. Field deployment results show that YOLOv7 achieves the highest precision, recall, and mean Average Precision (mAP) for weed detection. The dynamic laser weeding system significantly outperforms the static counterpart, enabling up to 2.8 times faster movement while successfully treating 90% of detected weeds. This work presents a proof of concept for dynamic weeding, laying the foundation for future developments in intelligent, autonomous crop protection systems. 10.1016/j.compag.2025.111004 0168-1699 https://doi.org/10.1016/j.compag.2025.111004 https://repositorio.uc.cl/handle/11534/105859 |
| spellingShingle | Dynamic weed control using selective laser application with object tracking and target scheduling Vargas Fernández, Juan Ignacio Weed detection Machine learning Hyperweed selection Laser 550 Ciencias de la tierra 15 Life on land 15 Vida de ecosistemas terrestres |
| status_str | publishedVersion |
| title | Dynamic weed control using selective laser application with object tracking and target scheduling |
| title_full | Dynamic weed control using selective laser application with object tracking and target scheduling |
| title_fullStr | Dynamic weed control using selective laser application with object tracking and target scheduling |
| title_full_unstemmed | Dynamic weed control using selective laser application with object tracking and target scheduling |
| title_short | Dynamic weed control using selective laser application with object tracking and target scheduling |
| title_sort | Dynamic weed control using selective laser application with object tracking and target scheduling |
| topic | Weed detection Machine learning Hyperweed selection Laser 550 Ciencias de la tierra 15 Life on land 15 Vida de ecosistemas terrestres |
| topic_facet | Weed detection Machine learning Hyperweed selection Laser 550 Ciencias de la tierra 15 Life on land 15 Vida de ecosistemas terrestres |
| url | https://doi.org/10.1016/j.compag.2025.111004 https://repositorio.uc.cl/handle/11534/105859 |