尚未偵測到更新。GitHub 發布版本後會顯示在這裡。
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證正在載入完整 README。 以下為已儲存的摘錄。
Detects marine oil spills in Sentinel-1 SAR imagery and attributes them to the
vessel most likely responsible. Preprocessed SAR scenes are segmented by a deep
learning model, dark patches are filtered against wind and contrast criteria to
reject look-alikes, and confirmed slicks are characterized by area, thickness
class and estimated volume. Each confirmed spill then fans out in parallel to
AIS-based vessel attribution and to a Lagrangian drift forecast, both surfaced
on a dashboard alongside the alert. Built for Smart India Hackathon.
Python 3.11 is the target runtime.檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
Detects marine oil spills in Sentinel-1 SAR imagery and attributes them to the
vessel most likely responsible. Preprocessed SAR scenes are segmented by a deep
learning model, dark patches are filtered against wind and contrast criteria to
reject look-alikes, and confirmed slicks are characterized by area, thickness
class and estimated volume. Each confirmed spill then fans out in parallel to
AIS-based vessel attribution and to a Lagrangian drift forecast, both surfaced
on a dashboard alongside the alert. Built for Smart India Hackathon.
Python 3.11 is the target runtime.檢視完整 README ↗