Wildfires pose significant global environmental, economic, and health threats. Technological advances have popularized Unmanned Aerial Vehicles (UAVs) for diverse applications, including monitoring. However, they face constraints like payload and battery limitations. UAVs could aid in wildfire management, but their utilization is challenging due to these limitations and vast monitoring areas. Therefore, strategies are needed to overcome UAV constraints. This study proposes an approach enabling drones to land strategically for data collection, thereby reducing battery consumption. The method leverages principles of stereo vision and utilizes a monocular camera’s motion to estimate the relative position of a selected landing site. Additionally, this study explores the YOLOv8 usage for detecting tree branches in a controlled scenario with landing selection based on a reward equation. The system allows the drone to attach itself using a hook to an artificial (e.g., aluminum frame, power line) or natural (e.g., tree branch) location. The system is limited to static landing sites detectable by the FAST feature detector algorithm. Results show that the Landing Site Estimation System (LSES) achieves over 90% accuracy in controlled scenarios. Additionally, when paired with navigation controllers, the LSES achieves a 95% success rate in landing attempts under controlled lighting and wind conditions.