I developed a target localization system in Python using onboard imagery and pose data from a Parrot AR.Drone 2.0 operating in a Vicon motion capture environment. The drone’s downward-facing camera was used to detect six green ground targets via color-based segmentation in HSV space, applying contour filtering and masking with OpenCV to identify valid candidates. Using the known camera intrinsics, distortion coefficients, and extrinsic calibration, I transformed each target’s image coordinates into the global Vicon frame by solving the pinhole camera model under the ground-plane constraint. To refine accuracy, I implemented a multi-stage k-means clustering algorithm to consolidate noisy detections across frames into final target estimates. This approach enabled robust georeferencing of detected landmarks with high precision.