Abstract: A technology is described for identifying hydrometeors. A method includes receiving an image of a hydrometeor captured using a camera. The hydrometeor in the image can be identified and analyzed to determine characteristics associated with the hydrometeor. Environmental measurements recorded substantially contemporaneously with the image can be obtained from environmental sensors located in proximity to the camera. A feature vector can be constructed using the hydrometeor characteristics and the environmental measurements. The feature vector can be input to a classification model used to classify the hydrometeor, and the classification model can output a classification for the hydrometeor using the feature vector.

Abstract: A technology is described for identifying hydrometeors. A method includes receiving an image of a hydrometeor captured using a camera. The hydrometeor in the image can be identified and analyzed to determine characteristics associated with the hydrometeor. Environmental measurements recorded substantially contemporaneously with the image can be obtained from environmental sensors located in proximity to the camera. A feature vector can be constructed using the hydrometeor characteristics and the environmental measurements. The feature vector can be input to a classification model used to classify the hydrometeor, and the classification model can output a classification for the hydrometeor using the feature vector.

Abstract: Imaging of falling objects is described. Multiple images of a falling object can be captured substantially simultaneously using multiple cameras located at multiple angles around the falling object. An epipolar geometry of the captured images can be determined. The images can be rectified to parallelize epipolar lines of the epipolar geometry. Correspondence points between the images can be identified. At least a portion of the falling object can be digitally reconstructed using the identified correspondence points to create a digital reconstruction.

Abstract: Imaging of falling objects is described. Multiple images of a falling object can be captured substantially simultaneously using multiple cameras located at multiple angles around the falling object. An epipolar geometry of the captured images can be determined. The images can be rectified to parallelize epipolar lines of the epipolar geometry. Correspondence points between the images can be identified. At least a portion of the falling object can be digitally reconstructed using the identified correspondence points to create a digital reconstruction.