Abstract: Provided is a three-dimensional object detection framework based on multi-source data knowledge transfer. By outputting an image feature extracted by an image feature extraction unit, an interested target selection unit outputs point cloud data of an interested target to a point cloud feature extraction unit according to the image feature; the point cloud feature extraction unit extracts a point cloud feature from the point cloud data; in a knowledge transfer unit, enable the image feature to learn the point cloud feature and update parameters of the image feature extraction unit, while a three-dimensional target parameter prediction unit updates parameters of the image feature and point cloud feature extraction units according to the image feature and the point cloud feature. Finally, the updated image feature extraction unit re-extracts the image feature to the three-dimensional target parameter prediction unit, which reckons and inputs three-dimensional parameters according to the image feature.