3D motion analysis based on machine learning in agriculture informatisation

in this paper, a motion retrieval system is investigated from a multiple-instance learning view. To retrieve similar motion data, each human joint’s motion clip is regarded as a bag, while each of its segments is regarded as an instance. First 3D temporal-spatial features and their keyspaces of each human joint are extracted. Then, data driven decision trees based on ensemble multiple instance are automatically constructed to reflect the influence of each point during the comparison of motion similarity. Last, we use the method of multiple instance retrieval to complete motion retrieval. Experiment results show that our approaches are effective for motion data retrieval in agriculture informatisation.