Human body behavior intelligent identification method based on multi-unmanned aerial vehicle visual angle image data driving

Abstract

The invention relates to a human body behavior intelligent identification method based on multi-unmanned aerial vehicle visual angle image data driving, and the method comprises the steps: observing from different angles, different heights and different distances through unmanned aerial vehicles in different directions relative to a same human body target, and collecting to obtain a video sequence containing a target behavior; processing a video sequence collected by each unmanned aerial vehicle to obtain a human body joint point coordinate sequence, and using a short-time-long-time deep neural network based on LSTM to model a time sequence of the human body joint point coordinate sequence to obtain a human body behavior recognition result probability of a single unmanned aerial vehicle; and finally, fusing the human behavior recognition result probabilities of all the unmanned aerial vehicles to obtain a human behavior recognition result. Compared with the prior art, the invention has the advantages that the robustness is high, the human behavior recognition effect is effectively enhanced, the method can be applied to various complex environments, and a new solution is provided for unmanned aerial vehicle human behavior recognition tasks.

Description

technical field [0001] The invention relates to the technical field of UAV visual behavior recognition, in particular to an intelligent human behavior recognition method driven by multi-UAV perspective image data. Background technique [0002] Human action recognition is an important research direction in the field of computer vision. The essence of the human behavior recognition process is to model the temporal-spatial relationship according to the behavior of the observed target, so as to judge the behavior category of the observed target. With the rapid development of artificial intelligence technology and image processing technology in recent years, human behavior recognition technology has also been rapidly improved, and is gradually applied to a wide range of fields such as human-computer interaction, urban monitoring systems, and motion analysis. [0003] As a highly integrated unmanned device, UAV can be applied to diverse mission requirements due to its strong mane...

AI Technical Summary

Problems solved by technology

But at the same time, because the depth camera is difficult to work normally in the outdoor environment, it is difficult to apply to most working scenarios of drones

Therefore, the accuracy and robustness of the recognition effect of the UAV behavior recognition method are largely limited.

Images