Trajectory loopback detection optimization method based on generative adversarial network

Abstract

The invention provides a generative adversarial network-based trajectory loopback detection optimization method, which comprises the following steps that: a data collection device acquires multi-target information and outputs a target coordinate position, a posture, a trajectory and a high-low resolution image set; constructing a generative adversarial network reconstruction production simulationtarget which comprises a first generator, a second generator, three local discriminators and a global discriminator, and outputting a simulation high-low resolution image set of a coordinate position,a posture, a track and a real target of the simulation target; loop detection is carried out to correct a target trajectory: a key frame is detected, a feature repetition rate is calculated, and a dictionary is constructed for the same target based on a two-dimensional high-low resolution image set, a low resolution image set and a three-dimensional RGB point cloud to judge a loop; and optimizingthe target trajectory based on the loopback frame, and outputting an optimized trajectory. The optimal trajectory is found while the trajectory is updated in real time, and accurate information is provided for unmanned control, target detection and recognition, feasible region detection, path planning and the like.

Description

technical field [0001] The invention relates to the fields of artificial intelligence, target detection and recognition, multi-sensor measurement, environment perception, etc., and in particular relates to a trajectory loop detection optimization method based on a generative confrontation network. Background technique [0002] For artificial intelligence, target detection and recognition, multi-sensor measurement and environmental perception technology, environmental perception is a necessary prerequisite for target detection and recognition, and target detection is an important part of environmental perception. Common target detection sensors are divided into : (1) TOF ranging image sensor, by emitting light waves or sound waves with different wavelengths, and then collecting the echo signals of the emitted waves to obtain information such as the distance, angle, reflection intensity, speed and other information of the target, and generate a multi-dimensional image of the ta...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problems in the prior art that a variety of sensors are used alone, the collected information is complex, scattered or even conflicting, the reliability of the collected information is reduced, and the optimization of the motion trajectory in the prior art is not accurate enough, and the gap between the actual trajectory and the other is large, the present invention The purpose of is to provide a trajectory loop detection optimization method based on generative confrontation network to achieve the output of the optimal trajectory of the target during the movement process

Images