Visual loopback detection method based on auto-encoding network

Abstract

The invention discloses a visual loopback detection method based on an auto-encoding network. The visual loopback detection method comprises the following steps: 1, acquiring an image; 2, calculatinga memorability score of the image, comparing the memorability score with a set memorability score threshold value, determining whether to reserve the image or not, and determining a key frame; 3, inputting the screened key frames into a trained convolutional self-encoding network, and obtaining a GIST global feature f after noise reduction; 4, taking out a feature fpre from the feature database, calculating cosine similarity of two feature vectors fpre and f, comparing the cosine similarity with a set similarity threshold, determining whether the frame is a candidate frame or not, and performing loop-back verification; and 5, in a loopback verification stage, on the premise of completing space consistency verification, carrying out time consistency verification, enabling one image to meetloopback conditions and become loopback candidate frames in a continuous motion process, enabling the obtained key frames to become candidate frames within a certain time range, and finally determining loopback only when the conditions are met.

Description

technical field [0001] The invention belongs to the field of visual SLAM, and in particular relates to a visual loopback detection method based on an autoencoder network. Background technique [0002] Visual loop detection is a key module in VSLAM (visual simultaneous localization and mapping, visual real-time positioning and map construction). In a complete visual SLAM process, the camera needs to be calibrated before the visual SLAM starts to run. The purpose is to determine The internal reference of the camera, after the SLAM system starts running, the camera acquires the image data of the current environment, the front-end visual odometer module calculates the motion of the camera and estimates the local map through two adjacent frames of images, and restores the depth information from the plane image; visual loop detection From the perspective of image similarity, judge whether the camera moves to the historical location. If there is a loop, provide this optimized infor...

AI Technical Summary

Problems solved by technology

The conditions that affect the performance of loop closure detection mainly include the following: 1) noise problems caused by changes in illumination and shooting angles during image capture; 2) the inability to accurately identify the correlation between image frames, resulting in the robot being unable to correctly estimate the current loop state

Images