Visual loopback detection method based on semantic segmentation and image restoration in dynamic scene

Abstract

The invention discloses a visual loopback detection method based on semantic segmentation and image restoration in a dynamic scene. The visual loopback detection method comprises the following steps:1) pre-training an ORB feature offline dictionary in a historical image library; 2) acquiring a current RGB image as a current frame, and segmenting out that the image belongs to a dynamic scene areaby using a DANet semantic segmentation network; 3) carrying out image restoration on the image covered by the mask by utilizing an image restoration network; 4) taking all the historical database images as key frames, and performing loopback detection judgment on the current frame image and all the key frame images one by one; 5) judging whether a loop is formed or not according to the similarityand epipolar geometry of the bag-of-words vectors of the two frames of images; and 6) performing judgement. The visual loopback detection method can be used for loopback detection in visual SLAM in adynamic operation environment, and is used for solving the problems that feature matching errors are caused by existence of dynamic targets such as operators, vehicles and inspection robots in a scene, and loopback cannot be correctly detected due to too few feature points caused by segmentation of a dynamic region.

Description

technical field [0001] The invention belongs to the field of visual SLAM, in particular to a visual loopback detection method based on semantic segmentation and image restoration in dynamic scenes. Background technique [0002] Visual SLAM (Simultaneous Localization And Mapping) is a robot that uses visual sensors to perceive the surrounding environment in an unknown environment, and estimates the pose of the sensor during the movement process, and at the same time realizes its own positioning based on the map and the establishment of augmented reality based on the positioning situation. Quantitative map. Loop detection is an important module in the visual SLAM system. Loop detection means that the robot can identify the scenes it has passed, making the map form a loop. When performing visual SLAM, the visual odometry will experience cumulative drift when estimating the pose. Therefore, the significance of loop closure detection is that the robot can use the global optimi...

AI Technical Summary

Problems solved by technology

[0008] In order to solve the above problems, the present invention provides a visual loop detection method based on semantic segmentation and image repair in dynamic scenes. , inspection robots and other dynamic targets lead to feature matching errors and the situation that loopbacks cannot be correctly detected due to too few feature points due to dynamic region segmentation. The detection method is characterized in that it comprises the following steps:

Images