Visual Robot Relocalization Based on Multi-Task CNN and Image-Similarity Strategy

Abstract

The traditional CNN for 6D robot relocalization which outputs pose estimations does not interpret whether the model is making sensible predictions or just guessing at random. We found that convnet representations trained on classification problems generalize well to other tasks. Thus, we propose a multi-task CNN for robot relocalization, which can simultaneously perform pose regression and scene recognition. Scene recognition determines whether the input image belongs to the current scene in which the robot is located, not only reducing the error of relocalization but also making us understand with what confidence we can trust the prediction. Meanwhile, we found that when there is a large visual difference between testing images and training images, the pose precision becomes low. Based on this, we present the dual-level image-similarity strategy (DLISS), which consists of two levels: initial level and iteration-level. The initial level performs feature vector clustering in the training set and feature vector acquisition in testing images. The iteration level, namely, the PSO-based image-block selection algorithm, can select the testing images which are the most similar to training images based on the initial level, enabling us to gain higher pose accuracy in testing set. Our method considers both the accuracy and the robustness of relocalization, and it can operate indoors and outdoors in real time, taking at most 27 ms per frame to compute. Finally, we used the Microsoft 7Scenes dataset and the Cambridge Landmarks dataset to evaluate our method. It can obtain approximately 0.33 m and 7.51∘ accuracy on 7Scenes dataset, and get approximately 1.44 m and 4.83∘ accuracy on the Cambridge Landmarks dataset. Compared with PoseNet, our CNN reduced the average positional error by 25% and the average angular error by 27.79% on 7Scenes dataset, and reduced the average positional error by 40% and the average angular error by 28.55% on the Cambridge Landmarks dataset. We show that our multi-task CNN can localize from high-level features and is robust to images which are not in the current scene. Furthermore, we show that our multi-task CNN gets higher accuracy of relocalization by using testing images obtained by DLISS.

Indoor Localization and Navigation based on Deep Learning using a Monocular Visual System

“…Xu, Chou and Dong [15] presented a multi sensor based indoor algorithm for a localization system, integrating a convolutional neural network (CNN) based on image retrieval, to determine the location of the robot. Another example is presented by Xie, Wang, Li and Tang [16] use a CNN robot localization to recognize the scene, reducing the error of relocating the robot.…”

Impact of High‐Tech Image Formats Based on Full‐Frame Sensors on Visual Experience and Film‐Television Production

“…He used the principle of light reflection and refraction and used multiple cameras to scan and shoot a scene in 360 degrees. For the first time, he made a true 3D reconstruction of the target scene, but his research did not simplify the calculation process and could not solve the problem of obtaining all point cloud data and color information corresponding to the scene from the same sensor at the same time [3].…”