UAV Based Indoor Localization and Objection Detection

Abstract

This article targets fast indoor positioning and 3D target detection for unmanned aerial vehicle (UAV) real-time task implementation. With the combined direct method and feature method, a method is proposed for fast and accurate position estimation of the UAV. The camera pose is estimated by the visual odometer via the photometric error between the frames. Then the ORB features can be extended from the keyframes for the map consistency improvement by Bundle Adjustment with local and global optimization. A depth filter is also applied to assist the convergence of the map points with depth information updates from multiple frames. Moreover, the convolutional neural network is used to detect the specific target in an unknown space, while YOLOv3 is applied to obtain the semantic information of the target in the images. Thus, the spatial map points of the feature in the keyframes can be associated with the target detection box, while the statistical outlier filter can be simultaneously applied to eliminate the noise points. Experiments with public dataset, and field experiments on the established UAV platform in indoor environments have been carried out for visual based fast localization and object detection in real-time for the efficacy verification of the proposed method.

Self-supervised monocular visual odometry based on cross-correlation

“…A regression loss function L r is used to constrain the position estimation, shown in equation (10).…”

“…Substantial research efforts [5,6] have been dedicated to devising a visual odometry estimation system that integrates accuracy, robustness and from consecutive images, followed by estimating relative pose between two adjacent frames based on geometric relationships. On the other hand [9,10], camera pose can be directly estimated by minimizing photometric errors, assuming photometric invariance. These methods have achieved good results in practical applications but suffer from the following drawbacks: (1) the former method substantially escalates algorithm complexity as robustness is augmented, resulting in heightened complexity in feature point description.…”

A Dual UAV Cooperative Positioning System With Advanced Target Detection and Localization

“…These positioning methods can usually be subdivided into methods based on monocular and stereo vision. Monocular vision positioning methods [17] use a monocular camera and can calculate the target's position relative to the UAV by methods such as triangulation or depth estimation using neural networks. The stereo usually use binocular cameras or simulates binocular cameras by using photos taken by monocular cameras at different locations to form stereo vision [18], and the position coordinates of the target can be found based on parallax information.…”