Drone Detection and Pose Estimation Using Relational Graph Networks

Abstract

With the upsurge in use of Unmanned Aerial Vehicles (UAVs), drone detection and pose estimation by using optical sensors becomes an important research subject in cooperative flight and low-altitude security. The existing technology only obtains the position of the target UAV based on object detection methods. To achieve better adaptability and enhanced cooperative performance, the attitude information of the target drone becomes a key message to understand its state and intention, e.g., the acceleration of quadrotors. At present, most of the object 6D pose estimation algorithms depend on accurate pose annotation or a 3D target model, which costs a lot of human resource and is difficult to apply to non-cooperative targets. To overcome these problems, a quadrotor 6D pose estimation algorithm was proposed in this paper. It was based on keypoints detection (only need keypoints annotation), relational graph network and perspective-n-point (PnP) algorithm, which achieves state-of-the-art performance both in simulation and real scenario. In addition, the inference ability of our relational graph network to the keypoints of four motors was also evaluated. The accuracy and speed were improved significantly compared with the state-of-the-art keypoints detection algorithm.

A Comprehensive Review on Design of Autonomous Robotic Boat for Rescue Applications

“…is IPM method is much more effective, especially in cases where the camera is close to the ground, which makes the tracking of features a cumbersome process. e authors of [91] have proposed a solution based on the convolutional neural network (CNN) model to detect the objects by drones. However, the methods distinguish shape and motion characteristics from small flying drone distances; this way, objects can be tracked or skipped effectively.…”

Unsupervised Human Detection with an Embedded Vision System on a Fully Autonomous UAV for Search and Rescue Operations

“…Moreover, the adaption of camera parameters, as well as motion parameters estimation based on the integration of video measurements and data obtained by UAVs, have always to be seriously taken into account [32]. The relentless motivation for image classification tasks based on deep learning and aerial images captured by UAVs has led to an abundance of research including vehicles [24,33,34], aerial vehicles [35,36,37,38,39], roads [40], buildings [41,42], cracks [43], birds [44], cattle [45], and wilt [46] detection. Another remarkable approach for object detection in very high-resolution aerial images has been proposed in [47].…”

Estimation of a Human-Maneuvered Target Incorporating Human Intention

“…Most dynamic targets to track or engage are either human-maneuvered or humans themselves. Estimating the state of such a human-maneuvered target is essential and important, and has attracted tremendous interest in the last decades [ 1 , 2 , 3 , 4 ]. Despite the importance, difficulty in the estimation of the human-maneuvered target lies in the motion uncertainty.…”