In this paper a vision-based system for detection, motion tracking and following of Unmanned Aerial Vehicle (UAV) with other UAV (follower) is presented. For detection of an airborne UAV we apply a convolutional neural network YOLO trained on a collected and processed dataset of 10,000 images. The trained network is capable of detecting various multirotor UAVs in indoor, outdoor and simulation environments. Furthermore, detection results are improved with Kalman filter which ensures steady and reliable information about position and velocity of a target UAV. Preserving the target UAV in the field of view (FOV) and at required distance is accomplished by a simple nonlinear controller based on visual servoing strategy. The proposed system achieves a realtime performance on Neural Compute Stick 2 with a speed of 20 frames per second (FPS) for the detection of an UAV. Justification and efficiency of the developed vision-based system are confirmed in Gazebo simulation experiment where the target UAV is executing a 3D trajectory in a shape of number eight.

This paper presents our approach to intercepting a faster intruder UAV, inspired by the MBZIRC 2020 Challenge 1. By utilizing a priori knowledge of the shape of the intruder’s trajectory, we can calculate an interception point. Target tracking is based on image processing by a YOLOv3 Tiny convolutional neural network, combined with depth calculation using a gimbal-mounted ZED Mini stereo camera. We use RGB and depth data from the camera, devising a noise-reducing histogram-filter to extract the target’s 3D position. Obtained 3D measurements of target’s position are used to calculate the position, orientation, and size of a figure-eight shaped trajectory, which we approximate using a Bernoulli lemniscate. Once the approximation is deemed sufficiently precise, as measured by the distance between observations and estimate, we calculate an interception point to position the interceptor UAV directly on the intruder’s path. Our method, which we have significantly improved based on the experience gathered during the MBZIRC competition, has been validated in simulation and through field experiments. Our results confirm that we have developed an efficient, visual-perception module that can extract information describing the intruder UAV’s motion with precision sufficient to support interception planning. In a majority of our simulated encounters, we can track and intercept a target that moves 30% faster than the interceptor. Corresponding tests in an unstructured environment yielded 9 out of 12 successful results.

No abstract

No abstract