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.

Object detection in aerial images is an important task for many applications such as reconnaissance, surveillance, search, and rescue. At present, convolution neural network-based aerial image object detection algorithms mainly focus on rotation invariance and scale invariance, but ignore an important characteristic of the aerial image that the image captured height is an important prior knowledge. At the same captured height, the target has a clear scale range. In this letter, a scale-aware network is proposed to determine the scale of predefined anchors, which can effectively reduce the scale search range, reduce the risk of overfitting, and improve the detection accuracy and speed in aerial images. Experiments on the VisDrone data set show that the proposed method can not only improve the detection speed by 18% but also improve the average accuracy by 1.6%.

With the continuous expansion of the application field of UAV intelligent systems to GNSS-denied environments, the existing navigation system can hardly meet low cost, high precision, and high robustness in such conditions. Most navigation systems used in GNSS-denied environments give up the connection between the map frame and the actual world frame, making them impossible to apply in practice. Therefore, this paper proposes a Lidar navigation system based on global ArUco, which is widely used in large-scale known GNSS-denied scenarios for UAVs. The system jointly optimizes the Lidar, inertial measurement unit, and global ArUco information by factor graph and outputs the pose in the real-world frame. The system includes a method to update the global ArUco confidence with sampling, improving accuracy while using the pose solved from the global ArUco. The system uses the global ArUco to maintain navigation when Lidar is degraded. The system also has a loop closure determination part based on ArUco, which reduces the consumption of computing resources. The navigation system has been tested in the dry coal shed of a thermal power plant using a UAV platform. Experiments demonstrate that the system can achieve global, accurate, and robust pose estimation in large-scale, complex GNSS-denied environments.

In aerial image object detection, how to efficiently detect different size objects in input images of different scales and obtain a unified multi-scale representation of the object is an important issue. Existing methods rarely consider the connection between multi-scale training and multi-scale inference, and do not well optimize the constraint of input object samples in the multi-scale training process, which limits the performance of multi-scale representation. In this study, an efficient object detection algorithm for aerial images is proposed to alleviate this problem. Firstly, we propose to use metric learning to obtain the scale representation boundary of each object class, reduce the support of indistinguishable objects at extreme scales in the training process, and enhance the effect of multi-scale representation. Secondly, indistinguishable small objects are merged into small object regions, and these regions are trained to recommend the detector to detect small objects on the following high-resolution scale. Thus, a reasonable association between multi-scale training and inference is established, and the efficiency of multi-scale inference is considerably improved. The proposed algorithm has been tested on three popular aerial image datasets, including VisDrone, DOTA and UAVDT. Experimental results show that it can improve the detection accuracy and reduce the number of processing pixels.

Object detection in UAV aerial images faces domain-adaptive challenges, such as changes in shooting height, viewing angle, and weather. These changes constitute a large number of fine-grained domains that place greater demands on the network’s generalizability. To tackle these challenges, we initially decompose image features into domain-invariant and domain-specific features using practical imaging condition parameters. The composite feature can improve domain generalization and single-domain accuracy compared to the conventional fine-grained domain-detection method. Then, to solve the problem of the overfitting of high-frequency imaging condition parameters, we mixed images from different imaging conditions in a balanced sampling manner as input for the training of the detection network. The data-augmentation method improves the robustness of training and reduces the overfitting of high-frequency imaging parameters. The proposed algorithm is compared with state-of-the-art fine-grained domain detectors on the UAVDT and VisDrone datasets. The results show that it achieves an average detection precision improvement of 5.7 and 2.4, respectively. The airborne experiments validate that the algorithm achieves a 20 Hz processing performance for 720P images on an onboard computer with Nvidia Jetson Xavier NX.