Unmanned aerial vehicle (UAV) image stitching techniques based on position and attitude information have shown clear speed superiority over feature-based counterparts. However, how to improve stitching accuracy and robustness remains a great challenge since position and attitude parameters are sensitive to noise introduced by sensors and external environment. To mitigate this issue, this work presents a simple yet effective stitching algorithm for UAV images based on a coarse-to-fine strategy. Specifically, we first conduct coarse registration using the position and attitude information obtained from GPS, IMU, and altimeter. Then, we introduce a novel offline calibration phase that is designed to regress the obtained global transformation matrix to the optimal one computed from feature-based algorithms, by using multi-layer perceptron (MLP) neural networks for fast correction. Consequently, the proposed method well integrates the complementary strengths of both parameter and feature-based methods, achieving an ideal speed–accuracy tradeoff. Moreover, to facilitate research on this topic, we establish a new dataset, named UAV-AIRPAI, that comprises over 100 UAV image pairs with position and attitude annotations to the community, opening up a promising direction for UAV image stitching. Extensive experiments on the UAV-AIRPAI dataset show that our method achieves superior accuracy compared to priors while running at a real-time speed of 0.0124 s per image pair. Code and data will be available at https://github.com/dededust/UAV-AIRPAI .

The popularity of unmanned aerial vehicles (UAVs) has made anti-UAV technology increasingly urgent. Object tracking, especially in thermal infrared videos, offers a promising solution to counter UAV intrusion. However, troublesome issues such as fast motion and tiny size make tracking infrared drone targets difficult and challenging. This work proposes a simple and effective spatio-temporal attention based Siamese method called SiamSTA, which performs reliable local searching and wide-range re-detection alternatively for robustly tracking drones in the wild. Concretely, SiamSTA builds a two-stage re-detection network to predict the target state using the template of first frame and the prediction results of previous frames. To tackle the challenge of small-scale UAV targets for long-range acquisition, SiamSTA imposes spatial and temporal constraints on generating candidate proposals within local neighborhoods to eliminate interference from background distractors. Complementarily, in case of target lost from local regions due to fast movement, a third stage re-detection module is introduced, which exploits valuable motion cues through a correlation filter based on change detection to re-capture targets from a global view. Finally, a state-aware switching mechanism is adopted to adaptively integrate local searching and global re-detection and take their complementary strengths for robust tracking. Extensive experiments on three anti-UAV datasets nicely demonstrate SiamSTA’s advantage over other competitors. Notably, SiamSTA is the foundation of the 1st-place winning entry in the 2nd Anti-UAV Challenge.

The pendulous integrating gyroscopic accelerometer (PIGA) sensor has an eccentric pendulum and continuous precession characteristics. The motion of its float is more complex compared to that of a gyroscope. Now there is no method for calibrating magnetic suspension disturbance torque of gyroscopic accelerometer. To address this, the mechanism by which disturbance torque affects instrument output when magnetic suspension system overcomes transverse pendulum torque is analyzed. A novel method for calibrating magnetic suspension disturbance torque by injecting excitation into the magnetic suspension control loop is proposed. The calibration test is carried out on the PIGA to obtain the equivalent force arm of the electromagnetic force of the PIGA. The equivalent force arm is multiplied by the electromagnetic force at the actual working time to get the disturbance torque of magnetic suspension. Accordingly, the influence of the magnetic suspension disturbance torque on the magnitude of PIGA precision is analyzed, and then the concerned error of the PIGA can be obtained. The tests in six PIGA showed consistency in the order of magnitude of the equivalent force arm of the electromagnetic force calibrated by the disturbance torque under different overload conditions. Typically, the magnetic suspension disturbance torque ranges from 10⁻⁹ to 7 × 10⁻⁸ Nm. This result verifies the effectiveness of the calibration method proposed in this paper. The method provides a new idea for compensating for the output error of the PIGA sensor, which is of an important reference value to improve the accuracy of the sensor.