To address the limitation of the existing UAV (unmanned aerial vehicles) photoelectric localization method used for moving objects, this paper proposes an improved two-UAV intersection localization system based on airborne optoelectronic platforms by using the crossed-angle localization method of photoelectric theodolites for reference. This paper introduces the makeup and operating principle of intersection localization system, creates auxiliary coordinate systems, transforms the LOS (line of sight, from the UAV to the target) vectors into homogeneous coordinates, and establishes a two-UAV intersection localization model. In this paper, the influence of the positional relationship between UAVs and the target on localization accuracy has been studied in detail to obtain an ideal measuring position and the optimal localization position where the optimal intersection angle is 72.6318°. The result shows that, given the optimal position, the localization root mean square error (RMS) will be 25.0235 m when the target is 5 km away from UAV baselines. Finally, the influence of modified adaptive Kalman filtering on localization results is analyzed, and an appropriate filtering model is established to reduce the localization RMS error to 15.7983 m. Finally, An outfield experiment was carried out and obtained the optimal results: ${\sigma }_B=1.63\times {10}^{-4}(°)$ , ${\sigma }_L=1.35\times {10}^{-4}(°)$ , ${\sigma }_H=15.8(m)$ , ${\sigma }_{sum}=27.6(m)$ , where ${\sigma }_B$ represents the longitude error, ${\sigma }_L$ represents the latitude error, ${\sigma }_H$ represents the altitude error, and ${\sigma }_{sum}$ represents the error radius.

In aerial target-tracking research, complex scenarios place extremely high demands on the precision and robustness of tracking algorithms. Although the existing target-tracking algorithms have achieved good performance in general scenarios, all of them ignore the correlation between contextual information to a certain extent, and the manipulation between features exacerbates the loss of information, leading to the degradation of precision and robustness, especially in the field of UAV target tracking. In response to this, we propose a new lightweight Siamese-based tracker, SiamCTCA. Its innovative cross-temporal aggregated strategy and three feature correlation fusion networks play a key role, in which the Transformer multistage embedding achieves cross-branch information fusion with the help of the intertemporal correlation interactive vision Transformer modules to efficiently integrate different levels of features, and the feed-forward residual multidimensional fusion edge mechanism reduces information loss by introducing residuals to cope with dynamic changes in the search region; and the response significance filter aggregation network suppresses the shallow noise amplification problem of neural networks. The modules are confirmed to be effective after ablation and comparison experiments, indicating that the tracker exhibits excellent tracking performance, and with faster tracking speeds than other trackers, these can be better deployed in the field of a UAV as a platform.

In order to improve the geo-location accuracy of the airborne optoelectronic platform and eliminate the influence of assembly systematic error on the accuracy, a systematic geo-location error correction method is proposed. First, based on the kinematic characteristics of the airborne optoelectronic platform, the geo-location model was established. Then, the error items that affect the geo-location accuracy were analyzed. The installation error between the platform and the POS was considered, and the installation error of platform’s pitch and azimuth was introduced. After ignoring higher-order infinitesimals, the least square form of systematic error is obtained. Therefore, the systematic error can be obtained through a series of measurements. Both Monte Carlo simulation analysis and in-flight experiment results show that this method can effectively obtain the systematic error. Through correction, the root-mean-square value of the geo-location error have reduced from 45.65 m to 12.62 m, and the mean error from 16.60 m to 1.24 m. This method can be widely used in systematic error correction of relevant photoelectric equipment.

Siamese network-based trackers satisfy the balance between performance and efficiency for visual tracking. However, they do not have enough robustness to handle the challenges of target occlusion and similar objects. In order to improve the robustness of the tracking algorithm, this paper proposes visual tracking with FPN based on Transformer and response map enhancement. In this paper, a feature pyramid structure based on Transformer is designed to encode robust target-specific appearance features, as well as the response map enhanced module to improve the tracker’s ability to distinguish object and background. Extensive experiments and ablation experiments are conducted on many challenging benchmarks such as UAV123, GOT-10K, LaSOT and OTB100. These results show that the tracking algorithm we proposed in this paper can effectively improve the tracking robustness against the challenges of target occlusion and similar object, and thus improve the precision rate and success rate of the tracking algorithm.

This paper presents a novel method of seamline determination for remote sensing image mosaicking. A two-level optimization strategy is applied to determine the seamline. Object-level optimization is executed firstly. Background regions (BRs) and obvious regions (ORs) are extracted based on the results of parametric kernel graph cuts (PKGC) segmentation. The global cost map which consists of color difference, a multi-scale morphological gradient (MSMG) constraint, and texture difference is weighted by BRs. Finally, the seamline is determined in the weighted cost from the start point to the end point. Dijkstra’s shortest path algorithm is adopted for pixel-level optimization to determine the positions of seamline. Meanwhile, a new seamline optimization strategy is proposed for image mosaicking with multi-image overlapping regions. The experimental results show the better performance than the conventional method based on mean-shift segmentation. Seamlines based on the proposed method bypass the obvious objects and take less time in execution. This new method is efficient and superior for seamline determination in remote sensing image mosaicking.