Abstract: Unmanned aerial vehicle (UAV) image stitching technology provides crucial support for the development of the low-altitude economy through efficient integration of aerial data. Panoramic views are generated by this technology, with significant improvements observed in decision-making accuracy and operational efficiency across various fields including path planning, ecological monitoring, and intelligent inspection, thereby effectively promoting the intelligent upgrading of related industries. To address issues such as low registration accuracy, misalignment, and ghosting caused by insufficient feature point extraction in low-texture UAV images, an \ell_1 -norm and gradient-constrained UAV image stitching method was proposed. First, feature points and lines are extracted from both target and reference images to enhance the robustness of feature matching, with the misalignment phenomenon in stitched images being effectively alleviated. Second, the \ell_1 -norm was employed for color difference measurement, while gradient constraints were incorporated to construct an energy function that guides seams through high-similarity continuous regions. Finally, graph-cut optimization is utilized to search for the optimal stitching path in overlapping areas, with Poisson blending being applied to achieve smooth transitions, leading to significant reduction of stitching artifacts. Experiments were conducted on two UAV image stitching datasets, where the proposed method was compared with three representative stitching methods (SPW, LPC, and MSF). The effectiveness and superiority of the proposed method were verified.The results show that compared with SPW, LPC, and MSF, the SSIM values of the proposed method are improved by 2.97%, 5.87%, and 3.07% respectively, while the PSNR values are increased by 0.595, 0.848, 0.841 dB respectively. In terms of visual effects, misalignment and ghosting during the stitching process are significantly improved by the proposed method, with structural integrity and texture details of objects being better preserved, resulting in enhanced overall quality of UAV image stitching. Both quantitative and qualitative analyses fully demonstrate the superior performance of the proposed method in low-texture scenarios.