The frequent illegal use of drones poses a serious threat to public security and property. Counter-drones are crucial tools. The prerequisite for an effective counter-drone is to detect drones accurately. With the rapid advancements in computer vision, vision-based drone detection methods have emerged as a hot topic of research. However, current reviews of vision-based drone detection are less focused on algorithmic summarization and analysis. For this reason, this survey aims to comprehensively review the latest methods for vision-based drone detection in complex environments, with the goal of providing a more thorough reference and guidance for related research. We first explore the imaging and drone characteristics in complex environments and summarize the main challenges of visual UAV detection. Then, we summarize the existing solutions for the main challenges. Finally, we systematically organize and introduce the commonly used datasets and evaluation metrics and conduct experiment comparisons based on the representative methods. We not only reveal the current development status of visual UAV detection but also analyze the deficiencies in current research. On this basis, we further look forward to future research directions and possible breakthroughs, with a view to providing useful insights for further research and development in related fields.

The purpose of infrared and visible image fusion (IVIF) is to acquire a more informative fused image by leveraging complementary information, facilitating human perception and machine vision. Among the existing fusion methods, the saliency-based methods conform to human perception characteristics and achieve relatively advantageous fusion performance. However, such methods fail to adaptively maintain the edge and intensity of salient objects, resulting in fixed fusion performance. To address these issue, we present ASIFusion, an adaptive saliency injection-based IVIF network. First, source images are inputted to the feature extraction encoder for fully extracting features. Meanwhile, the proposed adaptive saliency injection module detects salient objects in the infrared image and then learns the fusion weights of each channel, which serve as supplementary information for further fusion. These learned weights are utilized to merge the source images’ extracted features. Finally, the feature reconstruction decoder produces a fused image with injected saliency. The fused image maintains the intensity and edge of the salient objects and fully preserves the complementary information. Extensive experiments demonstrate that our proposed network outperforms state-of-the-art (SOTA) approaches with regard to fusion performance and computational efficiency.