UAVs are flexible in action, changeable in shooting angles, and complex and changeable in the shooting environment. Most of the existing stitching algorithms are suitable for images collected by UAVs in static environments, but the images are in fact being captured dynamically, especially in low-altitude flights. Considering that the great changes of the object position may cause the low-altitude aerial images to be affected by the moving foreground during stitching, so as to result in quality problems, such as splicing misalignment and tearing, a UAV aerial image stitching algorithm is proposed based on semantic segmentation and ORB. In the image registration, the algorithm introduces a semantic segmentation network to separate the foreground and background of the image and obtains the foreground semantic information. At the same time, it uses the quadtree decomposition idea and the classical ORB algorithm to extract feature points. By comparing the feature point information with the foreground semantic information, the foreground feature points can be deleted to realize feature point matching. Based on the accurate image registration, the image stitching and fusion will be achieved by the homography matrix and the weighted fusion algorithm. The proposed algorithm not only preserves the details of the original image, but also improves the four objective data points of information entropy, average gradient, peak signal-to-noise ratio and root mean square error. It can solve the problem of splicing misalignment tearing during background stitching caused by dynamic foreground and improves the stitching quality of UAV low-altitude aerial images.

Image stitching refers to stitching two or more images with overlapping areas through feature points matching to generate a panoramic image, which plays an important role in geological survey, military reconnaissance, and other fields. At present, the existing image stitching technologies mostly adopt images with good lighting conditions, but the lack of feature points in scenes with weak light such as morning or night will affect the image stitching effect, making it difficult to meet the needs of practical applications. When there exist concentrated areas of brightness such as lights and large dark areas in the nighttime image, it will further cause the loss of image details making the feature point matching unavailable. The obtained perspective transformation matrix cannot reflect the mapping relationship of the entire image, resulting in poor splicing effect, and it is difficult to meet the actual application requirements. Therefore, an adaptive image enhancement algorithm is proposed based on guided filtering to preprocess the nighttime image, and use the enhanced image for feature registration. The experimental results show that the image obtained by preprocessing the nighttime image with the proposed enhancement algorithm has better detail performance and color restoration, and greatly improves the image quality. By performing feature registration on the enhanced image, the number of matching logarithms of the image increases, so as to achieve high accuracy for images stitching.

Image stitching technology realizes alignment and fusion of a series of images with common pixel areas taken from different viewpoints of the same scene to produce a wide field of view panoramic image with natural structure. The night environment is one of the important scenes of human life, and the night image stitching technology has more urgent practical significance in the fields of security monitoring and intelligent driving at night. Due to the influence of artificial light sources at night, the brightness of the image is unevenly distributed and there are a large number of dark light areas, but often these dark light areas have rich structural information. The structural features hidden in the darkness are difficult to extract, resulting in ghosting and misalignment when stitching, which makes it difficult to meet the practical application requirements. Therefore, a nighttime image stitching method based on image decomposition enhancement is proposed to address the problem of insufficient line feature extraction in the stitching process of nighttime images. The proposed algorithm performs luminance enhancement on the structural layer, smoothes the nighttime image noise using a denoising algorithm on the texture layer, and finally complements the texture of the fused image by an edge enhancement algorithm. The experimental results show that the proposed algorithm improves the image quality in terms of information entropy, contrast, and noise suppression compared with other algorithms. Moreover, the proposed algorithm extracts the most line features from the processed nighttime images, which is more helpful for the stitching of nighttime images.

Frame buildings as important nodes of urban space. The include high-speed railway stations, airports, residences, and office buildings, which carry various activities and functions. Due to illumination irrationality and mutual occlusion between complex objects, low illumination situations frequently develop in these architectural environments. In this case, the location information of the target is difficult to determine. At the same time, the change in the indoor electromagnetic environment also affects the location information of the target. Therefore, this paper adopts the vision method to achieve target localization in low-illumination environments by feature matching of images collected in the offline state. However, the acquired images have serious quality degradation problems in low-illumination conditions, such as low brightness, low contrast, color distortion, and noise interference. These problems mean that the local features in the collected images are missing, meaning that they fail to achieve a match with the offline database images; as a result, the location information of the target cannot be determined. Therefore, a Visual Localization with Multiple-Similarity Fusions (VLMSF) is proposed based on the Nonlinear Enhancement And Local Mean Filtering (NEALMF) preprocessing enhancement. The NEALMF method solves the problem of missing local features by improving the quality of the acquired images, thus improving the robustness of the visual positioning system. The VLMSF method solves the problem of low matching accuracy in similarity retrieval methods by effectively extracting and matching feature information. Experiments show that the average localization error of the VLMSF method is only 8 cm, which is 33.33% lower than that of the Kears-based VGG-16 similarity retrieval method. Meanwhile, the localization error is reduced by 75.76% compared with the Perceptual hash (Phash) retrieval method. The results show that the method proposed in this paper greatly alleviates the influence of low illumination on visual methods, thus helping city managers accurately grasp the location information of targets under complex illumination conditions.