The paper proposes improvements to YOLOv8n to enhance small target detection capabilities and introduces coordinate attention (CA) to the C2f module to improve focus on spatial information and local details. CA enhances spatial feature representation and small object recognition and replaces Path Aggregation Network with Bidirectional Feature Pyramid Network (BiFPN) in the neck to better fuse multi-scale features. BiFPN enables more effective fusion of features at different scales and adds a smaller detection head to improve perception of very small targets. The additional detection head utilizes more shallow feature information and incorporates Omni-dimensional Dynamic Convolution (ODConv) to adaptively adjust convolution kernels. ODConv allows flexible capture of critical information for various target patterns and sizes. Experimental results show the proposed improvements lead to better performance on small object detection tasks, with increases in metrics like average precision mean (mAP), precision, and recall. The combined enhancements aim to address common challenges in small target detection such as low contrast, large-scale differences, and the need for fine-grained feature capture. Compared to the original YOLOv8n algorithm, this algorithm improves the average accuracy on small targets by 3.2% for mAP@50, 4.4% for mAP@75, 3% for Precision rate, and 4% for Recall.

The progress of Internet technology and the portability of mobile communication equipment have provided essential convenience for building an information society. Today, with networked and digital platforms as an important way of socializing, the information carrier is more based on images, videos, etc. The explosive growth of these multimedia data poses a huge challenge to efficient data storage and fast information retrieval. We design an algorithm combining Locality-sensitive Hashing (LSH) and Vision Transformer (ViT) to greatly improve the image matching rate and accuracy, and the algorithm is called ViT-LSH. The principle of LSH is to form the same hash value for points with similar distances in the data set. The results show that the LSH algorithm reduces space consumption and improves query processing efficiency compared with the other five schemes. Therefore, the LSH algorithm can help to quickly get the approximate nearest neighbor query results in a probabilistic manner, thereby ensuring the accuracy of the query results and the efficiency of time and space. The ViT divides the image into fixed-size image blocks ( Patch), uses Linear projection to project the Patch flatten to the specified dimension, gets the Tokens sequence, and adopts the sequence as the input of the feature to realize a new segmentation mode. The ViT does not employ down-sampling so that the image resolution is not reduced. The modeling of global information is a new semantic segmentation mode. The steps of ViT-LSH are as follows: first, preprocess the image, such as denoising, then segment the image, then extract features by ViT, and then reduce features' dimension. The LSH performs hash coding on the image features. After calculating the image's hash code, the image's similarity can be directly calculated by the Hamming distance, sorted according to the similarity, and the matching results are obtained. The experimental results exhibit that ViT-LSH can greatly enhance the efficiency and accuracy of image matching.