Search

Aerial image has the characteristics of large amount of data, small target scale and dense distribution, and its angle of view is downcast, which is different from the head up view of ordinary image. Therefore, the traditional target detection algorithm for ordinary image cannot adapt to the target detection task of aerial image. For small target detection in aerial images, an improved algorithm based on YOLO-v5, Small-Tiny-YOLO-v5, was proposed. Firstly, GhostNet network was used as the backbone network of the improved algorithm; secondly, the attention mechanism module was added in the backbone network; thirdly, an aerial image data set for small targets was constructed. In addition, the idea of transfer learning was integrated in the training of the improved algorithm. Experimental results show that the model parameters of the proposed improved algorithm are lower than the original YOLO algorithm,and the accuracy and speed are also better than the original algorithm.In the public dataset and the dataset constructed in this paper,the accuracy has increased by 0.009and0.024respectively,and the speed has increased by 73.735% and 58.641%respectively. [ABSTRACT FROM AUTHOR]

Aiming at the problems of similar appearance and occlusion of people in the video person re-identification, a video-based person re-identification model based on pyramid segmentation and attention mechanism was studied and designed. First, in order to enhance the recognition ability of the graph model for the local features of pedestrians, a multi-scale horizontal pyramid segmentation method was proposed. In addition, given that the simple spatiotemporal attention module was prone to damage person features due to occlusion, the spatiotemporal attention module was improved using the spatiotemporal correlation attention method, which gradually learns and aggregates spatially local information while interacting in time sequence to suppress person interference features and enhance discriminative features. This paper evaluates the model on Mars and DukeMTMC-VideoReID datasets, and the experimental results confirm the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]