Real-time detection and timely treatment of floating objects on rivers, lakes and reservoirs is very essential to protect water environment and maintain the safety of navigation and water projects. YOLOv5, as a one-stage object detection solution, is very suitable for real-time floating object detection. However, it suffers from the problem of the false detection and missed detection of floating objects especially of small floating objects. In this paper, we conducts a series of improvements on YOLOv5 to alleviate the problem. Concretely, we propose a hybrid attention mechanism supporting the interaction among channels over a long distance while preserving the direct correspondence between channels and their weights. Base on the attention mechanism, we propose an adaptive feature extraction module to capture the feature information of objects in the case of the feature loss caused by downsampling operations. Based on the attention mechanism and dilated encoder, we construct a feature expression enhancement module to cover large objects while not losing small objects in the same certain scale range. We also add a detection layer for small objects to improve the performance in detecting small floating objects. The experiments on the data set verify the usefulness and effectiveness of our work.

Traffic sign detection plays a vital role in assisted driving and automatic driving. YOLOv5, as a one-stage object detection solution, is very suitable for Traffic sign detection. However, it suffers from the problem of false detection and missed detection of small objects. To address this issue, we have made improvements to YOLOv5 and subsequently introduced YOLOv5-TS in this work. In YOLOv5-TS, a spatial pyramid with depth-wise convolution is proposed by replacing maximum pooling operations in spatial pyramid pooling with depth-wise convolutions. It is applied to the backbone to extract multi-scale features at the same time prevent feature loss. A Multiple Feature Fusion module is proposed to fuse multi-scale feature maps multiple times with the purpose of enhancing both the semantic expression ability and the detail expression ability of feature maps. To improve the accuracy in detecting small even extra small objects, a specialized detection layer is introduced by utilizing the highest-resolution feature map. Besides, a new method based on k-means++ is proposed to generate stable anchor boxes. The experiments on the data set verify the usefulness and effectiveness of our work.

Clustering is widely used as an unsupervised learning algorithm. However, it is often necessary to manually enter the number of clusters, and the number of clusters has a great impact on the clustering effect. At present, researchers propose some algorithms to determine the number of clusters, but the results are not very good for determining the number of clusters of data sets with complex and scattered shapes. To solve these problems, this paper proposes using the Gaussian Kernel density estimation function to determine the maximum number of clusters, use the change of center point score to get the candidate set of center points, and further use the change of the minimum distance between center points to get the number of clusters. The experiment shows the validity and practicability of the proposed algorithm.