Safety helmet wearing is a powerful guarantee of workers’ personal safety. Aiming at the collected safety helmet wearing pictures have characteristics of high density， small pixels and difficulty to detect， a small object detection algorithm of YOLOv5 （You Only Look Once version 5） for safety helmet was proposed. Firstly， based on YOLOv5 algorithm， the bounding box regression loss function and confidence prediction loss function were optimized to improve the learning effect of the algorithm on the features of dense small objects in training. Secondly， slicing aided fine-tuning and Slicing Aided Hyper Inference （SAHI） were introduced to make the small object produce a larger pixel area by slicing the pictures input into the network， and the effect of network inference and fine-tuning was improved. In the experiments， a dataset containing dense small objects of safety helmets in the industrial scenes was used for training. The experimental results show that compared with the original YOLOv5 algorithm， the improved algorithm can increase the precision by 0.26 percentage points， the recall by 0.38 percentage points. And the mean Average Precision （mAP） of the proposed algorithm reaches 95.77%， which is improved by 0.46 to 13.27 percentage points compared to several algorithms such as the original YOLOv5 algorithm. The results verify that the introduction of slicing aided fine-tuning and SAHI improves the precision and confidence of small object detection and recognition in the dense scenes， reduces the false detection and missed detection cases， and can satisfy the requirements of safety helmet wearing detection effectively.

As an important component of the surface meteorological observation, the daily observation of surface frost still relies on manual labor. Therefore, a new method for detecting frost based on computer vision was proposed. First, a k-nearest neighbor graph model was constructed by incorporating the manually labeled frosty image samples and the test samples which were acquired during the real-time detection. Second, the candidate frosty regions were extracted by rating those test samples using a graph-based manifold learning procedure which took the aforementioned frosty samples as the query nodes. Finally, those candidate frosty regions were identified by an on-line trained classifier based on Support Vector Machine (SVM). Some experiments were conducted in a standardized weather station and the manual observation was taken as the baseline. The experimental results demonstrate that the proposed method achieves an accuracy of 87% in frost detection and has a potential applicability in the operational surface observation.

Geometric transforms of the object in the imaging process can be represented by affine transform in most situations. Therefore, a method for shape matching using corners was proposed. Firstly, the corner of contour using Multi-scale Product Laplacian of Gaussian (MPLoG) operator was detected, and the feature points based on corner interval were adaptively extracted to obtain the key feature of shape. In order to cope with affine transform, the similarity of two shapes on Grassmann manifold Gr(2,n) were represented and measured. Finally, the iterative sequence shift matching was adopted for overcoming the dependency of Grassmann manifold on the starting point, and achieving shape matching. The proposed algorithm was tested on the database of shapes. The simulation results show that the proposed method can achieve shape recognition and retrieval effectively, and it has strong robustness against noise.