A method for aerosol extinction profile retrieval using ground-based multi-axis differential optical absorption spectroscopy (MAX-DOAS) is studied, which is based on a look-up table algorithm. The algorithm uses parametric method to represent aerosol extinction profiles and simulate different atmospheric aerosol states through atmospheric radiation transfer model. Based on the method, aerosol extinction profile was obtained during six cloud-free days. The O4 differential air mass factor (dAMF) measured by MAX-DOAS is compared with the corresponding model results under different atmospheric conditions (
R
2
=
0.78
). The aerosol optical thickness, aerosol weight factor in boundary layer, and the height of the boundary layer are obtained after the process of minimization and look-up table method. The retrieved aerosol extinction in boundary layer is compared with PM2.5 data measured by ground point instrument. The diurnal variation trends of the two methods are in good agreement. The correlation coefficients of the two methods are 0.71 when the aerosol optical thickness is smaller than 0.5. The results show that the look-up table method can obtain the aerosol state of the troposphere and provide validation for other instrument data.
Aiming at the problem of pedestrian behavior recognition in infrared images, a method based on Improved GoogLeNet is proposed. Firstly, by analyzing the application scenarios and the characteristics of common network models, GoogLeNet with better comprehensive performance is selected as the backbone network. Inspired by NIN, a kind of 1*1 convolution kernel structure is introduced to reduce the number of channels and significantly reduce the number of parameters. Then channel padding and resize to adapt to the network requirements for the training set and test set of the infrared image human behavior data set. Next, the fully connected layer and the classification output layer of the network are modified according to the number of behavior types contained in the data set. The convolution kernel and inception parameter in the pre-training network are introduced to accelerate the network training and improve the generalization ability of the network. Finally, the quantitative index is used to analyze the experimental results and judge the recognition performance of the network. Experimental results shows that the Mean Average Precision, Average Recall and F1 score obtained by the proposed algorithm are better than the traditional methods.
Pedestrian detection in infrared images has been a hot and difficult research topic in computer version. Traditional methods of pedestrian detection mainly depend on the manual feature for the expression of human body and the results largely relies on the feature representation. Designing artificial features is time-consuming and labor intensive, requires heuristic expertise and experience. Deep learning model based on convolution neural network can automatically learn feature representation from the original images, while avoiding the drawbacks of artificial features. Its difficulty is the choice of network parameters. In this paper, we propose to use deep learning method based on convolution neural network in the process of pedestrian detection. In addition, we analyze the impact of network layers, convolution kernel sizes and feature maps to pedestrian detection in infrared images. The results demonstrate the superiority of our method over traditional methods in detection rate and alarm rate.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.