The great performance of deep learning in many visual tasks largely depends on the big data volume and the improvement of computing power. But in many practical projects, it is usually difficult to provide enough data to complete the task. Concerning the problem that the number of infrared images is small and the infrared images are hard to collect, a method to generate infrared images based on color images was proposed to obtain more infrared image data. Firstly, the existing color image and infrared image data were employed to construct the paired datasets. Secondly, the generator and the discriminator of Generative Adversarial Network (GAN) model were formed based on the convolutional neural network and the transposed convolutional neural network. Thirdly, the GAN model was trained based on the paired datasets until the Nash equilibrium between the generator and the discriminator was reached. Finally, the trained generator was used to transform the color image from the color field to the infrared field. The experimental results were evaluated based on quantitative evaluation metrics. The evaluation results show that the proposed method can generate high-quality infrared images. In addition, after the L1 or L2 regularization constraint was added to the loss function, the FID (Fréchet Inception Distance) score was respectively reduced by 23.95, 20.89 on average compared to the FID score of loss function not adding the constraint. As an unsupervised data augmentation method, the method can also be applied to many other visual tasks that lack train data, such as target recognition, target detection and data imbalance.

In order to solve the problem of low recommendation precision in the traditional trip itinerary recommendation algorithm, a novel Personalized Trip Itinerary Recommendation (PTIR) algorithm based on Points Of Interest (POI) popularity and user interests was proposed. Firstly, the user's real-life travel histories were obtain by analyzing the data. Then user interests based on the time were proposed according to the stay time of each scenic spot. Finally, a calculation method of optimal trip itinerary was designed under the given travel time limits, start and end points. The experimental results of a Flickr data set show that, compared with the traditional algorithm with only considering POI popularity, the precision and recall of the proposed PTIR algorithm based on the POI popularity and user interests were greatly improved; and compared with the traditional algorithm with only considering the user interests, the precision and recall of the proposed PTIR algorithm based on the points of interest and user interests were also improved. The experimental results show that considering both the POI popularity and user interests can make the itinerary recommendation more precise.