Corner detection is the basic link of camera calibration, and its detection accuracy will directly affect the accuracy of camera calibration. In order to improve the extraction precision of the corners of the board, this paper put forward a new checkerboard corner detection method. Two kinds of corner point prototype templates are constructed by using the characteristics of the checkerboard. The similarity between the pixel points and the corner points is calculated by convolution of the convolution kernel and the image. The degree of similarity is used to distinguish the corner points from the non-corner points. The non-maximum suppression algorithm and the gradient statistical algorithm further screen out the target corner points. The experimental results show that the method used in this paper can accurately and quickly detect the corner position and has strong anti-interference ability.

Recent advances in communication enable individuals to use phones and computers to access information on the web. E-commerce has seen rapid development, e.g., Alibaba has nearly 12 hundred million customers in China. Click-Through Rate (CTR) forecasting is a primary task in the e-commerce advertisement system. From the traditional Logistic Regression algorithm to the latest popular deep neural network methods that follow a similar embedding and MLP, several algorithms are used to predict CTR. This research proposes a hybrid model combining the Deep Interest Network (DIN) and eXtreme Deep Factorization Machine (xDeepFM) to perform CTR prediction robustly. The cores of DIN and xDeepFM are attention and feature cross, respectively. DIN follows an adaptive local activation unit that incorporates the attention mechanism to adaptively learn user interest from historical behaviors related to specific advertisements. xDeepFM further includes a critical part, a Compressed Interactions Network (CIN), aiming to generate feature interactions at a vectorwise level implicitly. Furthermore, a CIN, plain DNN, and a linear part are combined into one unified model to form xDeepFM. The proposed end-to-end hybrid model is a parallel ensemble of models via multilayer perceptron. CIN and xDeepFM are trained in parallel, and their output is fed into a multilayer perceptron. We used the e-commerce Alibaba dataset with the focal loss as the loss function for experimental evaluation through online complex example mining (OHEM) in the training process. The experimental result indicates that the proposed hybrid model has better performance than other models.

In order to help engineers to better learn from accidents of reinforced concrete structures, accident identification and processing method, this article introduced the ideas of CBR to the accident case retrieval methods of reinforced concrete structures. At the same time, the fuzzy retrieval and knowledge index model of reinforced concrete structure accidents are presented. According to the approximate extent of construction conditions, the approximation of construction are determined, and similar cases with the current engineering cases then retrieved through the case of reinforced concrete structures, which the designer or construction workers can learn from.

No abstract