In this study, an advanced Kinect sensor was adopted to acquire infrared radiation (IR) images for liveness detection. The proposed liveness detection method based on infrared radiation (IR) images can deal with face spoofs. Face pictures were acquired by a Kinect camera and converted into IR images. Feature extraction and classification were carried out by a deep neural network to distinguish between real individuals and face spoofs. IR images collected by the Kinect camera have depth information. Therefore, the IR pixels from live images have an evident hierarchical structure, while those from photos or videos have no evident hierarchical feature. Accordingly, two types of IR images were learned through the deep network to realize the identification of whether images were from live individuals. In comparison with other liveness detection cross-databases, our recognition accuracy was 99.8% and better than other algorithms. FaceNet is a face recognition model, and it is robust to occlusion, blur, illumination, and steering. We combined the liveness detection and FaceNet model for identity authentication. For improving the application of the authentication approach, we proposed two improved ways to run the FaceNet model. Experimental results showed that the combination of the proposed liveness detection and improved face recognition had a good recognition effect and can be used for identity authentication.

With the aim to solve issues of robot object recognition in complex scenes, this paper proposes an object recognition method based on scene text reading. The proposed method simulates human-like behavior and accurately identifies objects with texts through careful reading. First, deep learning models with high accuracy are adopted to detect and recognize text in multi-view. Second, datasets including 102,000 Chinese and English scene text images and their inverse are generated. The F-measure of text detection is improved by 0.4% and the recognition accuracy is improved by 1.26% because the model is trained by these two datasets. Finally, a robot object recognition method is proposed based on the scene text reading. The robot detects and recognizes texts in the image and then stores the recognition results in a text file. When the user gives the robot a fetching instruction, the robot searches for corresponding keywords from the text files and achieves the confidence of multiple objects in the scene image. Then, the object with the maximum confidence is selected as the target. The results show that the robot can accurately distinguish objects with arbitrary shape and category, and it can effectively solve the problem of object recognition in home environments.

Urban rail transit is an important existence in the urban transportation system. In recent years, a large number of people will take it as their preferred travel mode, but the station failure caused by emergencies is inevitable. The impact on the whole system makes people put forward higher requirements for the operation of rail transit. Therefore, how to suppress the fault spread and how to quickly and effectively recover the urban rail transit system after the fault spread is an urgent problem to be solved. In this paper, based on the metro network data obtained from Gaode map, the network topology model was established by using the complex network theory. Then, the fault spread law of the metro network without recovery and the fault spread law with recovery were studied. Finally, the four strategies were simulated and compared.

Depression filling and direction assignment over flat areas are critical issues in hydrologic analysis. This paper proposes a method to handle depressions and flat areas in one procedure. Being different from the traditional raster neighbourhoods processing with little heuristic information, the method is designed to compensate for the inadequate searching information of other methods. The proposed method routes flow through depressions and flat areas by searching for the outlet using the heuristic information. Heuristic information can reveal the general trend slope of the DEM (digital elevation models) and help the proposed method find the outlet accurately. The method is implemented in Pascal and experiments are carried out on actual DEM data. It can be seen from the comparison with the four existing methods that the proposed method can get a closer match result with the ground truth network. Moreover, the proposed method can avoid the generation of the unrealistic parallel drainage lines, unreal drainage lines and spurious terrain features.