In recent years, with the improvement of Internet of Things (IOT) technology, a “shared” service concept has appeared in people’s life. In the limited available resources, it is of great value to study the optimal path of charging pile selection for shared cars. With the help of Internet of Things technology and through analyzing the collected data, this paper introduces three path optimization methods, the Dijkstra algorithm, heuristic algorithm A∗ , and improved particle swarm optimization (PSO) algorithm; establishes relevant convergence conditions; and takes the actual path cost as the criterion to judge the optimal path. In addition, this paper studies the optimal path from the shared car to the charging pile. Through the simulation experiment, the results show that compared with the traditional optimal path algorithm, the improved particle swarm optimization algorithm has strong parallelism and better search effect for optimal path selection in the case of large number of traffic path nodes and complex paths, which fully reflects the performance advantage of the algorithm.

This paper introduced a layout and perspective distortion independent recognition framework for captured Chinese document image. Under the framework, 1) Conditional random field (CRF) is employed for text line extraction from a global point of view. As the text line extraction is layout independent it could be widely used in different type of document images 2) A text line image based perspective distortion correction method is detailed and used in three different ways. 3) The text line extraction and perspective distortion correction are combined with character recognition to construct a recognition system. On three captured document image datasets, the proposed framework improves the accuracies from 94.03% to 95.20%, 13.01% to 93.71% and 10.63% to 92.68% respectively for different distortion degrees. The experimental results demonstrate that the introduced recognition framework is promising for solving layout and perspective distortion problems in captured document image recognition.