Search

Scene recognition is a hot research topic in the field of image recognition. It is necessary that we focus on the research on scene recognition, because it is helpful to the scene understanding topic, and can provide important contextual information for object recognition. The traditional approaches for scene recognition still have a lot of shortcomings. In these years, the deep learning method, which uses convolutional neural network, has got state-of-the-art results in this area. This thesis constructs a model based on multi-layer feature extraction of CNN and transfer learning for scene recognition tasks. Because scene images often contain multiple objects, there may be more useful local semantic information in the convolutional layers of the network, which may be lost in the full connected layers. Therefore, this paper improved the traditional architecture of CNN, adopted the existing improvement which enhanced the convolution layer information, and extracted it using Fisher Vector. Then this thesis introduced the idea of transfer learning, and tried to introduce the knowledge of two different fields, which are scene and object. We combined the output of these two networks to achieve better results. Finally, this thesis implemented the method using Python and PyTorch. This thesis applied the method to two famous scene datasets. the UIUC-Sports and Scene-15 datasets. Compared with traditional CNN AlexNet architecture, we improve the result from 81% to 93% in UIUC-Sports, and from 79% to 91% in Scene- 15. It shows that our method has good performance on scene recognition tasks.

This paper deals with a NC machine system containing displacement sensor and angle sensor, and measures TE(transmission error) data indirectly. This study uses an improved FFT algorithm based on linear interpolation to carry on spectrum analysis for TE data, determines the position of error source, and analyzed the origin of this error source. Experiment shows the efficiency of this algorithm improves about 4.7% than FFT algorithm's.

In comparison with gasoline, hydrogen possesses the properties of high combustion speed, wide flammability limit and small energy needed for ignition. To examine the effects of the hydrogen quantity supplied on the engine properties and its exhaust emission characteristic when the gasoline engine is fueled with gasoline and a small quantity of hydrogen, some fundamental experimental investigation was performed on a type BJ-492Q gasoline engine, thereby provided basis for application. From the experimental results the authors discovered that the flammability limit of the mixed fuel is extended with the increasing of the quantity of hydrogen supplied; the optimum ignition advance angle is decreased with it; the indicated thermal efficiency of the engine is raised with it but, on the contrary, its indicated thermal efficiency is decreased when the composite excessive air coefficient is smaller than 1.0; CO and HC emission concentration in the exhaust is remarkably decreased because of the small quantity of hydrogen supplied.