With the continuous development of target detection technology,the vehicle detection system for road scenes has been widely used in the field of automatic driving. Compared with the traditional target detector, though the target of vehicle detection is relatively simple, two major problems need to be solved. First, the characteristics which provided to the detector are usually incomplete in some complex road scenes, and other problems such as occlusion and deformation will occur. Second, it is necessary to estimate the distance of different vehicles to ensure the car can make timely evasive action in the process of automatic driving, which means it needs depth estimation of the target area of the image. Aiming at these two problems, a vehicle detection system based on anti⁃sample generation and depth map reconstruction was proposed. A confrontation network was designed for the pre⁃training target detection network called Faster⁃RCNN, which was used to generate a large number of samples during the training process, and train the vehicle detector with these samples. According to the detection results, the vehicle distance is estimated to inform the system to make evasive action in time through the reconstruction of 3D scene and camera pose recovery depth map. The experimental results show that this detection system can improve the detection effect and estimate the distance of the target vehicle without increasing the data training sample.

Due to equipment failures, natural disasters, supply shortage and increased demand for natural gas, the natural gas pipeline network operations department needs to distribute and adjust the supply for individual user. However, operation parameters were restricted by flowing law when natural gas flowed in the process of the pipeline system, the gas supply pressure and flow rate must also meet the requirements established by users. Based on the gas pipeline operation features, user needs and service priority, natural gas pipeline network resources optimization allocation model was put forward based on the priority service of important user to optimize the resources allocation and reduce the inefficiency utilization of natural gas and negative influence of shortage of natural gas supply. It took an actual example involving 33 pipes, 35 nodes, 3 compressor stations and the various types of users and applied the model and method, calculated the optimal operation schemes of pipeline system, which provided an important basis for operation scheduling.

A glycolipids type biosurfactant, as identified by FTIR was obtained from Enterobacter cloacae, a petroleum-degrading bacterium. The optimum productivity of the biosurfactant was obtained. An optimal yield of biosurfactant was achieved at a n(C)/n(N) ratio of 8.9 using glucose as carbon source and ammonium chloride as nitrogen source when the initial pH value of the culture media is 7.2. It is shown that the presence of the biosurfactant greatly enhanced water-solubility of phenanthrene and the removal of phenanthrene from kaolinite soil. These would thus improve the bioavailability of phenanthrene and intensify the bioremediation of petroleum contaminated soil.