Sonar Image Target Detection for Underwater Communication System Based on Deep Neural Network

Target signal acquisition and detection based on sonar images is a challenging task due to the complex underwater environment.In order to solve the problem that some semantic information in sonar images is lost and model detection performance is degraded due to the complex imaging environment,we proposed a more effective and robust target detection framework based on deep learning,which can make full use of the acoustic shadow information in the forward-looking sonar images to assist underwater target detection.Firstly,the weighted box fusion method is adopted to generate a fusion box by weighted fusion of prediction boxes with high confidence,so as to obtain accurate acoustic shadow boxes.Further,the acoustic shadow box is cut down to get the feature map containing the acoustic shadow information,and then the acoustic shadow feature map and the target information feature map are adaptively fused to make full use of the acoustic shadow feature information.In addition,we introduce a threshold processing module to improve the attention of the model to important feature information.Through the underwater sonar dataset provided by Pengcheng Laboratory,the proposed method improved the average accuracy by 3.14%at the IoU threshold of 0.7,which is better than the current traditional target detection model.

Light weighting opportunities and material choice for commercial vehicle frame structures from a design point of view

This paper focuses on an estimation of light weighting opportunities for the frame structure of com- mercial road vehicles. This estimation is based on simpli- fied static load cases which play a predominant role for the dimensioning of a frame structure and therefore these simplifications are not putting the general validity of the conclusions into question. A comparison of different ma- terials under this scenario shows that light metals do not show any weight reduction advantage in comparison to steel while a material-independent topology optimization has more weight reduction potential for the frame structure than a simple change of materials. Considering the con- straints of part complexity which is directly linked with production and assembly cost, the ladder frame structure has become the current state of the art design. Thus the paper also puts a spotlight on basic rules of node design and vertical load induction in order to keep the weight of such a design as low as possible. Practical examples from manufacturers show that the weight of a commercial vehicle could be reduced by 10%, and main parts of the frame structure could be reduced by 30% using high strength steel in combination with innovative production methods like roll forming.