Wetland experimental images are often affected by factors such as waves, weather conditions, and lighting, resulting in severe noise in the images. In order to improve the quality and accuracy of wetland experimental images, this paper proposes a wetland experimental image denoising method based on the fast finite shearlet transform (FFST) and a deep convolutional neural network model. The FFST is used to decompose the wetland experimental images, which can capture the features of different frequencies and directions in the images. The network model has a deep network structure and powerful feature extraction capabilities. By training the model, it can learn the relevant features in the wetland experimental images, thereby achieving denoising effects. The experimental results show that, compared to traditional denoising methods, the proposed method in this paper can effectively remove noise from wetland experimental images while preserving the details and textures of the images. This is of great significance for improving the quality and accuracy of wetland experimental images.

Background. The mainly lethal ability of ammunition fragments on creatures is achieved by hitting the effective organs or key parts of the biological body with high-speed projectiles. How to efficiently and accurately obtain the projectile speed and hitting position coordinates when the fragment hits the creature after the ammunition blast is the key to the scientific evaluation of ammunition power. Materials and Methods. For the measurement of fragment velocity and hitting coordinates, a series of flexible film circuit sensors can be generated by printing comb-like circuits on polyethylene terephthalate substrates using silver paste printing technology. These sensors are cheap, flexible, and easy to fold and can be printed into different shapes according to the characteristics of the test target to simulate the biological key organs or lethal parts. At the same time, the software and hardware design of the high-speed data signal reading and processing module can realize the data rapidly recording and processing and quickly give the ammunition fragment parameter test results. Results. The test accuracy of the fragment velocity of the laser light screen target and the flexible circuit sensor is compared through the live-fire test. It is proved that the test accuracy of the flexible sensor based on the polymer substrate can meet the accuracy requirements. The flexible sensor based on the organ simulation can quickly give the accurate hit position of the fragment. Conclusion. The newly polymer substrate printed circuit sensor system is a new type of sensor used to replace the laser screen target, and the copper comb printed circuit in the ammunition power test, which can improve the parameter test accuracy, reduce the test consumption, and improve the test quality.