![]() The processing of radar signal is the key to radar performance and has important research value. It is the most advantageous tool for azimuth and distance monitoring when the ship is sailing, which can effectively ensure the safety of the ship. ![]() ![]() The ship navigation radar is installed on the ship for positioning, navigation, obstacle avoidance, etc. With the development of shipping, ship radar has gradually gained popularity. Radar achieves the positioning and detection of an object by directionally launching electromagnetic energy, receiving the reflected electric wave of the object, and calculating the direction, speed and shape of the object, which has been widely used in fields, such as military, remote sensing, aviation and navigation. This is an Open Access article distributed under the terms of the Creative Commons Attribution License ( ), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The experiment proves the effectiveness of the proposed algorithm and provides some theoretical basis for the better processing of radar signals, which is beneficial to improve the environment perception ability of ships in harsh environments and promote the further development of the navigation industry. ![]() In the test of the algorithm, the radar signal processing algorithm designed in this study has good precision as monitoring error of the target's azimuth and distance is controlled within 1% and it also has a better suppression effect of sea clutter and rain and snow clutter, which can suppress the clutter well, improve the target clarity, and ensure the safe navigation of the ship. Firstly, the principle of radar azimuth and distance monitoring is introduced, then the pulse accumulation algorithm and median filtering algorithm are analyzed, and finally a sea clutter suppression algorithm based on sensitivity time control (STC) and a rain and snow clutter suppression algorithm based on constant false alarm rate are designed to improve the target monitoring performance of radar. In this paper, the signal processing algorithm is studied. * Corresponding author: effect of ship navigation radar signal processing has a great impact on the overall performance of the radar system. Support for new layers can be added as they become available.Įarly customers are already in design with the Vision C5 DSP.Zhengzhou University of Aeronautics, Zhengzhou, Henan 450046, PR China The Vision C5 DSP supports variable kernel sizes, depths, and input dimensions, and it accommodates several different coefficient compression/decompression techniques. As such, it leverages a comprehensive set of hand-optimized neural network library functions. The toolset will map any neural network trained with tools such as Caffe and TensorFlow into executable and highly optimized code for the Vision C5 DSP. If you?re concerned about designing with or programming the core, rest assured that it comes with the Cadence neural network mapper toolset, the same proven software toolset as the Vision P5 and P6 DSPs. Hence, the performance can scale based on application needs. It?s also architected for multi-processor designs. This frees up the host processor to handle other tasks. Note that the C5 DSP is not an accelerator, per se, but rather a complete, standalone DSP IP core that runs all neural network layers (convolution, fully connected, pooling and normalization). From a silicon perspective, the IP core consumes about 1 mm 2 of die area. Specifically, the Vision C5 DSP is aimed at automotive, surveillance, drone, and mobile/wearable applications, as it offers 1 TMAC/s computational capacity to run all neural network computational tasks. Tensilica claims that the IP core is the industry?s first standalone, self-contained neural network DSP IP core optimized for vision, radar/lidar, and fused-sensor applications with high-availability neural network computational needs. Times are obviously changing, as evidenced by Cadence?s Vision C5 DSP (which actually comes for the company?s Tensilica division). It wasn?t long ago that a system employing neural networks requires a host of big CPUs, and lots of associated board area. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |