Search

Millimeter-wave (MMW) radar hand gesture recognition technology is becoming important in many electronic device control applications. Currently, most existing approaches utilize the radical and micro-Doppler features from single-channel MMW radar, which ignores the different importance of the information contained in the micro-Doppler feature background or target areas. In this paper, we propose an algorithm for hand gesture recognition jointly using multi-channel signatures. The algorithm blends the information of both micro-Doppler features and instantaneous angles (azimuth and elevation) to accomplish hand gesture recognition performed with the convolutional neural network (CNN). To have a better features fusion and make CNN focus on the most important target signal regions and suppress the unnecessary noise areas, we apply the channel and spatial attention-based feature refinement modules. We also employ gesture movement mechanism-based data augmentation for more effective training to alleviate potential overfitting. Extensive experiments demonstrate the effectiveness and superiorities of the proposed algorithm. This method achieves a correct classification rate of 96.61%, approximately 5% higher than that of the single-channel-based recognition strategy as measured based on MMW radar datasets.

Recent years, bushfire has been more and more frequent because of climate changes. At the scene of fires, firefighters have used drones for surveillance. In this paper, a model is designed to determine the optimal number of drones needed for a bushfire based on the data from satellites. We design a greedy algorithm to plan the cruise lines with the minimal number of drones, covering the fire region. We divide a region (take Victoria, Australia as an example) into blocks, and analysed each block to get the average number of drones needed. We also model the fire probability distribution and finally determine the total number of drones that should be reserved. The simulation (The simulation code is publicly available via https://github.com/WRangers/msadab) results and analysis show the model is effective and can adapt to a real-time changing large-scale bushfire situation, adjusting the cruise scheme dynamically. The algorithm is helpful to make a budget on purchasing equipment, and also helps the fire department deploy drones in bushfires.