In recent years, hyperspectral imagery has played a significant role in IoV (Internet of Vehicles) vision areas such as target acquisition. Researchers are focusing on integrating detection sensors, detection computing units, and communication units into vehicles to expand the scope of target detection technology with hyperspectral imagery. As imaging spectroscopy technology gradually matures, the spectral resolution of captured hyperspectral images is increasing. At the same time, the volume of data is also increasing. As a result, the reliability of IoV applications is challenged. In this paper, an intelligent hyperspectral target detection method based on deep learning network is proposed. It is based on the residual network structure with the addition of an attention mechanism. The trained network model requires few computational resources and can provide the results in a short time. Our method improves the value of mAP50 by an average of 3.57% for all categories and by up to 5% for a single category on the public dataset.

近年来，高光谱图像在目标获取等 IoV（车联网）视觉领域发挥了重要作用。研究人员正专注于将检测传感器、检测计算单元和通信单元集成到车辆中，以利用高光谱图像扩大目标检测技术的范围。随着成像光谱技术的逐渐成熟，捕获的高光谱图像的光谱分辨率不断提高。与此同时，数据量也在不断增加。因此，车联网应用的可靠性受到挑战。本文提出了一种基于深度学习网络的智能高光谱目标检测方法。它基于残差网络结构，增加了注意力机制。训练好的网络模型需要很少的计算资源，并且可以在短时间内提供结果。我们的方法在公共数据集上将所有类别的 mAP50 值平均提高了 3.57%，对于单个类别提高了 5%。