基于注意力和角度间隔损失的高光谱目标跟踪北大核心CSCD

随着计算机技术的发展,基于深度学习的目标跟踪方法已成为计算机视觉领域中重要的研究方向;但跟踪环境的复杂多变使得跟踪算法在背景干扰、颜色相近等问题上仍面临巨大挑战。相比于传统彩色图像,高光谱图像包含丰富的辐射、空间和光谱信息,能够有效提升目标跟踪的准确率。提出了将注意力机制(attention mechanism)和加性角度间隔损失(additive angular margin loss, AAML)相结合的方法来进行针对高光谱图像的目标跟踪。通过融合多域神经网络对不同波段组合进行特征提取,同时设计了融合的注意力机制模型,使得来自不同波段组合之间的相似特征进行整合和强化,在目标背景颜色相近的情况下,网络会更多地注意目标物体,使得跟踪结果更为准确。在此基础上为了使目标和背景的区分更具有判别性,网络使用加性角度间隔损失作为损失函数,在训练过程中可以有效减小同类样本的类内距离,增大正负类样本的类间距离,从而提高网络的准确性和稳定性。实验结果表明,本文方法可使两种跟踪精度评价指标精确率和成功率分别提升1.3%和0.3%,相较于其他方法更具优势。

Hyperspectral target tracking based on attention mechanism and additive angular margin loss

With the development of computer technology, the target tracking methods based on deep learning have become an important research direction in the field of computer vision. However, the target tracking methods still face great challenges in complex environment such as background interference and color proximity. Compared with the traditional color images, the hyperspectral images contain rich radiation, spatial and spectral information, which can effectively improve the accuracy of target tracking. A method was proposed in combination with attention mechanism and additive angular margin loss (AAML) to perform target tracking for hyperspectral images. The features of different combinations of bands were extracted by fused multi-domain neural networks, and then the fused attention mechanism model was designed to make the similar features from different combinations of bands integrated and strengthened. Therefore, when the target background color was similar, the network would pay more attention to the target object, which made the tracking results more accurate. On this basis, in order to make the distinction between target and background more discriminative, the AAML was adopted as loss fuction to effectively reduce the intra-class distance of similar samples, increase the inter-class distance between centers of positive and negative samples, and improve the network accuracy and stability during the training process. The experimental results show that the accuracy and success rate of the two tracking accuracy evaluation indexes can be improved by 1.3% and 0.3% respectively, which has more advantages than other methods.