高光谱图像目标检测作为一个研究热点在**和民用方面的应用越来越广泛。为了能同时利用高光谱图像数据的空谱信息, 本文提出一种新的基于张量表示的高光谱图像目标检测算法。算法使用CP(Canonical Polyadic)张量分解技术和张量块分解(Block Term Decomposition, BTD)分别对高光谱数据进行盲源分析, 提取了有效的局部图像块空谱特征, 建立了一个基于稀疏表示和协作表示的检测模型, 针对多种类型背景复杂的场景数据进行实验, 并与当前流行的目标检测算法进行比较。从可视化检测结果来看, 本文算法在复杂背景和强噪声环境下, 有效提取了空谱特征, 对背景具有较好的抑制能力, 检测的目标显著。此外, 本文从接收机操作曲线(Receiver Operating Characteristic Curve, ROC)和ROC曲线下面积(Area Under Curve, AUC)等定量指标分析算法性能。以较为流行的Sandiego图像为例, 在10%的虚警率下, 本文算法取得90%的检测精度, AUC大于0.95。本文算法相较几种流行算法而言具有较高的检测精度, 更强的鲁棒性。

Target detection for Hyperspectral Images (HSIs) is gaining importance owing to its important military and civilian applications. This study proposed a novel target detection algorithm for HSIs based on tensor representation. The algorithm employed tensor analysis including CP and tensor block decompositions to implement blind source separation on hyperspectral data. First, effective spatial and spectral features of the blocks of local images were extracted. Then, a detection model based on sparse and collaborative representations was established. Experiments were conducted to evaluate the performance of our approach under multiple scenes with complex backgrounds. From the visual representation of the results, it can be concluded that the proposed approach effectively extracts the spatial-spectral features from scenes with strong noise and complex backgrounds. The approach has good ability to suppress the background and the target is salient. In addition, the performance of the approach is evaluated using quantitative metrics such as Receiver Operating Curve (ROC) and area under the ROC curve (AUC). Considering the popular HSI image of San Diego as an example, the approach achieves 90% detection rate with a false alarm rate of 10%, and the AUC is greater than 0.95. Hence, our approach outperforms other popular approaches.