Subpixel mapping (SPM) addresses the widespread mixed pixel problem in remote sensing images by predicting the spatial distribution of land cover within mixed pixels. However, conventional pixel-based spectral unmixing, a key pre-processing step for SPM, neglects valuable spatial contextual information and struggles with spectral variability, ultimately undermining SPM accuracy. Additionally, while extensively utilized, supervised spectral unmixing is labor-intensive and user-unfriendly. To address these issues, this paper proposes a fully automatic, unsupervised object-based SPM (UO-SPM) model that exploits object-scale information to reduce spectral unmixing errors and subsequently enhance SPM. Given that mixed pixels are typically located at the edges of objects (i.e., the inner part of objects is characterized by pure pixels), segmentation and morphological erosion are employed to identify pure pixels within objects and mixed pixels at the edges. More accurate endmembers are extracted from the identified pure pixels for the secondary spectral unmixing of the remaining mixed pixels. Experimental results on 10 study sites demonstrate that the proposed unsupervised object (UO)-based analysis is an effective model for enhancing both spectral unmixing and SPM. Specifically, the spectral unmixing results of UO show an average increase of 3.65 % and 1.09 % in correlation coefficient (R) compared to Fuzzy-C means (FCM) and linear spectral mixture model (LSMM)-derived coarse proportions, respectively. Moreover, the UO-derived results of four SPM methods (i.e., Hopfield neural network (HNN), Markov random field (MRF), pixel swapping (PSA) and radial basis function interpolation (RBF)) exhibit an average increase of 5.89 % and 3.04 % in overall accuracy (OA) across the four SPM methods and 10 study sites compared to the FCM and LSMM-based results, respectively. Moreover, the proportions of both mixed and pure pixels are more accurately predicted. The advantage of UO-SPM is more evident when the size of land cover objects is larger, benefiting from more accurate identification of objects.

中文翻译：

---

用于亚像素映射的基于对象的无监督光谱解混


亚像素制图 （SPM） 通过预测混合像素内土地覆被的空间分布来解决遥感图像中普遍存在的混合像素问题。然而，传统的基于像素的光谱解混是 SPM 的一个关键预处理步骤，它忽视了宝贵的空间上下文信息，并与光谱变化作斗争，最终破坏了 SPM 的准确性。此外，虽然被广泛使用，但监督光谱分离是劳动密集型的，并且对用户不友好。为了解决这些问题，本文提出了一种全自动、无监督的基于对象的 SPM （UO-SPM） 模型，该模型利用对象尺度信息来减少光谱解混误差，从而增强 SPM。鉴于混合像素通常位于对象的边缘（即，对象的内部以纯像素为特征），因此采用分割和形态侵蚀来识别对象内的纯像素和边缘的混合像素。从识别的纯像素中提取更准确的端元，用于剩余混合像素的二次光谱解混。在 10 个研究地点的实验结果表明，所提出的基于无监督对象 （UO） 的分析是增强光谱解混和 SPM 的有效模型。具体来说，UO 的光谱解混结果显示，与模糊 C 均值 （FCM） 和线性光谱混合模型 （LSMM） 衍生的粗略比例相比，相关系数 （R） 分别平均增加了 3.65 % 和 1.09 %。此外，四种 SPM 方法 （即 Hopfield 神经网络 （HNN）、马尔可夫随机场 （MRF）、像素交换 （PSA） 和径向基函数插值 （RBF）） 的 UO 衍生结果显示平均增加 5.89% 和 3.与基于 FCM 和 LSMM 的结果相比，4 种 SPM 方法和 10 个研究地点的总体准确率 （OA） 分别提高了 04%。此外，混合像素和纯像素的比例都可以更准确地预测。当土地覆盖对象的大小较大时，UO-SPM 的优势更加明显，受益于更准确的对象识别。