Impervious surface mapping is essential for urban environmental studies. Spectral Mixture Analysis (SMA) and its extensions are widely employed in impervious surface estimation from medium-resolution images. For SMA, inappropriate endmember combinations and inadequate endmember classes have been recognized as the primary reasons for estimation errors. Meanwhile, the spectral-only SMA, without considering urban spatial distribution, fails to consider spectral variability in an adequate manner. The lack of endmember class diversity and their spatial variations lead to over/underestimation. To mitigate these issues, this study integrates a hierarchical strategy and spatially varied endmember spectra to map impervious surface abundance, taking Wuhan and Wuzhou as two study areas. Specifically, the piecewise convex multiple-model endmember detection algorithm is applied to automatically hierarchize images into three regions, and distinct endmember combinations are independently developed in each region. Then, spatially varied endmember spectra are synthesized through neighboring spectra using the distance-based weight. Comparative analysis indicates that the proposed method achieves better performance than Hierarchical SMA and Fixed Four-endmembers SMA in terms of MAE, SE, and RMSE. Further analysis suggests that the hierarchical strategy can expand endmember class types and considerably improve the performance for the study areas in general, specifically in less developed areas. Moreover, we find that spatially varied endmember spectra facilitate the reduction of heterogeneous surface material variations and achieve the improved performance in developed areas.

Reliable UAV detection from ground-based cameras remains difficult under changing illumination, complex backgrounds, and residual displacement between visible and infrared sensors. This paper proposes the Bidirectional Feature Alignment and Transfer-Gated Fusion Network (BATF-Net), a dual-stream detector that preserves separate RGB- and infrared-reference coordinate systems. At the C3, C4, and C5 stages of a two-stream YOLOX-s architecture, an offset estimator shared across transfer directions predicts RGB-to-infrared and infrared-to-RGB displacement fields. Bilinear sampling maps each source features into the corresponding reference coordinates, after which a spatial gate derived from local response magnitude and post-alignment cosine similarity controls residual feature transfer. The network is trained end to end with two detection-head losses and requires neither pixel-level registration labels nor an auxiliary geometric objective. Under the stated validation protocol, the RGB-/infrared-reference ${\mathrm{AP}}_{50:95}$ values are 41.9%/56.9% on MM-UAV and 66.3%/60.6% on Anti-UAV. Compared with the RGB–infrared detector preceding MMA-SORT, these values are higher by 0.8/0.4 and 0.4/0.5 percentage points, respectively. BATF-Net requires 50.0 G FLOPs and runs at 167 frames/s, compared with 54.2 G FLOPs and 125 frames/s for the MMA-SORT detector on the reported platform. These results show that bidirectional alignment can improve paired RGB–infrared UAV detection while preserving sensor-specific outputs and real-time throughput on the evaluated platform.