Extracting change regions from bitemporal images is crucial to urban planning, land, and resources survey. In the literature, many methods obtaining difference between bitemporal remote sensing images have been proposed. However, there are still some problems due to the complexity of change conditions. In order to solve the above-mentioned problems, we propose a novel network called PPCNET, combining patch-level and pixel-level change detection for bitemporal remote sensing images. This network is divided into three branches: the dual structure is used to extract features of bitemporal images, respectively; changed or unchanged image regions are then detected through fully connected layers, and a soft-max layer at patch level. Once a change is detected at patch level, feature encoder and decoder at pixel level are activated to obtain accurate change boundary. Furthermore, a feature pyramid network-based architecture is employed to fuse information in different layers to further improve change detection effectiveness. Experiments on both satellite and aerial remote sensing images have verified that PPCNET network yields higher change detection accuracy with faster detection speed.

Semantic segmentation labels each pixel in high-resolution remote sensing (HRRS) images with a category. To tackle with the large size and complexity of HRRS images, this letter presents a novel multiscale feature aggregation lightweight network (MFALNet) for semantic segmentation. Unlike standard convolution, asymmetric depth-wise separable convolution residual (ADCR) unit is used to reduce the parameter size of the network and makes the optimized structure deeper but lightweight and less complex. The proposed network is an encoder–decoder structure, where multiscale feature aggregation is implemented in both the encoder and the decoder. The spatial self-attention block helps to capture long-range contextual information, and the gated convolution modules are further used for refining features when aggerating high- and low-level feature maps in the decoder. The proposed MFALNet has evaluated on the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen and Potsdam 2-D semantic labeling contest open benchmark data set, and the experimental results prove that the scheme can obtain a better tradeoff between segmentation accuracy and computational efficiency compared with the state-of-the-art semantic segmentation models.

Traditional crop classification methods have three critical limitations: (1) dependency on labor-intensive field surveys with limited spatial coverage, (2) susceptibility to human subjectivity during manual data collection, and (3) the inability to capture fine-grained spectral variations due to the lack of multispectral analysis. This research introduces an enhanced crop classification and identification model based on a residual ResNet network. This model leverages multispectral remote sensing images from unmanned aerial vehicles (UAVs) to accurately classify complex crop planting structures. The research focuses on four typical crops: sunflower, corn, beet, and pepper. By acquiring and preprocessing multispectral remote sensing image data, an improved ResNet50 model integrating the ACmix self-attention module and a coordinate attention mechanism is developed to enhance the classification and recognition accuracy of these crops. Experimental results demonstrate that the improved model achieves a classification accuracy of 97.8% on multispectral images, outperforming both RGB images and traditional methods. This research highlights the potential of combining UAV multispectral remote sensing technology with deep learning for precise crop classification, offering valuable technical support for precision agriculture management.

The desertified ecological restoration vegetation of Wuzhumuqin grassland plays an important role in the ecological restoration and protection of the region. However, there are few studies on the monitoring of the changes in ecological restoration vegetation in grassland sandy land in the past. In order to improve the low efficiency of ecological restoration vegetation monitoring, this study used Gaofen-6 (GF-6) remote sensing data to calculate the kernel Normalized Difference Vegetation Index (kNDVI) and vegetation coverage of ecological restoration vegetation and analyze their spatial and temporal trends. At the same time, a transform three-branch network structure based on deep learning is proposed to extract visual features. The kernel Normalized Difference Vegetation Index-position-temporal awareness transformer (kNDVI-PT-Former) model monitoring method based on two-phase remote sensing image features combined with kNDVI for spatio-temporal feature extraction can accurately obtain the vegetation changes in desertification ecological restoration in Wuzhumuqin grassland. The results show that the kNDVI of the study area shows an increasing trend from 2019 to 2024. The kNDVI value is 0.4086 in 2019 and 0.4927 in 2024. From the perspective of the change trend of vegetation coverage, the overall vegetation coverage of the Wuzhumuqin desertification restoration study area showed a gradual increase trend from 2019 to 2024, and the vegetation coverage increased by 19% in 2024 compared with 2019. The transformation of vegetation coverage from low level to high level in the study area is more prominent. Based on the self-built monitoring dataset of more than 5.2 million pairs of grassland vegetation changes, through model comparison and analysis, the kNDVI-PT-Former model obtains that the Class Pixel Accuracy (CPA) is 0.7295, the Intersection over Union (IoU) is 0.7228, and the overall monitoring accuracy of the model is improved by 11%. Furthermore, the stability of the model’s performance was confirmed through evaluation with five-fold cross-validation.

In recent years, deep learning has driven remarkable progress in remote sensing change detection (CD); however, practical deployment is still hindered by two limitations. First, CD results are easily degraded by imaging-induced uncertainties—mixed pixels and blurred boundaries, radiometric inconsistencies (e.g., shadows and seasonal illumination changes), and slight residual misregistration—leading to pseudo-changes and fragmented boundaries. Second, prevailing methods follow a static one-pass inference paradigm and lack an explicit feedback mechanism for adaptive error correction, which weakens generalization in complex or unseen scenes. To address these issues, we propose a feedback-driven CD framework that integrates a dual-branch U-Net with deep reinforcement learning (RL) for pixel-level probabilistic iterative refinement of an initial change probability map. The backbone produces a preliminary posterior estimate of change likelihood from multi-scale bi-temporal features, while a PPO-based RL agent formulates refinement as a Markov decision process. The agent leverages a state representation that fuses multi-scale features, prediction confidence/uncertainty, and spatial consistency cues (e.g., neighborhood coherence and edge responses) to apply multi-step corrective actions. From an imaging and interpretation perspective, the RL module can be viewed as a learnable, self-adaptive imaging optimization mechanism: for high-risk regions affected by blurred boundaries, radiometric inconsistencies, and local misalignment, the agent performs feedback-driven multi-step corrections to improve boundary fidelity and spatial coherence while suppressing pseudo-changes caused by shadows and illumination variations. Experiments on four datasets (CDD, SYSU-CD, PVCD, and BRIGHT) verify consistent improvements. Using SiamU-Net as an example, the proposed RL refinement increases mIoU by 3.07, 2.54, 6.13, and 3.1 points on CDD, SYSU-CD, PVCD, and BRIGHT, respectively, with similarly consistent gains observed when the same RL module is integrated into other representative CD backbones.

As the role of remote sensing continues to grow, the fusion technology of low-spatial-resolution hyperspectral images and high-spatial-resolution multispectral images has become increasingly critical. Traditional methods rely on fixed rules and exhibit poor robustness, whereas deep learning methods struggle to establish efficient interactions between local and global information due to the complexity of their underlying networks. Therefore, we propose a deep learning fusion module that combines pixel-wise adaptive wavelet transform with a spectral–spatial dual-branch extraction. Firstly, by utilizing the unique properties of the wavelet transform, it is possible to effectively preserve spectral information and extract spatial edge features, thereby achieving preliminary fusion by leveraging both low-frequency and high-frequency components. To compensate for the lack of nonlinear expression capability in the wavelet transform, a dual-branch parallel extraction of spectral and spatial features is subsequently performed in the deep learning module. The Multi-Scale Group Convolution module (MSGC) is utilized to extract spectral information, while the Spectral Compression and Spatially Guided Gating Module (SCSGM) is employed to extract spatial information, thereby enhancing the data’s adaptive capability. A bidirectional attention mechanism is interspersed within the module to capture complementary information across different scales, ultimately reconstructing a high-resolution hyperspectral image. Finally, the proposed fusion strategy demonstrates superior performance in practical image reconstruction, outperforming more than ten state-of-the-art fusion methods.