Remote sensing semantic segmentation encounters several challenges, including scale variation, the coexistence of class similarity and intra-class diversity, difficulties in modeling long-range dependencies, and shadow occlusions. Slender structures and complex boundaries present particular segmentation difficulties, especially in high-resolution imagery acquired by satellite and aerial cameras, UAV-borne optical sensors, and other imaging payloads. These sensing systems deliver large-area coverage with fine ground sampling distance, which magnifies domain shifts between different sensors and acquisition conditions. This work builds upon DeepLabV3+ and proposes complementary improvements at three stages: input, context, and decoder fusion. First, to mitigate the interference of complex and heterogeneous data distributions on network optimization, a feature-mapping network is introduced to project raw images into a simpler distribution before they are fed into the segmentation backbone. This approach facilitates training and enhances feature separability. Second, although the Atrous Spatial Pyramid Pooling (ASPP) aggregates multi-scale context, it remains insufficient for modeling long-range dependencies. Therefore, a routing-style global modeling module is incorporated after ASPP to strengthen global relation modeling and ensure cross-region semantic consistency. Third, considering that the fusion between shallow details and deep semantics in the decoder is limited and prone to boundary blurring, a fusion module is designed to facilitate deep interaction and joint learning through cross-layer feature alignment and coupling. The proposed model improves the mean Intersection over Union (mIoU) by 8.83% on the LoveDA dataset and by 6.72% on the ISPRS Potsdam dataset compared to the baseline. Qualitative results further demonstrate clearer boundaries and more stable region annotations, while the proposed modules are plug-and-play and easy to integrate into camera-based remote sensing pipelines and other imaging-sensor systems, providing a practical accuracy–efficiency trade-off.

Remote sensing semantic segmentation encounters several challenges, including scale variation, the coexistence of class similarity and intra-class diversity, difficulties in modeling long-range dependencies, and shadow occlusions. Slender structures and complex boundaries present particular segmentation difficulties, especially in high-resolution imagery acquired by satellite and aerial cameras, UAV-borne optical sensors, and other imaging payloads. These sensing systems deliver large-area coverage with fine ground sampling distance, which magnifies domain shifts between different sensors and acquisition conditions. This work builds upon DeepLabV3+ and proposes complementary improvements at three stages: input, context, and decoder fusion. First, to mitigate the interference of complex and heterogeneous data distributions on network optimization, a feature-mapping network is introduced to project raw images into a simpler distribution before they are fed into the segmentation backbone. This approach facilitates training and enhances feature separability. Second, although the Atrous Spatial Pyramid Pooling (ASPP) aggregates multi-scale context, it remains insufficient for modeling long-range dependencies. Therefore, a routing-style global modeling module is incorporated after ASPP to strengthen global relation modeling and ensure cross-region semantic consistency. Third, considering that the fusion between shallow details and deep semantics in the decoder is limited and prone to boundary blurring, a fusion module is designed to facilitate deep interaction and joint learning through cross-layer feature alignment and coupling. The proposed model improves the mean Intersection over Union (mIoU) by 8.83% on the LoveDA dataset and by 6.72% on the ISPRS Potsdam dataset compared to the baseline. Qualitative results further demonstrate clearer boundaries and more stable region annotations, while the modifications to the baseline are minimal and easy to integrate into camera-based remote sensing pipelines and other imaging-sensor systems.

Real-time machine-vision monitoring of group-housed juvenile sika deer is challenging because targets are often small, densely distributed and partially occluded, while edge deployment requires compact models. This study developed a lightweight system for non-contact behavior recognition under commercial farm-pen conditions. A fixed-camera dataset was constructed with five annotated categories: resting, standing, feeding, social and abnormal. The dataset was limited to one month of recordings from one fixed camera monitoring six juvenile sika deer in a single pen at one farm in Jilin Province, China. To reduce background interference during training, a Multi-target Bionic Foveal Augmentation (MBFA) strategy was proposed to generate target-guided, spatially nonuniform degradation based on the distribution of deer instances, without introducing additional inference cost. A Lightweight Selective Alignment Reorganization and Efficient Detection Network (LSARE-Net) was then designed to enhance local behavioral cues, contextual feature representation, and cross-scale fusion. On the test set, LSARE-Net achieved 91.26% recall, 93.47% mAP@0.5 and 80.24% mAP@0.5:0.95 with 0.70 M parameters and a 1.7 MB model size. After TensorRT conversion, it reached 62.64 FPS on an NVIDIA Jetson AGX Orin. These results demonstrate the feasibility of compact frame-level behavior detection under the evaluated pen conditions. The accompanying prototype organizes detections into behavioral summaries and abnormal-cue records for manual review.