This paper presents a thorough evaluation of twenty-one state-of-the-art widely-used crop segmentation algorithms, motived by their significance in vision tasks for further analysis. An ideal crop segmentation algorithm can effectively extract crop information, thus providing an important precondition for the application of intelligent agriculture analytics. In order to enable researchers in this field to fully understand various crop segmentation methods, this paper proposes a new classification strategy of object segmentation by dividing the algorithms into pixel-based and region-based approaches at first, and then systematically evaluating various crop segmentation methods with a unified data benchmark and four common metrics. A new dataset which incorporates crop variety, environment condition and observation distance into consideration is constructed for demonstrating the experiments and comparisons. The effectiveness and robustness of these algorithms were evaluated by three sets of comparative experiments. Based on the quantitative results, we summarize the advantages and disadvantages of the evaluated algorithms from the segmentation performances with four metric indicators. Furthermore, the discussion and evaluation results will provide great support for precision agriculture analysis.
Small object detection in UAV remote sensing remains challenging due to fine-grained feature loss during downsampling and unbalanced cross-scale feature aggregation. Conventional feature pyramid fusion may suffer from hard activation truncation or competitive weight suppression when heterogeneous feature scales are fused. To address these issues, we propose PSG-RTDETR, a P2-aware Softplus-Gated RT-DETR framework tailored for UAV-based dense small-object detection. Specifically, we integrate high-resolution P2 features into a bidirectional feature pyramid to preserve critical spatial details. Furthermore, we introduce Softplus normalization for smooth weight optimization and a sample-adaptive gating mechanism to dynamically suppress noisy shallow responses. Extensive experiments on VisDrone-DET demonstrate that, compared with the RT-DETR-ResNet18 baseline under the same ablation setting, PSG-RTDETR improves mAP50–95 and APsmall by 4.1 and 4.7 percentage points, respectively. Further validation on HIT-UAV confirms its strong generalizability across infrared modalities. These accuracy gains involve a clear computational trade-off: GFLOPs increase from 57.20 to approximately 110.23, while FPS decreases from 126.18 to 80.02 on an RTX 3090. Thus, PSG-RTDETR is better suited to accuracy-oriented off-board or near-real-time GPU analysis than to direct deployment on resource-constrained onboard UAV devices without further compression or acceleration.
Single image super-resolution (SISR) based on deep learning is a key research problem in the field of computer vision. However, existing super-resolution reconstruction algorithms often improve the quality of image reconstruction through a single network depth, ignoring the problems of reconstructing image texture structure and easy overfitting of network training. Therefore, this paper proposes a deep unfolding super-resolution network (USRNet) reconstruction method under the integrating channel attention mechanism, which is expected to improve the image resolution and restore the high-frequency information of the image. Thus, the image appears sharper. First, by assigning different weights to features, focusing on more important features and suppressing unimportant features, the details such as image edges and textures are better recovered, and the generalization ability is improved to cope with more complex scenes. Then, the CA (Channel Attention) module is added to USRNet, and the network depth is increased to better express high-frequency features; multi-channel mapping is introduced to extract richer features and enhance the super-resolution reconstruction effect of the model. The experimental results show that the USRNet with integrating channel attention has a faster convergence rate, is not prone to overfitting, and can be converged after 10,000 iterations; the average peak signal-to-noise ratios on the Set5 and Set12 datasets after the side length enlarged by two times are, respectively, 32.23 dB and 29.72 dB, and are dramatically improved compared with SRCNN, SRMD, PAN, and RCAN. The algorithm can generate high-resolution images with clear outlines, and the super-resolution effect is better.