Limited by the GPU memory, the current mainstream detectors fail to directly apply to large-scale remote sensing images for object detection. Moreover, the scale range of objects in remote sensing images is much wider than that of general images, which also greatly hinders the existing methods to effectively detect geospatial objects of various scales. For achieving high-performance object detection on large-scale remote sensing images, this article proposes a much faster and more accurate detecting framework, called cropping region proposal network-based scale folding network (CRPN-SFNet). In our framework, the CRPN includes a weak semantic RPN for quickly locating interesting regions and a strategy of generating cropping regions to effectively filter out meaningless regions, which can greatly reduce the computation and storage burden. Meanwhile, the proposed SFNet leverages the scale folding-based training and testing methods to extend the valid detection range of existing detectors, which is beneficial for detecting remote sensing objects of various scales, including very small and very large geospatial objects. Extensive experiments on the public Dataset for Object deTection in Aerial images data set indicate that our CRPN can help our detector deal the larger image faster with the limited GPU memory; meanwhile, the SFNet is beneficial to achieve more accurate detection of geospatial objects with wide-scale range. For large-scale remote sensing images, the proposed detection framework outperforms the state-of-the-art object detection methods in terms of accuracy and speed.

For various remote sensing objects, the current detection framework based on a single detection pipeline fails to provide satisfactory detection accuracy. In order to further improve the object recognition ability of the detection model, this article introduces the effective “multiexpert” mechanism into the field of remote sensing object detection and then constructs a multiexpert detection network (MEDNet). In this model, we first construct multiple feature pyramids (MFPs) to replace the traditional single feature pyramid to enrich the semantic representation ability of the model. Then, we equip multiple detection experts (MDEs) to leverage multiple kinds of features from MFP to perform different semantic predictions. As the first CNN-based multiexpert detection model for remote sensing images, we tailor a loss distance-based k-experts clustering (LD-kEC) strategy to assign training samples to different detection experts in an unsupervised fashion. By this strategy, we can directly use the existing remote sensing dataset without expert labels for end-to-end training of our multiexpert model. The experimental results prove that the proposed multiexpert-based detector can indeed significantly improve the object detection performance for remote sensing images.

For objects with arbitrary angles in optical remote sensing images, the oriented bounding box regression task often faces the problem of ambiguous boundaries between positive and negative samples. The statistical analysis of existing label assignment strategies reveals that anchors with low intersection-over-union (IoU) between ground truth (GT) may also accurately surround the GT after decoding. Therefore, this paper proposes an attention-based mean-max balance assignment (AMMBA) strategy, which consists of two parts: mean-max balance assignment (MMBA) strategy and balance feature pyramid with attention (BFPA). MMBA employs the Mean-max Assignment (MMA) and Balance Assignment (BA) to dynamically calculate a positive threshold and adaptively match better positive samples for each GT for training. Meanwhile, to meet the need of MMBA for more accurate feature maps, we construct a BFPA module, which integrates spatial and scale attention mechanisms to promote global information propagation. Combined with S2ANet, our AMMBA method can effectively achieve state-of-the-art performance, with a precision of 80.91% on the DOTA dataset in a simple plug-and-play fashion. Extensive experiments on three challenging optical remote sensing image datasets (DOTA-v1.0, HRSC, and DIOR-R) further demonstrate the balance between precision and speed in single-stage object detectors. Our AMMBA has enough potential to assist all existing remote sensing models in a simple way to achieve better detection performance. Code is available at https://github.com/promisekoloer/AMMBA.

Although hydrogen embrittlement (HE) behavior has been extensively studied in bulk materials, little is known about H-related deformation and the fracture of nanograined materials. In this study, H segregation and HE mechanisms of nanograined Fe with different grain sizes are unveiled, following the employment of classical molecular dynamics simulations. The H segregation ratio increased, but the local H concentration at the grain boundaries (GBs) decreased with decreases in the grain size at a given bulk H concentration. The results demonstrate that H atoms increased the yield stress of nanograined models irrespective of the grain size. Furthermore, it is revealed that brittle fractures were inhibited, and the resistance to HE increased as the grain size decreased, due to the fact that the small-grain models had a lower local H concentration at the GBs and an enhanced GB-mediated intergranular deformation. These results are a clear indication of the utility of grain refinement to resist H-induced brittle failure.

Generally, the interesting objects in aerial images are completely different from objects in nature, and the remote sensing objects in particular tend to be more distinctive in aspect ratio. The existing convolutional networks have equal aspect ratios of the receptive fields, which leads to receptive fields either containing non-relevant information or being unable to fully cover the entire object. To this end, we propose Horizontal and Vertical Convolution, which is a plug-and-play module to address different aspect ratio problems. In our method, we introduce horizontal convolution and vertical convolution to expand the receptive fields in the horizontal and vertical directions, respectively, to reduce redundant receptive fields, so that remote sensing objects with different aspect ratios can achieve better receptive fields coverage, thereby achieving more accurate feature representation. In addition, we design an attention module to dynamically aggregate these two sub-modules to achieve more accurate feature coverage. Extensive experimental results on the DOTA and HRSC2016 datasets show that our HVConv achieves accuracy improvements in diverse detection architectures and obtains SOTA accuracy (mAP score of 77.60% with DOTA single-scale training and mAP score of 81.07% with DOTA multi-scale training). Various ablation studies were conducted as well, which is enough to verify the effectiveness of our model.