In recent years, the advancement of unmanned aerial vehicle (UAV) technology has led to the gradual application of UAV aeromagnetic technology in small-area production for precise measurements. The flexibility of unmanned platforms allows for efficient detection. Unlike pilot-controlled fixed-wing aircraft, UAV platforms have smaller payloads and shorter endurance. Hence, it is essential to simplify the field acquisition process as much as possible. This has led to the development of rapid solution algorithms for magnetic compensation coefficients and related software. This letter is based on the Tolles and Lawson aeromagnetic compensation model. It analyzes the relationship between attitude and magnetic total field data, proposes a small signal improvement (SSI) algorithm, and conducts magnetic compensation experiments on two different types of fixed-wing UAVs. The results show better compensation effects.

Recently, weakly supervised methods for scene text spotter are increasingly popular with researchers due to their potential to significantly reduce dataset annotation efforts. The latest progress in this field is text spotter based on single or multi-point annotations. However, this method struggles with the sensitivity of text recognition to the precise annotation location and fails to capture the relative positions and shapes of characters, leading to impaired recognition of texts with extensive rotations and flips. To address these challenges, this paper develops a novel method named Coarse-point-supervised Scene Text Spotter (Cps-STS). Cps-STS first utilizes a few approximate points as text location labels and introduces a learnable position modulation mechanism, easing the accuracy requirements for annotations and enhancing model robustness. Additionally, we incorporate a Spatial Compatibility Attention (SCA) module for text decoding to effectively utilize spatial data such as position and shape. This module fuses compound queries and global feature maps, serving as a bias in the SCA module to express text spatial morphology. In order to accurately locate and decode text content, we introduce features containing spatial morphology information and text content into the input features of the text decoder. By introducing features with spatial morphology information as bias terms into the text decoder, ablation experiments demonstrate that this operation enables the model to effectively identify and utilize the relationship between text content and position to enhance the recognition performance of our model. One significant advantage of Cps-STS is its ability to achieve full supervision-level performance with just a few imprecise coarse points at a low cost. Extensive experiments validate the effectiveness and superiority of Cps-STS over existing approaches.

Gravity inversion for basement relief is an important method to depict the structure of the sedimentary basin. At present, researches on this topic are mainly based on the assumption of minimum structure using different norms. However, in practical applications, it is often difficult for these methods to determine appropriate norms. Hence, errors are easily introduced, especially for complex relief. To solve this problem, this study presents a CNN-based gravity inversion method for complex basement relief with both rifted and smooth features. A multitask learning neural network has been designed, which can extract rifted and smooth features through different subnetworks. Then, a converged subnetwork is constructed to merge different features for getting undulations of the basement. The presented method is tested on a synthetic model. The results show that, compared with traditional L2-norm-based methods, this method exhibits improvement in accuracy and ease of use in recovering complex basement relief. Finally, the method is applied to gravity data collected in the Los Angeles Basin in California. The obtained structure shows good consistency with known structure.

The Intersection over Union (IoU) has been widely employed in various stages of object detection owing to its ability to quantify the similarity between boxes objectively. However, in densely packed scenes full of crowded and small-sized objects, adjacent positive boxes often exhibit high levels of overlap. This overlap interference compromises the consistency between quality evaluation and confidence, leading to ambiguous box prediction within the previous IoU-based models. To address this issue, we design a novel learning paradigm tailored for Dense scenes based on IoU, called DeIoU. This approach effectively suppresses unnecessary overlap between predicted boxes and thereby enhances representation learning for non-salient objects. Specifically, it consists of a dense box regression loss${\mathcal {L}}_{DeIoU}$and a one-to-many (O2M) label matching strategy guided by DeIoU. These components focus on calibrating the position and shape prediction quality during the model training, learning distinguishable object features by penalizing overlap interference between neighboring boxes. Extensive experiments on four object detection datasets including SKU-110K, CrowdHuman, MS COCO 2017, and DIOR, demonstrate that our DeIoU-based learning strategy outperforms other state-of-the-art methods. Notably, the proposed method delivers a substantial improvement (average$1.3~{AP}$and$1.8~MR^{-2}$) across popular detectors on SKU-110K and CrowdHuman while exhibiting distinct competitiveness on small objects within natural scenes.

Delineation of the basement relief structure is of great significance for oil and gas exploration in sedimentary basins. In literature, a number of methods have been presented to depict the basement relief with gravity anomaly. However, existing methods still have some limitations, such as local morphological distortion caused by improper use of known depth points, and imprecise solutions yield from inaccurate determination of the underground density contrasts. To address the above two issues, this study proposes an improved high-precision method to characterize the basement relief. For the proposed method, a new prior depth soft constraint, which is based on a cosine attenuation function, is introduced to utilize the known depth at a few points more rationally. Moreover, a physical property constraint, which is based on the least square theory, is employed to constrain the fitting between the recovered gravity anomaly and the observations better. The effectiveness of the proposed method is tested and validated on synthetic data with noise and real data in Sydney, Australia.

Current oriented object detection methods mainly utilize a vanilla coordinate-angle representation for bounding box regression, which usually suffers from inconsistency between the bounding box regression losses and prediction errors induced with respect to different rotation angles, aspect ratios, and scales. Therefore, although the existing oriented object detectors have achieved very good performances under coarse evaluation metrics such as AP50, their performance significantly degrades when using stricter evaluation metric such as AP75. To address the abovementioned issues, we propose a new regression method with bounding box vectorization that implicitly represents the shape and orientation of an object with a set of orthogonal vectors. By doing this, the proposed method delicately avoids the inconsistency issues encountered in oriented bounding box regression. During training, we introduce the Tanimoto coefficient to evaluate the similarity of the bounding box vector in a shape- and orientation-aware manner, and we refer to the proposed box-to-vector loss as the B2V loss. In addition to 2D object detection, the proposed method can be easily generalized to 3D scenarios involving orientation estimation, such as autonomous driving. We evaluate the proposed method through extensive experiments conducted on four popular oriented object detection datasets, including both 2D and 3D datasets, where the proposed method significantly outperforms the recently developed state-of-the-art methods when using a more accurate evaluation metric.

Staircase approximation in the simulation of the arbitrarily irregular surface will cause artificial interference of wavefield. The body-fit coordinate transformation can accurately simulate the arbitrarily irregular surface and avoid the staircase approximation. The finite difference method (FDM) based on body-fit coordinate system (BFCS) can simulate the propagation process of wavefield in the media with an undulating surface. Currently, the collocated grid is usually used in BFCS. However, adopting this method to simulate waves based on the first-order velocity-stress wave equation in the BFCS will cause oscillation due to the odd-even decoupling; therefore, additional filtering operations are required. To solve the above problem, we propose collocate-staggered grid (CSG) to simulate the first-order velocity-stress wave equation in the 2-D BFCS. CSG uses staggered grid scheme to calculate the equation parameters and adopts collocated grid scheme to store these values. We use second-order accuracy spatial and temporal difference for numerical tests. The results show that the elastic wavefield modeling method in the BFCS using CSG difference scheme has the characteristics of high accuracy and stable. This method is suitable for the wavefield simulation in a medium with a large Poisson’s ratio.