Arbitrary-Oriented Object Detection (AOOD) has found broad applications in embodied intelligence, autonomous driving, and satellite remote sensing. However, current AOOD frameworks face challenges in ineffective feature extraction and orientation regression inaccuracy. Inspired by Hilbert curve's intrinsic locality-preserving property, we propose a flexible Hilbert curve-Encoded Rotation-Equivariant Oriented Object Detector (HERO-Det). Our innovations include: (i) a novel Hilbert curve traversal convolution paradigm with a dimensionality reduction scheme, which employs locality-preserving spatial filling curves for feature transformation, (ii) a Hilbert pyramid transformer enabling hierarchical construction of multi-scale feature sequences through space-folding operations, as well as (iii) an orientation-adaptive prediction head that decouples rotation-equivariant regression features from invariant classification cues to resolve orientation regression dilemmas in two-stage detectors. Extensive experiments show HERO-Det achieves state-of-the-art performance on AOOD benchmarks, with mAP of 79.56%, 90.64%, 90.10%, and 80.47% on DOTA, HRSC2016, SSDD, and HRSID, respectively. Performance gains in cross-task validation further demonstrate the versatility of our method to diverse vision tasks, such as medical image segmentation and 3D object detection.

Compound fault diagnosis in multi-joint industrial robots is a critical yet underexplored problem in industrial internet of things, where the simultaneous degradation of multiple joints poses a severe challenge for reliable operation. Unlike conventional methods limited to single-fault scenarios, this paper addresses the compositional generalization challenge—requiring models trained only on simple faults to accurately recognize unseen higher-order fault compositions. To this end, we propose StateMix Network (SMNet), a multi-stage architecture that preserves atomic joint-level representations before compositional diagnosis. Specifically, a Single-Joint Feature Extraction (SJFE) backbone extracts clean joint-private features, which are then fused by an Attention-Guided Dilated Fusion (AGDF) neck employing parallel Cascaded Dilated Convolution Blocks (CDCBs) bracketed by a dual-path attention mechanism for scale- and context-aware integration. Finally, a Mamba-based sequence mixer models long-range cross-joint dependencies to capture global fault dynamics. Extensive experiments on in-situ vibration data from a single six-joint industrial robot platform, under a strict train-on-simple/evaluate-on-complex protocol, demonstrate that SMNet consistently outperforms representative baselines in macro-Precision, Recall, and F1-score, particularly on unseen triple- and quadruple-joint compositions. Ablation and sensitivity analyses further validate the effectiveness of each module. This work presents a diagnostic approach that effectively generalizes from simple to complex fault scenarios in industrial robots.

Traditional pedestrian detection methods based on red-green-blue (RGB) images struggle in adverse illumination, but a key capability required for pedestrian detection is all-day detection due to its critical role in diverse applications, e.g., security, surveillance, and autonomous driving. To address this issue, multispectral pedestrian detection attempts to introduce thermal images to supplement the RGB images, since they can be captured based on heat radiation difference without relying on external light sources. However, how to fuse the two modalities effectively is still lacking in-depth investigation. To prompt this field, we propose an implicit illumination-aware representation to address the limited availability of specific illumination labels in existing multispectral datasets, coupled with a prefusion feature alignment strategy to reconcile spatial misalignments of identical objects across modalities. We also identify four critical fusion challenges, revealing persistent limitations in existing multispectral detectors' ability to holistically address these issues, particularly regarding underdeveloped cross-modal interactions and suboptimal cross-domain feature fusion. To this end, we propose a universal multispectral pedestrian detection paradigm (UMPDP), which includes a modality alignment module (MAM) for adaptive feature space alignment, a differential modality fusion module (DMFM) to enhance the relationship of different modalities, and a task-conditioned illumination module (TCIM) to dynamically adjust network weights based on illumination condition. Extensive experiments on KAIST and CVC-14 datasets demonstrate the general effectiveness of our proposed method. Code is available at https://github.com/gongyan1/UMPDP.

Railway Automatic Switch (RAS) plays a crucial role in Turnout Switching System (TSS). The size of RAS’s Stationary Contacts (SCs) directly affects connectivity of the pivotal control and feedback circuit, which further influences the remaining useful life of TSS. However, it is impossible to avoid normal wear and tear or fractures of SC during daily operation, resulting in size change of SCs. Therefore, it is vital to monitor the size of SCs. However, due to lack of wear samples, it is hard to design automatic algorithms for this task, especially for developing currently popular deep learning. To this end, this paper proposes a computer vision method forrailway automatic switch stationary contacts wear detection under few-shot occasions.Our method includes two key modules: a Few Shot SC DETection (FSDet) module and a Contour-based Size MEAsurement (CSMea) module, which together form a system that achieves accurate SC detection and size monitoring. The FSDet module formulates a multi-template deep feature matching pipeline, which plays the role of detecting all SCs in an image under the few shot manner. Then, the CSMea module takes the above detected SC patches as input and detects wear regions utilizing contour features and key point features. Finally, size of SCs can be calculated in image level by computing average pixels distance in wear regions and rescaled into real world level using image calibration tools. Experimental results demonstrate that the proposed method can accurately and robustly detect and measure the size of different SC structures in few-shot occasions.