Small object detection remains a challenge in the remote sensing field due to feature loss during downsampling and interference from complex backgrounds. A novel network, termed SEMA-YOLO, is proposed in this paper as an enhanced YOLOv11-based framework incorporating three technical advancements. By fundamentally reducing information loss and incorporating a cross-scale feature fusion mechanism, the proposed framework significantly enhances small object detection performance. First, the Shallow Layer Enhancement (SLE) strategy reduces backbone depth and introduces small-object detection heads, thereby increasing feature map size and improving small object detection performance. Then, the Global Context Pooling-enhanced Adaptively Spatial Feature Fusion (GCP-ASFF) architecture is designed to optimize cross-scale feature interaction across four detection heads. Finally, the RFA-C3k2 module, which integrates Receptive Field Adaptation (RFA) with the C3k2 structure, is introduced to achieve more refined feature extraction. SEMA-YOLO demonstrates significant advantages in complex urban environments and dense target areas, while its generalization capability meets the detection requirements across diverse scenarios. The experimental results show that SEMA-YOLO achieves mAP₅₀ scores of 72.5% on the RS-STOD dataset and 61.5% on the AI-TOD dataset, surpassing state-of-the-art models.

Due to the ability to provide point clouds and Doppler velocity, as well as the adaptability in harsh weather conditions, 4D Radar has emerged as a new option for Simultaneous Localization and Mapping (SLAM). However, there is limited research on both robustness and computational efficiency, which are essential requirements for deploying 4D Radar as a specialized sensor in harsh weather. This paper proposes a fast and robust Radar-Inertial-Odometry (RIO) approach, named FAR-RIO. Specifically, we propose a dynamic point filtering based on full covariance propagation, along with an isotropic uncertainty model for accurate registration. In particular, leveraging the dual-observation capability of 4D radar, we design a novel dual-observation update pipeline for the iterated error-state Kalman filter (IESKF), coupled with a corresponding keyframe selection strategy, significantly reducing computational load while minimizing accuracy loss. Our method approaches state-of-the-art performance on various sensors and runs significantly faster than existing methods.

A precise RGB-colored point cloud map serves as a reliable data foundation and a compact multi-sensor representation for tasks such as 3D perception, localization, and navigation. Therefore, efficient and accurate alignment between camera and LiDAR is essential. However, most existing color mapping methods require precise time synchronization and well-calibrated extrinsic value, and these colorizing frameworks are often hard to use. In this paper, we propose EasyColor, a precise colorization method that jointly leverages LiDAR reflectivity and visual constraint, effectively removing the need for time synchronization and extrinsic calibration between the two sensors. Our method follows a plug-and-play framework. Given an image sequence and a pre-built point cloud map, we first generate 2D reflectivity image sequence by exploiting variations in LiDAR reflectivity intensity. A cross-domain matching network, combined with a Perspective-n-Point (PnP) solver, is employed to align the reflectivity and camera image sequence. To further optimize camera poses and ensure photometric consistency, we fuse visual epipolar geometric constraint and PnP constraint. Our joint optimization produces both accurate and photometrically consistent colored map, along with optimized camera poses. Extensive experiments demonstrate that EasyColor achieves precise point cloud colorization without requiring synchronized LiDAR and camera data and extrinsic values. To facilitate future research, we will release EasyColor and dataset after review stage.