Sensor calibration is a fundamental step for improving the performance in sensor fusion, the aim of which is to spatially and temporally register sensors with respect to each other. This paper presents a high-accuracy autocalibration method to estimate extrinsic parameters between LiDAR and an IMU. LiDAR/IMU calibration is a challenging task since the raw measurements are distorted, biased, noisy, and asynchronous. Our calibration approach adopts continuous-time trajectory estimation wherein the IMU trajectory is modeled by Gaussian process(GP) regression with respect to the independent sampling timestamps. Accordingly, the distorted and delayed LiDAR points sampled at discrete timestamps can be analytically modeled in on-manifold batch optimization. To efficiently and accurately associate laser points with stable environmental objects, the method is carried out in known environments with a point map that is segmented as structured planes and managed by a specially designed octree map. We thoroughly investigated factors relevant to the calibration accuracy and evaluated the performance of the proposed method using both simulated and real-world datasets. The results demonstrate that the accuracy and robustness of our calibration approach are sufficient for most applications.

In this paper, we investigate the paradigm of deep learning techniques to enhance the performance of visual-based SLAM systems, particularly in challenging environments. By leveraging deep feature extraction and matching methods, we propose a robust, versatile hybrid visual SLAM framework, Rover-SLAM, aimed at improving adaptability in adverse conditions, such as dynamic lighting conditions, areas with weak textures, and camera jitter. Building on excellent learning-based algorithms of recent years, we designed from scratch a novel system that uses the same feature extraction and matching approaches for all SLAM tasks. Our system supports multiple modes, including monocular, stereo, monocular-inertial, and stereo-inertial configurations, offering flexibility to address diverse real-world scenarios. Through comprehensive experiments conducted on publicly available datasets and self-collected data, we demonstrate the superior performance of our Rover-SLAM system compared to the SOTA approaches. We also conducted an in-depth analysis of the integration of visual SLAM with deep learning methods quantitatively to provide insights for future research endeavors in this domain. The experimental results showcase the system’s capability of achieving higher localization accuracy and robust tracking performance.

Cameras and LiDAR sensors have been extensively utilized in autonomous systems to enhance perception accuracy and robustness, owing to the highly complementary nature of their characteristics. The spatial and temporal relationships between these sensors are crucial for multi-sensor fusion technology, making calibration between heterogeneous sensors extremely important. This calibration process typically involves estimating the extrinsic parameters between sensors. Over the past two decades, with the advancement of camera and LiDAR technologies, numerous spatial calibration solutions have been proposed for various sensor configurations. The question of whether LiDAR-camera calibration has been fully resolved has arisen and been extensively discussed. This review addresses this question by thoroughly analyzing the anatomy of mainstream LiDAR-camera calibration systems. Consequently, we thoroughly dissect the key technologies in each component of the calibration framework and discuss the future efforts in each direction. Furthermore, we summarize and list available open-source codes and datasets for LiDAR-camera calibration to facilitate other researchers’ use and comparison of these tools. To further contribute to the community, the latest open-source code and datasets in this research field will be continuously maintained and updated on our homepage https://github.com/haoxinnihao/LiDAR-camera-calibration-summary.

Traditional LiDAR odometry (LO) systems mainly leverage geometric information obtained from the traversed surroundings to register lazer scans and estimate LiDAR ego-motion, while they may be unreliable in dynamic or degraded environments. This paper proposes InTEn-LOAM, a low-drift and robust LiDAR odometry and mapping method that fully exploits implicit information of lazer sweeps (i.e., geometric, intensity and temporal characteristics). The specific content of this work includes method innovation and experimental verification. With respect to method innovation, we propose the cylindrical-image-based feature extraction scheme, which makes use of the characteristic of uniform spatial distribution of lazer points to boost the adaptive extraction of various types of features, i.e., ground, beam, facade and reflector. We propose a novel intensity-based point registration algorithm and incorporate it into the LiDAR odometry, enabling the LO system to jointly estimate the LiDAR ego-motion using both geometric and intensity feature points. To eliminate the interference of dynamic objects, we propose a temporal-based dynamic object removal approach to filter them out in the resulting points map. Moreover, the local map is organized and downsampled using a temporal-related voxel grid filter to maintain the similarity between the current scan and the static local map. With respect to experimental verification, extensive tests are conducted on both simulated and real-world datasets. The results show that the proposed method achieves similar or better accuracy with respect to the state-of-the-art in normal driving scenarios and outperforms geometric-based LO in unstructured environments.

For infrared target segmentation, Convolutional Neural Networks based (CNN-based) methods have largely improved the segmentation accuracy. Previous CNN-based methods typically improved the segmentation accuracy by enhancing and aggregating multi-level features. But the existence of semantic gap between features from different semantic levels limits the improvement of feature aggregation. To address this problem and improve the segmentation accuracy of infrared targets with tiny sizes and irregular shapes, the Multi-Attention Shape Adaptive Network (MASANet) is proposed in this paper. Specifically, a Spatially Feature Fusion Dense-nested Unet (SFFDUnet) is designed as the feature extraction and aggregation backbone. Based on SFFDUnet, the Bi-directional Shape Adaptive Attention with Channel-wise Shape Enhance (BSAA-CSE) block is proposed as a multi-attention mechanism to reduce the semantic gap between features. Moreover, the multi-scale multi-branch deep supervision is introduced to stabilize the training process and enable model pruning. In addition, a new infrared target dataset CITY-IRTD is also constructed to evaluate the performance of our method. Experiments demonstrate the effectiveness of our method in reducing the semantic gap between features to be fused. As a result, our MASANet has achieved better performance on both public and our self-developed datasets, compared to other state-of-the-art infrared target segmentation methods. Codes and the dataset will be released at https://github.com/twentyfiveYang/MASANet_CITY-IRTD.

While traditional oblique photogrammetry offers high-fidelity accuracy, it suffers from significant processing latency, making it less suitable for time-sensitive applications such as emergency response. Real-time incremental aerial mapping, which prioritizes immediate visualization, faces key challenges including the efficiency–accuracy trade-off, long-range drift, and appearance inconsistency under resource constraints and illumination variation. To address these issues, we propose a novel real-time large-scale orthomosaicking system that integrate learning-based VO(visual odometry) with GNSS(global navigation satellite system) via hierarchical alignment for efficient aerial orthomosaic generation. By combining robust hybrid VO with tightly-coupled optimization of GNSS-derived relative transforms, our method effectively mitigates long-range drift in large-scale environments. Furthermore, we introduce a semantic-aware coarse-to-fine mosaic plane fitting and a dual orthorectification strategy to adaptively balances local accuracy and global geomatric consistency. Finally, the multi-band Laplacian blending is employed to ensure seamless appearance transitions. Experimental results demonstrate that our system outperforms commercial solutions in both speed and consistency, particularly in complex urban structures, texture-sparse regions, and flight boundary areas. These results confirm that our method is able to deliver superior mapping quality while maintaining real-time performance.