Lidar-based 3D object detection and classification is a critical task for autonomous driving. However, inferencing from exceedingly sparse 3D data in real-time is a formidable challenge. Complex-YOLO solves the problem of point cloud disorder and sparsity by projecting it onto the bird’s-eye view and realizes real-time 3D object detection based on LiDAR. However, Complex-YOLO has no object height detection, a shallow network depth, and poor small-size object detection accuracy. To address these issues, this paper has made the following improvements: (1) adds a multi-scale feature fusion network to improve the algorithm’s capability to detect small-size objects; (2) uses a more advanced RepVGG as the backbone network to improve network depth and overall detection performance; and (3) adds an effective height detector to the network to improve the height detection. Through experiments, we found that our algorithm’s accuracy achieved good performance on the KITTI dataset, while the detection speed and memory usage were very superior, 48FPS on RTX3070Ti and 20FPS on GTX1060, with a memory usage of 841Mib.

Semantic segmentation finds wide-ranging applications and stands as a crucial task in the realm of computer vision. It holds significant implications for scene comprehension and decision-making in unmanned systems, including domains such as autonomous driving, unmanned aerial vehicles, robotics, and healthcare. Consequently, there is a growing demand for high precision in semantic segmentation, particularly for these contents. This paper introduces DPNet, a novel image semantic segmentation method based on the Deeplabv3 plus architecture. (1) DPNet utilizes ResNet-50 as the backbone network to extract feature maps at various scales. (2) Our proposed method employs the BiFPN (Bi-directional Feature Pyramid Network) structure to fuse multi-scale information, in conjunction with the ASPP (Atrous Spatial Pyramid Pooling) module, to handle information at different scales, forming a dual pyramid structure that fully leverages the effective features obtained from the backbone network. (3) The Shuffle Attention module is employed in our approach to suppress the propagation of irrelevant information and enhance the representation of relevant features. Experimental evaluations on the Cityscapes dataset and the PASCAL VOC 2012 dataset demonstrate that our method outperforms current approaches, showcasing superior semantic segmentation accuracy.

We propose a generation system of continuous-variable (CV) three-color entangled state of bright optical beams based on two cascaded standard nondegenerate optical parametric oscillators (NOPOs) above the threshold. One of signal and idler beams produced by the first NOPO is used for the pump light of the second NOPO. The three-color entanglement among signal and idler beams produced by the second NOPO and the retained another beam of the first NOPO is theoretically demonstrated. The symplectic eigenvalues of the partial transposition covariance matrix of the generated optical entangled state are numerically calculated in terms of experimentally reachable system parameters. The optimal operation conditions of the cascaded NOPOs system for obtaining high entanglement are found. The calculated results explicitly demonstrate that the OPO action can transfer entanglement. Due to that the cavity parameters and the nonlinear crystals of the two NOPOs can be freely chosen, the flexibility of the proposed protocol is relatively good and the system can be also extended to prepare entangled states with more parts easily.

3D object detection using LiDAR is critical for autonomous driving. However, the point cloud data in autonomous driving scenarios is sparse. Converting the sparse point cloud into regular data representations (voxels or projection) often leads to information loss due to downsampling or excessive compression of feature information. This kind of information loss will adversely affect detection accuracy, especially for objects with fewer reflective points like cyclists. This paper proposes a multi-modal point cloud 3D object detector based on projection features and voxel features, which consists of two branches. One, called the voxel branch, is used to extract fine-grained local features. Another, called the projection branch, is used to extract projection features from a bird's-eye view and focus on the correlation of local features in the voxel branch. By feeding voxel features into the projection branch, we can compensate for the information loss in the projection branch while focusing on the correlation between neighboring local features in the voxel features. To achieve comprehensive feature fusion of voxel features and projection features, we propose a multi-modal feature fusion module (MSSFA). To further mitigate the loss of crucial features caused by downsampling, we propose a voxel feature extraction method (VR-VFE), which samples feature points based on their importance for the detection task. To validate the effectiveness of our method, we tested it on the KITTI dataset and ONCE dataset. The experimental results show that our method has achieved significant improvement in the detection accuracy of objects with fewer reflection points like cyclists.

Satellite signal interruptions disable unmanned aerial vehicle (UAV) navigation, making visual localization a vital alternative. To improve robustness in oblique flight paths and complex environments, we propose the UAV visual geo-localization network with transformer and hypergraph feature aggregation enhancement (HTGL). First, we enhanced feature extraction capabilities by optimizing the downsampling strategy and attention allocation mechanism in the backbone network. Second, we designed the Hypergraph Feature Aggregation Enhancement (HFAE) module based on hypergraph-based adaptive correlation enhancement (HyperACE) to improve the model’s ability to capture higher-order correlations. Furthermore, we constructed the Complex Scene Rotation dataset (CSR10) and proposed a method for simulating winter scenes, thereby overcoming the limitations of existing research in terms of scenes, flight directions, and seasons. Additionally, two evaluation metrics—pixel distance root mean square error (PD-RMSE) and geographic distance root mean square error (GD-RMSE)—were introduced to enable a comprehensive assessment of algorithm performance. Experimental results show that HTGL achieved RDS scores of 85.95% (+1.4%), 83.64% (+4.1%), and 91.52% (+1.49%) on the UL14, UL14_ROT, and CSR10 datasets, respectively, demonstrating strong robustness in rotated and complex scenes. Actual deployment and flight tests on the Jetson Orin NX platform further validated the model’s excellent engineering practicality.