3D object detection is an important task in autonomous driving scenario, which is the basis of perception and understanding of 3D scenes. LiDAR and camera are two commonly used sensors in 3D object detection tasks. Ho...
详细信息
ISBN:
(纸本)9781665409858
3D object detection is an important task in autonomous driving scenario, which is the basis of perception and understanding of 3D scenes. LiDAR and camera are two commonly used sensors in 3D object detection tasks. However, using a single sensor to collect data will make some objects difficult to detect because both sensors have insurmountable shortcomings. Unexpectedly, LiDAR-only detection methods tend to show better performance than the multi-sensor methods in public benchmarks. This shows that people need to further explore the methods of combining the data of the two sensors. Recently, PointPainting has been presented to combine the data of LiDAR and camera more efficiently by attaching the result of image semantic segmentation to point cloud data as new channels. In this paper, we propose an error anchor punishment mechanism based on image semantic segmentation results. After the semantic augmentation of the point cloud data, we judge whether the semantic result of each point is correct by traversing the groundtruth boxes. Further, we assign different weights to each anchor according to the error points contained in each anchor. Experimental results on the KITTI valid set show that SemanticAnchors achieves better performance in both 3D and birds eyes view benchmarks. In particular, our method adds little extra computation and achieves performance improvement in all categories.
Increasing the number of lines of lidar can alleviate the sparsity of point cloud, but the cost of high-line lidar is higher. From the perspective of algorithm, the fusion of continuous point clouds frames can obtain ...
详细信息
ISBN:
(纸本)9781665409858
Increasing the number of lines of lidar can alleviate the sparsity of point cloud, but the cost of high-line lidar is higher. From the perspective of algorithm, the fusion of continuous point clouds frames can obtain more abundant information, which is expected to be a means to achieve high-performance object detection on low-line lidar. At present, most multi-frame point cloud fusion methods stack different frames after registration. This fusion method, which introduces GPS, ego-motion, and other information for registration, can only align static objects, not larger moving objects. In this paper, we implement a multi-frame fusion method based on Non-Local, which does not need registration and takes into account both moving and stationary objects. We validated the model performance on the NuScenes dataset. Experimental results show that the performance of the proposed fusion method is better than that of fusion method by stacking frames after registration.
Synthetic aperture radar (SAR) tomography (TomoSAR) enables the reconstruction and three-dimensional (3D) localization of targets based on multiple two-dimensional (2D) observations of the same scene. The resolving al...
详细信息
Tomographic SAR (TomoSAR) technology has gained significant attention in recent years due to its three-dimensional imaging capability. However, in practical applications, phase errors between different channels can de...
Tomographic SAR (TomoSAR) technology has gained significant attention in recent years due to its three-dimensional imaging capability. However, in practical applications, phase errors between different channels can degrade the quality of three-dimensional imaging. Current state-of-the-art methods for phase error compensation based on autofocus techniques suffer from high computational complexity, making them unsuitable for large-scale three-dimensional imaging. In this paper, we propose a multi-channel phase error estimation method based on error back-propagation training optimization. By utilizing the TomoSAR model that incorporates phase errors from multiple channels, we construct a matrix containing the parameters to be estimated for inter-channel phase errors. Through stochastic gradient descent algorithm, we iteratively optimize the parameters of the phase error matrix, ultimately obtaining an estimation of the inter-channel phase errors. Experimental results validate the accuracy of the proposed method.
Stereo matching in remote sensing has recently garnered increased attention, primarily focusing on supervised learning. However, datasets with ground truth generated by expensive airbone Lidar exhibit limited quantity...
详细信息
ISBN:
(数字)9798350360325
ISBN:
(纸本)9798350360332
Stereo matching in remote sensing has recently garnered increased attention, primarily focusing on supervised learning. However, datasets with ground truth generated by expensive airbone Lidar exhibit limited quantity and diversity, constraining the effectiveness of supervised networks. In contrast, unsupervised learning methods can leverage the increasing availability of very-high-resolution (VHR) remote sensing images, offering considerable potential in the realm of stereo matching. Motivated by this intuition, we propose a novel unsupervised stereo matching network for VHR remote sensing images. A light-weight module to bridge confidence with predicted error is introduced to refine the core model. Robust unsupervised losses are formulated to enhance network convergence. The experimental results on US3D and WHU-Stereo datasets demonstrate that the proposed network achieves superior accuracy compared to other unsupervised networks and exhibits better generalization capabilities than supervised models. Our code will be available at https://***/Elenairene/CBEM.
With the SAR satellites have gradually become one of the most important methods of Earth observation, rapid interpretation of SAR images has become particularly important. However, the unique imaging mechanism of SAR ...
详细信息
Integrating Synthetic Aperture Radar (SAR) imaging with unmanned aerial vehicles (UAVs) plays a crucial role in urban area surveillance and situational awareness, benefiting from the low cost, small size, and high fle...
详细信息
ISBN:
(数字)9798350360325
ISBN:
(纸本)9798350360332
Integrating Synthetic Aperture Radar (SAR) imaging with unmanned aerial vehicles (UAVs) plays a crucial role in urban area surveillance and situational awareness, benefiting from the low cost, small size, and high flexibility of SAR carried by drones. However, the dense arrangement of high-rise buildings in urban environments creates Urban Canyons and numerous visual blind spots due to occlusion, which weakens the perception capability of SAR. Additionally, SAR imaging results of moving vehicles on the roads between buildings result in severe defocusing due to their non-cooperative motion. In this paper, we establish a vehicle signal model for SAR imaging with UAVs that considers the vehicle body’s translation and the wheels’ rotation. The range history modulation and imaging characteristics of returns caused by translation and micro-motion are derived. Simulation results validate the correctness of the theoretical analysis, and the proposed theory helps explain SAR imaging results, providing support for high-precision focusing and three-dimensional imaging of non-line-of-sight (NLOS) SAR images.
Image-based synthetic aperture radar (SAR) target three-dimensional (3D) reconstruction is an important application for extracting target information from high-resolution two-dimensional (2D) SAR images. However, due ...
详细信息
ISBN:
(数字)9798331515669
ISBN:
(纸本)9798331515676
Image-based synthetic aperture radar (SAR) target three-dimensional (3D) reconstruction is an important application for extracting target information from high-resolution two-dimensional (2D) SAR images. However, due to the complex mechanism of SAR imaging, developing a data-driven, fully automated 3D reconstruction framework with explicit physical constraints is very difficult. Thus, this paper proposes a differentiable framework for image-based SAR target reconstruction with 3D Gaussian Splatting, which can automatically realize the 3D target reconstruction from multi-view SAR images. Specifically, the proposed differentiable framework accumulates and generates simulated SAR images according to the SAR imaging geometry and projection during the forward simulation stage. By calculating the loss between the simulated and ground truth SAR images and backpropagating, the spatial positions of the 3D Gaussians are continuously adjusted until convergence, generating the 3D point cloud model of the target. The experiment is conducted on the constructed T72 SAR image dataset and the reconstruction results demonstrate the effectiveness of the proposed framework.
Highly-squinted synthetic aperture radar (SAR) echo has the characteristic of severe range-azimuth coupling, requiring specialized imaging algorithms. applications of compressed sensing in SAR imaging can effectively ...
Highly-squinted synthetic aperture radar (SAR) echo has the characteristic of severe range-azimuth coupling, requiring specialized imaging algorithms. applications of compressed sensing in SAR imaging can effectively improve the resolution and other indicators. However, inaccurate manual parameters can affect the algorithm output. This article proposes an improved alternating direction method of multipliers (ADMM) for solving sparse reconstruction models under highly-squinted conditions. By adaptively adjusting the penalty parameter in ADMM via hyper-gradient descent (HD), the problem caused by inaccurate manual parameter is solved. Compared with matched filtering methods and other optimization methods, this method can suppress noise and speed up convergence. The effectiveness of the proposed method can be validated through the approximate observation of both simulated scenes and real scenes captured by the GF-3 SAR satellite.
For moving targets in synthetic aperture radar (SAR) images, the obvious features are defocusing and dislocation. To estimate motion parameters accurately is a premise for the precise imaging of moving targets. Howeve...
详细信息
暂无评论