Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input t...Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the RGB images.Depth-based methods attempt to convert estimated depth maps to pseudo-LiDAR and then use LiDAR-based object detectors or focus on the perspective of image and depth fusion learning.However,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with convolutions.Different from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth information.Then we develop a novel Swin-Transformer-based backbone with a fusion module to process RGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each other.Furthermore,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input tokens.Our method is the first Swin-Transformer-based backbone architecture for monocular 3D object detection.The experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.展开更多
The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms.Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost,lowpow...The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms.Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost,lowpower solution compared to LiDAR solutions in the field of autonomous driving.However,this technique has some problems,i.e.,(1)the poor quality of generated Pseudo-LiDAR point clouds resulting from the nonlinear error distribution of monocular depth estimation and(2)the weak representation capability of point cloud features due to the neglected global geometric structure features of point clouds existing in LiDAR-based 3D detection networks.Therefore,we proposed a Pseudo-LiDAR confidence sampling strategy and a hierarchical geometric feature extraction module for monocular 3D object detection.We first designed a point cloud confidence sampling strategy based on a 3D Gaussian distribution to assign small confidence to the points with great error in depth estimation and filter them out according to the confidence.Then,we present a hierarchical geometric feature extraction module by aggregating the local neighborhood features and a dual transformer to capture the global geometric features in the point cloud.Finally,our detection framework is based on Point-Voxel-RCNN(PV-RCNN)with high-quality Pseudo-LiDAR and enriched geometric features as input.From the experimental results,our method achieves satisfactory results in monocular 3D object detection.展开更多
Drogue recognition and 3D locating is a key problem during the docking phase of the autonomous aerial refueling （AAR）. To solve this problem, a novel and effective method based on monocular vision is presented in th...Drogue recognition and 3D locating is a key problem during the docking phase of the autonomous aerial refueling （AAR）. To solve this problem, a novel and effective method based on monocular vision is presented in this paper. Firstly, by employing computer vision with red-ring-shape feature, a drogue detection and recognition algorithm is proposed to guarantee safety and ensure the robustness to the drogue diversity and the changes in environmental condi- tions, without using a set of infrared light emitting diodes （LEDs） on the parachute part of the dro- gue. Secondly, considering camera lens distortion, a monocular vision measurement algorithm for drogue 3D locating is designed to ensure the accuracy and real-time performance of the system, with the drogue attitude provided. Finally, experiments are conducted to demonstrate the effective- ness of the proposed method. Experimental results show the performances of the entire system in contrast with other methods, which validates that the proposed method can recognize and locate the drogue three dimensionally, rapidly and precisely.展开更多
针对单目3D目标检测在视角变化引起的物体大小变化以及物体遮挡等情况下效果不佳的问题,提出一种融合深度信息和实例分割掩码的新型单目3D目标检测方法。首先,通过深度-掩码注意力融合(DMAF)模块,将深度信息与实例分割掩码结合,以提供...针对单目3D目标检测在视角变化引起的物体大小变化以及物体遮挡等情况下效果不佳的问题,提出一种融合深度信息和实例分割掩码的新型单目3D目标检测方法。首先,通过深度-掩码注意力融合(DMAF)模块,将深度信息与实例分割掩码结合,以提供更准确的物体边界;其次,引入动态卷积,并利用DMAF模块得到的融合特征引导动态卷积核的生成,以处理不同尺度的物体;再次,在损失函数中引入2D-3D边界框一致性损失函数,调整预测的3D边界框与对应的2D检测框高度一致,以提高实例分割和3D目标检测任务的效果;最后,通过消融实验验证该方法的有效性,并在KITTI测试集上对该方法进行验证。实验结果表明,与仅使用深度估计图和实例分割掩码的方法相比,在中等难度下对车辆类别检测的平均精度提高了6.36个百分点,且3D目标检测和鸟瞰图目标检测任务的效果均优于D4LCN(Depth-guided Dynamic-Depthwise-Dilated Local Convolutional Network)、M3D-RPN(Monocular 3D Region Proposal Network)等对比方法。展开更多
针对现有的三维视觉定位方法依赖昂贵传感器设备、系统成本高且在复杂多目标定位中准确度和鲁棒性不足的问题,提出一种基于单目图像的多目标三维视觉定位方法。该方法结合自然语言描述,在单个RGB图像中实现对多个三维目标的识别。为此,...针对现有的三维视觉定位方法依赖昂贵传感器设备、系统成本高且在复杂多目标定位中准确度和鲁棒性不足的问题,提出一种基于单目图像的多目标三维视觉定位方法。该方法结合自然语言描述,在单个RGB图像中实现对多个三维目标的识别。为此,构建一个多目标视觉定位数据集Mmo3DRefer,并设计跨模态匹配网络TextVizNet。TextVizNet通过预训练的单目检测器生成目标的三维边界框,并借助信息融合模块与信息对齐模块实现视觉与语言信息的深度整合,进而实现文本指导下的多目标三维检测。与CORE-3DVG(Contextual Objects and RElations for 3D Visual Grounding)、3DVG-Transformer和Multi3DRefer(Multiple 3D object Referencing dataset and task)等5种方法对比的实验结果表明,与次优方法Multi3DRefer相比,TextVizNet在Mmo3DRefer数据集上的F1-score、精确度和召回率分别提升了8.92%、8.39%和9.57%,显著提升了复杂场景下基于文本的多目标定位精度,为自动驾驶和智能机器人等实际应用提供了有效支持。展开更多
基金supported in part by the Major Project for New Generation of AI (2018AAA0100400)the National Natural Science Foundation of China (61836014,U21B2042,62072457,62006231)the InnoHK Program。
文摘Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the RGB images.Depth-based methods attempt to convert estimated depth maps to pseudo-LiDAR and then use LiDAR-based object detectors or focus on the perspective of image and depth fusion learning.However,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with convolutions.Different from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth information.Then we develop a novel Swin-Transformer-based backbone with a fusion module to process RGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each other.Furthermore,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input tokens.Our method is the first Swin-Transformer-based backbone architecture for monocular 3D object detection.The experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.
基金supported by the National Key Research and Development Program of China(2020YFB1807500)the National Natural Science Foundation of China(62072360,62001357,62172438,61901367)+4 种基金the key research and development plan of Shaanxi province(2021ZDLGY02-09,2023-GHZD-44,2023-ZDLGY-54)the Natural Science Foundation of Guangdong Province of China(2022A1515010988)Key Project on Artificial Intelligence of Xi'an Science and Technology Plan(2022JH-RGZN-0003,2022JH-RGZN-0103,2022JH-CLCJ-0053)Xi'an Science and Technology Plan(20RGZN0005)the Proof-ofconcept fund from Hangzhou Research Institute of Xidian University(GNYZ2023QC0201).
文摘The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms.Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost,lowpower solution compared to LiDAR solutions in the field of autonomous driving.However,this technique has some problems,i.e.,(1)the poor quality of generated Pseudo-LiDAR point clouds resulting from the nonlinear error distribution of monocular depth estimation and(2)the weak representation capability of point cloud features due to the neglected global geometric structure features of point clouds existing in LiDAR-based 3D detection networks.Therefore,we proposed a Pseudo-LiDAR confidence sampling strategy and a hierarchical geometric feature extraction module for monocular 3D object detection.We first designed a point cloud confidence sampling strategy based on a 3D Gaussian distribution to assign small confidence to the points with great error in depth estimation and filter them out according to the confidence.Then,we present a hierarchical geometric feature extraction module by aggregating the local neighborhood features and a dual transformer to capture the global geometric features in the point cloud.Finally,our detection framework is based on Point-Voxel-RCNN(PV-RCNN)with high-quality Pseudo-LiDAR and enriched geometric features as input.From the experimental results,our method achieves satisfactory results in monocular 3D object detection.
基金supported by the National Natural Science Foundation of China(Nos.61473307,61304120)
文摘Drogue recognition and 3D locating is a key problem during the docking phase of the autonomous aerial refueling （AAR）. To solve this problem, a novel and effective method based on monocular vision is presented in this paper. Firstly, by employing computer vision with red-ring-shape feature, a drogue detection and recognition algorithm is proposed to guarantee safety and ensure the robustness to the drogue diversity and the changes in environmental condi- tions, without using a set of infrared light emitting diodes （LEDs） on the parachute part of the dro- gue. Secondly, considering camera lens distortion, a monocular vision measurement algorithm for drogue 3D locating is designed to ensure the accuracy and real-time performance of the system, with the drogue attitude provided. Finally, experiments are conducted to demonstrate the effective- ness of the proposed method. Experimental results show the performances of the entire system in contrast with other methods, which validates that the proposed method can recognize and locate the drogue three dimensionally, rapidly and precisely.
文摘针对单目3D目标检测在视角变化引起的物体大小变化以及物体遮挡等情况下效果不佳的问题,提出一种融合深度信息和实例分割掩码的新型单目3D目标检测方法。首先,通过深度-掩码注意力融合(DMAF)模块,将深度信息与实例分割掩码结合,以提供更准确的物体边界;其次,引入动态卷积,并利用DMAF模块得到的融合特征引导动态卷积核的生成,以处理不同尺度的物体;再次,在损失函数中引入2D-3D边界框一致性损失函数,调整预测的3D边界框与对应的2D检测框高度一致,以提高实例分割和3D目标检测任务的效果;最后,通过消融实验验证该方法的有效性,并在KITTI测试集上对该方法进行验证。实验结果表明,与仅使用深度估计图和实例分割掩码的方法相比,在中等难度下对车辆类别检测的平均精度提高了6.36个百分点,且3D目标检测和鸟瞰图目标检测任务的效果均优于D4LCN(Depth-guided Dynamic-Depthwise-Dilated Local Convolutional Network)、M3D-RPN(Monocular 3D Region Proposal Network)等对比方法。
文摘针对现有的三维视觉定位方法依赖昂贵传感器设备、系统成本高且在复杂多目标定位中准确度和鲁棒性不足的问题,提出一种基于单目图像的多目标三维视觉定位方法。该方法结合自然语言描述,在单个RGB图像中实现对多个三维目标的识别。为此,构建一个多目标视觉定位数据集Mmo3DRefer,并设计跨模态匹配网络TextVizNet。TextVizNet通过预训练的单目检测器生成目标的三维边界框,并借助信息融合模块与信息对齐模块实现视觉与语言信息的深度整合,进而实现文本指导下的多目标三维检测。与CORE-3DVG(Contextual Objects and RElations for 3D Visual Grounding)、3DVG-Transformer和Multi3DRefer(Multiple 3D object Referencing dataset and task)等5种方法对比的实验结果表明,与次优方法Multi3DRefer相比,TextVizNet在Mmo3DRefer数据集上的F1-score、精确度和召回率分别提升了8.92%、8.39%和9.57%,显著提升了复杂场景下基于文本的多目标定位精度,为自动驾驶和智能机器人等实际应用提供了有效支持。
