首页/论文/2004.08582

arXiv 2004.085822020-04-18cs.CV

BiFNet: Bidirectional Fusion Network for Road Segmentation

Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）

Haoran Li, Yaran Chen, Qichao Zhang, Dongbin Zhao

英文摘要：

Multi-sensor fusion-based road segmentation plays an important role in the intelligent driving system since it provides a drivable area. The existing mainstream fusion method is mainly to feature fusion in the image space domain which causes the perspective compression of the road and damages the performance of the distant road. Considering the bird's eye views(BEV) of the LiDAR remains the space structure in horizontal plane, this paper proposes a bidirectional fusion network(BiFNet) to fuse the image and BEV of the point cloud. The network consists of two modules: 1) Dense space transformation module, which solves the mutual conversion between camera image space and BEV space. 2) Context-based feature fusion module, which fuses the different sensors information based on the scenes from corresponding features.This method has achieved competitive results on KITTI dataset.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

SAM增强的道路数据集分割：自动驾驶中关键类别的平衡

SAM-Enhanced Segmentation on Road Datasets: Balancing Critical Classes in Autonomous Driving

Department of Mechanical and Industrial Engineering, Tallinn University of Technology（塔林技术大学机械与工业工程系）；FinEst Centre for Smart Cities, Tallinn University of Technology（塔林技术大学智能城市研究中心）；Department of Computer Science and Engineering, Universitas Mercatorum（默卡托姆大学计算机科学与工程系）；Department of Computer Science and Engineering, Chalmers University of Technology（挑战者技术大学计算机科学与工程系）；University of Gothenburg（哥德堡大学）

提出基于SAM的标注流水线，将ZOD数据集的边界框转换为密集像素级语义掩码，并评估不同架构在类别不平衡下的性能，通过双向迁移学习实现跨传感器配置的有效迁移。

2026-05-27cs.CVcs.RO

BsS-YOLO增强道路裂缝检测精度：优化特征融合与注意力机制

Enhancing Road Crack Detection Accuracy with BsS-YOLO: Optimizing Feature Fusion and Attention Mechanisms

Saint Petersburg State University（圣彼得堡国立大学）

本文提出BsS-YOLO模型，通过增强PAN和BiFPN优化多尺度特征融合，并集成SimAM和Shuffle Attention机制，在道路裂缝检测中实现mAP提升2.8%，适用于城市道路维护和高速公路检查。

2024-12-14cs.CV

雷达-相机BEV多任务学习：用于联合3D检测与分割的跨任务注意力桥

Radar-Camera BEV Multi-Task Learning with Cross-Task Attention Bridge for Joint 3D Detection and Segmentation

Hacettepe University（哈切特佩大学）

提出CTAB（跨任务注意力桥）模块，通过共享BEV空间中的多尺度可变形注意力在检测和分割分支间交换特征，实现联合3D检测与分割的多任务学习，在nuScenes上提升分割性能且检测几乎不受影响。

2026-05-26cs.CV

增强路面裂缝分类的双向级联神经网络

Enhancing Pavement Crack Classification with Bidirectional Cascaded Neural Networks

Al-Ahliyya Amman University（阿曼阿赫利耶大学）；Ministry of Public Work of Kuwait（科威特公共工程部）；Queensland University of Technology（昆士兰科技大学）；Arab American University（阿拉伯美国大学）

本研究提出双向级联神经网络（BCNN），利用前向和后向信息流及级联结构，在599张增强图像上实现87%准确率的路面裂缝分类，显著提升维护效率。

2025-03-27cs.CV

YOLOv8在单目俯视多车辆目标检测中的应用

Application of YOLOv8 in monocular downward multiple Car Target detection

针对自动驾驶感知成本高、受环境影响大且分辨率有限的问题，提出融合结构重参数化、双向金字塔与新检测流程的改进YOLOv8，实现多尺度及小目标检测，精度达65%。

2025-07-23cs.AIcs.CV

ETLNet：一种利用智能手机传感器进行道路异常检测的高效TCN-BiLSTM网络

ETLNet: An Efficient TCN-BiLSTM Network for Road Anomaly Detection Using Smartphone Sensors

IIIT Allahabad（阿拉哈巴德印度信息技术学院）；University at Buffalo（布法罗大学）

针对视觉道路异常检测受光照和标识影响的问题，本文提出融合TCN与BiLSTM的ETLNet，利用智能手机加速度计和陀螺仪数据检测道路异常，减速带检测F1分数达99.3%。

2024-12-06cs.AIcs.CV

更多相关论文收起更多论文

基于相机-IMU融合的新型数据集与道路表面分类框架

A New Dataset and Framework for Robust Road Surface Classification via Camera-IMU Fusion

Voxar Labs（Voxar实验室）；Centro de Informática（计算机中心）；Universidade Federal de Pernambuco（佩纳布卢克联邦大学）

本文提出了一种基于相机-IMU融合的新型数据集和框架，通过多模态注意力机制提升道路表面分类的鲁棒性和泛化能力。

2026-01-29cs.AIcs.CV

CoDS：基于专家驱动检测与BEV分割的鲁棒协同感知

CoDS: Robust Collaborative Perception via Expert-driven Detection and BEV Segmentation

Peking University（北京大学）；Macau University of Science and Technology（澳门科技大学）

针对多源噪声导致协同感知性能下降的问题，提出CoDS框架，通过CoRM、S-MoE和BTCI模块提升鲁棒性，在公开数据集上优于基线且抗噪稳定。

2026-08-17cs.CV

Deep Feature Mining via Attention-based BiLSTM-GCN for Human Motor Imagery Recognition

Northeast Electric Power University（东北电力大学）；Changchun University of Science and Technology（长春理工大学）；University of Sydney（悉尼大学）

Recognition accuracy and response time are both critically essential ahead of building practical electroencephalography (EEG) based brain-computer interface (BCI). Recent approaches, however, have either compromised in the classification accuracy or responding time. This paper presents a novel deep learning approach designed towards remarkably accurate and responsive motor imagery (MI) recognition based on scalp EEG. Bidirectional Long Short-term Memory (BiLSTM) with the Attention mechanism manages to derive relevant features from raw EEG signals. The connected graph convolutional neural netwo…

2021-12-02cs.CVcs.HCcs.LG

Edge-Aided Sensor Data Sharing in Vehicular Communication Networks

Fraunhofer Institute for Transportation and Infrastructure Systems IVI（弗劳恩霍夫交通与基础设施系统研究所）；Technical University of Munich（慕尼黑工业大学）；Technische Hochschule Ingolstadt（英戈尔施塔特应用技术大学）

Sensor data sharing in vehicular networks can significantly improve the range and accuracy of environmental perception for connected automated vehicles. Different concepts and schemes for dissemination and fusion of sensor data have been developed. It is common to these schemes that measurement errors of the sensors impair the perception quality and can result in road traffic accidents. Specifically, when the measurement error from the sensors (also referred as measurement noise) is unknown and time varying, the performance of the data fusion process is restricted, which represents a major cha…

2022-06-17cs.CVcs.MAeess.SP

TriBand-BEV：基于高度感知的鸟瞰图与高分辨率特征融合的实时仅LiDAR三维行人检测

TriBand-BEV: Real-Time LiDAR-Only 3D Pedestrian Detection via Height-Aware BEV and High-Resolution Feature Fusion

Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）

本文提出TriBand-BEV方法，通过高度感知的鸟瞰图与高分辨率特征融合实现实时LiDAR-only三维行人检测，采用轻量级鸟瞰图张量映射，单网络一次通过检测车辆、行人和自行车，提升检测精度与速度。

2026-05-12cs.AIcs.CVcs.LG