Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving Yurong
是之前講過的虛擬激光雷達的改進版。 之前的文章有個缺點是說，對於遠處的物體，檢測效果不好。 這篇文章通過改進雙目攝像機的深度估計網絡讓檢測的位置更準確，還進一步利用4線的特別便宜的激光雷達來微調檢測結果。 最終的效果： 比之前的那篇文章，效果提升了27%。在某些指標上，可以和64線的激光雷達媲美。 4線的激光雷達比64線的激光雷達價格要低兩個數量級。這一套設備（4線激光雷達+攝像頭）比之前64
相關文章
- 1. 每天一篇論文 373/1000 PSEUDO-LIDAR++:ACCURATE DEPTH FOR 3D OBJECT DETECTION IN AUTONOMOUS DRIVING
- 2. Multi-View 3D Object Detection Network for Autonomous Driving
- 3. Stereo R-CNN based 3D Object Detection for Autonomous Driving
- 4. Pillar-based Object Detection for Autonomous Driving
- 5. 【3D 目標檢測】2019 CVPR Learning 2D to 3D Lifting for Object Detection in 3D for Autonomous Vehicles
- 6. 解讀ECCV2020：Pillar-based Object Detection for Autonomous Driving
- 7. Sliding Shapes for 3D Object Detection in Depth Images
- 8. 論文閱讀CVPR2019——Stereo R-CNN based 3D Object Detection for Autonomous Driving
- 9. [論文解讀]Multi-View 3D Object Detection Network for Autonomous Driving
- 10. MV3D：Multi-View 3D Object Detection Network for Autonomous Driving（翻譯）
- 更多相關文章...
- • Swift for-in 循環 - Swift 教程
- • Scala for循環 - Scala教程
- • 互聯網組織的未來：剖析GitHub員工的任性之源
- • 爲了進字節跳動，我精選了29道Java經典算法題，帶詳細講解
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. 每天一篇論文 373/1000 PSEUDO-LIDAR++:ACCURATE DEPTH FOR 3D OBJECT DETECTION IN AUTONOMOUS DRIVING
- 2. Multi-View 3D Object Detection Network for Autonomous Driving
- 3. Stereo R-CNN based 3D Object Detection for Autonomous Driving
- 4. Pillar-based Object Detection for Autonomous Driving
- 5. 【3D 目標檢測】2019 CVPR Learning 2D to 3D Lifting for Object Detection in 3D for Autonomous Vehicles
- 6. 解讀ECCV2020：Pillar-based Object Detection for Autonomous Driving
- 7. Sliding Shapes for 3D Object Detection in Depth Images
- 8. 論文閱讀CVPR2019——Stereo R-CNN based 3D Object Detection for Autonomous Driving
- 9. [論文解讀]Multi-View 3D Object Detection Network for Autonomous Driving
- 10. MV3D：Multi-View 3D Object Detection Network for Autonomous Driving（翻譯）