MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contexts

被引:8
|
作者
Wu, Zizhang [1 ]
Gan, Yuanzhu [1 ]
Wang, Lei [1 ]
Chen, Guilian [1 ]
Pu, Jian [2 ]
机构
[1] Zongmu Technol, Shanghai, Peoples R China
[2] Fudan Univ, Shanghai, Peoples R China
关键词
D O I
10.1109/ICRA48891.2023.10161442
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Monocular 3D object detection reveals an economical but challenging task in autonomous driving. Recently center-based monocular methods have developed rapidly with a great trade-off between speed and accuracy, where they usually depend on the object center's depth estimation via 2D features. However, the visual semantic features without sufficient pixel geometry information, may affect the performance of clues for spatial 3D detection tasks. To alleviate this, we propose MonoPGC, a novel end-to-end Monocular 3D object detection framework with rich Pixel Geometry Contexts. We introduce the pixel depth estimation as our auxiliary task and design depth cross-attention pyramid module (DCPM) to inject local and global depth geometry knowledge into visual features. In addition, we present the depth-space-aware transformer (DSAT) to integrate 3D space position and depth-aware features efficiently. Besides, we design a novel depth-gradient positional encoding (DGPE) to bring more distinct pixel geometry contexts into the transformer for better object detection. Extensive experiments demonstrate that our method achieves the state-of-the-art performance on the KITTI dataset.
引用
收藏
页码:4842 / 4849
页数:8
相关论文
共 50 条
  • [21] Monocular Object Detection Using 3D Geometric Primitives
    Carr, Peter
    Sheikh, Yaser
    Matthews, Iain
    COMPUTER VISION - ECCV 2012, PT I, 2012, 7572 : 864 - 878
  • [22] Monocular 3D Object Detection from Roadside Infrastructure
    Huang, Delu
    Wen, Feng
    2024 35TH IEEE INTELLIGENT VEHICLES SYMPOSIUM, IEEE IV 2024, 2024, : 1672 - 1677
  • [23] Dense-JANet for Monocular 3D Object Detection
    Shang, Xiaoqing
    Cheng, Zhiwei
    Shi, Su
    Cheng, Zhuanghao
    Huang, Hongcheng
    2020 IEEE 23RD INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), 2020,
  • [24] Monocular 3D object detection for an indoor robot environment
    Kim, Jiwon
    Lee, GiJae
    Kim, Jun-Sik
    Kim, Hyunwoo J.
    Kim, KangGeon
    2020 29TH IEEE INTERNATIONAL CONFERENCE ON ROBOT AND HUMAN INTERACTIVE COMMUNICATION (RO-MAN), 2020, : 438 - 445
  • [25] MonoCD: Monocular 3D Object Detection with Complementary Depths
    Yan, Longfei
    Yan, Pei
    Xiong, Shengzhou
    Xiang, Xuanyu
    Tan, Yihua
    2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2024, : 10248 - 10257
  • [26] A New Monocular 3D Object Detection with Neural Network
    Hong, Weijie
    Liu, Yiguang
    Zheng, Yunan
    Wang, Ying
    Shi, Xuelei
    PATTERN RECOGNITION AND COMPUTER VISION (PRCV 2018), PT IV, 2018, 11259 : 174 - 185
  • [27] 3D Visual Object Detection from Monocular Images
    Wang, Qiaosong
    Rasmussen, Christopher
    ADVANCES IN VISUAL COMPUTING, ISVC 2019, PT I, 2020, 11844 : 168 - 180
  • [28] Competition for roadside camera monocular 3D object detection
    Jia, Jinrang
    Shi, Yifeng
    Qu, Yuli
    Wang, Rui
    Xu, Xing
    Zhang, Hai
    NATIONAL SCIENCE REVIEW, 2023, 10 (06)
  • [29] Monocular 3D Object Detection with Depth from Motion
    Wang, Tai
    Pang, Jiangmiao
    Lin, Dahua
    COMPUTER VISION, ECCV 2022, PT IX, 2022, 13669 : 386 - 403
  • [30] Objects are Different: Flexible Monocular 3D Object Detection
    Zhang, Yunpeng
    Lu, Jiwen
    Zhou, Jie
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 3288 - 3297