Vehicle 3D Space Detection Method Based on Monocular Vision

doi:10.12068/j.issn.1005-3026.2022.03.004

Abstract

Abstract: Aiming at the problem of low detection precision of 3D bounding box based on monocular vehicle detection， a new network method based on improved FPN (feature pyramid networks) feature fusion， ResNet residual unit， and fully connected layer was proposed. In the training phase， the three-dimensional size of vehicles， residual angle and confidence are regressed. In the reasoning phase， the three-dimensional size and local angle(α)of vehicles are detected. The 3D bounding box of vehicles are reconstructed and drawn from the center coordinates， the three-dimensional size of vehicles， the yaw angle(θ)， and the camera intrinsic matrix. The proposed method is tested on the KITTI verification set. Compared with the results of the original method， the proposed method improves the average precision of 3D bounding box of vehicles(AP_3D)to 0.60%， 1.37%， and 1.41%， respectively， under the three detection levels of easy， moderate and difficult.

Key words: feature fusion; monocular vehicle detection; computer vision; deep learning; KITTI

CLC Number:

TP181

GU De-ying， ZHANG Song， MENG Fan-wei. Vehicle 3D Space Detection Method Based on Monocular Vision[J]. Journal of Northeastern University(Natural Science), 2022, 43(3): 328-334.

References

[1]张鹏，宋一凡，宗立波，等.3D目标检测进展综述［J］.计算机科学，2020，47(4):94-102.(Zhang Peng，Song Yi-fan，Zong Li-bo，et al.Review of 3D object detection ［J］.Computer Science，2020，47(4):94-102.)
[2]Chen X，Kundu K，Zhang Z，et al.Monocular 3D object detection for autonomous driving［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE，2016:2147-2156.
[3]Pavlakos G，Zhou X，Chan A，et al.6-DoF object pose from semantic keypoints［C］//2017 IEEE International Conference on Robotics and Automation(ICRA).Singapore:IEEE，2017:2011-2018.
[4]Roddick T，Kendall A，Cipolla R，et al.Orthographic feature transform for monocular 3D object detection［J］.arXiv preprint arXiv:1811.08188，2018.
[5]Brazil G，Liu X.M3d-rpn:monocular 3D region proposal network for object detection［C］//Proceedings of the IEEE International Conference on Computer Vision.Seoul:IEEE，2019:9287-9296.
[6]Weng X，Kitani K.Monocular 3D object detection with pseudo-lidar point cloud［C］//International Conference on Computer Vision Workshops.Seoul:IEEE，2019:857-866.
[7]Liu Z，Wu Z，Tóth R.Smoke:single-stage monocular 3d object detection via key-point-estimation［C］//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.Seattle:IEEE，2020:996-997.
[8]Mousavian A，Anguelov D，Flynn J，et al.3D bounding box estimation using deep learning and geometry［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE，2017:7074-7082.
[9]Simonyan K，Zisserman A.Very deep convolutional networks for large-scale image recognition［J］.arXiv preprint arXiv:1409.1556，2014.
[10]Lin T Y，Dollár P，Girshick R，et al.Feature pyramid networks for object detection ［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE，2017:2117-2125.
[11]He K，Zhang X，Ren S，et al.Deep residual learning for image recognition［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE，2016:770-778.
[12]Shen F，Gan R，Zeng G.Weighted residuals for very deep networks［C］//2016 3rd Internationl Conference on Systems and Informatics(ICSAI).Shanghai:IEEE，2016:936-941.
[13]Clevert D A，Unterthiner T，Hochreiter S.Fast and accurate deep network learning by exponential linear units(elus)［J］.arXiv preprint arXiv:1511.07289，2015.
[14]Chen X，Kundu K，Zhu Y，et al.3D object proposals using stereo imagery for accurate object class detection［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，40(5):1259-1272.
[15]Xiang Y，Choi W，Lin Y，et al.Data-driven 3D voxel patterns for object category recognition［C］//Proceedings of the IEEE Conferenceon Computer Vision and Pattern Recognition.Boston:IEEE，2015:1903-1911.