Abstract
3D object detection is one of the most challenging research tasks in computer vision. In order to solve the problem of template information dependency of 3D object proposal in the method of 3D object detection based on 2.5D information, we proposed a 3D object detector based on fusion of vanishing point and prior orientation, which estimates an accurate 3D proposal from 2.5D data, and provides an excellent start point for 3D object classification and localization. The algorithm first calculates three mutually orthogonal vanishing points by the Euler angle principle and projects them into the pixel coordinate system. Then, the top edge of the 2D proposal is sampled by the preset sampling pitch, and the first one vertex is taken. Finally, the remaining seven vertices of the 3D proposal are calculated according to the linear relationship between the three vanishing points and the vertices, and the complete information of the 3D proposal is obtained. The experimental results show that this proposed method improves the Mean Average Precision score by 2.7% based on the Amodal3Det method.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ross G, Jeff D, Trevor D, et al. Rich feature hierarchies for accurate object detection and semantic segmentation [C]// 2014 Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 580–587.
Girshick R. Fast R-CNN [C]// 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 1440–1448.
Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137–1149.
Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 779–788.
Redmon J, Farhadi A. YOLO9000: Better, faster, stronger [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6517–6525.
Liu W, Anguelov D, Erhan D, et al. SSD: Single shot multibox detector [C]// European Conference on Computer Vision. Heidelberg: Springer-Verlag, 2016: 21–37.
Bao Z, Lyu C. Real-time hand gesture recognition based on Kinect [J]. Progress in Laser and Optoelectronics, 2018, 55(03): 031008.
Gupta S, Arbelaez P, Malik J. Perceptual organization and recognition of indoor scenes from RGB-D images [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2013: 564–571.
Bo L, Ren X, Fox D. Unsupervised feature learning for RGB-D based object recognition [C]// Experimental Robotics. Heidelberg: Springer-Verlag, 2013: 387–402.
Bo L, Ren X, Fox D. Learning hierarchical sparse features for RGB-D object recognition [J]. The International Journal of Robotics Research, 2014, 33(4): 581–599.
Socher R, Huval B, Bath B, et al. Convolutional-recursive deep learning for 3D object classification [C]// Advances in Neural Information Processing Systems. 2012: 656–664.
Gupta S, Girshick R, Arbeláez P, et al. Learning rich features from RGB-D images for object detection and segmentation [C]// European Conference on Computer Vision. Heidelberg: Springer-Verlag, 2014: 345–360.
Gupta S, Arbeláez P, Girshick R, et al. Aligning 3D models to RGB-D images of cluttered scenes [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015: 4731–4740.
Gupta S, Hoffman J, Malik J. Cross modal distillation for supervision transfer [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 2827–2836.
Su H, Maji S, Kalogerakis E, et al. Multi-view convolutional neural networks for 3D shape recognition [C]// Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 945–953.
Deng Z, Jan L. Amodal detection of 3D objects: Inferring 3D bounding boxed from 2D ones in RGB-depth images [C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 1063–6919.
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition [EB/OL]. [2018-09-04]. https://arxiv.org/abs/1409.1556.
Fang Z, Zhao H, Gao Y. Prior direction angle estimation in 3D object detection [J]. Transducer and Microsystem Technologies, 2019, 38(6): 35–38.
Song S R, Xiao J X. Sliding shapes for 3D object detection in depth images [C]//2014 European Conference on Computer Vision. Heidelberg: Springer-Verlag, 2014: 634–651.
Song S R, Xiao J X. Deep sliding shapes for amodal 3D object detection in RGB-D images [J]. Computer Science, 2015, 139(2): 808–816.
Ren Z, Sudderth E B. Three-dimensional object detection and layout prediction using clouds of oriented gradients [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 1525–1533.
Slabaugh G G. Computing Euler angles from a rotation matrix [J]. Retrieved on August, 1999, 6(2000): 39–63.
Yang S, Scherer S. CubeSLAM: Monocular 3D object detection and SLAM without prior models [EB/OL]. [2018-06-01]. https://arxiv.org/abs/1806.00557.
Author information
Authors and Affiliations
Corresponding author
Additional information
Foundation item: Supported by the National Natural Science Foundation of China (61772328, 61802253, 61831018)
Biography: GAO Yongbin, male, Ph. D., Associate professor, research direction: machine learning, computer vision.
Rights and permissions
About this article
Cite this article
Gao, Y., Zhao, H., Fang, Z. et al. 3D Object Detection Based on Vanishing Point and Prior Orientation. Wuhan Univ. J. Nat. Sci. 24, 369–375 (2019). https://doi.org/10.1007/s11859-019-1408-4
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11859-019-1408-4