Abstract
Anchor box mechanism is of vital importance for deep network based object detection. Current object detectors put anchors uniformly in the entire image, so the false positives along with training and testing costs are increased significantly. In this work, we break through the homogeneity limitation in anchor putting by introducing geometric constraints for pedestrian detection. We first deduce the relationship between the height of the pedestrian and its location in image plane using geometrical priors, for which we only need to know the rough relative height between camera and pedestrian. As a result, we narrow down the distribution space of anchors with a certain pixel height from 2D to 1D. In implementation, we propose a novel Geometric Constrained Loss, by which the new anchor mechanism is embedded into the deep learning architecture. To further remove false positives in inference, Geometric Constrained Suppression is introduced. Complemented with two effective prediction modules, Dilated Double Shots Detector is designed to achieve better performance. Comprehensive experiments conducted on KITTI and Caltech datasets validate the superior performance and generalization ability of our method for both one-stage and two-stage methods, in both training and inference phases.
This research is supported by the funding from NSFC programs (61673269, 61273285, U1764264).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Seriously occluded and truncated examples are ignored.
References
Benenson, R., Mathias, M., Timofte, R., Van Gool, L.: Pedestrian detection at 100 frames per second. In: CVPR, pp. 2903–2910. IEEE (2012)
Benenson, R., Timofte, R., Van Gool, L.: Stixels estimation without depth map computation. In: ICCV Workshops, pp. 2010–2017. IEEE (2011)
Cai, Z., Fan, Q., Feris, R.S., Vasconcelos, N.: A unified multi-scale deep convolutional neural network for fast object detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 354–370. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_22
Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., Urtasun, R.: Monocular 3D object detection for autonomous driving. In: CVPR, pp. 2147–2156 (2016)
Chen, X., et al.: 3D object proposals for accurate object class detection. In: NIPS, pp. 424–432 (2015)
Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS, pp. 379–387 (2016)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. CVPR 2005. vol. 1, pp. 886–893. IEEE (2005)
Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: CVPR, pp. 304–311 (2009)
Eckstein, M.P., Koehler, K., Welbourne, L.E., Akbas, E.: Humans, but not deep neural networks, often miss giant targets in scenes. Curr. Biol. 27(18), 2827–2832 (2017)
Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR, pp. 1–8 (2008)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. TPAMI 32(9), 1627–1645 (2010)
Fu, C.Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: DSSD: deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 (2017)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the KITTI vision benchmark suite. In: CVPR, pp. 3354–3361 (2012)
Gidaris, S., Komodakis, N.: LocNet: improving localization accuracy for object detection. In: CVPR, pp. 789–798 (2016)
Girshick, R.: Fast R-CNN. In: ICCV, pp. 1440–1448 (2015)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580–587 (2014)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2980–2988 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Hoiem, D., Efros, A.A., Hebert, M.: Putting objects in perspective. IJCV 80(1), 3–15 (2008)
Hu, P., Ramanan, D.: Finding tiny faces. In: CVPR, pp. 1522–1530 (2017)
Huang, J., et al.: Speed/accuracy trade-offs for modern convolutional object detectors. In: CVPR (2017)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML, pp. 448–456 (2015)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: ICCV (2017)
Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Liu, W., Rabinovich, A., Berg, A.C.: ParseNet: looking wider to see better. arXiv preprint arXiv:1506.04579 (2015)
Mao, J., Xiao, T., Jiang, Y., Cao, Z.: What can help pedestrian detection? In: CVPR, p. 3 (2017)
Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483–499. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_29
Park, D., Ramanan, D., Fowlkes, C.: Multiresolution models for object detection. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 241–254. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15561-1_18
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: CVPR, pp. 779–788 (2016)
Redmon, J., Farhadi, A.: YOLO9000: Better, Faster, Stronger. arXiv preprint arXiv:1612.08242 (2016)
Ren, J., et al.: Accurate single stage detector using recurrent rolling convolution. In: CVPR, pp. 752–760 (2017)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91–99 (2015)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. IJCV 115(3), 211–252 (2015)
Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: CVPR, pp. 761–769 (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Sudowe, P., Leibe, B.: Efficient use of geometric constraints for sliding-window object detection in video. In: Crowley, J.L., Draper, B.A., Thonnat, M. (eds.) ICVS 2011. LNCS, vol. 6962, pp. 11–20. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-23968-7_2
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: AAAI, pp. 4278–4284 (2017)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR, pp. 2818–2826 (2016)
Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. IJCV 104(2), 154–171 (2013)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR (2016)
Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: CVPR, p. 2 (2017)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn., January 2006
Zitnick, C.L., Dollár, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 391–405. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_26
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Fang, L., Zhao, X., Song, X., Zhang, S., Yang, M. (2019). Putting the Anchors Efficiently: Geometric Constrained Pedestrian Detection. In: Jawahar, C., Li, H., Mori, G., Schindler, K. (eds) Computer Vision – ACCV 2018. ACCV 2018. Lecture Notes in Computer Science(), vol 11365. Springer, Cham. https://doi.org/10.1007/978-3-030-20873-8_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-20873-8_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20872-1
Online ISBN: 978-3-030-20873-8
eBook Packages: Computer ScienceComputer Science (R0)