Abstract
When merging existing similar datasets, it would be attractive to benefit from a higher detection rate of objects and the additional partial ground-truth samples for improving object classification. To this end, a novel CNN detector with a hierarchical binary classification system is proposed. The detector is based on the Single-Shot multibox Detector (SSD) and inspired by the hierarchical classification used in the YOLO9000 detector. Localization and classification are separated during training, by introducing a novel loss term that handles hierarchical classification in the loss function (SSD-ML). We experiment with the proposed SSD-ML detector on the generic PASCAL VOC dataset and show that additional super-categories can be learned with minimal impact on the overall accuracy. Furthermore, we find that not all objects are required to have classification label information as classification performance only drops from \(73.3\%\) to \(70.6\%\) while \(60\%\) of the label information is removed. The flexibility of the detector with respect to the different levels of details in label definitions is investigated for a traffic surveillance application, involving public and proprietary datasets with non-overlapping class definitions. Including classification label information from our dataset raises the performance significantly from \(70.7\%\) to \(82.2\%\). The experiments show that the desired hierarchical labels can be learned from the public datasets, while only using box information from our dataset. In general, this shows that it is possible to combine existing datasets with similar object classes and partial annotations and benefit in terms of growth of detection rate and improved class categorization performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bertinetto, L., Mueller, R., Tertikas, K., Samangooei, S., Lord, N.A.: Making better mistakes: leveraging class hierarchies with deep networks. In: Proceedings of the IEEE/CVF CVPR (2020)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE CVPR, vol. 1, pp. 886–893. IEEE (2005)
Everingham, M., et al.: The PASCAL visual object classes challenge 2012 (VOC2012) results (2012)
Everingham, M., et al.: The PASCAL visual object classes challenge 2007 (VOC2007) results (2007)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE CVPR (2014)
He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)
Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. IJCV (2020)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE ICCV, pp. 2980–2988 (2017)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
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
Luo, Z., et al.: MIO-TCD: a new benchmark dataset for vehicle classification and localization. IEEE Trans. Image Proc. 27(10), 5129–5141 (2018). https://doi.org/10.1109/TIP.2018.2848705
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR, pp. 779–788 (2016). https://doi.org/10.1109/CVPR.2016.91
Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: CVPR, pp. 6517–6525 (2017). https://doi.org/10.1109/CVPR.2017.690
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)
Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE ICCV, pp. 9627–9636 (2019)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE CVPR (2001)
Wen, L., et al.: UA-DETRAC: a new benchmark and protocol for multi-object detection and tracking. arXiv CoRR abs/1511.04136 (2015)
Zou, Z., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: a survey (2019)
Zwemer., M.H., Wijnhoven., R.G.J., de With., P.H.N.: SSD-ML: hierarchical object classification for traffic surveillance. In: Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISAPP, vol. 5, pp. 250–259 (2020). https://doi.org/10.5220/0008902402500259
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Zwemer, M.H., Wijnhoven, R.G.J., de With, P.H.N. (2022). Hierarchical Object Detection and Classification Using SSD Multi-Loss. In: Bouatouch, K., et al. Computer Vision, Imaging and Computer Graphics Theory and Applications. VISIGRAPP 2020. Communications in Computer and Information Science, vol 1474. Springer, Cham. https://doi.org/10.1007/978-3-030-94893-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-94893-1_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-94892-4
Online ISBN: 978-3-030-94893-1
eBook Packages: Computer ScienceComputer Science (R0)