Abstract
In this paper we reinvestigate Deep Convolutional Neural Networks (DCNNs) for RGB-D based object recognition. A previously proposed method in which DCNNs are pretrained on a large-scale RGB database and just fine-tuned to process colorized depth images is taken up and extended. We introduce and analyse multiple solutions to improve depth colorization and propose a new method for depth colorization based on surface normals. We show that our improvements increase the classification accuracy significantly, such that we can present new state-of-the-art results for the Washington RGB-D dataset. Our results also indicate that classification using only surface normals without RGB images outperforms classification using pure RGB images, which is to our knowledge a novel discovery in the field of DCNNs.
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
References
Asif, U., Bennamoun, M., Sohel, F.: Efficient RGB-D object categorization using cascaded ensembles of randomized decision trees. In: IEEE International Conference on Robotics and Automation, ICRA 2015, pp. 1295–1302 (2015)
Blum, M., Springenberg, J., Wuelfing, J., Riedmiller, M.: A learned feature descriptor for object recognition in RGB-D data. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pp. 1298–1303 (2012)
Bo, L., Lai, K., Ren, X., Fox, D.: Object recognition with hierarchical kernel descriptors. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1729–1736 (2011)
Bo, L., Ren, X., Fox, D.: Depth kernel descriptors for object recognition. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 821–826 (2011)
Bo, L., Ren, X., Fox, D.: Unsupervised feature learning for RGB-D based object recognition. In: Proceedings of the International Symposium on Experimental Robtics (ISER), pp. 387–402 (2012)
Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 248–255 (2009)
Donahue, J.: Caffenet. https://github.com/BVLC/caffe/tree/master/models/bvlc_reference_caffenet. Accessed 26 Feb 2016
Eitel, A., Springenberg, J.T., Spinello, L., Riedmiller, M., Burgaard, W.: Multimodal deep learning for robust RGB-D object recognition. In: IROS Conference, pp. 681–687 (2015)
Gupta, S., Girshick, R., Arbeláez, P., Malik, J.: Learning rich features from RGB-D images for object detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VII. LNCS, vol. 8695, pp. 345–360. Springer, Heidelberg (2014)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1106–1114 (2012)
Lai, K., Bo, L., Ren, X., Fox, D.: A large-scale hierarchical multi-view RGB-D object dataset. In: Proceedings of the IEEE International Conference on Robotics, pp. 1817–1824 (2011)
Schwarz, M., Schulz, H., S.B.: RGB-D object recognition and pose estimation based on pre-trained convolutional neural network features. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 1329–1335 (2015)
Socher, R., Huval, B., Bhat, B., Manning, C., Ng, A.: Convolutional-recursive deep learning for 3D object classification. Adv. Neural Inf. Process. Syst. (NIPS) 25, 656–664 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Madai-Tahy, L., Otte, S., Hanten, R., Zell, A. (2016). Revisiting Deep Convolutional Neural Networks for RGB-D Based Object Recognition. In: Villa, A., Masulli, P., Pons Rivero, A. (eds) Artificial Neural Networks and Machine Learning – ICANN 2016. ICANN 2016. Lecture Notes in Computer Science(), vol 9887. Springer, Cham. https://doi.org/10.1007/978-3-319-44781-0_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-44781-0_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-44780-3
Online ISBN: 978-3-319-44781-0
eBook Packages: Computer ScienceComputer Science (R0)