Exploiting multi-layer features using a CNN-RNN approach for RGB-D object recognition
15th European Conference on Computer Vision, ECCV 2018, Munich, Almanya, 8 - 14 Eylül 2018, cilt.11131 LNCS, ss.675-688, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Cilt numarası: 11131 LNCS
- Doi Numarası: 10.1007/978-3-030-11015-4_51
- Basıldığı Şehir: Munich
- Basıldığı Ülke: Almanya
- Sayfa Sayıları: ss.675-688
- Anahtar Kelimeler: Convolutional neural network, Recursive neural network, RGB-D object recognition, Transfer learning
- Hacettepe Üniversitesi Adresli: Evet
Özet
This paper proposes an approach for RGB-D object recognition by integrating a CNN model with recursive neural networks. It first employs a pre-trained CNN model as the underlying feature extractor to get visual features at different layers for RGB and depth modalities. Then, a deep recursive model is applied to map these features into high-level representations. Finally, multi-level information is fused to produce a strong global representation of the entire object image. In order to utilize the CNN model trained on large-scale RGB datasets for depth domain, depth images are converted to a representation similar to RGB images. Experimental results on the Washington RGB-D Object dataset show that the proposed approach outperforms previous approaches.