RGB-D object recognition based on the joint deep random kernel convolution and ELM

@article{Yin2020RGBDOR,
  title={RGB-D object recognition based on the joint deep random kernel convolution and ELM},
  author={Yunhua Yin and Huifang Li},
  journal={Journal of Ambient Intelligence and Humanized Computing},
  year={2020},
  pages={1-10}
}
  • Yunhua Yin, Huifang Li
  • Published 28 September 2018
  • Computer Science
  • Journal of Ambient Intelligence and Humanized Computing
Nowadays RGB-D object recognition has been a challenging and important task in computer vision field. Convolutional Neural Network is a current popular algorithm for feature extraction from RGB and Depth modality separately, which cannot fully exploit some potential and complementary information between different modalities. The conventional training methods designed for CNN involve many gradient-descent searching, and usually face some troubles such as time-consuming convergence, local minima… 
2 Citations
Extreme learning machine with coefficient weighting and trained local receptive fields for image classification
TLDR
The proposed extreme learning machine with coefficient weighting and trained local receptive fields (ELM-WLRF) achieves superior classification accuracy, and requires shorter training time compared with other state-of-the-art ELM-LRF-based algorithms.
Convolutional Extreme Learning Machines: A Systematic Review
TLDR
A systematic review that investigates alternative deep learning architectures that use extreme learning machine (ELM) for a faster training to solve problems based on image analysis to cope with some of the current problems in the image-based computer vision analysis.

References

SHOWING 1-10 OF 47 REFERENCES
Large-Margin Multi-Modal Deep Learning for RGB-D Object Recognition
TLDR
Experimental results on two widely used RGB-D object datasets show that the proposed general CNN-based multi-modal learning framework achieves comparable performance to state-of-the-art methods specifically designed forRGB-D data.
Convolutional-Recursive Deep Learning for 3D Object Classification
TLDR
This work introduces a model based on a combination of convolutional and recursive neural networks (CNN and RNN) for learning features and classifying RGB-D images, which obtains state of the art performance on a standardRGB-D object dataset while being more accurate and faster during training and testing than comparable architectures such as two-layer CNNs.
Semi-supervised Learning for RGB-D Object Recognition
TLDR
A new semi-supervised learning framework based on RGB and depth (RGB-D) images to improve object recognition and can compete against with other state-of-the-art methods with only 20% labeled data.
A learned feature descriptor for object recognition in RGB-D data
TLDR
A new, learned, local feature descriptor for RGB-D images, the convolutional k-means descriptor, which automatically learns feature responses in the neighborhood of detected interest points and is able to combine all available information, such as color and depth into one, concise representation.
Multi-Modal Local Receptive Field Extreme Learning Machine for object recognition
TLDR
This paper proposes an effective Multi-Modal Local Receptive Field Extreme Learning Machine (MM-ELM-LRF) structure, while maintaining ELM's advantages of training efficiency, and shows that the proposed multiple modality fusion method achieves better recognition performance.
HandSense: smart multimodal hand gesture recognition based on deep neural networks
TLDR
The HandSense is proposed, a new system for the multi-modal HGR based on a combined RGB and depth cameras to improve the fine-grained action descriptors as well as preserve the ability to perform general action recognition.
RGB-D Object Recognition: Features, Algorithms, and a Large Scale Benchmark
TLDR
A large-scale, hierarchical multi-view object dataset collected using an RGB-D camera is introduced and it is demonstrated that combining color and depth information substantially improves quality of results.
Unsupervised Feature Learning for RGB-D Based Object Recognition
TLDR
HMP uses sparse coding to learn hierarchical feature representations from raw RGB-D data in an unsupervised way and enables superior object recognition results using linear support vector machines.
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
...
...