Logo image
A Multi-modal, discriminative and spatially invariant CNN for RGB-D object labeling
Journal article   Peer reviewed

A Multi-modal, discriminative and spatially invariant CNN for RGB-D object labeling

U. Asif, M. Bennamoun and F. Sohel
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.40(9), pp.2051-2065
2017
url
Link to Published Version *Subscription may be requiredView

Abstract

While deep convolutional neural networks have shown a remarkable success in image classification, the problems of inter-class similarities, intra-class variances, the effective combination of multimodal data, and the spatial variability in images of objects remain to be major challenges. To address these problems, this paper proposes a novel framework to learn a discriminative and spatially invariant classification model for object and indoor scene recognition using multimodal RGB-D imagery. This is achieved through three postulates: 1) spatial invariance - this is achieved by combining a spatial transformer network with a deep convolutional neural network to learn features which are invariant to spatial translations, rotations, and scale changes, 2) high discriminative capability - this is achieved by introducing Fisher encoding within the CNN architecture to learn features which have small inter-class similarities and large intra-class compactness, and 3) multimodal hierarchical fusion - this is achieved through the regularization of semantic segmentation to a multi-modal CNN architecture, where class probabilities are estimated at different hierarchical levels (i.e., imageand pixel-levels), and fused into a Conditional Random Field (CRF)- based inference hypothesis, the optimization of which produces consistent class labels in RGB-D images. Extensive experimental evaluations on RGB-D object and scene datasets, and live video streams (acquired from Kinect) show that our framework produces superior object and scene classification results compared to the state-of-the-art methods.

Details

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

#3 Good Health and Well-Being

Source: InCites

Metrics

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types
Domestic collaboration
Citation topics
4 Electrical Engineering, Electronics & Computer Science
4.17 Computer Vision & Graphics
4.17.128 Deep Visual Recognition
Web Of Science research areas
Computer Science, Artificial Intelligence
Engineering, Electrical & Electronic
ESI research areas
Engineering
Logo image