Multi-modal local receptive field extreme learning machine for object recognition

Liu, Huaping; Li, Fengxue; Xu, Xinying; Sun, Fuchun

doi:10.1016/j.neucom.2017.04.077

Cited by 32 publications

(9 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That in turn allows for combining even heterogeneous data from very different sources and lets the machine learning model to process joint representation in order to produce an output. That type of fusion is widely spread in robotics community in areas such as object recognition [19] and scene recognition [20] tasks. Multi-modal fusion applied to robot motion planning was presented in [21] and contact-rich manipulation tasks in [7].…”

Section: Data Fusion Approachesmentioning

confidence: 99%

On Robustness of Multi-Modal Fusion—Robotics Perspective

2020

View full text Add to dashboard Cite

The efficient multi-modal fusion of data streams from different sensors is a crucial ability that a robotic perception system should exhibit to ensure robustness against disturbances. However, as the volume and dimensionality of sensory-feedback increase it might be difficult to manually design a multimodal-data fusion system that can handle heterogeneous data. Nowadays, multi-modal machine learning is an emerging field with research focused mainly on analyzing vision and audio information. Although, from the robotics perspective, haptic sensations experienced from interaction with an environment are essential to successfully execute useful tasks. In our work, we compared four learning-based multi-modal fusion methods on three publicly available datasets containing haptic signals, images, and robots’ poses. During tests, we considered three tasks involving such data, namely grasp outcome classification, texture recognition, and—most challenging—multi-label classification of haptic adjectives based on haptic and visual data. Conducted experiments were focused not only on the verification of the performance of each method but mainly on their robustness against data degradation. We focused on this aspect of multi-modal fusion, as it was rarely considered in the research papers, and such degradation of sensory feedback might occur during robot interaction with its environment. Additionally, we verified the usefulness of data augmentation to increase the robustness of the aforementioned data fusion methods.

show abstract

Section: Data Fusion Approachesmentioning

confidence: 99%

On Robustness of Multi-Modal Fusion—Robotics Perspective

2020

View full text Add to dashboard Cite

show abstract

“…They fused separately processed RGB and depth images through a CCA layer and a combining layer was introduced to the multi-view CNN. H. Liu et al [21] developed an extreme learning machine (ELM) structure using a multi-modal local receptive field (MM-LRF). There, LRF is used as a feature extractor for each modality, and a shared layer is proposed for combining the features.…”

Section: Sustainable Multi-objects Recognition Via Depth Imagesmentioning

confidence: 99%

“…Finally, they used Hough voting for the recognition of the object. H. Liu et al [21] presented a multi-modal architecture named MM-ELM-LRF. They extracted features for both of the modalities (RGB and depth) by applying ELM-LRF.…”

Section: Rgb-d Object Rgb-d Scenes Nyudv1mentioning

confidence: 99%

Automated Sustainable Multi-Object Segmentation and Recognition via Modified Sampling Consensus and Kernel Sliding Perceptron

2020

View full text Add to dashboard Cite

Object recognition in depth images is challenging and persistent task in machine vision, robotics, and automation of sustainability. Object recognition tasks are a challenging part of various multimedia technologies for video surveillance, human–computer interaction, robotic navigation, drone targeting, tourist guidance, and medical diagnostics. However, the symmetry that exists in real-world objects plays a significant role in perception and recognition of objects in both humans and machines. With advances in depth sensor technology, numerous researchers have recently proposed RGB-D object recognition techniques. In this paper, we introduce a sustainable object recognition framework that is consistent despite any change in the environment, and can recognize and analyze RGB-D objects in complex indoor scenarios. Firstly, after acquiring a depth image, the point cloud and the depth maps are extracted to obtain the planes. Then, the plane fitting model and the proposed modified maximum likelihood estimation sampling consensus (MMLESAC) are applied as a segmentation process. Then, depth kernel descriptors (DKDES) over segmented objects are computed for single and multiple object scenarios separately. These DKDES are subsequently carried forward to isometric mapping (IsoMap) for feature space reduction. Finally, the reduced feature vector is forwarded to a kernel sliding perceptron (KSP) for the recognition of objects. Three datasets are used to evaluate four different experiments by employing a cross-validation scheme to validate the proposed model. The experimental results over RGB-D object, RGB-D scene, and NYUDv1 datasets demonstrate overall accuracies of 92.2%, 88.5%, and 90.5% respectively. These results outperform existing state-of-the-art methods and verify the suitability of the method.

show abstract

“…ELM can speed up learning by randomly generating input weights and hidden biases and by adopting Moore-Penrose (MP) generalized inversion to determine the output weights. Compared with the traditional gradient-based learning algorithms, ELM not only has faster learning speed and higher generalization performance, but also avoids the difficulties of stopping conditions, learning rate, learning cycle and local minimization encountered by gradient-based learning methods [8]. ELM and its variants [9][10][11] have been applied in many fields [12][13][14], including boiler combustion system modeling [15,16].…”

Section: Introductionmentioning

confidence: 99%

Combustion Optimization for Coal Fired Power Plant Boilers Based on Improved Distributed ELM and Distributed PSO

Chen

Ren

et al. 2019

Energies

Self Cite

View full text Add to dashboard Cite

Increasing the combustion efficiency of power plant boilers and reducing pollutant emissions are important for energy conservation and environmental protection. The power plant boiler combustion process is a complex multi-input/multi-output system, with a high degree of nonlinearity and strong coupling characteristics. It is necessary to optimize the boiler combustion model by means of artificial intelligence methods. However, the traditional intelligent algorithms cannot deal effectively with the massive and high dimensional power station data. In this paper, a distributed combustion optimization method for boilers is proposed. The MapReduce programming framework is used to parallelize the proposed algorithm model and improve its ability to deal with big data. An improved distributed extreme learning machine is used to establish the combustion system model aiming at boiler combustion efficiency and NOx emission. The distributed particle swarm optimization algorithm based on MapReduce is used to optimize the input parameters of boiler combustion model, and weighted coefficient method is used to solve the multi-objective optimization problem (boiler combustion efficiency and NOx emissions). According to the experimental analysis, the results show that the method can optimize the boiler combustion efficiency and NOx emissions by combining different weight coefficients as needed.

show abstract

Multi-modal local receptive field extreme learning machine for object recognition

Cited by 32 publications

References 1 publication

On Robustness of Multi-Modal Fusion—Robotics Perspective

On Robustness of Multi-Modal Fusion—Robotics Perspective

Automated Sustainable Multi-Object Segmentation and Recognition via Modified Sampling Consensus and Kernel Sliding Perceptron

Combustion Optimization for Coal Fired Power Plant Boilers Based on Improved Distributed ELM and Distributed PSO

Contact Info

Product

Resources

About