Pyramid-based Image Interpolation

Sujee, R.; Padmavathi, S

doi:10.1109/iccci.2018.8441313

Cited by 9 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, DMI simply reflects spatial information of actions in single scale. In order to capture multi-scale changes of human motions, we adopt the Gaussian pyramid transform which has been demonstrated the practicability in increasing scale diversity [27,29]. As shown in Fig.…”

Section: Proposed Methods For Human Action Recognitionmentioning

confidence: 99%

Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences

Huang

et al. 2021

Preprint

View full text Add to dashboard Cite

Human action recognition is an active research area in computer vision. Although great process has been made, previous methods mostly recognize actions based on depth data at only one scale, and thus they often neglect multi-scale features that provide additional information action recognition in practical application scenarios. In this paper, we present a novel framework focusing on multiscale motion information to recognize human actions from depth video sequences. We propose a multi-scale feature map called Laplacian pyramid depth motion images(LP-DMI). We employ depth motion images (DMI) as the templates to generate the multi-scale static representation of actions. Then, we caculate LP-DMI to enhance multi-scale dynamic information of motions and reduces redundant static information in human bodies. We further extract the multi-granularity descriptor called LP-DMI-HOG to provide more discriminative features. Finally, we utilize extreme learning machine (ELM) for action classification. The proposed method yeilds the recognition accuracy of 93.41%, 85.12%, 91.94% on public MSRAc-tion3D dataset, UTD-MHAD and DHA dataset. Through extensive experiments, we prove that our method outperforms state-of-the-art benchmarks.

show abstract

Section: Proposed Methods For Human Action Recognitionmentioning

confidence: 99%

Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences

Huang

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The use of image enhancement as a preliminary step to classification or segmentation problems is applicable for many computer vision use cases [11]. Superresolution networks are CNN based networks that are trained on high resolution images to serve the purpose of noise free image interpolation [12,13]. Image enhancement is essential for precise segmentation of floor plans; this was made very clear in the application by Han et al The use of a super-resolution framework called SRCNN enhances sectional 2D data for more precision on target output in their work [6].…”

Section: Literature Reviewmentioning

confidence: 99%

Enhanced Object Detection in Floor-plan through Super Resolution

Khare¹,

Kamal²,

HB³

et al. 2021

Preprint

View full text Add to dashboard Cite

Building Information Modelling (BIM) software use scalable vector formats to enable flexible designing of floor plans in the industry. Floor plans in the architectural domain can come from many sources that may or may not be in scalable vector format. The conversion of floor plan images to fully annotated vector images is a process that can now be realized by computer vision. Novel datasets in this field have been used to train Convolutional Neural Network (CNN) architectures for object detection. Image enhancement through Super-Resolution (SR) is also an established CNN based network in computer vision that is used for converting low resolution images to high resolution ones. This work focuses on creating a multi-component module that stacks a SR model on a floor plan object detection model. The proposed stacked model shows greater performance than the corresponding vanilla object detection model. For the best case, the the inclusion of SR showed an improvement of 39.47% in object detection over the vanilla network. Data and code are made publicly available at https://github.com/rbg-research/Floor-Plan-Detection.

show abstract

Plant Leaf Recognition Using Machine Learning Techniques

Sujee

Thangavel

2020

New Trends in Computational Vision and Bio-Inspired Computing

View full text Add to dashboard Cite

Pyramid-based Image Interpolation

Cited by 9 publications

References 4 publications

Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences

Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences

Enhanced Object Detection in Floor-plan through Super Resolution

Plant Leaf Recognition Using Machine Learning Techniques

Contact Info

Product

Resources

About