Background Subtraction on Depth Videos with Convolutional Neural Networks

Liu, Lei; Li, Guangli; Dong, Xiao; Zhao, Peng; Feng, Xiaobing

doi:10.1109/ijcnn.2018.8489230

Cited by 17 publications

(16 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve this problem, the data was normalized through equation 1. Therefore, the data range was converted to a range of 0 and 1[32]. In Equation 1, R is the input image matrix and R * is the post-normalization raw image.…”

Section: Preprocess and Augmentation Pipelinementioning

confidence: 99%

See 1 more Smart Citation

Depth Dataset Using Microsoft Kinect-v2

Heravi

Delgarmi

et al. 2021

Preprint

View full text Add to dashboard Cite

In biomedical imaging studies, numerous methods have been used to capture human data, mostly by using magnetic resonance imaging (MRI) and computed tomography (CT). However, due to being inexpensive and accessibility of Microsoft Kinect, its usage has been significantly increased in recent years. In this study, we aimed to represent the procedure of data acquisition, which includes a set of depth images from individuals’ back surfaces. The goal of image acquisition is to investigate spinal deformities and landmark detection of the back surface. Traditional imaging systems are challenging, most notably because of ionized beams in the data acquisition process, which has not been solved yet. Indeed, noninvasiveness is the most crucial advantage of our study. Our imaging system was set in a dim laboratory, and the University approved the ethical letter of Medical Sciences before data acquisition. After that, the subjects (total 105; 50 women and 55 men) were recruited, and data images were captured from the back surface. Then, we increased the imaging data size by using the augmentation method to use deep learning methods in future works. Finally, this Dataset leads us to the desired output in our study procedure.

show abstract

Section: Preprocess and Augmentation Pipelinementioning

confidence: 99%

“…(3) Figure 7 shows an example of vector maps obtained by the above method. Given the nature of the Kinect sensor, the derived depth images are very noisy [7]. Hence, it is necessary to apply a preprocessing step to improve the quality of the depth image.…”

Section: -1-1-groundtruth Translation (Or Annotation Technique)mentioning

confidence: 99%

Depth Dataset Using Microsoft Kinect-v2

Heravi

Delgarmi

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Wang et al [213] proposed a CNN based approach for background subtraction on depth videos called BGSNet-D (BackGround Subtraction neural Networks for Depth video). The objective is to use only depth data for background subtraction in order to deal with scenarios where color information is not available.…”

Section: Current Research Trends and Future Research Directionsmentioning

confidence: 99%

A Comprehensive Survey of Video Datasets for Background Subtraction

Kalsotra

Arora

2019

IEEE Access

View full text Add to dashboard Cite

Background subtraction is an effective method of choice when it comes to detection of moving objects in videos and has been recognized as a breakthrough for the wide range of applications of intelligent video analytics (IVA). In recent years, a number of video datasets intended for background subtraction have been created to address the problem of large realistic datasets with accurate ground truth. The use of these datasets enables qualitative as well as quantitative comparisons and allows benchmarking of different algorithms. Finding the appropriate dataset is generally a cumbersome task for an exhaustive evaluation of algorithms. Therefore, we systematically survey standard video datasets and list their applicability for different applications. This paper presents a comprehensive account of public video datasets for background subtraction and attempts to cover the lack of a detailed description of each dataset. The video datasets are presented in chronological order of their appearance. Current trends of deep learning in background subtraction along with top-ranked background subtraction methods are also discussed in this paper. The survey introduced in this paper will assist researchers of the computer vision community in the selection of appropriate video dataset to evaluate their algorithms on the basis of challenging scenarios that exist in both indoor and outdoor environments.INDEX TERMS Background model, background subtraction, challenges, datasets, deep neural networks, foreground, intelligent video analytics (IVA), video frames.

show abstract

“…Lim et al used an encoder-decoder-structured convolutional neural network for background subtraction [32]. Wang et al used BGSNet-D to detect moving objects in the scenes where color information was not available [33]. Yu et al [34] combined background subtraction and CNN for moving objects detection in pumping-unit scene.…”

Section: Introductionmentioning

confidence: 99%

“…Table 1 shows an overview of these methods. [32] Wang [33] Fully CNNs Zeng [23,35] learned supervised specific Cinelli [24] Yang [26] In this paper, a novel framework based on CNN is proposed to improve background subtraction. In the proposed method, the lower convolution layers are used to extract the general features of a video.…”

Section: Introductionmentioning

confidence: 99%

Refinement of Background-Subtraction Methods Based on Convolutional Neural Network Features for Dynamic Background

Yang

2019

Algorithms

View full text Add to dashboard Cite

Advancing the background-subtraction method in dynamic scenes is an ongoing timely goal for many researchers. Recently, background subtraction methods have been developed with deep convolutional features, which have improved their performance. However, most of these deep methods are supervised, only available for a certain scene, and have high computational cost. In contrast, the traditional background subtraction methods have low computational costs and can be applied to general scenes. Therefore, in this paper, we propose an unsupervised and concise method based on the features learned from a deep convolutional neural network to refine the traditional background subtraction methods. For the proposed method, the low-level features of an input image are extracted from the lower layer of a pretrained convolutional neural network, and the main features are retained to further establish the dynamic background model. The evaluation of the experiments on dynamic scenes demonstrates that the proposed method significantly improves the performance of traditional background subtraction methods.

show abstract

Background Subtraction on Depth Videos with Convolutional Neural Networks

Cited by 17 publications

References 30 publications

Depth Dataset Using Microsoft Kinect-v2

Depth Dataset Using Microsoft Kinect-v2

A Comprehensive Survey of Video Datasets for Background Subtraction

Refinement of Background-Subtraction Methods Based on Convolutional Neural Network Features for Dynamic Background

Contact Info

Product

Resources

About