Moving Object Detection in Video via Hierarchical Modeling and Alternating Optimization

Li, Linhao; Hu, Qinghua; Li, Xin

doi:10.1109/tip.2018.2882926

Cited by 26 publications

(28 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method is the underlying principle of the HOG (Histogram of Oriented Gradients) feature descriptor. The other commonly used method to count objects is through background subtraction [38]. It works on the principle of assuming that the background is static and thus the comparison of two frames can be used to identify differences.…”

Section: Artycul Prototypementioning

confidence: 99%

ARTYCUL: A Privacy-Preserving ML-Driven Framework to Determine the Popularity of a Cultural Exhibit on Display

Tanwar

Chauhan

Yafi

2021

Sensors

View full text Add to dashboard Cite

We present ARTYCUL (ARTifact popularitY for CULtural heritage), a machine learning(ML)-based framework that graphically represents the footfall around an artifact on display at a museum or a heritage site. The driving factor of this framework was the fact that the presence of security cameras has become universal, including at sites of cultural heritage. ARTYCUL used the video streams of closed-circuit televisions (CCTV) cameras installed in such premises to detect human figures, and their coordinates with respect to the camera frames were used to visualize the density of visitors around the specific display items. Such a framework that can display the popularity of artifacts would aid the curators towards a more optimal organization. Moreover, it could also help to gauge if a certain display item were neglected due to incorrect placement. While items of similar interest can be placed in vicinity of each other, an online recommendation system may also use the reputation of an artifact to catch the eye of the visitors. Artificial intelligence-based solutions are well suited for analysis of internet of things (IoT) traffic due to the inherent veracity and volatile nature of the transmissions. The work done for the development of ARTYCUL provided a deeper insight into the avenues for applications of IoT technology to the cultural heritage domain, and suitability of ML to process real-time data at a fast pace. While we also observed common issues that hinder the utilization of IoT in the cultural domain, the proposed framework was designed keeping in mind the same obstacles and a preference for backward compatibility.

show abstract

Section: Artycul Prototypementioning

confidence: 99%

ARTYCUL: A Privacy-Preserving ML-Driven Framework to Determine the Popularity of a Cultural Exhibit on Display

Tanwar

Chauhan

Yafi

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Then, structural features of pixel-wise or region-wise spatiotemporal relationships of adjacent pixels are generally considered robust enough to video noises: temporal information that contained in object motion are extracted to assist background subtraction in [44] and the framework is then improved in [45]; in [46], spatial descriptors produced by saliency detectors are integrated with shape constraint to constrain the moving objects; a spatiotemporal slice-based SVD is proposed by Kajo et al to produce more effective tensor completion in 2018 [47]; in 2019, [20] proposes a pixel-wise short term temporal quantization way to extract detail background patches.…”

Section: Spatiotemporal Solutionsmentioning

confidence: 99%

“…These sparsity based background modeling ways have attracted more attentions in the past few years, as the sparsity constraint usually results in algorithms with stable performance and high generalization ability. Common constraints for background includes low-rank [19], rank-1 [20] and sparse coding [21]. Comparisons of the above two unsupervised ways can be queried in [22].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Tensor Foreground-Background Separation Algorithm Based on Dynamic Dictionary Update and Active Contour Detection

Pei

Yang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Foreground-background separation of surveillance video, that models static background and extracts moving foreground simultaneously, attracts increasing attentions in building a smart city. Conventional techniques towards this always consider the background as primary target and tend to adopt low-rank constraint as its estimator, which provides finite (equal to the value of rank) alternatives when constructing the background. However, in practical missions, although general sketch of background is stable, some details change constantly. Aimed at this, we propose to represent the general background by a linear combination of some atoms and record the detailed background by spatiotemporal clustered patches. Then, the moving foreground is considered as a mixture of active contours and continuous contents. Eventually, joint optimization is conducted under a unified framework, i.e., alternating direction multipliers method (ADMM), and produces our tensor model for hierarchical background and hierarchical foreground separation (THHS). The employed tensor space, which agrees with the instinct structure of video data, benefits all the spatiotemporal designs in both background modular and foreground part. Experimental results show that THHS is more adaptive to the dynamic background and produces more accurate foreground when compared against current state-of-the-art techniques.INDEX TERMS Dictionary learning, foreground-background separation, active contour model, quantization, hierarchical modeling.

show abstract

“…Thus, before the comparison between the proposed approach and other compared algorithms, the training data and pre-trained networks utilized in algorithms are discussed. The proposed approach is compared [87] 0.8200 N/A 0.6300 0.7200 0.8600 0.8400 0.7900 0.6000 0.3600 N/A 0.4600 N/A B-SSSR [26] 0.9700 0.9500 0.9300 0.7400 0.9300 0.8600 0.9200 N/A N/A N/A 0.8700 N/A MSCL-FL [25] 0.9400 0.9000 0.8600 0.8400 0.8600 0.8600 0.8800 VI, the proposed approach achieves better results in almost all these videos compared to D-DPDL [78], since the proposed approach learns the entire histogram rather than an expected value of the histogram. Unfortunately, the proposed ADNN-IBRM does not work very well for the videos "I IL 01" and "I IL 02."…”

Section: Evaluation Of Arithmetic Distribution For Background Subtractionmentioning

confidence: 99%

Dynamic Deep Pixel Distribution Learning for Background Subtraction

Zhao

Basu

2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

We propose a new Arithmetic Distribution Neural Network (ADNN) for learning the distributions of temporal pixels during background subtraction. In our ADNN, the arithmetic distribution operations are utilized to propose the arithmetic distribution layers, including the product distribution layer and the sum distribution layer. Furthermore, in order to improve the accuracy of the proposed approach, an improved Bayesian refinement model based on neighboring information, with a GPU implementation, is introduced. In the forward pass and backpropagation of the proposed arithmetic distribution layers, histograms are considered as probability density functions rather than matrices. Thus, the proposed approach is able to utilize the probability information of the histogram and achieve promising results with a very simple architecture compared to traditional convolutional neural networks. Evaluations using standard benchmarks demonstrate the superiority of the proposed approach compared to state-of-the-art traditional and deep learning methods. To the best of our knowledge, this is the first method to propose network layers based on arithmetic distribution operations for learning distributions during background subtraction.

show abstract

Moving Object Detection in Video via Hierarchical Modeling and Alternating Optimization

Cited by 26 publications

References 50 publications

ARTYCUL: A Privacy-Preserving ML-Driven Framework to Determine the Popularity of a Cultural Exhibit on Display

ARTYCUL: A Privacy-Preserving ML-Driven Framework to Determine the Popularity of a Cultural Exhibit on Display

A Tensor Foreground-Background Separation Algorithm Based on Dynamic Dictionary Update and Active Contour Detection

Dynamic Deep Pixel Distribution Learning for Background Subtraction

Contact Info

Product

Resources

About