Visual Attention Based Motion Object Detection and Trajectory Tracking

Guo, Wen; Xu, Changsheng; Ma, Shugen; Xu, Min

doi:10.1007/978-3-642-15696-0_43

Cited by 7 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method used motion prediction metrics to identify the occurrence of false alarms and control the activation based on the template matching phase. Jia et al [32] proposed a Bayesian fusion template-based matching algorithm to improve target monitoring. This method used two different template matchings combined with Bayesian theory for weighting.…”

Section: B Template Matchingmentioning

confidence: 99%

Human Memory Update Strategy: A Multi-Layer Template Update Mechanism for Remote Visual Monitoring

Liu

Wang

Liu

et al. 2021

IEEE Trans. Multimedia

214

View full text Add to dashboard Cite

In the era of rapid development of artificial intelligence, the integration of multimedia and human-artificial intelligence (H-AI) has become an important research hotspot. Especially in the multimedia environment, effective remote visual monitoring has become the exploration direction of many scholars. The use of traditional filtering algorithm (CF) for real-time monitoring in the context of multimedia is a practical strategy. However, most existing filtering-based visual monitoring algorithms still have the problems of insufficient robustness and effectiveness. Therefore, by considering the strategy of updating human memory, this paper proposes a multi-layer template update mechanism to achieve effective monitoring in a multimedia environment. In this strategy, the weighted template of the high-confidence matching memory is used as the confidence memory, and the unweighted template of the low-confidence matching memory is used as the cognitive memory. Through the alternate use of confidence memory, matching memory, and cognitive memory, it is ensured that the target will not be lost during the monitoring process. Experimental result s show that this strategy does not affect the speed (still real-time) and improves the robustness in the multimedia background.

show abstract

Section: B Template Matchingmentioning

confidence: 99%

Human Memory Update Strategy: A Multi-Layer Template Update Mechanism for Remote Visual Monitoring

Liu

Wang

Liu

et al. 2021

IEEE Trans. Multimedia

214

View full text Add to dashboard Cite

show abstract

“…13 With the development of biological vision, motion saliency has attracted great interest from researchers, and many saliency-based moving object detection methods have been designed. Guo et al 16 applied a visual attention model that was built by the combination of the static and motion feature to detect moving objects. Yi et al 14 constructed a dynamic attention model based on the intensity difference of consecutive two frames.…”

Section: Introductionmentioning

confidence: 99%

“…2,[14][15][16] Second, the three-dimensional volumes are considered as constituted by a stack of x − t planes or y − t planes on which the algorithms are carried to calculate the saliency maps. To extract the motion information, there are mainly three approaches to the spatiotemporal volume.…”

Section: Introductionmentioning

confidence: 99%

Motion saliency detection based on temporal difference

Zhi-hu

Xiong

Zhang

2015

J. Electron. Imaging

View full text Add to dashboard Cite

Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 08/21/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspxAbstract. We focus on motion saliency detection, which has attracted much attention in recent years. Distinct from conventional algorithms, without considering the spatial information of the input frames, our method is solely based on the temporal difference of corresponding pixels. To be specific, the difference is modeled as two parts, i.e., symmetric frame difference and background sample difference. The first term calculates the differences of adjacent frames, including not only the previous n frames but also the backward n frames. To obtain the background sample difference, N samples taken from the previous frames are stored, and the differences between the coming pixel and all its corresponding samples are accumulated. The initialization and updating policies of the samples follow the off-the-shelf visual background extractor method. Finally, the motion saliency map is generated by fusing the aforementioned two features. We describe our method in full detail and compare it with three other state-of-the-art motion detection techniques. Experiments on a variety of visual surveillance databases verify that the proposed algorithm consistently outperformed the compared methods. We also demonstrate how the generated saliency maps can be used to create high-quality segmentation masks for moving object detection. Wang, Xiong, and Zhang: Motion saliency detection based on temporal difference Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 08/21/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Journal of Electronic Imaging 033022-10 May∕Jun 2015 • Vol. 24(3) Wang, Xiong, and Zhang: Motion saliency detection based on temporal difference Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 08/21/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx

show abstract