Stationary foreground detection for video-surveillance based on foreground and motion history images

Ortego, Diego; SanMiguel, Juan C.

doi:10.1109/avss.2013.6636619

Cited by 7 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Again, these authors proposed further SFD algorithms [56,66,67] based on intensity, motion, shape, and foreground accumulation features to learn the transitions between the states of three FSMs that model the spatio-temporal patterns at different abstraction levels (pixel, blob, and event) to detect abandoned and stolen objects. Moreover, the accumulation of foreground and motion features with occlusion handling was proposed in [68] and extended in [57] with structural features to increase robustness against illumination changes before thresholding a stationary history image (the staticness map). Furthermore, there are several approaches [69,70,71,72] adopting different complexities of object tracking over blobs extracted from a stationary foreground mask [63].…”

Section: Stages Of Abandoned Object Detectionmentioning

confidence: 99%

Abandoned Object Detection in Video-Surveillance: Survey and Comparison

Luna

SanMiguel

Ortego

et al. 2018

Sensors

Self Cite

View full text Add to dashboard Cite

During the last few years, abandoned object detection has emerged as a hot topic in the video-surveillance community. As a consequence, a myriad of systems has been proposed for automatic monitoring of public and private places, while addressing several challenges affecting detection performance. Due to the complexity of these systems, researchers often address independently the different analysis stages such as foreground segmentation, stationary object detection, and abandonment validation. Despite the improvements achieved for each stage, the advances are rarely applied to the full pipeline, and therefore, the impact of each stage of improvement on the overall system performance has not been studied. In this paper, we formalize the framework employed by systems for abandoned object detection and provide an extensive review of state-of-the-art approaches for each stage. We also build a multi-configuration system allowing one to select a range of alternatives for each stage with the objective of determining the combination achieving the best performance. This multi-configuration is made available online to the research community. We perform an extensive evaluation by gathering a heterogeneous dataset from existing data. Such a dataset allows considering multiple and different scenarios, whereas presenting various challenges such as illumination changes, shadows, and a high density of moving objects, unlike existing literature focusing on a few sequences. The experimental results identify the most effective configurations and highlight design choices favoring robustness to errors. Moreover, we validated such an optimal configuration on additional datasets not previously considered. We conclude the paper by discussing open research challenges arising from the experimental comparison.

show abstract

Section: Stages Of Abandoned Object Detectionmentioning

confidence: 99%

Abandoned Object Detection in Video-Surveillance: Survey and Comparison

Luna

SanMiguel

Ortego

et al. 2018

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The object feature extraction is prerequisite of object tracking and detection. Generally the foreground detection [5] is adopted to obtain the tracking object. In recent years, approaches for model-free tracking [6] became popular.…”

Section: Introductionmentioning

confidence: 99%

Multiple Object Tracking Based on Motion Estimation and Structural constraints

Wan¹,

Liu²,

Chen³

et al. 2014

Proceedings of the 2014 International Conference on Mechatronics, Electronic, Industrial and Control Engineering

View full text Add to dashboard Cite

To solve the time-consuming problem and the low efficiency of the global exhaustive searching in the object tracking, this paper propose a new search strategy based on motion estimation and structural constraints. First, the motion vector of one object is calculated, associating with the location of the object in the previous frame, its moving direction and scope are predicted in the current frame. Then, with the combination of structural constraints between objects, the accurate search direction and scope of the other targets can be determined. We choose five videos for the experiment to confirm the superiority of the search algorithm in this paper. For each video, all these measurements are averaged over all objects, over all frames, and over five separate runs of the tracker. Experimental results show that the new search method can narrow the search range and enhance the searching efficiency under the condition of no affect on the tracking accuracy, thus the complexity of the multi-object tracking algorithm will be reduced.

show abstract

“…al. [25] proposed usage of foreground and motion images history for stationary foreground detection. They used both pixel level and frame level analysis of foreground and motion data.…”

Section: Fig 1 Steps Employed In Visual Surveillance For Viotmentioning

confidence: 99%

Change Detection Algorithms for Surveillance in Visual IoT: A Comparative Study

Akram

Zafar

Akbar

et al. 2018

Mehran Univ. res. j. eng. technol.

View full text Add to dashboard Cite

A common DVS for VIoT comprises several phases as shown in Fig. 1. ChD is performed as in-network processing on low-form factor VIoT devices. For video surveillance, object classification and tracking is done as Back-office processing on servers.The efficiency and effectiveness of VIoT based DVS is dependent upon algorithms used at every step. This paper focuses on comparison of various ChD algorithms suitable for resource constrained devices in VIoT.ChD refers to monitoring temporal changes in images.ChD algorithms can be categorized in several ways. One way to categorize them is based on image representation processing. This process is represented in Fig. 2. The remainder of the manuscript is organized as follows; FIG. 1. STEPS EMPLOYED IN VISUAL SURVEILLANCE FOR VIOTSection 2 provides a detailed review of related work;Section 3 describes the simulation framework, evaluation parameters along with results and performance analysis.Sections 4 and 5 summarize the results and suggest possible future work. RELATED WORK

show abstract

Stationary foreground detection for video-surveillance based on foreground and motion history images

Cited by 7 publications

References 18 publications

Abandoned Object Detection in Video-Surveillance: Survey and Comparison

Abandoned Object Detection in Video-Surveillance: Survey and Comparison

Multiple Object Tracking Based on Motion Estimation and Structural constraints

Change Detection Algorithms for Surveillance in Visual IoT: A Comparative Study

Contact Info

Product

Resources

About