Recent Approaches in Background Modeling for Static Cameras

Bouwmans, Thierry

doi:10.1201/b17223-4

Cited by 5 publications

(10 citation statements)

References 144 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Background modeling (or background subtraction ) and the related foreground detection (or change detection) are important steps in video surveillance and well-established themes in computer vision (for an exhaustive survey, see the book [ 9 ]). Conventional background modeling methods exploit the temporal variation of each pixel to model the background.…”

Section: Related Workmentioning

confidence: 99%

A Novel Background Modeling Algorithm for Hyperspectral Ground-Based Surveillance and Through-Foliage Detection

Schreiber

Opitz

2022

Sensors

View full text Add to dashboard Cite

Foliage penetration is an unsolved important part of border surveillance of remote areas between regular border crossing points. Detecting penetrating objects (e.g., persons and cars) through dense foliage in various climate conditions using visual sensors is prone to high fault rates. Through-foliage scenarios contain an unprecedented amount of occlusion—in fact, they often contain fragmented occlusion (for example, looking through the branches of a tree). Current state-of-the-art detectors based on deep learning perform inadequately under moderate-to-heavy fragmented occlusion. The FOLDOUT project builds a system that combines various sensors and technologies to tackle this problem. Consequently, a hyperspectral sensor was investigated due to its extended spectral bandwidth, beyond the range of typical RGB sensors, where vegetation exhibits pronounced reflectance. Due to the poor performance of deep learning approaches in through-foliage scenarios, a novel background modeling-based detection approach was developed, dedicated to the characteristics of the hyperspectral sensor, namely strong correlations between adjacent spectral bands and high redundancy. The algorithm is based on local dimensional reduction, where the principal subspace of each pixel is maintained and adapted individually over time. The successful application of the proposed algorithm is demonstrated in a through-foliage scenario comprised of heavy fragmented occlusion and a highly dynamical background, where state-of-the-art deep learning detectors perform poorly.

show abstract

Section: Related Workmentioning

confidence: 99%

A Novel Background Modeling Algorithm for Hyperspectral Ground-Based Surveillance and Through-Foliage Detection

Schreiber

Opitz

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Foreground segmentation is key in many applications, such as video-surveillance [20], aiming to classify each image pixel into foreground or background, thus producing a foreground mask containing the regions of interest (i.e., blobs), which represent the foreground [20,21,22]. For example, such a foreground can be related to every object in the scene [23,24] or only to the salient objects [21].…”

Section: Stages Of Abandoned Object Detectionmentioning

confidence: 99%

“…For example, such a foreground can be related to every object in the scene [23,24] or only to the salient objects [21]. In videos, the foreground may correspond to all moving objects [20], to specific temporal salient objects [25], to some relevant spatio-temporal patterns [26], or to pre-defined image labels [27].…”

Section: Stages Of Abandoned Object Detectionmentioning

confidence: 99%

“…Background Subtraction (BS) is often used for AOD due to the relative control of camera motion. Traditional BS algorithms usually consist of four stages [20]: modeling, to statistically represent the background of the scene; initialization, to acquire the first model; maintenance, to adapt the model to scene variations over time; and detection, to segment foreground objects by comparing each frame and the model. Segmenting the foreground addresses several challenges affecting segmentation performance [20].…”

Section: Stages Of Abandoned Object Detectionmentioning

confidence: 99%

“…Traditional BS algorithms usually consist of four stages [20]: modeling, to statistically represent the background of the scene; initialization, to acquire the first model; maintenance, to adapt the model to scene variations over time; and detection, to segment foreground objects by comparing each frame and the model. Segmenting the foreground addresses several challenges affecting segmentation performance [20]. False positives may be caused by illumination changes (non-accurate model adaptation), camera jitter (pixel misalignment between current and background images due to camera motion), ghosts (objects wrongly included in the background model), dynamic backgrounds (background motion difficult to handle by the model), camouflages (foreground and background sharing similar appearance), and cast shadows (shadows from objects are sometimes detected).…”

Section: Stages Of Abandoned Object Detectionmentioning

confidence: 99%

See 2 more Smart Citations

Abandoned Object Detection in Video-Surveillance: Survey and Comparison

Luna

SanMiguel

Ortego

et al. 2018

Sensors

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

SPIRA: an automatic system to support lower limb injury assessment

Bailon

Damas

Pomares

et al. 2018

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Lower limb injuries, especially those related to the knee joint, are some of the most common and severe injuries among sport practitioners. Consequently, a growing interest in the identification of subjects with high risk of injury has emerged during last years. One of the most commonly used injury risk factor is the measurement of joint angles during the execution of dynamic movements. To that end, techniques such as human motion capture and video analysis have been widely used. However, traditional procedures to measure joint angles present certain limitations, which makes this practice not practical in common clinical settings. This work presents SPIRA, a novel 2D video analysis system directed to support practitioners during the evaluation of joint angles in functional tests. The system employs an infrared camera to track retro-reflective markers attached to the patient's body joints and provide a real-time measurement of the joint angles in a cost-and-time-effective way. The information gathered by the sensor is processed and managed through a computer application that guides the expert during the execution of the tests and expedites the analysis of the results. In order to show the potential of the SPIRA system, a case study has been conducted, performing the analysis with the both the proposed system and a gold-standard in 2D offline video analysis. The results (ICC( ) = 0.996) reveal a good agreement between both tools and prove the reliability of SPIRA. KeywordsInjury risk • Lower limb • Joint angles • Marker tracking • Computer vision • Kinect • 2D video analysis * Carlos Bailon

show abstract

Recent Approaches in Background Modeling for Static Cameras

Cited by 5 publications

References 144 publications

A Novel Background Modeling Algorithm for Hyperspectral Ground-Based Surveillance and Through-Foliage Detection

A Novel Background Modeling Algorithm for Hyperspectral Ground-Based Surveillance and Through-Foliage Detection

Abandoned Object Detection in Video-Surveillance: Survey and Comparison

SPIRA: an automatic system to support lower limb injury assessment

Contact Info

Product

Resources

About