A physically motivated pixel-based model for background subtraction in 3D images

Braham, Marc; Lejeune, Antoine; Droogenbroeck, Marc Van

doi:10.1109/ic3d.2014.7032591

Cited by 11 publications

(12 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case calculating the AUC becomes problematic, and using other metrics derived from a ROC curve becomes more suitable for comparing algorithms (classifiers). An example of such a metric is the Euclidean distance to the upper lefthand corner or "oracle" (Braham et al 2014). In the case of PCA, the minimum distance to the upper lefthand corner is 0.3, while for our algorithm it is 0.2, which again confirms its superiority.…”

Section: Performancementioning

confidence: 99%

Low-rank plus sparse decomposition for exoplanet detection in direct-imaging ADI sequences

González

Absil

et al. 2016

A&A

View full text Add to dashboard Cite

Context. Data processing constitutes a critical component of high-contrast exoplanet imaging. Its role is almost as important as the choice of a coronagraph or a wavefront control system, and it is intertwined with the chosen observing strategy. Among the data processing techniques for angular differential imaging (ADI), the most recent is the family of principal component analysis (PCA) based algorithms. It is a widely used statistical tool developed during the first half of the past century. PCA serves, in this case, as a subspace projection technique for constructing a reference point spread function (PSF) that can be subtracted from the science data for boosting the detectability of potential companions present in the data. Unfortunately, when building this reference PSF from the science data itself, PCA comes with certain limitations such as the sensitivity of the lower dimensional orthogonal subspace to non-Gaussian noise. Aims. Inspired by recent advances in machine learning algorithms such as robust PCA, we aim to propose a localized subspace projection technique that surpasses current PCA-based post-processing algorithms in terms of the detectability of companions at near real-time speed, a quality that will be useful for future direct imaging surveys. Methods. We used randomized low-rank approximation methods recently proposed in the machine learning literature, coupled with entry-wise thresholding to decompose an ADI image sequence locally into low-rank, sparse, and Gaussian noise components (LLSG). This local three-term decomposition separates the starlight and the associated speckle noise from the planetary signal, which mostly remains in the sparse term. We tested the performance of our new algorithm on a long ADI sequence obtained on β Pictoris with VLT/NACO. Results. Compared to a standard PCA approach, LLSG decomposition reaches a higher signal-to-noise ratio and has an overall better performance in the receiver operating characteristic space. This three-term decomposition brings a detectability boost compared to the full-frame standard PCA approach, especially in the small inner working angle region where complex speckle noise prevents PCA from discerning true companions from noise.

show abstract

Section: Performancementioning

confidence: 99%

Low-rank plus sparse decomposition for exoplanet detection in direct-imaging ADI sequences

González

Absil

et al. 2016

A&A

View full text Add to dashboard Cite

show abstract

“…In the last few years many researchers have been investigating toward the use of depth data and colour information in video surveillance to segment background of the scene. 11,[31][32][33][34][35][36][37][38][39] The shapes of objects which are captured by depth sensor in the scene are not affected by shadows, illumination changes and interreflections. Therefore, depth information could help to provide much more robustness to such a phenomenon.…”

Section: Motion Detectionmentioning

confidence: 99%

“…However, background subtraction methods based on only depth data frequently produce invalid outcomes. 40,41 Depth data are usually noisy and have some restrictions for certain surfaces in measurement which typically is referred to as "holes" 31 or "Absent Depth Observations (ADO)" in the literature. 11 These failures come from several physical phenomena such as the production of depth camouflage, depth shadows, absorption by black objects, limitation on distances, lower sensitivity at longer distances and absent observations, etc.…”

Section: Motion Detectionmentioning

confidence: 99%

Nonparametric background modelling and segmentation to detect micro air vehicles using RGB-D sensor

Dorudian

Lauria

Swift

2019

International Journal of Micro Air Vehicles

View full text Add to dashboard Cite

A novel approach to detect micro air vehicles in GPS-denied environments using an external RGB-D sensor is presented. The nonparametric background subtraction technique incorporating several innovative mechanisms allows the detection of high-speed moving micro air vehicles by combining colour and depth information. The proposed method stores several colour and depth images as models and then compares each pixel from a frame with the stored models to classify the pixel as background or foreground. To adapt to scene changes, once a pixel is classified as background, the system updates the model by finding and substituting the closest pixel to the camera with the current pixel. The background model update presented uses different criteria from existing methods. Additionally, a blind update model is added to adapt to background sudden changes. The proposed architecture is compared with existing techniques using two different micro air vehicles and publicly available datasets. Results showing some improvements over existing methods are discussed.

show abstract

“…The system stores the first N (N = 20 in our experiments) number of frames to initialise the models (system initialization step). Typically, depth frames are noisy and have some limitations for certain materials, surfaces and black color which known as "holes" [17] or "Absent Depth Observations (ADO) " [3]. In the proposed method these unknown pixel values in the depth frame will be filled by neighboring values before storing in the model.…”

Section: The Proposed Algorithmsmentioning

confidence: 99%

Moving Object Detection Using Adaptive Blind Update and RGB-D Camera

2019

View full text Add to dashboard Cite

A novel background subtraction approach using RGB-D camera and an adaptive blind updating policy is introduced. This method in initialization creates a model to store background pixels to compare each pixel of the new frame with the model in the same location to identify background pixels. The background-model update presented in this paper uses regular and blind update which also has a different criteria from existing methods. In particular, blind update frequently changes based on the background changes and the speed of moving object. This will allow the scene model to adapt to the changes in the background, detecting the stationary moving object and reducing the ghost phenomenon. In addition, proposed bootstrapping segmentation and shadow detection are added to the system to improve the accuracy of the algorithm in shadow and depth camouflage scenarios.The proposed method is compared with the original method and other state of the art algorithms. Experimental results show significant improvement in those videos that stationary object appear. In addition, the benchmark results also indicate strong and stable results compared to the other state of the art algorithms.

show abstract

A physically motivated pixel-based model for background subtraction in 3D images

Cited by 11 publications

References 22 publications

Low-rank plus sparse decomposition for exoplanet detection in direct-imaging ADI sequences

Low-rank plus sparse decomposition for exoplanet detection in direct-imaging ADI sequences

Nonparametric background modelling and segmentation to detect micro air vehicles using RGB-D sensor

Moving Object Detection Using Adaptive Blind Update and RGB-D Camera

Contact Info

Product

Resources

About