Bayesian modeling of dynamic scenes for object detection

By Yaser Sheikh, Mubarak Shah. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005

713 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/f52f68f7d6391e1be0a08964aadad801a07f9c37

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Spatiotemporal Saliency in Dynamic Scenes (2010, background): “…2. explicit [14], or approximate [23], compensation of camera motion; 3. foreground objects that move in a consistent direction (an assumption that we denote as temporal coherence) [6], [16], [28] or have faster variations in appearance than the background [24]; or 4. explicit background models.”
Background Subtraction in Real Applications: Challenges, Current Models and Future Directions (2019, background): “AND Spampinato et al. (2014) [338] GMM [341], APMM [109], IM [279], Wave-Back [281] - - - Fish Detector Spampinato et al. (2014) [339] Textons based KDE [339] Liu et al. (2016) [226] Running Average-Three CFD [226] Idem RA-TCFD Idem RA-TCFD RGB AND Huang et al. (2016) [154] SuBSENSE [340] Idem SuBSE”
Segmenting Salient Objects from Images and Videos (2010, background): “Perhaps the most common approach to reduce scene clutter is to detect moving objects against a static background [8–10].”
SuBSENSE: A Universal Change Detection Method With Local Adaptive Sensitivity (2015, methodology): “Nonparametric models based on Kernel Density Estimation (KDE) [14] were also introduced early on and improved in more recent state-of-the-art methods [11], [15], [16].”
Ensemble Video Object Cut in Highly Dynamic Scenes (2013, methodology): “The second row are the results obtained by using Bayesian modeling [23].”
Recent Advanced Statistical Background Modeling for Foreground Detection - A Systematic Survey (2011, methodology): “Some authors used Markov Random Fields [107-109], hierarchical approaches [110-113], multi-level approaches [100, 114-118], multiple backgrounds [119, 121], graph cuts [81], multi-layer approaches [122, 123], tracking feedback [128, 129] or specific post-processing [130-131].”
Decomposition into Low-rank plus Additive Matrices for Background/Foreground Separation: A Review for a Comparative Evaluation with a Large-Scale Dataset (2015, methodology): “Then, we computed the metrics used in the BMC dataset [333] such as the detection rate, the specificity, the false positive rate, the false negative rate, the percentage of wrong classifications, the precision and the F-Measure.”
Video Processing From Electro-Optical Sensors for Object Detection and Tracking in a Maritime Environment: A Survey (2016, methodology): “We note that the approach of [148] falls in motion segmentation category where pre-segmentation of the foreground is not assumed and the persistently mobile Gaus-”
Coupled ensemble graph cuts and object verification for animal segmentation from highly cluttered videos (2015, neutral): “There is a significant body of research conducted during the past two decades on background modeling and foreground object detection [2] [3] [4] [5] [6] [7].”
On the plausibility of the discriminant center-surround hypothesis for visual saliency. (2008, background): “, see Sheikh and Shah (2005) for a review).”
Animal Detection From Highly Cluttered Natural Scenes Using Spatiotemporal Object Region Proposals and Patch Verification (2016, background): “Sheikh and Shah incorporate the temporal and spatial consistencies into a single model [3].”
Traditional and recent approaches in background modeling for foreground detection: An overview (2014, methodology): “Camera jitter Statistical Models: MOG [244][52][223][225], KDE [230][228][193], SVR [280], SVDD [255] Advanced Statistical Models: DMM [114], KGMM [77], KGHMM [168], ViBe [21], PBAS [124] Fuzzy Models: T2-FMOG [18]”