Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects

By Nikos Paragios, Rachid Deriche. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000

1,224 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/67c4d66740c6cf8e47a565b5d5a1918397b94c8a

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Shape recovery algorithms using level sets in 2-D/3-D medical imagery: a state-of-the-art review (2002, neutral): “[28], [29] and Kornprobst et al.”
Recent developments in human motion analysis (2003, background): “Recent work of Paragios and Deriche [77] presented a variational framework for detecting and tracking multiple moving objects in image sequences.”
Segmenting and tracking fluorescent cells in dynamic 3-D microscopy with coupled active surfaces (2005, methodology): “D) image, the resulting front can be used to initialize segmentation of the next image, provided that motions between consecutive imaging times are modest, thereby achieving tracking [14], [18], [25].”
Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation (2005, methodology): “Others tackled the problem of segmenting motion by treating the problems of motion estimation in disjoint sets and optimization of the motion boundaries separately (Schnörr, 1992; Black, 1994; Caselles and Coll, 1996; Odobez and Bouthemy, 1998; Paragios and Deriche, 2000; Farnebäck, 2001).”
Robust online appearance models for visual tracking (2001, background): “, [15], [22], [26]) 1296 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL.”
A survey of video processing techniques for traffic applications (2003, methodology): “Two general approaches have been employed for feature aggregation, namely motion-based and model-based approaches [64].”
A survey on activity recognition and behavior understanding in video surveillance (2013, methodology): “[121] used the geodesic active contour originated by Paragios and Deriche [130], in which the state information (normal velocity) with every particle on a contour is represented by means of a level set functions.”
A survey on visual surveillance of object motion and behaviors (2004, methodology): “Paragios et al. [30] detect and track multiple moving objects in image sequences using a geodesic active contour objective function and a level set formulation scheme.”
Geodesic Active Regions and Level Set Methods for Supervised Texture Segmentation (2002, methodology): “…in Paragios and Deriche (1999b) for supervised texture segmentation and then extended to deal with the un-supervised image segmentation case in Paragios and Deriche (2000a), and successfully exploited in Paragios and Deriche (1999c) to provide an elegant solution to the motion estimation and…”
Active Contour External Force Using Vector Field Convolution for Image Segmentation (2007, methodology): “ACTIVE models [1], or deformable models [2], have been widely used for image segmentation [3]–[6] and objects tracking [7]–[10].”
A Topology Preserving Level Set Method for Geometric Deformable Models (2003, background): “Deformable models are broadly classified as either parametric deformable models (see [1], [2], [3], [4], [5]) or geometric deformable models (see [6], [7], [8], [9], [10], [11], [12], [13], [14], [15], [16]) according to their representation and implementation.”
Opening up Open World Tracking (2021, methodology): “Early methods in vision-based tracking [27,59,85] and robotic perception [54,76] utilized class-agnostic, bottom-up segmentation as a tracking cue, e.g ., based on LiDAR point cloud clustering [53, 79] or background modeling and foreground grouping [32,73,85].”