Moving foreground object detection via robust SIFT trajectories

Sun, Shih-Wei; Wang, Yu-Chiang Frank; Huang, Fay; Liao, Hong-Yuan Mark

doi:10.1016/j.jvcir.2012.12.003

Cited by 30 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Taking advantage of dense optical flow description, in the literature has been proposed new kinematics models that search to extend motion information in more than two frames. It consists of local motion trajectories that represent local primitives that follow interest points along the sequences, describing kinematics information in relatively large intervals of time [14,15]. For instance the KLT-Tracker uses an extension of pyramidal Lukas-Kanade [16] to follow relevant motion vectors, obtaining coherent motion trajectories of coherent edges along the sequence.…”

Section: Computing Long Motion Trajectoriesmentioning

confidence: 99%

3D+T dense motion trajectories as kinematics primitives to recognize gestures on depth video sequences

Martínez

Castillo²,

Bautista

2019

Rev. politec.

View full text Add to dashboard Cite

RGB-D sensors have allowed attacking many classical problems in computer vision such as segmentation, scene representations and human interaction, among many others. Regarding motion characterization, typical RGB-D strategies are limited to namely analyze global shape changes and capture scene flow fields to describe local motions in depth sequences. Nevertheless, such strategies only recover motion information among a couple of frames, limiting the analysis of coherent large displacements along time. This work presents a novel strategy to compute 3D+t dense and long motion trajectories as fundamental kinematic primitives to represent video sequences. Each motion trajectory models kinematic words primitives that together can describe complex gestures developed along videos. Such kinematic words were processed into a bag-of-kinematic-words framework to obtain an occurrence video descriptor. The novel video descriptor based on 3D+t motion trajectories achieved an average accuracy of 80% in a dataset of 5 gestures and 100 videos.

show abstract

Section: Computing Long Motion Trajectoriesmentioning

confidence: 99%

3D+T dense motion trajectories as kinematics primitives to recognize gestures on depth video sequences

Martínez

Castillo²,

Bautista

2019

Rev. politec.

View full text Add to dashboard Cite

show abstract

“…Object tracking is the process of segmenting a moving object of interest from a video scene and keeping track of its motion, orientation, occlusion, to extract useful information [15]. Then, by using simple data association techniques in combination with adaptive background subtraction or frame differencing, a fixed camera can effectively track the moving objects in real-time [16]. Traditionally, tracking and identification has been considered separately, the target is firstly identified and then tracked kinematically to sustain the identification.…”

Section: Object Trackingmentioning

confidence: 99%

Real-Time detection and tracking moving vehicles for video surveillance systems using FPGA

Fadhel¹,

Al-Shamaa²,

Taher³

2018

IJET

View full text Add to dashboard Cite

With the growth of the electronic and communication devices, computer vision has become an significant application of smart cities. A smart city is controlled by smart autonomous systems. Many algorithms have been developed to satisfy these smart cities. This paper concerned with addressing the moving objects (vehicles) by using morphological techniques. For computational cheapness. The simulation has been built by a MATLAB 2012a and its implementation was done using Xilinx-ISE 14.6 (2013) XC3S700A-FPGA board that provides an exceptional tool for mixing between two platforms, the ISE 14.6(2013) and the MATLAB (2012a) platforms. MATLAB provides components for FPGA that invoke Verilog code of Xilinx platform, to avoid the size weakness of XC3S700A-FPGA board.

show abstract

“…For motion segmentation with the strong parallax, sparse motion field estimation is a common approach [17,18]. The sparse motion field of the corners is recovered and the corners that belong to the same motion pattern are classified according to their motion consistency [17,19,20]. The constraint equations are applied in the optical flow to decompose the background and foreground [21].…”

Section: Related Workmentioning

confidence: 99%

Motion Segmentation by New Three-View Constraint from a Moving Camera

Ren

et al. 2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

We propose a new method for the motion segmentation using a moving camera. The proposed method classifies each image pixel in the image sequence as the background or the motion regions by applying a novel three-view constraint called the “parallax-based multiplanar constraint.” This new three-view constraint, being the main contribution of this paper, is derived from the relative projective structure of two points in three different views and implemented within the “Plane + Parallax” framework. The parallax-based multiplanar constraint overcomes the problem of the previous geometry constraint and does not require the reference plane to be constant across multiple views. Unlike the epipolar constraint, the parallax-based multiplanar constraint modifies the surface degradation to the line degradation to detect the motion objects followed by a moving camera in the same direction. We evaluate the proposed method with several video sequences to demonstrate the effectiveness and robustness of the parallax-based multiplanar constraint.

show abstract

Moving foreground object detection via robust SIFT trajectories

Cited by 30 publications

References 14 publications

3D+T dense motion trajectories as kinematics primitives to recognize gestures on depth video sequences

3D+T dense motion trajectories as kinematics primitives to recognize gestures on depth video sequences

Real-Time detection and tracking moving vehicles for video surveillance systems using FPGA

Motion Segmentation by New Three-View Constraint from a Moving Camera

Contact Info

Product

Resources

About