A region based CAMShift tracking with a moving camera

Kassir, Mohamad Mahdi; Palhang, Maziar

doi:10.1109/icrom.2014.6990943

Cited by 9 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Object tracking can be divided into online systems (for which tracking is done on a frame-by-frame basis), or offline systems (which take longer sequences into account), like in [ 21 , 22 ]. In the online systems, targets are usually followed using classic tracking approaches, like the Extended Kalman Filters (EKFs) [ 23 ], particle filters [ 24 ] or mean-shift tracking [ 25 ]. In [ 26 ], a simultaneously detection and trajectory estimation over a hypothesis test model extended with stereo depth and visual odometry is presented.…”

Section: Previous Workmentioning

confidence: 99%

Fast Object Motion Estimation Based on Dynamic Stixels

Morales

Morell

Toledo

et al. 2016

Sensors

View full text Add to dashboard Cite

The stixel world is a simplification of the world in which obstacles are represented as vertical instances, called stixels, standing on a surface assumed to be planar. In this paper, previous approaches for stixel tracking are extended using a two-level scheme. In the first level, stixels are tracked by matching them between frames using a bipartite graph in which edges represent a matching cost function. Then, stixels are clustered into sets representing objects in the environment. These objects are matched based on the number of stixels paired inside them. Furthermore, a faster, but less accurate approach is proposed in which only the second level is used. Several configurations of our method are compared to an existing state-of-the-art approach to show how our methodology outperforms it in several areas, including an improvement in the quality of the depth reconstruction.

show abstract

Section: Previous Workmentioning

confidence: 99%

Fast Object Motion Estimation Based on Dynamic Stixels

Morales

Morell

Toledo

et al. 2016

Sensors

View full text Add to dashboard Cite

show abstract

“…In this paper, we adopt a single-LED indoor positioning system, use rotation vector sensor obtain rotation angle and decode the picture obtained by camera. And use the camshaft algorithm [14] to improve the real-time performance by tracking the downlight on the pixel surface to improve the real-time performance of the positioning system. The accuracy and real-time performance are good in the case of arbitrary three-axis angle.…”

mentioning

confidence: 99%

Research on indoor real-time positioning technology of LED visible light communication based on arbitrary three-axis rotation angle

Liu

Wang

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

LED visible light communication indoor positioning system based on three-axis rotation angle of cell phone, including modulated signal LED downlight, rotation vector sensor and camera of smartphone, target tracking module and developed positioning method. The main processes are: the three-axis rotation angle of cell phone obtained from the rotation vector sensor, the position information of LED downlight image in pixel coordinate system obtained from the camera, the LED downlight position information obtained by decoding method, bring the above information into the positioning system. Meanwhile, the target tracking module based on Continuously Adaptive Mean-shift (CAMSHIFT) algorithm can effectively enhance the system operation speed and improve the real-time performance, and the three-axis rotation angle can effectively adapt to the cell phone pose transformation. This positioning system performs well in terms of positioning accuracy and real-time performance.

show abstract