Multiple kernel tracking with SSD

Hager, Gregory D.; Dewan, M. Ali Akber; Stewart, Charles

doi:10.1109/cvpr.2004.1315112

Cited by 202 publications

(184 citation statements)

References 10 publications

Supporting

Mentioning

184

Contrasting

Order By: Relevance

“…Note that the distance can be computed instead with the Bhattacharyya distance utilized in [16,18] as shown in [22] or with any other suitable distance metric. The color histograms are Table 5.1: Data payload in a packet.…”

Section: Particle Filter Settingsmentioning

confidence: 99%

See 1 more Smart Citation

Resource-aware distributed particle filtering for cluster-based object tracking in wireless camera networks

Hong

Medeiros

Shin

et al. 2016

IJSNET

View full text Add to dashboard Cite

Section: Particle Filter Settingsmentioning

confidence: 99%

“…In unimodal tracking [13,22], the probability distribution that represents the position of the target object is assumed to have a single mode. Theoretically, unimodal tracking computes the MAP (maximum a posterior) estimates as the current position of the object in each frame:…”

Section: Single-camera Object Trackingmentioning

confidence: 99%

Resource-aware distributed particle filtering for cluster-based object tracking in wireless camera networks

Hong

Medeiros

Shin

et al. 2016

IJSNET

View full text Add to dashboard Cite

“…Kernel-based tracking that minimizes the Matusita distance between the feature distributions using a Newtonstyle method, as well as the extension to the use of multiple kernels, were developed in [8]. This last work implemented a location and scale tracker as well as a wand tracker.…”

Section: Previous Workmentioning

confidence: 99%

Visual Tracking by Affine Kernel Fitting Using Color and Object Boundary

Leichter

Lindenbaum

Rivlin

2007

2007 IEEE 11th International Conference on Computer Vision

View full text Add to dashboard Cite

“…The tracker determined object location in real-time by mean-shifting the kernel in the gradient-ascending direction of the differentiated objective function. Owing to its simplicity, robustness, and speed, it has been popular and has evolved over the years [7,14,24]. In particular, [43] represents an elongated, rigid object by an asymmetric kernel and determines its location, scale, and orientation.…”

Section: Related Workmentioning

confidence: 99%

Pose-Configurable Generic Tracking of Elongated Objects

Węsierski

Horain

2013

2013 IEEE International Conference on Computer Vision

View full text Add to dashboard Cite

Elongated objects have various shapes and can shift, rotate, change scale, and be rigid or deform by flexing, articulating, and vibrating, with examples as varied as a glass bottle, a robotic arm, a surgical suture, a finger pair, a tram, and a guitar string. This generally makes tracking of poses of elongated objects very challenging.We describe a unified, configurable framework for tracking the pose of elongated objects, which move in the image plane and extend over the image region. Our method strives for simplicity, versatility, and efficiency. The object is decomposed into a chained assembly of segments of multiple parts that are arranged under a hierarchy of tailored spatio-temporal constraints. In this hierarchy, segments can rescale independently while their elasticity is controlled with global orientations and local distances.While the trend in tracking is to design complex, structure-free algorithms that update object appearance online, we show that our tracker, with the novel but remarkably simple, structured organization of parts with constant appearance, reaches or improves state-of-the-art performance. Most importantly, our model can be easily configured to track exact pose of arbitrary, elongated objects in the image plane. The tracker can run up to 100 fps on a desktop PC, yet the computation time scales linearly with the number of object parts. To our knowledge, this is the first approach to generic tracking of elongated objects.

show abstract

Multiple kernel tracking with SSD

Cited by 202 publications

References 10 publications

Resource-aware distributed particle filtering for cluster-based object tracking in wireless camera networks

Resource-aware distributed particle filtering for cluster-based object tracking in wireless camera networks

Visual Tracking by Affine Kernel Fitting Using Color and Object Boundary

Pose-Configurable Generic Tracking of Elongated Objects

Contact Info

Product

Resources

About