Contour-based motion estimation and object tracking for real-time applications

Techmer, A.

doi:10.1109/icip.2001.958202

Cited by 32 publications

(24 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The very fast results are balanced by a low tolerance to most of the difficulties and a rather imprecise localization of the object. In contrast, methods that track the object boundary [2] offers an accurate detection, but, it is obvious that highly distinctive contours are required. They use deformable contours, like "snakes", that behave badly in the case of small or fast moving objects.…”

Section: Introductionmentioning

confidence: 87%

A tracking repositioning algorithm using keypoint labeling

Trichet

Mérialdo

2008

2008 International Workshop on Content-Based Multimedia Indexing

View full text Add to dashboard Cite

This paper reports some work undertaken during the development of a generic object tracking application based on a keypoint model. In our previous work, we proposed a keypoint labeling algorithm to distinguish object from background keypoints. This article is the continuation of this work and deals with the problem of handling object deformation using the keypoint labels. In consequence, we introduce an algorithm to refine the bounding box position according to the surrounding keypoint labels. Experimental results are shown to validate this theory.

show abstract

Section: Introductionmentioning

confidence: 87%

A tracking repositioning algorithm using keypoint labeling

Trichet

Mérialdo

2008

2008 International Workshop on Content-Based Multimedia Indexing

View full text Add to dashboard Cite

show abstract

“…Reference source not found.). Details of the single processing steps are given in [6] and [7]. For example, the most time-consuming step of the whole application, the gradient filter (7x7, 32-bit data), takes 112 lasec for one frame of 120 rows to 80 columns.…”

Section: Demonstration Applicationsmentioning

confidence: 99%

100 GOPS vision processor for automotive applications

Ramacher

Brüs

Hachmann

et al. 2003

SIGARCH Comput. Archit. News

View full text Add to dashboard Cite

Car vision systems for the improvement of driver's comfort and saj~ty will be introduced in the next car generation, with an exponential market growth in the next years. The Corporate Research division of lnfineon Technologies AG has developed a fully programmable vision processor, which fulfills the requirements of low power, low system costs, and high computational performance (e.g., robust approaches for object detection based on stereo processing need a performance of more than 15 GIPS). The prototype currently available achieves a peak performance of 53 GOPS. With a redesign in 0.13 Itm CMOS technology, the performance increases to more than 100 GOPS, while the power consumption is less than 500 mW and the die size reduces to 70 mm 2.

show abstract

“…M. Bertozzi et al developed a system, Generic Obstacle and Lane Detection system (GOLD), which performs both lane and obstacle detection in front of the vehicle [5]. The contour-based motion estimation and object tracking system was developed in detecting approaching vehicles in [6]. However, the above systems only consider the situation of approaching vehicles in front-rear direction.…”

Section: Introductionmentioning

confidence: 97%

A real-time vision-based safety assist system

Chen

Peng

et al. 2008

2008 IEEE International Conference on Systems, Man and Cybernetics

View full text Add to dashboard Cite

In this paper, a real-time vision-based safety assist system is proposed to provide the driver an assistance system improving the security on driving and after parking. The estimated distances and a friendly intuitive graph are shown on the screen for drivers to examine the distance between other vehicles. The driving status can also be recorded in H.264. Furthermore, the users' mobile phones can monitor the images inside the vehicles to prevent the thieves after parking. The system has been implemented with the embedded systems and tested by the real road environment.

show abstract

Contour-based motion estimation and object tracking for real-time applications

Cited by 32 publications

References 9 publications

A tracking repositioning algorithm using keypoint labeling

A tracking repositioning algorithm using keypoint labeling

100 GOPS vision processor for automotive applications

A real-time vision-based safety assist system

Contact Info

Product

Resources

About