Combining multiple motion estimates for vehicle tracking

Gil, Sylvia; Milanese, Ruggero; Pun, Thierry

doi:10.1007/3-540-61123-1_149

Cited by 22 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Changing the parameters of the model with time allows adaptation to long-term changes in the motion characteristics. Gil et al [24] combined multiple motion estimators for vehicle tracking. Vehicle detection was performed using two features: the bounding rectangle of the moving vehicle, where the convex hull of the vehicle is computed for every frame and then translated according to the predicted motion parameters, and an updated 2-D pattern (gray-level mask) based on optimization of the correlation between the pattern and the image using the motion parameters.…”

Section: Related Workmentioning

confidence: 99%

Estimating relative vehicle motions in traffic scenes

Duric

Goldenberg

Rivlin

et al. 2002

Pattern Recognition

View full text Add to dashboard Cite

Autonomous operation of a vehicle on a road calls for understanding of various events involving the motions of the vehicles in its vicinity. In this paper we show how a moving vehicle which is carrying a camera can estimate the relative motions of nearby vehicles. We show how to "smooth" the motion of the observing vehicle, i.e. to correct the image sequence so that transient motions (primarily rotations) resulting from bumps, etc. are removed and the sequence corresponds more closely to the sequence that would have been collected if the motion had been smooth. We also show how to detect the motions of nearby vehicles relative to the observing vehicle. We present results for several road image sequences which demonstrate the e ectiveness of our approach. ?

show abstract

Section: Related Workmentioning

confidence: 99%

Estimating relative vehicle motions in traffic scenes

Duric

Goldenberg

Rivlin

et al. 2002

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Point features that are seen moving rigidly together are grouped into a single vehicle. Gil et al [15] introduce a method for combining contour-based and regionbased approaches: one is based on the boundaring-box of the moving object; and the other uses the object's 2D pattern. This work compares two combining approaches, a linear and a Kalman filter based approach.…”

Section: Introductionmentioning

confidence: 99%

Segmenting Traffic Scenes from Grey Level and Motion Information

Bedenas

Boder

Pla

2001

Pattern Analysis & Applications

View full text Add to dashboard Cite

This paper is concerned with an efficient estimation and segmentation of 2D motion from image sequences, with the focus on traffic monitoring applications. In order to reduce the computational load to achieve real-time implementation, the proposed approach makes use of simplifying assumptions that the camera is stationary, and that the projection of vehicles motion on the image plane can be approximated by translation. We show that satisfactory results can be achieved even under such apparently restrictive assumptions. The use of 2D motion analysis and the pre-segmentation stage significantly reduces the computational load, and the region-based motion estimator gives robustness to noise and changes in the illumination conditions.

show abstract

“…Our earlier work was published in [6,7,10]. Related problems are lane transition [36], autonomous convoy driving [25,57] and traffic monitoring using a stationary camera [11,12,23,28,35,41]. A collection of articles on vision-based vehicle guidance can be found in [46].…”

mentioning

confidence: 99%

Real-time multiple vehicle detection and tracking from a moving vehicle

Betke

Haritaoglu

Davis

2000

Machine Vision and Applications

265

101

View full text Add to dashboard Cite

Abstract.A real-time vision system has been developed that analyzes color videos taken from a forward-looking video camera in a car driving on a highway. The system uses a combination of color, edge, and motion information to recognize and track the road boundaries, lane markings and other vehicles on the road. Cars are recognized by matching templates that are cropped from the input data online and by detecting highway scene features and evaluating how they relate to each other. Cars are also detected by temporal differencing and by tracking motion parameters that are typical for cars. The system recognizes and tracks road boundaries and lane markings using a recursive least-squares filter. Experimental results demonstrate robust, real-time car detection and tracking over thousands of image frames. The data includes video taken under difficult visibility conditions.

show abstract

Combining multiple motion estimates for vehicle tracking

Cited by 22 publications

References 10 publications

Estimating relative vehicle motions in traffic scenes

Estimating relative vehicle motions in traffic scenes

Segmenting Traffic Scenes from Grey Level and Motion Information

Real-time multiple vehicle detection and tracking from a moving vehicle

Contact Info

Product

Resources

About