3D vehicle sensor based on monocular vision

Ponsa, Daniel; López, Antonio; Lumbreras, Felipe; Serrat, Joan; Graf, T.

doi:10.1109/itsc.2005.1520204

Cited by 48 publications

(39 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In these illustrations, (a), (b) and (c) columns show results by using three different, but constant, horizon line positions, while (d) column depicts the corresponding results obtained by using a horizon line position automatically computed by the proposed technique. Following the algorithm presented in (Ponsa et al, 2005), a 3D grid, sampling the road plane, is projected on the 2D image. The projected grid nodes are used as references to define the bottom-left corners of pedestrian sized searching windows.…”

Section: Resultsmentioning

confidence: 99%

“…In general, monocular systems are used on an offline pose estimation basis. To this end, the car should be at rest and should face a flat road; once the camera pose is estimated its values are assumed to keep constant, or vary within a predefined range, during the on-line process (e.g., Ponsa et al, 2005;Bertozzi et al, 2003b). Although useful in most of highway scenarios, constant camera position and orientation is not a valid assumption to be used in urban scenarios since in general, vehicle pose is easily affected by road imperfections or artifacts (e.g., rough road, speed bumps), car's accelerations, uphill/downhill driving, to mention a few.…”

Section: Previous Approachesmentioning

confidence: 99%

“…Applications such as obstacle avoidance, pedestrian detection, or traffic signal recognition, could both speed up the whole process and make use of additional information by a precise estimation of the current camera extrinsic parameters, related to the road. Most of recent works (e.g., Bertozzi et al, 2003b;Coulombeau & Laurgeau, 2002;Liang et al, 2003;Ponsa et al, 2005;Labayrade & Aubert, 2003) assume, or impose, a scene prior knowledge to simplify the problem. Although prior knowledge has been extensively used to tackle the driver assistance problem, it should be carefully used since it may lead to wrong results.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Stereo Vision Camera Pose Estimation for On-Board Applications

Sappa¹,

Gerónimo²,

Dornaika³

et al. 2007

Scene Reconstruction Pose Estimation and Tracking

Self Cite

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Previous Approachesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Stereo Vision Camera Pose Estimation for On-Board Applications

Sappa¹,

Gerónimo²,

Dornaika³

et al. 2007

Scene Reconstruction Pose Estimation and Tracking

Self Cite

View full text Add to dashboard Cite

“…After crossing AOIs have been recognized by crossing classifier, HOG based pedestrian detection (Dalal, 2005) and Haar-like vehicle detection (Ponsa, 2005 andKim, 2012) The progressive increase and then sharp decrease of the ordinate in Chart 12(a) lie in that, in sequence image, the width of a crossing in images progressive increases as it becomes closer, and sharply decreases until it disappears.…”

Section: Automatic Selection Of Appropriate Images For Defilement Andmentioning

confidence: 99%

Automatic Pedestrian Crossing Detection and Impairment Analysis Based on Mobile Mapping System

Liu¹,

Zhang²,

Li³

2017

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Pedestrian crossing, as an important part of transportation infrastructures, serves to secure pedestrians' lives and possessions and keep traffic flow in order. As a prominent feature in the street scene, detection of pedestrian crossing contributes to 3D road marking reconstruction and diminishing the adverse impact of outliers in 3D street scene reconstruction. Since pedestrian crossing is subject to wearing and tearing from heavy traffic flow, it is of great imperative to monitor its status quo. On this account, an approach of automatic pedestrian crossing detection using images from vehicle-based Mobile Mapping System is put forward and its defilement and impairment are analyzed in this paper. Firstly, pedestrian crossing classifier is trained with low recall rate. Then initial detections are refined by utilizing projection filtering, contour information analysis, and monocular vision. Finally, a pedestrian crossing detection and analysis system with high recall rate, precision and robustness will be achieved. This system works for pedestrian crossing detection under different situations and light conditions. It can recognize defiled and impaired crossings automatically in the meanwhile, which facilitates monitoring and maintenance of traffic facilities, so as to reduce potential traffic safety problems and secure lives and property.

show abstract

“…www.intechopen.com  Form recognition and classification: The form recognition allows finding a certain object from the raw data in order to classify it and to take a decision; this can be to stop your camera-equipped car when an obstacle is detected (Ponsa and al., 2005). This method is based on two different steps: firstly, the system needs to learn what kind of object it has to detect.…”

Section: Algorithms Used For Diagnosis Helpingmentioning

confidence: 99%