3D vision sensing for improved pedestrian safety

Grubb, Grant; Zelinsky, Alexander; Nilsson, Lars J; Rilbe, M.

doi:10.1109/ivs.2004.1336349

Cited by 86 publications

(63 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [20] a foreground region is obtained by clustering in the disparity space. In [2,10] ROIs are selected considering the x-and y-projections of the disparity space following the v-disparity representation [11]. In [1] object hypotheses are obtained by using a subtractive clustering in the 3D space in world coordinates.…”

Section: Related Workmentioning

confidence: 99%

Dense Stereo-Based ROI Generation for Pedestrian Detection

Keller

Llorca

Gavrila

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper investigates the benefit of dense stereo for the ROI generation stage of a pedestrian detection system. Dense disparity maps allow an accurate estimation of the camera height, pitch angle and vertical road profile, which in turn enables a more precise specification of the areas on the ground where pedestrians are to be expected. An experimental comparison between sparse and dense stereo approaches is carried out on image data captured in complex urban environments (i.e. undulating roads, speed bumps). The ROI generation stage, based on dense stereo and specific camera and road parameter estimation, results in a detection performance improvement of factor five over the stateof-the-art based on ROI generation by sparse stereo. Interestingly, the added processing cost of computing dense disparity maps is at least partially amortized by the fewer ROIs that need to be processed at the system level.

show abstract

Section: Related Workmentioning

confidence: 99%

Dense Stereo-Based ROI Generation for Pedestrian Detection

Keller

Llorca

Gavrila

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…By that the ground plane can be marked with the help of the known camera parameters and the depth image. Another way is presented in [4]. Hough transformation in conjunction with a 2D-histogram of depth values and vertical position (vdisparity) is used to estimate the ground plane parameters.…”

Section: Previous Workmentioning

confidence: 99%

“…To generate hypotheses the depth image is segmented by region growing in [6]. The v-disparity method is used in [4] to detect pedestrians. Due to graph-cut objects are generated in [7].…”

Section: Previous Workmentioning

confidence: 99%

“…The features known from the literature are edge images [3], gradient magnitudes [5], intensity values [3] and the Fourier coefficients of the object contour [6]. Popular approaches to classify the hypotheses with the extracted features are SVM [4], [7] or AdaBoost [3]. In [5] the classification is done by an artificial neural network and in [6] a thresholding technique is used.…”

Section: Previous Workmentioning

confidence: 99%

“…One of them are the horizontal and vertical edge images [4]. The image gradient magnitudes [5], the pure intensity or depth values and the haar-like features from Viola and Jones [11] were also tested.…”

Section: A Feature Extractionmentioning

confidence: 99%

See 2 more Smart Citations

Pedestrian recognition using combined low-resolution depth and intensity images

Rapus¹,

Munder²,

Baratoff³

et al. 2008

2008 IEEE Intelligent Vehicles Symposium

View full text Add to dashboard Cite

Abstract-We present a novel system for pedestrian recognition through depth and intensity measurements. A 3D-Camera is used as main sensor, which provides depth and intensity measurements with a resolution of 64x8 pixels and a depth range of 0-20 meters.The first step consists of extracting the ground plane from the depth image by an adaptive flat world assumption. An AdaBoost head-shoulder detector is then used to generate hypotheses about possible pedestrian positions. In the last step every hypothesis is classified with AdaBoost or a SVM as pedestrian or non-pedestrian. We evaluated a number of different features known from the literature. The best result was achieved by Fourier descriptors in combination with the edges of the intensity image and an AdaBoost classifier, which resulted in a recognition rate of 83.75 percent.

show abstract

Application Challenges from a Bird's‐Eye View

Scaramuzza

López²,

Imiya³

et al. 2017

Computer Vision in Vehicle Technology

View full text Add to dashboard Cite

Computer Vision in Vehicle Technology focuses on computer vision as on-board technology, bringing together fields of research where computer vision is progressively penetrating: the automotive sector, unmanned aerial and underwater vehicles. It also serves as a reference for researchers of current developments and challenges in areas of the application of computer vision, involving vehicles such as advanced driver assistance (pedestrian detection, lane departure warning, traffic sign recognition), autonomous driving and robot navigation (with visual simultaneous localization and mapping) or unmanned aerial vehicles (obstacle avoidance, landscape classification and mapping, fire risk assessment).

show abstract

3D vision sensing for improved pedestrian safety

Cited by 86 publications

References 8 publications

Dense Stereo-Based ROI Generation for Pedestrian Detection

Dense Stereo-Based ROI Generation for Pedestrian Detection

Pedestrian recognition using combined low-resolution depth and intensity images

Application Challenges from a Bird's‐Eye View

Contact Info

Product

Resources

About