Pedestrian recognition using combined low-resolution depth and intensity images

Rapus, Martin; Munder, S.; Baratoff, Gregory; Denzler, Joachim

doi:10.1109/ivs.2008.4621195

Cited by 13 publications

(10 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, for Smart Airbag systems, Devarakota et al [6] used 3-D images to classify vehicle occupants as adults or children, leaning forward or backward. A pedestrian detection system based on depth and intensity images was proposed by Rapus et al [7]. A multi-part based people detection using 2-D range data was proposed by Mozos et al [8].…”

Section: Related Workmentioning

confidence: 99%

Scene Segmentation and Pedestrian Classification from 3-D Range and Intensity Images

Xue

Phung

Bouzerdoum

2012

2012 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

. (2012). Scene segmentation and pedestrian classification from 3-D range and intensity images. IEEE International Conference on . Australia: IEEE. Scene segmentation and pedestrian classification from 3-D range and intensity images AbstractThis paper proposes a new approach to classify obstacles using a time-of-flight camera, for applications in assistive navigation of the visually impaired. Combining range and intensity images enables fast and accurate object segmentation, and provides useful navigation cues such as distances to the nearby obstacles and obstacle types. In the proposed approach, a 3-D range image is first segmented using histogram thresholding and mean-shift grouping. Then Fourier and GIST descriptors are applied on each segmented object to extract shape and texture features. Finally, support vector machines are used to recognize the obstacles. This paper focuses on classifying pedestrian and non-pedestrian obstacles. Evaluated on an image data set acquired using a time-of-flight camera, the proposed approach achieves a classification rate of 99.5%. ABSTRACTThis paper proposes a new approach to classify obstacles using a time-of-flight camera, for applications in assistive navigation of the visually impaired. Combining range and intensity images enables fast and accurate object segmentation, and provides useful navigation cues such as distances to the nearby obstacles and obstacle types. In the proposed approach, a 3-D range image is first segmented using histogram thresholding and mean-shift grouping. Then Fourier and GIST descriptors are applied on each segmented object to extract shape and texture features. Finally, support vector machines are used to recognize the obstacles. This paper focuses on classifying pedestrian and non-pedestrian obstacles. Evaluated on an image data set acquired using a time-of-flight camera, the proposed approach achieves a classification rate of 99.5%.

show abstract

Section: Related Workmentioning

confidence: 99%

Scene Segmentation and Pedestrian Classification from 3-D Range and Intensity Images

Xue

Phung

Bouzerdoum

2012

2012 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

show abstract

“…Other approaches have fused information from different modalities on feature-level by establishing a joint feature space (low-level fusion): [1,22] combined gray-level intensity with motion. In [17], intensity and depth features derived from a 3D camera with very low resolution (pedestrian heights between 4 and 8 pixels) were utilized. Finally, fusion can occur on classifier-level [1,2].…”

Section: Related Workmentioning

confidence: 99%

“…We follow a high-level fusion strategy which allows to tune features specifically to each modality and base the final decision on a combined vote of the individual classifiers. As opposed to lowlevel fusion approaches [17,22], this strategy does not suffer from the increased dimensionality of a joint feature space.…”

Section: Related Workmentioning

confidence: 99%

High-Level Fusion of Depth and Intensity for Pedestrian Classification

Rohrbach

Enzweiler

Gavrila

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper presents a novel approach to pedestrian classification which involves a high-level fusion of depth and intensity cues. Instead of utilizing depth information only in a pre-processing step, we propose to extract discriminative spatial features (gradient orientation histograms and local receptive fields) directly from (dense) depth and intensity images. Both modalities are represented in terms of individual feature spaces, in each of which a discriminative model is learned to distinguish between pedestrians and non-pedestrians. We refrain from the construction of a joint feature space, but instead employ a high-level fusion of depth and intensity at classifier-level. Our experiments on a large real-world dataset demonstrate a significant performance improvement of the combined intensity-depth representation over depth-only and intensity-only models (factor four reduction in false positives at comparable detection rates). Moreover, high-level fusion outperforms low-level fusion using a joint feature space approach.

show abstract

“…In particular, Time-ofFlight (ToF) based devices [13] and Microsoft's low-cost Kinect [7] are of special interest and popularity. Among others, these real-time capable RI sensors are currently deployed in controller-free gaming in consumer electronics and hold potential for biometric face recognition [3] or pedestrian detection in automotive industry [18]. Furthermore, the deployment of RI technologies in medical engineering is subject to current research with a broad range of applications such as fractionated radiotherapy [19] or image guided liver surgery [15].…”

Section: Introductionmentioning

confidence: 99%

Real-time preprocessing for dense 3-D range imaging on the GPU: Defect interpolation, bilateral temporal averaging and guided filtering

Wasza

Bauer

Hornegger

2011

2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)

View full text Add to dashboard Cite

Recent advances in range imaging (RI) have enabled dense 3-D scene acquisition in real-time. However, due to physical limitations and the underlying range sampling principles, range data are subject to noise and may contain invalid measurements. Hence, data preprocessing is a prerequisite for practical applications but poses a challenge with respect to real-time constraints. In this paper, we propose a generic and modality-independent pipeline for efficient RI data preprocessing on the graphics processing unit (GPU). The contributions of this work are efficient GPU implementations of normalized convolution for the restoration of invalid measurements, bilateral temporal averaging for dynamic scenes, and guided filtering for edge-preserving denoising. Furthermore, we show that the transformation from range measurements to 3-D world coordinates can be computed efficiently on the GPU.

show abstract

Pedestrian recognition using combined low-resolution depth and intensity images

Cited by 13 publications

References 13 publications

Scene Segmentation and Pedestrian Classification from 3-D Range and Intensity Images

Scene Segmentation and Pedestrian Classification from 3-D Range and Intensity Images

High-Level Fusion of Depth and Intensity for Pedestrian Classification

Real-time preprocessing for dense 3-D range imaging on the GPU: Defect interpolation, bilateral temporal averaging and guided filtering

Contact Info

Product

Resources

About