Disparity Statistics for Pedestrian Detection: Combining Appearance, Motion and Stereo

Walk, Stefan; Schindler, Konrad; Schiele, Bernt

doi:10.1007/978-3-642-15567-3_14

Cited by 29 publications

(36 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar phenomenon has also been observed in Ref. [29] when combining Haar feature. Due to enriched feature pool, NOGCF with all the structures improves over NOGCF with 2 × 2 cell/block structure only.…”

Section: Evaluation Of the Detectors On Image Datasetssupporting

confidence: 87%

A Real-Time Human Detection System for Video

Zeng

Wang

Lin

et al. 2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis work presents a real-time human detection system for VGA (Video Graphics Array, 640 × 480) video, which well suits visual surveillance applications. To achieve high running speed and accuracy, firstly we design multiple fast scalar feature types on the gradient channels, and experimentally identify that NOGCF (Normalized Oriented Gradient Channel Feature) has better performance with Gentle AdaBoost in cascaded classifiers. A confidence measure for cascaded classifiers is developed and utilized in the subsequent tracking stage. Secondly, we propose to use speedup techniques including a detector pyramid for multi-scale detection and channel compression for integral channel calculation respectively. Thirdly, by integrating the detector's discrete detected humans and continuous detection confidence map, we employ a two-layer tracking by detection algorithm for further speedup and accuracy improvement. Compared with other methods, experiments show the system is significantly faster with 20 fps running speed in VGA video and has better accuracy as well.

show abstract

Section: Evaluation Of the Detectors On Image Datasetssupporting

confidence: 87%

A Real-Time Human Detection System for Video

Zeng

Wang

Lin

et al. 2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…We follow [35] and work with disparity values directly rather than depth to avoid problems with infinite depth, and amplifying errors at small disparities. Estimating the dense disparity field for a single stereo pair of 960 × 540 pixels takes approximately 30 seconds on a modern GPU using the implementation from [5].…”

Section: Methodsmentioning

confidence: 99%

“…Also, no articulated person model was used. Many recent works have investigated the use of stereo (or depth) signal in tasks such as person detection [19,29,32,35], pose estimation [31], and segmenta- tion [21]. Given the success in these individual tasks, the challenge now is to take a step further, and look at these problems jointly in scenarios involving multiple interacting people (see Figure 1).…”

Section: Related Workmentioning

confidence: 99%

“…The disparity features are obtained by computing HOG on disparity maps. Our HOG feature representation for disparity maps is similar to that used in [32,35] for person/pedestrian detection. We track the person detections computed in each frame of the video, and interpolate to fillin any missing detections, similar to [13].…”

Section: Estimating An Articulated Pose Maskmentioning

confidence: 99%

See 1 more Smart Citation

Pose Estimation and Segmentation of People in 3D Movies

Alahari

Seguin

Šivic

et al. 2013

2013 IEEE International Conference on Computer Vision

View full text Add to dashboard Cite

We seek to obtain a pixel-wise segmentation and pose estimation of multiple people in a stereoscopic video. This involves challenges such as dealing with unconstrained stereoscopic video, non-stationary cameras, and complex indoor and outdoor dynamic scenes. The contributions of our work are two-fold: First, we develop a segmentation model incorporating person detection, pose estimation, as well as colour, motion, and disparity cues. Our new model explicitly represents depth ordering and occlusion. Second, we introduce a stereoscopic dataset with frames extracted from feature-length movies "StreetDance 3D" and "Pina". The dataset contains 2727 realistic stereo pairs and includes annotation of human poses, person bounding boxes, and pixel-wise segmentations for hundreds of people. The dataset is composed of indoor and outdoor scenes depicting multiple people with frequent occlusions. We demonstrate results on our new challenging dataset, as well as on the H2view dataset from (Sheasby et al. ACCV 2012).

show abstract

“…Babenko et al (B. Babenko and Belongie, 2008) proposed an approach for simultaneously separating data into coherent groups and training separate classifiers for each; (C. Wojek and Schiele, 2009) showed that both (S. Maji and Malik, 2008) and (B. Babenko and Belongie, 2008) gave modest gains over linear SVMs and AdaBoost for pedestrian detection, especially when used in combination (S. Walk and Schiele, 2010).…”

Section: Related Workmentioning

confidence: 99%

Towards Reliable Real-time Person Detection

Serban

Simha

Bathrinarayanan

et al. 2014

Proceedings of the 9th International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:We propose a robust real-time person detection system, which aims to serve as solid foundation for developing solutions at an elevated level of reliability. Our belief is that clever handling of input data correlated with efficacious training algorithms are key for obtaining top performance. We introduce a comprehensive training method based on random sampling that compiles optimal classifiers with minimal bias and overfit rate. Building upon recent advances in multi-scale feature computations, our approach attains state-of-the-art accuracy while running at high frame rate.

show abstract

Disparity Statistics for Pedestrian Detection: Combining Appearance, Motion and Stereo

Cited by 29 publications

References 23 publications

A Real-Time Human Detection System for Video

A Real-Time Human Detection System for Video

Pose Estimation and Segmentation of People in 3D Movies

Towards Reliable Real-time Person Detection

Contact Info

Product

Resources

About