A real-time pedestrian detection system based on structure and appearance classification

Bansal, Mayank; Jung, Soon Ki; Matei, Bogdan; Eledath, Jayan; Sawhney, Harpreet

doi:10.1109/robot.2010.5509841

Cited by 23 publications

(55 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To deal with this problem, several approaches have been proposed to restrict the evaluation of the detector to only few ROIs that are extracted based on, e.g., stereo range data [1,2,8], motion [5], or scene geometry [11]. In this paper we follow a similar strategy of ROI extraction based on stereo information in order to reduce the search space for the detector.…”

Section: Related Workmentioning

confidence: 99%

“…In order to achieve this, we exploit information about the location of the objects on the ground plane based on the stereo data, similar to [2]. The ROI extraction process is visualized in Fig.…”

Section: Roi Extractionmentioning

confidence: 99%

“…Similar to [2] we generate regions of interest (ROIs) based on the stereo data in order to reduce the search space of the detector. Our approach learns a continuous normalized depth template from annotations of human upper bodies and slides this template over the extracted depth ROIs at several scales c 2012.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Close-Range Human Detection and Tracking for Head-Mounted Cameras

Mitzel

Leibe

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

In this paper we consider the problem of multi-person detection from the perspective of a head mounted stereo camera. As pedestrians close to the camera cannot be detected by classical full-body detectors due to strong occlusion, we propose a stereo depth-template based detection approach for close-range pedestrians. We perform a sliding window procedure, where we measure the similarity between a learned depth template and the depth image. To reduce the search space of the detector we slide the detector only over few selected regions of interest that are generated based on depth information. The region-of-interest selection allows us to further constrain the number of scales to be evaluated, significantly reducing the computational cost. We present experiments on stereo sequences recorded from a head-mounted camera setup in crowded shopping street scenarios and show that our proposed approach achieves superior performance on this very challenging data.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Roi Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Close-Range Human Detection and Tracking for Head-Mounted Cameras

Mitzel

Leibe

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

show abstract

“…They usually restrict detector evaluation to a small number of pre-selected ROIs [11] based on 3D geometry [3], motion [5], texture content [20], or stereo depth [10]. Recent approaches targeted at mobile robotics have adopted similar strategies [1,2]. However, such approaches risk losing detections if the corresponding regions are missed by the ROI selection stage.…”

Section: Introductionmentioning

confidence: 99%

“…(2) In order to satisfy the conflicting goals of detecting new objects while stabilizing already existing tracks, we propose a two-tiered realization of the Poisson process model that takes into account a track's accumulated uncertainty. (3) We experimentally show that the proposed framework achieves robust multi-person tracking performance even with few ROI detector evaluations, making it possible to reduce detector evaluation to a minimum.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Multi-Person Tracking with Time-Constrained Detection

Mitzel¹,

Sudowe²,

Leibe³

2011

Procedings of the British Machine Vision Conference 2011

View full text Add to dashboard Cite

This paper presents a robust real-time multi-person tracking framework for busy street scenes. Tracking-by-detection approaches have recently been successfully applied to this task. However, their run-time is still limited by the computationally expensive object detection component. In this paper, we therefore consider the problem of making best use of an object detector with a fixed and very small time budget. The question we ask is: given a fixed time budget that allows for detector-based verification of k small regions-of-interest (ROIs) in the image, what are the best regions to attend to in order to obtain stable tracking performance? We address this problem by applying a statistical Poisson process model in order to rate the urgency by which individual ROIs should be attended to. These ROIs are initially extracted from a 3D depth-based occupancy map of the scene and are then tracked over time. This allows us to balance the system resources in order to satisfy the twin goals of detecting newly appearing objects, while maintaining the quality of existing object trajectories.

show abstract