Real-time multi-person tracking with detector assisted structure propagation

Mitzel, Dennis; Leibe, Bastian

doi:10.1109/iccvw.2011.6130357

Cited by 35 publications

(33 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thirdly, the outlier blob localization approach and switching strategy are proposed to maintain effective searching window for object reacquisition after complete occlusion. The superior performance against the appearance-based [3,12,5] and detection-based tracking approaches [13,14,10] on well-known binocular datasets [8,15,16] proves the effectiveness of the proposed tracking algorithm.…”

Section: Introductionmentioning

confidence: 87%

“…In recent years, the depth-assisted systems [13,14,10] achieve better detection recall rates on the same datasets [8] and also outperform in other scenarios, so we choose to use the numerical results from [13,14,10] and compare our recall rate (successful tracked objects/total annotations), derived from the same evaluation criteria in [8,13,14,10]), with the defined best recall rates (false posi- Fig. 9.…”

Section: Methodsmentioning

confidence: 99%

“…10. The table shows the recall rate (successful tracked objects/total annotations) for our tracker and three competing methods [13,14,10] (false positives/image = 0.5). The best and second best results are displayed in red and blue for each sequence.…”

Section: Methodsmentioning

confidence: 99%

“…Additionally, [10,14,13] extract ROIs from an image by projecting the 3D points from a depth map onto the estimated 2D ground plane and in turn constrain object detection within those ROIs. Interactions between different pedestrians are explicitly modeled using long-term tracking trajectory candidates optimization and selection in a data association manner.…”

Section: Previous Workmentioning

confidence: 99%

“…To make depth cue applicable to most of tracking situations, we use an improved generic stereo algorithm [7] to generate dense depth map from a binocular video sequence. Our tracking scenario is similar to [8][9][10] which is extremely challenging due to various factors such as motion blur, varying lighting, continuously interacting moving objects, frequent partial and complete occlusion and mobile camera placement. We exploit discrete object-depth labels on generated depth map repetitively over time to drive the object tracking and segmentation in crowd dynamic scenes, based on the assumption of statistically uniform depth distribution within the object area.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Robust Object Tracking in Crowd Dynamic Scenes Using Explicit Stereo Depth

Lü

Hager

et al. 2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

Abstract. In this paper, we exploit robust depth information with simple color-shape appearance model on single object tracking in crowd dynamic scenes. Since binocular video streams are captured from a moving camera rig, background subtraction cannot provide a reliable enhancement of region of interest. Our main contribution is a novel tracking strategy to employ explicit stereo depth to track and segment object in crowd dynamic scenes with occlusion handling. Appearance cues including color and shape play a secondary role to further extract the foreground acquired by previous depth-based segmentation. The proposed depth-driven tracking approach can largely alleviate the drifting issue, especially when the object frequently interacts with similar background in long sequence tracking. The problems caused by rapid object appearance change can also be avoided due to the stability of the depth cue. Furthermore, we propose a new, yet simple and effective depth-based scheme to cope with complete occlusion in tracking. From experiments on a large collection of challenging outdoor and indoor sequences, our algorithm demonstrates accurate and reliable tracking performance which outperforms other state-of-the-art competing algorithms.

show abstract

Section: Introductionmentioning

confidence: 87%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Robust Object Tracking in Crowd Dynamic Scenes Using Explicit Stereo Depth

Lü

Hager

et al. 2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

show abstract

Real Time People Tracking in Crowded Environments with Range Measurements

2013

View full text Add to dashboard Cite

RGB-D Human Detection and Tracking for Industrial Environments

Munaro

Lewis

Chambers

et al. 2015

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Reliably detecting and tracking movements of nearby workers on the factory floor are crucial to the safety of advanced manufacturing automation in which humans and robots share the same workspace. In this work, we address the problem of multiple people detection and tracking in industrial environments by proposing algorithms which exploit both color and depth data to robustly track people in real time. For people detection, a cascade organization of these algorithms is proposed, while tracking is performed based on a particle filter which can interpolate sparse detection results by exploiting color histograms of people. Tracking results of different combinations of the proposed methods are evaluated on a novel dataset collected with a consumer RGB-D sensor in an industrial-like environment. Our techniques obtain good tracking performances even in an industrial setting and reach more than 30Hz update rate. All these algorithms have been released as open source as part of the ROS-Industrial project

show abstract

Real-time multi-person tracking with detector assisted structure propagation

Cited by 35 publications

References 17 publications

Robust Object Tracking in Crowd Dynamic Scenes Using Explicit Stereo Depth

Robust Object Tracking in Crowd Dynamic Scenes Using Explicit Stereo Depth

Real Time People Tracking in Crowded Environments with Range Measurements

RGB-D Human Detection and Tracking for Industrial Environments

Contact Info

Product

Resources

About