Cascaded Confidence Filtering for Improved Tracking-by-Detection

Stalder, Severin; Gräbner, Helmut; Gool, Luc Van

doi:10.1007/978-3-642-15549-9_27

Cited by 66 publications

(35 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In many tracking-by-detection approaches [15], [22], the detection responses are obtained by global scanning using the human detector, which is too time intensive for time-critical online tracking systems.…”

Section: Real-time Player Detectionmentioning

confidence: 99%

Online Learned Player Recognition Model Based Soccer Player Tracking and Labeling for Long-Shot Scenes

Zhao

Wang

et al. 2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYSoccer player tracking and labeling suffer from the similar appearance of the players in the same team, especially in long-shot scenes where the faces and the numbers of the players are too blurry to identify. In this paper, we propose an efficient multi-player tracking system. The tracking system takes the detection responses of a human detector as inputs. To realize real-time player detection, we generate a spatial proposal to minimize the scanning scope of the detector. The tracking system utilizes the discriminative appearance models trained using the online Boosting method to reduce data-association ambiguity caused by the appearance similarity of the players. We also propose to build an online learned player recognition model which can be embedded in the tracking system to approach online player recognition and labeling in tracking applications for long-shot scenes by two stages. At the first stage, to build the model, we utilize the fast k-means clustering method instead of classic k-means clustering to build and update a visual word vocabulary in an efficient online manner, using the informative descriptors extracted from the training samples drawn at each time step of multi-player tracking. The first stage finishes when the vocabulary is ready. At the second stage, given the obtained visual word vocabulary, an incremental vector quantization strategy is used to recognize and label each tracked player. We also perform importance recognition validation to avoid mistakenly recognizing an outlier, namely, people we do not need to recognize, as a player. Both quantitative and qualitative experimental results on the long-shot video clips of a real soccer game video demonstrate that, the proposed player recognition model performs much better than some state-of-the-art online learned models, and our tracking system also performs quite effectively even under very complicated situations.

show abstract

Section: Real-time Player Detectionmentioning

confidence: 99%

Online Learned Player Recognition Model Based Soccer Player Tracking and Labeling for Long-Shot Scenes

Zhao

Wang

et al. 2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…These approaches detect humans in each frame and gradually associate them into tracks based on motion and appearance cues. Appearance models are often pre-defined [9,4] or online learned [1,12,13]. Occlusions are often ignored [13,2] or modeled as potential nodes in an association graph [4,1], but have not been used explicitly for appearance modeling, indicating high possibilities that parts used for modeling appearances of a person belong to other individuals.…”

Section: Related Workmentioning

confidence: 99%

Online Learned Discriminative Part-Based Appearance Models for Multi-human Tracking

Yang

Nevatia

2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

Abstract. We introduce an online learning approach to produce discriminative part-based appearance models (DPAMs) for tracking multiple humans in real scenes by incorporating association based and category free tracking methods. Detection responses are gradually associated into tracklets in multiple levels to produce final tracks. Unlike most previous multi-target tracking approaches which do not explicitly consider occlusions in appearance modeling, we introduce a part based model that explicitly finds unoccluded parts by occlusion reasoning in each frame, so that occluded parts are removed in appearance modeling. Then DPAMs for each tracklet is online learned to distinguish a tracklet with others as well as the background, and is further used in a conservative category free tracking approach to partially overcome the missed detection problem as well as to reduce difficulties in tracklet associations under long gaps. We evaluate our approach on three public data sets, and show significant improvements compared with state-of-art methods.

show abstract

“…Based on this line of work to improve person detectors locally and using scene specific context, we recently proposed a novel approach to increase the robustness of any generic person detection algorithm. The cascaded confidence filter [4] successively incorporates constraints on the size of the object, on the appearance of the background and on the smoothness of the trajectories. In fact, we model the continuous detection confidences similarly to traditional background pixel color modeling.…”

Section: Basic Object Detection and Trackingmentioning

confidence: 99%

Tools for semi-automatic monitoring of industrial workflows

Mörzinger

Sardis

Rosenberg

et al. 2010

Proceedings of the First ACM International Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams

Self Cite

View full text Add to dashboard Cite

This paper describes a tool chain for monitoring complex workflows. Statistics obtained from automatic workflow monitoring in a car assembly environment assist in improving industrial safety and process quality. To this end, we propose automatic detection and tracking of humans and their activity in multiple networked cameras. The described tools offer human operators retrospective analysis of a huge amount of pre-recorded and analyzed footage from multiple cameras in order to get a comprehensive overview of the workflows. Furthermore, the tools help technical administrators in adjusting algorithms by letting the user correct detections (for relevance feedback) and ground truth for evaluation. Another important feature of the tool chain is the capability to inform the employees about potentially risky conditions using the tool for automatic detection of unusual scenes.

show abstract

Cascaded Confidence Filtering for Improved Tracking-by-Detection

Cited by 66 publications

References 13 publications

Online Learned Player Recognition Model Based Soccer Player Tracking and Labeling for Long-Shot Scenes

Online Learned Player Recognition Model Based Soccer Player Tracking and Labeling for Long-Shot Scenes

Online Learned Discriminative Part-Based Appearance Models for Multi-human Tracking

Tools for semi-automatic monitoring of industrial workflows

Contact Info

Product

Resources

About