Results 1 - 10
of
58
Online Multi-Person Trackingby-Detection from a Single, Uncalibrated Camera
- PAMI
"... Abstract—In this paper, we address the problem of automatically detecting and tracking a variable number of persons in complex scenes using a monocular, potentially moving, uncalibrated camera. We propose a novel approach for multi-person tracking-bydetection in a particle filtering framework. In ad ..."
Abstract
-
Cited by 77 (0 self)
- Add to MetaCart
Abstract—In this paper, we address the problem of automatically detecting and tracking a variable number of persons in complex scenes using a monocular, potentially moving, uncalibrated camera. We propose a novel approach for multi-person tracking-bydetection in a particle filtering framework. In addition to final high-confidence detections, our algorithm uses the continuous confidence of pedestrian detectors and online trained, instance-specific classifiers as a graded observation model. Thus, generic object category knowledge is complemented by instance-specific information. The main contribution of this paper is to explore how these unreliable information sources can be used for robust multi-person tracking. The algorithm detects and tracks a large number of dynamically moving persons in complex scenes with occlusions, does not rely on background modeling, requires no camera or ground plane calibration, and only makes use of information from the past. Hence, it imposes very few restrictions and is suitable for online applications. Our experiments show that the method yields good tracking performance in a large variety of highly dynamic scenarios, such as typical surveillance videos, webcam footage, or sports sequences. We demonstrate that our algorithm outperforms other methods that rely on additional information. Furthermore, we analyze the influence of different algorithm components on the robustness. Index Terms—Multi-object tracking, tracking-by-detection, detector confidence particle filter, pedestrian detection, particle filtering, sequential monte carlo estimation, online learning, detector confidence, surveillance, sports analysis, traffic safety 1
An online learned crf model for multi-target tracking
- In CVPR
, 2012
"... We introduce an online learning approach for multitarget tracking. Detection responses are gradually associated into tracklets in multiple levels to produce final tracks. Unlike most previous approaches which only focus on producing discriminative motion and appearance models for all targets, we fur ..."
Abstract
-
Cited by 43 (0 self)
- Add to MetaCart
(Show Context)
We introduce an online learning approach for multitarget tracking. Detection responses are gradually associated into tracklets in multiple levels to produce final tracks. Unlike most previous approaches which only focus on producing discriminative motion and appearance models for all targets, we further consider discriminative features for distinguishing difficult pairs of targets. The tracking problem is formulated using an online learned CRF model, and is transformed into an energy minimization problem. The energy functions include a set of unary functions that are based on motion and appearance models for discriminating all targets, as well as a set of pairwise functions that are based on models for differentiating corresponding pairs of tracklets. The online CRF approach is more powerful at distinguishing spatially close targets with similar appearances, as well as in dealing with camera motions. An efficient algorithm is introduced for finding an association with low energy cost. We evaluate our approach on three public data sets, and show significant improvements compared with several state-of-art methods. 1.
Teaching 3d geometry to deformable part models
- In Proc. CVPR
, 2012
"... Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the detection of individual objects, higher-level applica-tions such as 3D scene understanding or 3D object tracking would bene ..."
Abstract
-
Cited by 38 (7 self)
- Add to MetaCart
(Show Context)
Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the detection of individual objects, higher-level applica-tions such as 3D scene understanding or 3D object tracking would benefit from more fine-grained object hypotheses in-corporating 3D geometric information, such as viewpoints or the locations of individual parts. In this paper, we help narrowing the representational gap between the ideal in-put of a scene understanding system and object class detec-tor output, by designing a detector particularly tailored to-wards 3D geometric reasoning. In particular, we extend the successful discriminatively trained deformable part models to include both estimates of viewpoint and 3D parts that are consistent across viewpoints. We experimentally verify that adding 3D geometric information comes at minimal perfor-mance loss w.r.t. 2D bounding box localization, but outper-forms prior work in 3D viewpoint estimation and ultra-wide baseline matching. 1.
We are family: Joint pose estimation of multiple persons
- In ECCV
, 2010
"... Abstract. We present a novel multi-person pose estimation framework, which extends pictorial structures (PS) to explicitly model interactions between people and to estimate their poses jointly. Interactions are modeled as occlusions between people. First, we propose an occlusion probability predicto ..."
Abstract
-
Cited by 38 (2 self)
- Add to MetaCart
(Show Context)
Abstract. We present a novel multi-person pose estimation framework, which extends pictorial structures (PS) to explicitly model interactions between people and to estimate their poses jointly. Interactions are modeled as occlusions between people. First, we propose an occlusion probability predictor, based on the location of persons automatically detected in the image, and incorporate the predictions as occlusion priors into our multi-person PS model. Moreover, our model includes an inter-people exclusion penalty, preventing body parts from different people from occupying the same image region. Thanks to these elements, our model has a global view of the scene, resulting in better pose estimates in group photos, where several persons stand nearby and occlude each other. In a comprehensive evaluation on a new, challenging group photo datasets we demonstrate the benefits of our multi-person model over a state-of-the-art single-person pose estimator which treats each person independently. 1
3d2pm - 3d deformable part models
- In ECCV
, 2012
"... Abstract. As objects are inherently 3-dimensional, they have been mod-eled in 3D in the early days of computer vision. Due to the ambiguities arising from mapping 2D features to 3D models, 2D feature-based models are the predominant paradigm in object recognition today. While such models have shown ..."
Abstract
-
Cited by 27 (4 self)
- Add to MetaCart
Abstract. As objects are inherently 3-dimensional, they have been mod-eled in 3D in the early days of computer vision. Due to the ambiguities arising from mapping 2D features to 3D models, 2D feature-based models are the predominant paradigm in object recognition today. While such models have shown competitive bounding box (BB) detection perfor-mance, they are clearly limited in their capability of fine-grained reason-ing in 3D or continuous viewpoint estimation as required for advanced tasks such as 3D scene understanding. This work extends the deformable part model [1] to a 3D object model. It consists of multiple parts mod-eled in 3D and a continuous appearance model. As a result, the model generalizes beyond BB oriented object detection and can be jointly op-timized in a discriminative fashion for object detection and viewpoint estimation. Our 3D Deformable Part Model (3D2PM) leverages on CAD data of the object class, as a 3D geometry proxy. 1
Monocular 3d scene modeling and inference: Understanding multi-object traffic scenes
- In Proceedings of ECCV
, 2010
"... Abstract. Scene understanding has (again) become a focus of computer vision research, leveraging advances in detection, context modeling, and tracking. In this paper, we present a novel probabilistic 3D scene model that encompasses multi-class object detection, object tracking, scene labeling, and 3 ..."
Abstract
-
Cited by 22 (6 self)
- Add to MetaCart
(Show Context)
Abstract. Scene understanding has (again) become a focus of computer vision research, leveraging advances in detection, context modeling, and tracking. In this paper, we present a novel probabilistic 3D scene model that encompasses multi-class object detection, object tracking, scene labeling, and 3D geometric relations. This integrated 3D model is able to represent complex interactions like inter-object occlusion, physical exclusion between objects, and geometric context. Inference allows to recover 3D scene context and perform 3D multi-object tracking from a mobile observer, for objects of multiple categories, using only monocular video as input. In particular, we show that a joint scene track-let model for the evidence collected over multiple frames substantially improves performance. The approach is evaluated for two different types of challenging on-board sequences. We first show a substantial improvement to the state-of-the-art in 3D multi-people tracking. Moreover, a similar performance gain is achieved for multi-class 3D tracking of cars and trucks on a new, challenging dataset. 1
Joint 3d estimation of objects and scene layout
- In NIPS
, 2011
"... We propose a novel generative model that is able to reason jointly about the 3D scene layout as well as the 3D location and orientation of objects in the scene. In particular, we infer the scene topology, geometry as well as traffic activities from a short video sequence acquired with a single camer ..."
Abstract
-
Cited by 19 (9 self)
- Add to MetaCart
(Show Context)
We propose a novel generative model that is able to reason jointly about the 3D scene layout as well as the 3D location and orientation of objects in the scene. In particular, we infer the scene topology, geometry as well as traffic activities from a short video sequence acquired with a single camera mounted on a moving car. Our generative model takes advantage of dynamic information in the form of vehicle tracklets as well as static information coming from semantic labels and ge-ometry (i.e., vanishing points). Experiments show that our approach outperforms a discriminative baseline based on multiple kernel learning (MKL) which has ac-cess to the same image information. Furthermore, as we reason about objects in 3D, we are able to significantly increase the performance of state-of-the-art object detectors in their ability to estimate object orientation. 1
Continuous Energy Minimization for Multi-Target Tracking
"... Abstract—Many recent advances in multiple target tracking aim at finding a (nearly) optimal set of trajectories within a temporal window. To handle the large space of possible trajectory hypotheses, it is typically reduced to a finite set by some form of data-driven or regular discretization. In thi ..."
Abstract
-
Cited by 18 (3 self)
- Add to MetaCart
(Show Context)
Abstract—Many recent advances in multiple target tracking aim at finding a (nearly) optimal set of trajectories within a temporal window. To handle the large space of possible trajectory hypotheses, it is typically reduced to a finite set by some form of data-driven or regular discretization. In this work we propose an alternative formulation of multi-target tracking as minimization of a continuous energy. Contrary to recent approaches, we focus on designing an energy that corresponds to a more complete representation of the problem, rather than one that is amenable to global optimization. Besides the image evidence, the energy function takes into account physical constraints, such as target dynamics, mutual exclusion, and track persistence. In addition, partial image evidence is handled with explicit occlusion reasoning, and different targets are disambiguated with an appearance model. To nevertheless find strong local minima of the proposed non-convex energy we construct a suitable optimization scheme that alternates between continuous conjugate gradient descent and discrete trans-dimensional jump moves. These moves, which are executed such that they always reduce the energy, allow the search to escape weak minima and explore a much larger portion of the search space of varying dimensionality. We demonstrate the validity of our approach with an extensive quantitative evaluation on several public datasets. Index Terms—Multi-object tracking, tracking-by-detection, visual surveillance, continuous optimization. F 1
Monocular 3D scene understanding with explicit occlusion reasoning
- In CVPR
, 2011
"... Scene understanding from a monocular, moving cam-era is a challenging problem with a number of applica-tions including robotics and automotive safety. While re-cent systems have shown that this is best accomplished with a 3D scene model, handling of partial object occlu-sion is still unsatisfactory. ..."
Abstract
-
Cited by 18 (4 self)
- Add to MetaCart
(Show Context)
Scene understanding from a monocular, moving cam-era is a challenging problem with a number of applica-tions including robotics and automotive safety. While re-cent systems have shown that this is best accomplished with a 3D scene model, handling of partial object occlu-sion is still unsatisfactory. In this paper we propose an ap-proach that tightly integrates monocular 3D scene tracking-by-detection with explicit object-object occlusion reason-ing. Full object and object part detectors are combined in a mixture of experts based on their expected visibility, which is obtained from the 3D scene model. For the difficult case of multi-people tracking, we demonstrate that our approach yields more robust detection and tracking of partially visible pedestrians, even when they are occluded over long periods of time. Our approach is evaluated on two challenging se-quences recorded from a moving camera in busy pedestrian zones and outperforms several state-of-the-art approaches. 1.
People tracking in rgb-d data with on-line boosted target models
- In IEEE/RSJ Int. Conf. on
, 2011
"... Abstract — People tracking is a key component for robots that are deployed in populated environments. Previous works have used cameras and 2D and 3D range finders for this task. In this paper, we present a 3D people detection and tracking approach using RGB-D data. We combine a novel multi-cue perso ..."
Abstract
-
Cited by 18 (1 self)
- Add to MetaCart
(Show Context)
Abstract — People tracking is a key component for robots that are deployed in populated environments. Previous works have used cameras and 2D and 3D range finders for this task. In this paper, we present a 3D people detection and tracking approach using RGB-D data. We combine a novel multi-cue person detector for RGB-D data with an on-line detector that learns individual target models. The two detectors are integrated into a decisional framework with a multi-hypothesis tracker that controls on-line learning through a track interpretation feedback. For on-line learning, we take a boosting approach using three types of RGB-D features and a confidence maximization search in 3D space. The approach is general in that it neither relies on background learning nor a ground plane assumption. For the evaluation, we collect data in a populated indoor environment using a setup of three Microsoft Kinect sensors with a joint field of view. The results demonstrate reliable 3D tracking of people in RGB-D data and show how the framework is able to avoid drift of the on-line detector and increase the overall tracking performance. I.
