Results 1 - 10
of
56
M.: Person re-identification by symmetry-driven accumulation of local features
- In: IEEE Conf. Computer Vision and Pattern Recognition
, 2010
"... In this paper, we present an appearance-based method for person re-identification. It consists in the extraction of features that model three complementary aspects of the human appearance: the overall chromatic content, the spatial arrangement of colors into stable regions, and the presence of recur ..."
Abstract
-
Cited by 152 (6 self)
- Add to MetaCart
(Show Context)
In this paper, we present an appearance-based method for person re-identification. It consists in the extraction of features that model three complementary aspects of the human appearance: the overall chromatic content, the spatial arrangement of colors into stable regions, and the presence of recurrent local motifs with high entropy. All this information is derived from different body parts, and weighted opportunely by exploiting symmetry and asymmetry perceptual principles. In this way, robustness against very low resolution, occlusions and pose, viewpoint and illumination changes is achieved. The approach applies to situations where the number of candidates varies continuously, considering single images or bunch of frames for each individual. It has been tested on several public benchmark datasets (ViPER, iLIDS, ETHZ), gaining new state-of-the-art performances. 1.
Re-identification by relative distance comparison
- In PAMI
, 2013
"... Abstract—Matching people across nonoverlapping camera views at different locations and different times, known as person reidentification, is both a hard and important problem for associating behavior of people observed in a large distributed space over a prolonged period of time. Person reidentifica ..."
Abstract
-
Cited by 55 (8 self)
- Add to MetaCart
(Show Context)
Abstract—Matching people across nonoverlapping camera views at different locations and different times, known as person reidentification, is both a hard and important problem for associating behavior of people observed in a large distributed space over a prolonged period of time. Person reidentification is fundamentally challenging because of the large visual appearance changes caused by variations in view angle, lighting, background clutter, and occlusion. To address these challenges, most previous approaches aim to model and extract distinctive and reliable visual features. However, seeking an optimal and robust similarity measure that quantifies a wide range of features against realistic viewing conditions from a distance is still an open and unsolved problem for person reidentification. In this paper, we formulate person reidentification as a relative distance comparison (RDC) learning problem in order to learn the optimal similarity measure between a pair of person images. This approach avoids treating all features indiscriminately and does not assume the existence of some universally distinctive and reliable features. To that end, a novel relative distance comparison model is introduced. The model is formulated to maximize the likelihood of a pair of true matches having a relatively smaller distance than that of a wrong match pair in a soft discriminant manner. Moreover, in order to maintain the tractability of the model in large scale learning, we further develop an ensemble RDC model. Extensive experiments on three publicly available benchmarking datasets are carried out to demonstrate the clear superiority of the proposed RDC models over related popular person reidentification techniques. The results also show that the new RDC models are more robust against visual appearance changes and less susceptible to model overfitting compared to other related existing models. Index Terms—Person reidentification, feature quantification, feature selection, relative distance comparison Ç 1
Probabilistic modeling of scene dynamics for applications in visual surveillance
- IEEE Trans. Pattern Anal. Mach. Intell
, 2009
"... Abstract—We propose a novel method to model and learn the scene activity, observed by a static camera. The proposed model is very general and can be applied for solution of a variety of problems. The motion patterns of objects in the scene are modeled in the form of a multivariate nonparametric prob ..."
Abstract
-
Cited by 37 (3 self)
- Add to MetaCart
(Show Context)
Abstract—We propose a novel method to model and learn the scene activity, observed by a static camera. The proposed model is very general and can be applied for solution of a variety of problems. The motion patterns of objects in the scene are modeled in the form of a multivariate nonparametric probability density function of spatiotemporal variables (object locations and transition times between them). Kernel Density Estimation is used to learn this model in a completely unsupervised fashion. Learning is accomplished by observing the trajectories of objects by a static camera over extended periods of time. It encodes the probabilistic nature of the behavior of moving objects in the scene and is useful for activity analysis applications, such as persistent tracking and anomalous motion detection. In addition, the model also captures salient scene features, such as the areas of occlusion and most likely paths. Once the model is learned, we use a unified Markov Chain Monte Carlo (MCMC)-based framework for generating the most likely paths in the scene, improving foreground detection, persistent labeling of objects during tracking, and deciding whether a given trajectory represents an anomaly to the observed motion patterns. Experiments with real-world videos are reported which validate the proposed approach.
People Detection using Color and Depth Images ⋆
"... Abstract. We present a strategy that combines color and depth images to detect people in indoor environments. Similarity of image appearance and closeness in 3D position over time yield weights on the edges of a directed graph that we partition greedily into tracklets, sequences of chronologically o ..."
Abstract
-
Cited by 10 (0 self)
- Add to MetaCart
(Show Context)
Abstract. We present a strategy that combines color and depth images to detect people in indoor environments. Similarity of image appearance and closeness in 3D position over time yield weights on the edges of a directed graph that we partition greedily into tracklets, sequences of chronologically ordered observations with high edge weights. Each tracklet is assigned the highest score that a Histograms-of-Oriented Gradients (HOG) person detector yields for observations in the tracklet. High-score tracklets are deemed to correspond to people. Our experiments show a significant improvement in both precision and recall when compared to the HOG detector alone. 1
Identifying Players in Broadcast Sports Videos using Conditional Random Fields
"... We are interested in the problem of automatic tracking and identification of players in broadcast sport videos shot with a moving camera from a medium distance. While there are many good tracking systems, there are fewer methods that can identify the tracked players. Player identification is challen ..."
Abstract
-
Cited by 9 (0 self)
- Add to MetaCart
(Show Context)
We are interested in the problem of automatic tracking and identification of players in broadcast sport videos shot with a moving camera from a medium distance. While there are many good tracking systems, there are fewer methods that can identify the tracked players. Player identification is challenging in such videos due to blurry facial features (due to fast camera motion and low-resolution) and rarely visible jersey numbers (which, when visible, are deformed due to player movements). We introduce a new system consisting of three components: a robust tracking system, a robust person identification system, and a conditional random field (CRF) model that can perform joint probabilistic inference about the player identities. The resulting system is able to achieve a player recognition accuracy up to 85 % on unlabeled NBA basketball clips. 1.
Consistent Re-identification in a Camera Network
"... Abstract. Most existing person re-identification methods focus on find-ing similarities between persons between pairs of cameras (camera pair-wise re-identification) without explicitly maintaining consistency of the results across the network. This may lead to infeasible associations when results fr ..."
Abstract
-
Cited by 7 (4 self)
- Add to MetaCart
(Show Context)
Abstract. Most existing person re-identification methods focus on find-ing similarities between persons between pairs of cameras (camera pair-wise re-identification) without explicitly maintaining consistency of the results across the network. This may lead to infeasible associations when results from different camera pairs are combined. In this paper, we pro-pose a network consistent re-identification (NCR) framework, which is formulated as an optimization problem that not only maintains consis-tency in re-identification results across the network, but also improves the camera pairwise re-identification performance between all the indi-vidual camera pairs. This can be solved as a binary integer programing problem, leading to a globally optimal solution. We also extend the pro-posed approach to the more general case where all persons may not be present in every camera. Using two benchmark datasets, we validate our approach and compare against state-of-the-art methods.
Viewpoint invariant human re-identification in camera networks using pose priors and subject-discriminative features
- IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 2013
"... Human re-identification across cameras with non-overlapping fields of view is one of the most important and difficult problems in video surveillance and analysis. However, current algorithms are likely to fail in real-world scenarios for several reasons. For example, surveillance cameras are typical ..."
Abstract
-
Cited by 6 (4 self)
- Add to MetaCart
Human re-identification across cameras with non-overlapping fields of view is one of the most important and difficult problems in video surveillance and analysis. However, current algorithms are likely to fail in real-world scenarios for several reasons. For example, surveillance cameras are typically mounted high above the ground plane, causing serious perspective changes. Also, most algorithms approach matching across images using the same descriptors, regardless of camera viewpoint or human pose. Here, we introduce a re-identification algorithm that addresses both problems. We build a model for human appearance as a function of pose, using training data gathered from a calibrated camera. We then apply this “pose prior” in online re-identification to make matching and identification more robust to viewpoint. We further integrate person-specific features learned over the course of tracking to improve the algorithm’s performance. We evaluate the performance of the proposed algorithm and compare it to several state-of-the-art algorithms, demonstrating superior performance on standard benchmarking datasets as well as a challenging new airport surveillance scenario.
Domain Transfer for Person Re-identification
"... Automatic person re-identification in is a crucial capability underpinning many applications in public space video surveillance. It is challenging due to intra-class variation in person appearance when observed in different views, together with limited inter-class variability. Various recent approac ..."
Abstract
-
Cited by 4 (3 self)
- Add to MetaCart
Automatic person re-identification in is a crucial capability underpinning many applications in public space video surveillance. It is challenging due to intra-class variation in person appearance when observed in different views, together with limited inter-class variability. Various recent approaches have made great progress in re-identification performance using discriminative learning techniques. However, these approaches are fundamentally limited by the requirement of extensive annotated training data for every pair of views. For practical re-identification, this is an unreasonable assumption, as annotating extensive volumes of data for every pair of cameras to be re-identified may be impossible or prohibitively expensive. In this paper we move toward relaxing this strong assumption by investigating flexible multi-source transfer of re-identification models across camera pairs. Specifically, we show how to leverage prior re-identification models learned for a set of source view pairs (domains), and flexibly combine these to obtain good re-identification performance in a target view pair (domain) with greatly reduced training data requirements in the target domain.
Sarc3d: a new 3d body model for people tracking and re-identi cation
- In Proc. of ICIAP
, 2011
"... Abstract. We propose a new simplified 3D body model (called Sarc3D) for surveillance application, that can be created, updated and compared in rea-time. People are detected and tracked in each calibrated camera, and their silhouette, appearance, position and orientation are extracted and used to pla ..."
Abstract
-
Cited by 4 (1 self)
- Add to MetaCart
(Show Context)
Abstract. We propose a new simplified 3D body model (called Sarc3D) for surveillance application, that can be created, updated and compared in rea-time. People are detected and tracked in each calibrated camera, and their silhouette, appearance, position and orientation are extracted and used to place, scale and orientate a 3D body model. Foreach vertex of the model a signature (color features, reliability and saliency) is com-puted from the 2D appearance images and exploited for mathing. This approach achieves robustness against partial occlusions, pose and view-point changes. The complete proposal and a full experimental evaluation is presented, using a new benchmark suite and the PETS2009 dataset. Key words: 3D human model, People Re-identification 1 Introduction and related work People Re-identification is a fundamental task for the analysis of long-term activ-ities and behaviors of specific people. Algorithms have to be robust in challeng-ing situations, like widely varying camera viewpoints and orientations, varying
Tracking in Sparse Multi-Camera Setups using Stereo Vision
"... Abstract—Tracking with multiple cameras with nonoverlapping fields of view is challenging due to the differences in appearance that objects typically have when seen from different cameras. In this paper we use a probabilistic approach to track people across multiple, sparsely distributed cameras, wh ..."
Abstract
-
Cited by 4 (2 self)
- Add to MetaCart
(Show Context)
Abstract—Tracking with multiple cameras with nonoverlapping fields of view is challenging due to the differences in appearance that objects typically have when seen from different cameras. In this paper we use a probabilistic approach to track people across multiple, sparsely distributed cameras, where an observation corresponds to a person walking through the field of view of a camera. Modelling appearance and spatio-temporal aspects probabilistically allows us to deal with the uncertainty but, to obtain good results, it is important to maximise the information content of the features we extract from the raw video images. Occlusions and ambiguities within an observation result in noise, thus making the inference less confident. In this paper, we propose to position stereo cameras on the ceiling, facing straight down, thus greatly reducing the possibility of occlusions. This positioning also leads to specific requirements of the algorithms for feature extraction, however. Here, we show that depth information can be used to solve ambiguities and extract meaningful features, resulting in significant improvements in tracking accuracy. I.
