Results 1 - 10
of
77
Learning a deep compact image representation for visual tracking
- In NIPS
, 2013
"... In this paper, we study the challenging problem of tracking the trajectory of a moving object in a video with possibly very complex background. In contrast to most existing trackers which only learn the appearance of the tracked object on-line, we take a different approach, inspired by recent advanc ..."
Abstract
-
Cited by 12 (4 self)
- Add to MetaCart
(Show Context)
In this paper, we study the challenging problem of tracking the trajectory of a moving object in a video with possibly very complex background. In contrast to most existing trackers which only learn the appearance of the tracked object on-line, we take a different approach, inspired by recent advances in deep learning architectures, by putting more emphasis on the (unsupervised) feature learning problem. Specifically, by using auxiliary natural images, we train a stacked de-noising autoencoder offline to learn generic image features that are more robust against variations. This is then followed by knowledge transfer from offline train-ing to the online tracking process. Online tracking involves a classification neural network which is constructed from the encoder part of the trained autoencoder as a feature extractor and an additional classification layer. Both the feature extrac-tor and the classifier can be further tuned to adapt to appearance changes of the moving object. Comparison with the state-of-the-art trackers on some challenging benchmark video sequences shows that our deep learning tracker is more accurate while maintaining low computational cost with real-time performance when our MATLAB implementation of the tracker is used with a modest graphics process-ing unit (GPU). 1
Tracking Revisited using RGBD Camera: Unified Benchmark and Baselines
"... Despite significant progress, tracking is still considered to be a very challenging task. Recently, the increased popularity of depth sensors has made it possible to obtain reliable depth easily. This may be a game changer for tracking, since depth can be used to prevent model drift and handle occlu ..."
Abstract
-
Cited by 7 (1 self)
- Add to MetaCart
(Show Context)
Despite significant progress, tracking is still considered to be a very challenging task. Recently, the increased popularity of depth sensors has made it possible to obtain reliable depth easily. This may be a game changer for tracking, since depth can be used to prevent model drift and handle occlusion. We also observe that current tracking algorithms are mostly evaluated on a very small number of videos collected and annotated by different groups. The lack of a reasonable size and consistently constructed benchmark has prevented a persuasive comparison among different algorithms. In this paper, we construct a unified benchmark dataset of 100 RGBD videos with high diversity, propose different kinds of RGBD tracking algorithms using 2D or 3D model, and present a quantitative comparison of various algorithms with RGB or RGBD input. We aim to lay the foundation for further research in both RGB and RGBD tracking, and will make our dataset as well as evaluation server available online. 1.
Monocular Multiview Object Tracking with 3D Aspect Parts
"... Abstract. In this work, we focus on the problem of tracking objects un-der significant viewpoint variations, which poses a big challenge to tradi-tional object tracking methods. We propose a novel method to track an object and estimate its continuous pose and part locations under severe viewpoint ch ..."
Abstract
-
Cited by 5 (1 self)
- Add to MetaCart
(Show Context)
Abstract. In this work, we focus on the problem of tracking objects un-der significant viewpoint variations, which poses a big challenge to tradi-tional object tracking methods. We propose a novel method to track an object and estimate its continuous pose and part locations under severe viewpoint change. In order to handle the change in topological appear-ance introduced by viewpoint transformations, we represent objects with 3D aspect parts and model the relationship between viewpoint and 3D aspect parts in a part-based particle filtering framework. Moreover, we show that instance-level online-learned part appearance can be incorpo-rated into our model, which makes it more robust in difficult scenarios with occlusions. Experiments are conducted on a new dataset of chal-lenging YouTube videos and a subset of the KITTI dataset [14] that include significant viewpoint variations, as well as a standard sequence for car tracking. We demonstrate that our method is able to track the 3D aspect parts and the viewpoint of objects accurately despite significant changes in viewpoint.
MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization
"... Abstract. We propose a multi-expert restoration scheme to address the model drift problem in online tracking. In the proposed scheme, a tracker and its histor-ical snapshots constitute an expert ensemble, where the best expert is selected to restore the current tracker when needed based on a minimum ..."
Abstract
-
Cited by 5 (0 self)
- Add to MetaCart
(Show Context)
Abstract. We propose a multi-expert restoration scheme to address the model drift problem in online tracking. In the proposed scheme, a tracker and its histor-ical snapshots constitute an expert ensemble, where the best expert is selected to restore the current tracker when needed based on a minimum entropy criterion, so as to correct undesirable model updates. The base tracker in our formulation exploits an online SVM on a budget algorithm and an explicit feature mapping method for efficient model update and inference. In experiments, our tracking method achieves substantially better overall performance than 32 trackers on a benchmark dataset of 50 video sequences under various evaluation settings. In addition, in experiments with a newly collected dataset of challenging sequences, we show that the proposed multi-expert restoration scheme significantly improves the robustness of our base tracker, especially in scenarios with frequent occlu-sions and repetitive appearance variations. 1
Consensus-based Matching and Tracking of Keypoints for Object Tracking
"... We propose a novel keypoint-based method for long-term model-free object tracking in a combined matching-and-tracking framework. In order to localise the object in every frame, each keypoint casts votes for the object center. As erroneous keypoints are hard to avoid, we employ a novel consensus-base ..."
Abstract
-
Cited by 4 (2 self)
- Add to MetaCart
(Show Context)
We propose a novel keypoint-based method for long-term model-free object tracking in a combined matching-and-tracking framework. In order to localise the object in every frame, each keypoint casts votes for the object center. As erroneous keypoints are hard to avoid, we employ a novel consensus-based scheme for outlier detection in the voting behaviour. To make this approach computationally feasible, we propose not to employ an accumulator space for votes, but rather to cluster votes directly in the image space. By transforming votes based on the current keypoint constel-lation, we account for changes of the object in scale and rotation. In contrast to competing approaches, we refrain from updating the appearance information, thus avoiding the danger of making errors. The use of fast keypoint detec-tors and binary descriptors allows for our implementation to run in real-time. We demonstrate experimentally on a diverse dataset that is as large as 60 sequences that our method outperforms the state-of-the-art when high accu-racy is required and visualise these results by employing a variant of success plots. 1.
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-60597 Torchlight Navigation
"... Abstract—A common computer vision task is navigation and mapping. Many indoor navigation tasks require depth knowledge of flat, unstructured surfaces (walls, floor, ceiling). With passive illumination only, this is an ill-posed problem. Inspired by small children using a torchlight, we use a spotlig ..."
Abstract
-
Cited by 3 (2 self)
- Add to MetaCart
(Show Context)
Abstract—A common computer vision task is navigation and mapping. Many indoor navigation tasks require depth knowledge of flat, unstructured surfaces (walls, floor, ceiling). With passive illumination only, this is an ill-posed problem. Inspired by small children using a torchlight, we use a spotlight for active illumination. Using our torchlight approach, depth and orientation estimation of unstructured, flat surfaces boils down to estimation of ellipse parameters. The extraction of ellipses is very robust and requires little computational effort. Keywords-torchlight, pose estimation, active illumination, plane estimation, ellipses; I.
Exploiting spatialredundancy of image sensor for motion robust rPPG
- IEEE Trans. on Biomedical Engineering
"... can measure cardiac activity by detecting pulse-induced colour variations on human skin using an RGB camera. State-of-the-art rPPG methods are sensitive to subject body motions (e.g., motion-induced colour distortions). This study proposes a novel framework to improve the motion robustness of rPPG. ..."
Abstract
-
Cited by 3 (3 self)
- Add to MetaCart
(Show Context)
can measure cardiac activity by detecting pulse-induced colour variations on human skin using an RGB camera. State-of-the-art rPPG methods are sensitive to subject body motions (e.g., motion-induced colour distortions). This study proposes a novel framework to improve the motion robustness of rPPG. The basic idea of this work originates from the observation that a camera can simultaneously sample multiple skin regions in parallel, and each of them can be treated as an independent sensor for pulse measurement. The spatial-redundancy of an image sensor can thus be exploited to distinguish the pulse-signal from motion-induced noise. To this end, the pixel-based rPPG sensors are constructed to estimate a robust pulse-signal using motion-compensated pixel-to-pixel pulse extraction, spatial pruning, and temporal filtering. The evaluation of this strategy is not based on a full clinical trial, but on 36 challenging benchmark videos consisting of subjects that differ in gender, skin-types and performed motion-categories. Experimental results show that the proposed method improves the SNR of the state-of-the-art rPPG technique from 3.34dB to 6.76dB, and the agreement (±1.96σ) with instantaneous reference pulse-rate from 55 % to 80 % correct. ANOVA with post-hoc comparison shows that the improvement on motion robustness is significant. The rPPG method developed in this study has a performance that is very close to that of the contact-based sensor under realistic situations, while its computational efficiency allows real-time processing on an off-the-shelf computer. Index Terms—Biomedical monitoring, photoplethysmography, remote sensing, motion analysis. I.
N.: Constructing adaptive complex cells for robust visual tracking
- In: ICCV (2013
"... Representation is a fundamental problem in object track-ing. Conventional methods track the target by describing its local or global appearance. In this paper we present that, besides the two paradigms, the composition of local region histograms can also provide diverse and important object cues. We ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
Representation is a fundamental problem in object track-ing. Conventional methods track the target by describing its local or global appearance. In this paper we present that, besides the two paradigms, the composition of local region histograms can also provide diverse and important object cues. We use cells to extract local appearance, and construct complex cells to integrate the information from cells. With different spatial arrangements of cells, complex cells can explore various contextual information at multiple scales, which is important to improve the tracking perfor-mance. We also develop a novel template-matching algo-rithm for object tracking, where the template is composed of temporal varying cells and has two layers to capture the target and background appearance respectively. An adap-tive weight is associated with each complex cell to cope with occlusion as well as appearance variation. A fusion weight is associated with each complex cell type to preserve the global distinctiveness. Our algorithm is evaluated on 25 challenging sequences, and the results not only confirm the contribution of each component in our tracking system, but also outperform other competing trackers. 1.
Transfer Learning Based Visual Tracking with Gaussian Processes Regression
"... Abstract. Modeling the target appearance is critical in many modern visual track-ing algorithms. Many tracking-by-detection algorithms formulate the probability of target appearance as exponentially related to the confidence of a classifier out-put. By contrast, in this paper we directly analyze thi ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
Abstract. Modeling the target appearance is critical in many modern visual track-ing algorithms. Many tracking-by-detection algorithms formulate the probability of target appearance as exponentially related to the confidence of a classifier out-put. By contrast, in this paper we directly analyze this probability using Gaussian Processes Regression (GPR), and introduce a latent variable to assist the track-ing decision. Our observation model for regression is learnt in a semi-supervised fashion by using both labeled samples from previous frames and the unlabeled samples that are tracking candidates extracted from the current frame. We further divide the labeled samples into two categories: auxiliary samples collected from the very early frames and target samples from most recent frames. The auxiliary samples are dynamically re-weighted by the regression, and the final tracking re-sult is determined by fusing decisions from two individual trackers, one derived from the auxiliary samples and the other from the target samples. All these ingre-dients together enable our tracker, denoted as TGPR, to alleviate the drifting issue from various aspects. The effectiveness of TGPR is clearly demonstrated by its excellent performances on three recently proposed public benchmarks, involving 161 sequences in total, in comparison with state-of-the-arts. 1
Adaptive Color Attributes for Real-Time Visual Tracking
"... Visual tracking is a challenging problem in computer vi-sion. Most state-of-the-art visual trackers either rely on luminance information or use simple color representations for image description. Contrary to visual tracking, for ob-ject recognition and detection, sophisticated color features when co ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
Visual tracking is a challenging problem in computer vi-sion. Most state-of-the-art visual trackers either rely on luminance information or use simple color representations for image description. Contrary to visual tracking, for ob-ject recognition and detection, sophisticated color features when combined with luminance have shown to provide ex-cellent performance. Due to the complexity of the tracking problem, the desired color feature should be computation-ally efficient, and possess a certain amount of photometric invariance while maintaining high discriminative power. This paper investigates the contribution of color in a tracking-by-detection framework. Our results suggest that color attributes provides superior performance for visual tracking. We further propose an adaptive low-dimensional variant of color attributes. Both quantitative and attribute-based evaluations are performed on 41 challenging bench-mark color sequences. The proposed approach improves the baseline intensity-based tracker by 24 % in median distance precision. Furthermore, we show that our approach out-performs state-of-the-art tracking methods while running at more than 100 frames per second. 1.
