Online Improved Eigen Tracking
Summary (2 min read)
Introduction
- There are numerous tracking algorithms proposed in the literature like mean-shift or camshift algorithms, appearance based tracker etc.
- An appearance-based tracker (EigenTracker [1]) can track moving objects undergoing appearance changes powered by dimensionality reduction techniques.
- There can be several ways by virtue of which the power of EigenTracker and particle filter can be combined like [7] and [8].
- The main features of their approach are the tracker initialization, presence of prediction framework, effective subspace update algorithm [4] and avoidance of non-linear optimizations.
2.1. The Prediction Mechanism
- These 5 motion parameters can track the object with its bounding box being an oriented rectangle.
- This seed point is needed for sampling windows around it.
- The predictive framework helps generating better seed values for diverse object dynamics.
- The measurement is the set of five motion parameters obtained from the image, Zt. The observation model has Gaussian peaks around each observation, and constant density otherwise.
- The state estimate is used to generate the predictions for the next frame.
2.2. Initialization of the tracker
- Accurate tracker initialization is a difficult problem.
- The authors have used a moving object segmentation method based on the improved PCA which is a simplified version of the methodology used in [3] for moving object detection and segmentation.
- For this technique to work the background should be still or changing slowly such as grassplot or cloud for the analyzing frames.
- Secondly, the calculation result is improved in the following way.
- E effectively eliminates the blur of the eigen images of the moving object.
2.3. On-the-fly Eigen space Updates
- In most tracking problems, the object of interest undergoes changes in appearance over time.
- It is not feasible to learn all possible poses and shapes even for a particular domain of application, off-line.
- Therefore, one needs to learn and update the relevant Eigen spaces on the fly.
- Since a naive O(mN3) algorithm (for N images having m pixels each) is time-consuming, the authors use an efficient-estimation motivated by optimal incremental principal component analysis of O(mNk) algorithm (for k most significant singular values) proposed by Juyang Weng et al. [4].
2.4. The Overall Tracking Scheme
- The following section outlines their overall tracking scheme.
- For all subsequent frames, the next step is to obtain the measurements – taking the minimum distant prediction from the learnt sub-space (in RGB plane) as the description of the tracked object.
- The authors then update the eigen-spaces incrementally.
- Finally, the authors predict the motion parameters values for the next frame.
- The idea behind the subspace construction for the appearance based tracking is the uniform L2 reconstruction error norm Error∞(L, {x1, · · · xN}) = maxid2(L, xi) (5) To define the quality of approximation, the authors use the uniform reconstruction error norm Error∞ introduced in Equation 5 in their approach.
4. Remark and Discussions
- The computational complexity of the algorithm is dominated by the number of windows generated from the sampling.
- Like all appearance-based tracker it cannot handle situation like sudden pose or illumination changes or fully occlusion, but it can handle partial occlusion and gradual pose or illumination changes .
- There are three important free parameters in their algorithm, N, the number of samples to pick and l, amnesic parameter for the subspace update and k, the number of principal components.
6. Experiments and Results
- The authors current implementation runs at about 0.25 to 0.5 frames/sec with 320x240 and 176x144 video input respectively on a standard Intel centrino P4 1.8 MHz machine and thus it is quite expected that C implementation easily can run on real time.
- The authors test cases contain scenarios which a real-world tracker encounters, including changes in appearance, large pose variations, significant lighting variation and shadowing, partial occlusion, object partly leaving field of view, large scale changes, cluttered backgrounds, and quick motion resulting in motion blur.
- It is evident from the above table that incorporation of predictive framework makes the tracker more robust.
- Coastguard sequence has presence of the boat up to frames 100 out of total 300 frames and then it disappears .
- Hall is the sequence where a person (tracking object) appears in frame 25 and disappears after 140th frame, and in that interval it changes poses heavily.
7. Summary and conclusions
- The authors have introduced a technique for predictively learning the statistical distribution on-line with an Eigen subspace representation of an object that is being tracked with a fast EigenSpace update technique.
- The resulting tracker is both simple and fast.
- The method can robustly track an object in the presence of large viewpoint changes, partial occlusion, lighting variation, changes to the shape of the object shaky cameras, and motion blur.
- Moreover avoidance of non-linear optimization makes their tracking task faster than that of [7].
Did you find this useful? Give us your feedback
Citations
27 citations
8 citations
Cites methods from "Online Improved Eigen Tracking"
...[40] have enhanced the capabilities of the Eigen tracker by augmenting it with a condensation-based predictive framework to increase its efficiency and also made it fast by avoiding non-linear optimizations....
[...]
6 citations
2 citations
1 citations
Cites background or methods from "Online Improved Eigen Tracking"
...We use the algorithm given by authors in [14] et al for online appearance based tracking of the objects....
[...]
...The camera carries out appearance based tracking [14] on each of the objects in its view....
[...]
References
5,804 citations
"Online Improved Eigen Tracking" refers methods in this paper
...The Isard and Blake CONDENSATION algorithm [2] can represent simultaneous multiple hypothesis....
[...]
1,343 citations
479 citations
"Online Improved Eigen Tracking" refers methods in this paper
...The main features of our approach are the tracker initialization, presence of prediction framework, effective subspace update algorithm [4] and avoidance of non-linear optimizations....
[...]
184 citations
"Online Improved Eigen Tracking" refers background or methods in this paper
...[6] proposes a fast appearance tracker which eliminates non-linear optimizations completely but it lacks the benefit of predictive framework....
[...]
...We enhance the capabilities of the EigenTracker by augmenting it with a CONDENSATION-based predictive framework to increase its efficiency and also make it fast by avoiding non-linear optimization like [6]....
[...]
49 citations
"Online Improved Eigen Tracking" refers background in this paper
...There can be several ways by virtue of which the power of EigenTracker and particle filter can be combined like [7] and [8]....
[...]