Share This Paper. Figures, Tables, and Topics from this paper.
Figures and Tables. Citations Publications citing this paper. Coping with uncertain dynamics in visual tracking: redundant state models and discrete search methods Leonid Taycher. Interested in publishing with us? Contact book Taeseok Jin. References Publications referenced by this paper. Hybrid Monte Carlo. Kennedy S. This paper proposes a centroid iteration algorithm with multiple features based on a posterior probability measure [ 15 ] for object tracking. The main goal is to solve the difficulties in real scenes such as similarly colored backgrounds, object occlusions, low illumination color image and sudden illumination changes.
The proposed algorithm consists of a target model construction step and a localization step. It can describe important information of the image the edge, the corner and so on. Then, this new texture feature and the color are combined to constitute the multiple features used in the target model, which we call the color and texture CT feature in this paper. After obtaining the target, three strategies for updating the target model are presented to reduce the tracking mistakes. The rest of the paper is organized as follows: in Section 2 , a local color texture feature based on the DCS-LBP along with its simplified form is introduced.
In Section 3 , the proposed tracking algorithm is illustrated in detail. Experimental results are shown in Section 4. Section 5 draws conclusions. Feature descriptors are very important in matching-based tracking algorithms, especially for applications in real scenes. In some simple scenes, color can work well because it distinguishes the targets from the background easily and contains a lot of useful information of the target. However, in complex scenes containing similarly colored backgrounds, object occlusions, low illumination color image and sudden illumination changes, the tracker only using the color feature may easily miss the target.
One of the solutions is to integrate multiple features in the target model for reliable tracking. The LBP is an illumination invariant texture feature. The operator uses the gray levels of the neighboring pixels to describe the central pixel. There are two extensions of the LBP [ 26 ]. The first one is to make the LBP as a rotation invariant feature as proposed by Ojala et al.
It is defined as:. Equation 2 selects the minimal number to simply the function. The second one is the uniform LBP, which contains at most one 0—1 and one 1—0 transition when viewed as a circular bit string. The uniform LBP codes contain a lot of useful structural information. Ojala et al. The following operator L B P 8 , 1 r i u 2 is a uniform and rotation invariant pattern with U v a l u e of at most Nine uniform patterns of L B P 8 , 1 r i u 2.
In Section 2. They calculated the center-symmetric pairs of the pixels as defined in the following function:. This operator halves the calculations of LBP codes at the same neighbors. Tan et al. The codes above it are set to 2 and the ones below it are set to 0. However, it is no longer invariant to gray-level transformations. The LTP is insensitive to noise, but its computation is too complex. T is the threshold used to eliminate the influence of weak noise. The value of T determines the anti-noise capability of the operator. The upper-part and the lower-part of the DCS-LBP should be calculated separately and then be combined together for use.
Table 1 shows examples of all of these five local patterns. The first row are three local parts of an image including texture flat areas, texture flat areas with noise, and texture change areas.
The threshold is set to be 5. The other three patterns are distinguishable and are all insensitive to noise, among which the computational complexity of the DCS-LBP is lower than the other two. It should be noted that there is a great amount of redundant information in the DCS-LBP, which might cause matching errors. Thus, further optimization is necessary. There are nine rotation invariant patterns. Pattern 5 to Pattern 8, which cannot describe the primitive structural information corresponding of the local image, are not uniform patterns.
Pattern 0 to Pattern 4 each has its identity. Pattern 0 and Pattern 1 represent noise points, dark points and smooth regions. Pattern 2 represents the terminal. Pattern 3 represents angular points. Pattern 4 represents boundary. Feature representation of the target model is very important for mean-shift based tracking algorithms. However, in real scenes which contain similarly colored background, object occlusion, low illumination color image and sudden illumination changes, the original mean-shift algorithm can not track the target continuously.
Inspired by [ 16 ], we consider designing a new feature combining the color and the texture. The Value, which is measured with some white points, is often used for description of surface colors and remains roughly constant even with brightness and color changes under different illuminations. The new feature which combines the color and the texture is called the CT feature in this paper. The CT feature can be considered as a special texture feature terminal, angular point, boundary and some special points with a certain color.
Figure 4 shows three target models. For the CT feature, Figure 4 b,c is the same and are different from Figure 4 a, which can not be distinguished using the color alone. The CT feature has the rotation invariant identity and can distinguish between different texture patterns. The calculation process of the CT feature is as follows.
- free public records dickinson county michigan!
- brooklyn ny property assesor search?
- Mh sampling matlab;
- car rental search for best rates!
- copy of death certificate scotland.
- south carolina vehicle license check.
- st albans police vt public records.
Firstly, let P i be the set of pixels of the target. Figure 5 shows the representation of a target model by the proposed method. Figure 5 a is the first frame of a sequence. The target is showed in Figure 5 b. The histogram of the CT feature is showed in Figure 5 c. The representation model of the target by the proposed algorithm. Recently, many similarity measures are used in object tracking algorithms, such as the Euclidean distance, the Bhattacharyya coefficient, the histogram intersection distance, and so on.
However, there is still lots of mismatching or misidentification in the tracking process. One of the reasons is that the target model contains some background pixels [ 15 ]. This paper proposes using the similarity measure based on maximum posterior probability to solve the problem. By introducing the candidate area, the maximum posterior probability measure PPM is able to decrease the influence of background and increase the importance of the target model in the tracking process.
The PPM is a function to evaluate the similarity of the candidate and the target defined as:. Thus, the original PPM can be converted into a simple one as [ 15 ]:. Therefore, we compute the incremental part to obtain the PPM of neighborhood, which makes the recursive algorithm a suitable one. According to Equation 9 , the PPM value of each pixel will be calculated, respectively.
Thus, the matching process is simplified to find a target candidate region with the biggest sum of PPM value. The similarity measure of the target candidate and the target model is:. Figure 6 shows the PPM of the target model. The target bounded by the blue box and the target candidate region bounded by the green box in Figure 6 a are resized. The target model and the target candidate region are showed in Figure 6 b. The PPM of the target model, which holds monotonic and distinct peak shapes, is showed in Figure 6 c.http://theranchhands.com/images/show/the-development-of-a-new-triphasic-oral-contraceptive-the-proceedings-of-a-special-symposium-held.php
People tracking using hybrid Monte Carlo filtering - IEEE Conference Publication
The maximum posterior probability of the target model. During the tracking process, the target always changes in shape, size, or color. Thus, the target model must be updated. The update must abide by certain rules to prevent the tracking drift. Three strategies are proposed for the target model update.
Introduce an adaptive process to fit the target region to a variable target scale for the purpose of precise target tracking. Compute the similarity measure of the scale adapted target. If it is greater than a parameter, update the target model.
Robust particle tracker via Markov Chain Monte Carlo posterior sampling
Strategy 1 introduces a scale adaptation function given by [ 15 ]:. In Equation 12 , the expanding condition means the pixels around the border are likely to be a part of the target.
- getting a birth certificate in ontario!
- death index root security social!
- CA2664187A1 - Dynamic state estimation - Google Patents!
- background checks news public records!
The contracting condition means the target region should be reduced consequently. The function is an empirical one. The parameters should be trained by a great number of experiments. Strategy 2 shows that the frame will not be updated until the similarity measure is greater than a certain parameter. In real scenes, some sudden changes may cause the tracking drift, so the update can not work every frame.
If Equation 13 is satisfied, we considered p as the reliable CT feature model, and update the target model with p :. Strategy 3 introduces a parameter into the algorithm to prevent the target model from being updated completely. Because of the limitations of the description to the target model, p can not take the place of q.
The center of the target y i is the initial position of the tracking object.
People tracking using hybrid Monte Carlo filtering
Set y i as the initial position. Calculate the PPM values g x i of each pixel of the region by Equation Calculate the target location by Equation Adjust the scale of the target region by Equation Decide whether to update the target by Equation If satisfied, update the target model by Equation The environments are set in some real scenes with similarly colored backgrounds, object occlusions, low illumination color image, and sudden illumination changes [ 12 ].
As the visual tracking benchmark, the test sequences are tagged with the following four attributes: low illumination color image LI , sudden illumination changes IC , object occlusion OC , similarly colored background SCB see Table 2. We designed a tracking system based on Matlab Ra 8. Kwon, J. In: Forsyth, D. LNCS, vol. Liang, F. Zhou, X. Arulampalam, S. Gilks, W.
Most Downloaded Articles
Geyer, C. Roberts, O. Yang, M. Personalised recommendations.