Scale and orientation adaptive mean shift tracking

Abstract

-A scale and orientation adaptive mean shift tracking (SOAMST) algorithm is proposed in this paper to address the problem of how to estimate the scale and orientation changes of the target under the mean shift tracking framework. In the original mean shift tracking algorithm, the position of the target can be well estimated, while the scale and orientation changes can not be adaptively estimated. Considering that the weight image derived from the target model and the candidate model can represent the possibility that a pixel belongs to the target, we show that the original mean shift tracking algorithm can be derived using the zero th and the first order moments of the weight image. With the zero th order moment and the Bhattacharyya coefficient between the target model and candidate model, a simple and effective method is proposed to estimate the scale of target. Then an approach, which utilizes the estimated area and the second order center moment, is proposed to adaptively estimate the width, height and orientation changes of the target. Extensive experiments are performed to testify the proposed method and validate its robustness to the scale and orientation changes of the target.

Top-down Spatial Attention for Visual Search: Novelty Detection-Tracking Using Spatial Memory with a Mobile Robot

“…Ning et al [19] proposed the Scale and Orientation Adaptive Mean Shift Tracking (SOAMST) algorithm, which also offers invariance to rotations and scale, and it also updates search region for each frame. Moreover, it can accomplish tracking even under low resolution and low quality image conditions so it can be a good candidate for indoor real-time robot based subject tracking applications [19].…”

“…Moreover, it can accomplish tracking even under low resolution and low quality image conditions so it can be a good candidate for indoor real-time robot based subject tracking applications [19]. On the other hand, it also has problems with high illumination changes, and the tracking may fail if the background region has similar representation to reference frame.…”

“…In sum, there are many powerful tracking algorithms using color images as expressed work or more in literature [14][15][16][17][18][19]. However, in general, for at-home daily observation, they can be easily affected by the image data or environmental conditions such as low resolution image, low texture quality of the image, and high illumination changes, subject pose or gait differences, and etc.…”

A Novel Object of Interest Extraction Method for Mobile Mapping Systems

“…To evaluating the performance of the proposed object-shaped kernel scale invariant mean shift algorithm, we have performed comparisons with the standard adaptive mean shift algorithm (Comaniciu et al, 2003) and a newest scale adaptive mean shift algorithm, SOAMST (Ning et al, 2011), which adaptively selects scale by compute the moment. In all experiments, the RGB color space was taken as feature space and quantized to 8×8×8 bins.…”

A More Robust Mean Shift Tracker on Joint Color-CLTP Histogram

“…Among various object tracking methods, the mean shift tracker has recently attracted many researchers' attention [2] [3] [4] [5] [6] [7] [8] [9]due to its simplicity and efficiency.…”