• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권10호
• /
• pp.4929-4947
• /
• 2017

In visual object tracking, Correlation Filter-based Tracking (CFT) systems have arouse recently to be the most accurate and efficient methods. The CFT's circularly shifts the larger search window to find most likely position of the target. The need of larger search window to cover both background and object make an algorithm sensitive to the background and the target occlusions. Further, the use of fixed-sized windows for training makes them incapable to handle scale variations during tracking. To address these problems, we propose two layer target representation in which both global and local appearances of the target is considered. Multiple local patches in the local layer provide robustness to the background changes and the target occlusion. The target representation is enhanced by employing additional reversed RGB channels to prevent the loss of black objects in background during tracking. The final target position is obtained by the adaptive weighted average of confidence maps from global and local layers. Furthermore, the target scale variation in tracking is handled by the statistical model, which is governed by adaptive constraints to ensure reliability and accuracy in scale estimation. The proposed structural enhancement is tested on VTBv1.0 benchmark for its accuracy and robustness.

• 대한교통학회지
• /
• 제19권6호
• /
• pp.131-142
• /
• 2001

Previous OD matrix estimation methods from link traffic counts have focused on the formulation of mathematical model and its solution algorithm. Thereby those methods have assumed that true or real OD is similar to the target OD and paid little attention to the properties of the change of OD structure. Although it is general situation that each OD pair increases or decreases due to significant land use and to large time variation between target OD with real OD, those methods have set unrealistic assumptions that target OD increases or decreases uniformly and that the OD structure does not change. Therefore those methods have showed poor performance of OD estimation in general situation. To cope with the problem. this paper suggests a new concept of OD matrix structure and shows the shortcomings of previous method′s dependancy on target OD matrix. We divide "OD trips" into "OD scale" and "OD structure". Where OD scale is a quantitative magnitude of OD trips and "OD structure" is ordinal OD scale. This paper use the same solution algorithm developed by Baek et al. (2000) for analysing the OD structure. Results of numerical examples show that the performance of the method is better than that of previous methods, while the previous methods have better performance in estimation only when OD trips increase or decrease. In addition to, if OD structure does not change, the results show that the error of estimation is low relatively regardless of the large difference of trips between target OD and real OD. This paper also shows that the model performance on OD structure and on OD trips is low as the number of origins that OD structure is changed increase. From the results we suggest that the change of OD structure can be more important information than the difference between target OD and real OD in OD estimation steps.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.165-168
• /
• 2004

This paper propose a target tracker using phase correlation. The tracker consist of a pre-processing module, a translation estimation module based on phase correlation, a fine motion estimation module applied when confidence rate could not fulfill a threshold value and a reference image update module. The fine motion estimation module measure the shift, rotation and scale of input image compared to reference using Fourier-Mellin transform. Proposed tracker was tested its accuracy and robustness using some real indoor and outdoor image sequences.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권11호
• /
• pp.5624-5638
• /
• 2016

A novel method based on Surf points is proposed to detect and lock-track single ground target in aerial videos. Videos captured by moving cameras contain complex motions, which bring difficulty in moving object detection. Our approach contains three parts: moving target template detection, search area estimation and target tracking. Global motion estimation and compensation are first made by grids-sampling Surf points selecting and matching. And then, the single ground target is detected by joint spatial-temporal information processing. The temporal process is made by calculating difference between compensated reference and current image and the spatial process is implementing morphological operations and adaptive binarization. The second part improves KALMAN filter with surf points scale information to predict target position and search area adaptively. Lastly, the local Surf points of target template are matched in this search region to realize target tracking. The long-term tracking is updated following target scaling, occlusion and large deformation. Experimental results show that the algorithm can correctly detect small moving target in dynamic scenes with complex motions. It is robust to vehicle dithering and target scale changing, rotation, especially partial occlusion or temporal complete occlusion. Comparing with traditional algorithms, our method enables real time operation, processing $520{\times}390$ frames at around 15fps.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권2호
• /
• pp.805-825
• /
• 2017

Correlation Filter-based Trackers (CFTs) gained popularity recently for their effectiveness and efficiency. To deal with the size changes of the target which may degenerate the tracking performance, scale estimation has been introduced in existing CFTs. However, the variations of the aspect ratio were usually neglected, which also influence the size of the target. In this paper, Size Aware Correlation Filter Trackers (SACFTs) are proposed to deal with this problem. The SACFTs not only determine the translation and scale variations, but also take the aspect ratio changes into consideration, thus a better estimation of the size of the target can be realized, which improves the overall tracking performance. And competing results can be achieved compared with state-of-the-art methods according to the experiments conducted on two large scale datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2328-2344
• /
• 2022

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

• 대한임베디드공학회논문지
• /
• 제12권4호
• /
• pp.231-238
• /
• 2017

Detecting small infrared targets from the low-SCR images at a long distance is very hard. The previous Local Contrast Method (LCM) algorithm based on the human visual system shows a superior performance of detecting small targets by a background suppression technique through local contrast measure. However, its slow processing speed due to the heavy multi-scale processing overhead is not suitable to a variety of real-time applications. This paper presents a lightweight real-time small target detection algorithm, called by the Improved Selective Local Contrast Method (ISLCM), to reduce the scale-invariant computational overhead. The proposed ISLCM applies the improved local contrast measure to the predicted selective region so that it may have a comparable detection performance as the previous LCM while guaranteeing low scale-invariant computational load by exploiting both adaptive scale estimation and small target feature feasibility. Experimental results show that the proposed algorithm can reduce its computational overhead considerably while maintaining its detection performance compared with the previous LCM.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1744-1760
• /
• 2021

Since correlation filter appeared in the field of object tracking, it plays an increasingly vital role due to its excellent performance. Although many sophisticated trackers have been successfully applied to track the object accurately, very few of them attaches importance to the scale and rotation estimation. In order to address the above limitation, we propose a novel method combined with Fourier-Mellin transform and confidence evaluation strategy for robust object tracking. In the first place, we construct a correlation filter to locate the target object precisely. Then, a log-polar technique is used in the Fourier-Mellin transform to cope with the rotation and scale changes. In order to achieve subpixel accuracy, we come up with an efficient surface fitting mechanism to obtain the optimal calculation result. In addition, we introduce a confidence evaluation strategy modeled on the output response, which can decrease the impact of image noise and perform as a criterion to evaluate the target model stability. Experimental experiments on OTB100 demonstrate that the proposed algorithm achieves superior capability in success plots and precision plots of OPE, which is 10.8% points and 8.6% points than those of KCF. Besides, our method performs favorably against the others in terms of SRE and TRE validation schemes, which shows the superiority of our proposed algorithm in scale and rotation evaluation.

• 대한인간공학회지
• /
• 제32권3호
• /
• pp.237-243
• /
• 2013

Objective: The present study developed an estimation method of boundary zone representative humanoids(hereafter, EBZ method) using descriptive statistics on the design target population. Background: The boundary zone method(hereafter, BZ method) generates representative humanoids at a boundary zone that statistically accommodates a designated percent of the design target population; however, the BZ method has a practical limitation because it requires a large scale anthropometric database on the design target population. Method: The EBZ method developed in the present study consisted of 3 steps. In the first step, the boundary zone of accommodating a designated percent(e.g., 90%) is formed under the assumption of normal distributions for anthropometric sizes. In the second step, cases that fall within the boundary zone are estimated using descriptive statistics(mean, standard deviation, and covariance) on the design target population. In the last step, K-mean cluster analysis is conducted for the cases, and representative humanoids are selected from each of clusters. Results: Evaluation results showed that mean accommodation percent of the EBZ method was 90.9%(range: 90.8~91.1%) which is similar to the target percent(90%). In addition, standard deviation of accommodation percent for 100 repetitions was 0.1%. Lastly, the number of representative humanoids generated by the EBZ method(n = 20) was similar to the BZ method(n = 16). Conclusion: The EBZ method can generate representative humanoids which accommodate a designated percent of the design target population using descriptive statistics. Application: The EBZ method can be utilized in the generation of humanoids for ergonomic design and evaluation of products when the large scale anthropometric database on the design target population is not existed.

• 상하수도학회지
• /
• 제25권4호
• /
• pp.547-554
• /
• 2011

In small-scale water systems, the measurement of quality of raw water in running water is generally implemented when the quality of water is stable and frequency of measurement is low. However, units such as water temperature and pH, which are easily monitored, are frequently measured. In establishing an improvement plan for a water treatment system, the range of concentration of the target material present in the raw water of the running water provides relevant information. If the concentration of target material can be specified by the quality of water of data items that are measured daily, inverse estimation of the range of concentration is possible as well. In this paper, we took note of manganese in the raw water from Ogasawara-mura, Tokyo, and estimated the manganese concentration in the raw water of the running water for the past five years. Based on the results obtained, we have proposed a manganese removal system, considering the current situation and geographical conditions of Ogasawara-mura.