• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.434-436
• /
• 2006

In a visual driver-assistance system, separating moving objects from fixed objects are an important problem to maintain multiple hypothesis for the state. Color and edge-based tracker can often be "distracted" causing them to track the wrong object. Many researchers have dealt with this problem by using multiple features, as it is unlikely that all will be distracted at the same time. In this paper, we improve the accuracy and robustness of real-time tracking by combining a color histogram feature with a brightness of Optical Flow-based feature under a Sequential Monte Carlo framework. And it is also excepted from Tracking as time goes on, reducing density by Adaptive Particles Number in case of the fixed object. This new framework makes two main contributions. The one is about the prediction framework which separating moving objects from fixed objects and the other is about measurement framework to get a information from the visual data under a partial occlusion.

• Korean Journal of Computational Design and Engineering
• /
• v.4 no.1
• /
• pp.60-68
• /
• 1999

In reverse engineering (RE) sustems, the quality of the data aquisition process is crucial to the accuracy of the reverse engineered three dimensional computer-aided design (CAD) model. However, these tasks are predominantly done manually, and little work has been done to improve the efficiency of scanning by determining the minimum number of scans and the optimal scanning directions. In this paper, new scanning and registration methods using tooling balls are developed to assist in determining the optimal parameter for these processes. When the object to scanned has no concavity, attaching path of the object and its bounding rectangle are used for optimal scanning and registration. Then minimum number of tooling balls and their positions are calculated automatically. In the case of concave parts, the scanning plan should include a complete scan of the concave area. With the surface normal vector and the scanning direction, the minimum degree of rotating the part can be calculated. But the maximum rotation should be restricted in order to prevent occlusion of the part. Finally tow sample part ar scanned based on the proposed methods and the results are discussed.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.7
• /
• pp.807-818
• /
• 1988

This paper proposes new algorithms for the estimation of displacement vector and moving object extraction using difference picture. First, the relations between the boundary of moving objects in two consecutive image and the boundary of difference picture regions are analyzed, then displacement vector estimation algorithm is proposed. Using the estimated displacement vector, moving objects are directly extracted from difference picture. Since the proposed algorithms do not process gray-valued image, they have a short processing time and are suitable to real time processing. From the experimental results, we observed that, if difference picture is wel extracted, the proposecd algorithms work well even in the circumstances of complex background, fast or slow motion, rotation etc., including occlusion where is not moving area.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.80-88
• /
• 2023

RGB-thermal (RGB-T) tracking using unmanned aerial vehicles (UAVs) involves challenges with regards to the similarity of objects, occlusion, fast motion, and motion blur, among other issues. In this study, we propose dynamic tracking aggregation (DTA) as a unified framework to perform object detection and data association. The proposed approach obtains fused features based a transformer model and an L1-norm strategy. To link the current frame with recent information, a dynamically updated embedding called dynamic tracking identification (DTID) is used to model the iterative tracking process. For object association, we designed a long short-term tracking aggregation module for dynamic feature propagation to match spatial and temporal embeddings. DTA achieved a highly competitive performance in an experimental evaluation on public benchmark datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.9
• /
• pp.2483-2494
• /
• 2024

Instance segmentation is a challenging research in the field of computer vision, which combines the prediction results of object detection and semantic segmentation to provide richer image feature information. Focusing on the instance segmentation in the street scene, the real-time instance segmentation method based on SOLOv2 is proposed in this paper. First, a cross-stage fusion backbone network based on position attention is designed to increase the model accuracy and reduce the computational effort. Then, the loss of shallow location information is decreased by integrating two-way feature pyramid networks. Meanwhile, cross-stage mask feature fusion is designed to resolve the small objects missed segmentation. Finally, the adaptive minimum loss matching method is proposed to decrease the loss of segmentation accuracy due to object occlusion in the image. Compared with other mainstream methods, our method meets the real-time segmentation requirements and achieves competitive performance in segmentation accuracy.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.81-89
• /
• 2021

Under natural conditions, Apple detection has the problems of occlusion and small object detection difficulties. This paper proposes an improved model based on SSD. The SSD backbone network VGG16 is replaced with the ResNet50 network model, and the receptive field structure RFB structure is introduced. The RFB model amplifies the feature information of small objects and improves the detection accuracy of small objects. Combined with the attention mechanism (SE) to filter out the information that needs to be retained, the semantic information of the detection objectis enhanced. An improved SSD algorithm is trained on the VOC2007 data set. Compared with SSD, the improved algorithm has increased the accuracy of occlusion and small object detection by 3.4% and 3.9%. The algorithm has improved the false detection rate and missed detection rate. The improved algorithm proposed in this paper has higher efficiency.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.341-350
• /
• 2022

In this paper, we propose a deep learning based on-device augmented reality (AR) system in which multiple input images are used to implement the correct occlusion in a real environment. The proposed system is composed of three technical steps; camera pose estimation, depth estimation, and object augmentation. Each step employs various mobile frameworks to optimize the processing on the on-device environment. Firstly, in the camera pose estimation stage, the massive computation involved in feature extraction is parallelized using OpenCL which is the GPU parallelization framework. Next, in depth estimation, monocular and multiple image-based depth image inference is accelerated using the mobile deep learning framework, i.e. TensorFlow Lite. Finally, object augmentation and occlusion handling are performed on the OpenGL ES mobile graphics framework. The proposed augmented reality system is implemented as an application in the Android environment. We evaluate the performance of the proposed system in terms of augmentation accuracy and the processing time in the mobile as well as PC environments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.10
• /
• 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.

• Korean Journal of Cognitive Science
• /
• v.14 no.3
• /
• pp.51-59
• /
• 2003

Various perceptual distortions in spatial vision occur during eye movements. Most of the studies on perceptual distortion have focused on the conjunctive eye movements. Recently, Li, Kham, Kim & Yoon (2002) reported that subjects experienced perceptual distortion of 3D slant of an object defined by the spatiotemproal pattern of occlusion. The present research examined whether the subjects experienced the same perceptual distortion in the target object whose luminance is different from that of background. It also examined the effect of the reference on the perceptual distortion of 3D slant of an object.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.5161-5178
• /
• 2019

Correlation Filter was recently demonstrated to have good characteristics in the field of video object tracking. The advantages of Correlation Filter based trackers are reflected in the high accuracy and robustness it provides while maintaining a high speed. However, there are still some necessary improvements that should be made. First, most trackers cannot handle multi-scale problems. To solve this problem, our algorithm combines position estimation with scale estimation. The difference from the traditional method in regard to the scale estimation is that, the proposed method can track the scale of the object more quickly and effective. Additionally, in the feature extraction module, the feature representation of traditional algorithms is relatively simple, and furthermore, the tracking performance is easily affected in complex scenarios. In this paper, we design a novel and powerful feature that can significantly improve the tracking performance. Finally, traditional trackers often suffer from model drift, which is caused by occlusion and other complex scenarios. We introduce a relocation component to detect object at other locations such as the secondary peak of the response map. It partly alleviates the model drift problem.