• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.4
• /
• pp.381-389
• /
• 2022

Detecting partially occluded objects is difficult due to the appearances and shapes of occluders are highly variable. These variabilities lead to challenges of localizing accurate bounding box or classifying objects with visible object parts. To address these problems, we propose a two-stage part-based attention approach for robust object detection under partial occlusion. First, our part attention network(PAN) captures the important object parts and then it is used to generate weighted object features. Based on the weighted features, the re-weighted object features are produced by our reinforced PAN(RPAN). Experiments are performed on our collected military vehicle dataset and synthetic occlusion dataset. Our method outperforms the baselines and demonstrates the robustness of detecting objects under partial occlusion.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.307-310
• /
• 2009

In this paper, we present a robust shape matching approach based on bottom-up segmentation. We show how over-segmentation results can be used to overcome both ambiguity of contour matching and occlusion. To measure the shape difference between a template and the object in the input, we use oriented chamfer matching. However, in contrast to previous work, we eliminate the affection of the background clutters before calculating the shape differences using over-segmentation results. By this method, we can increase the matching cost interval between true matching and false matching, which gives reliable results. Finally, our experiments also demonstrate that our method is robust despite the presence of occlusion.

• Journal of Broadcast Engineering
• /
• v.17 no.6
• /
• pp.1040-1047
• /
• 2012

In this paper, we propose a ball tracking algorithm robust against occlusion in broadcasting soccer video sequences. Soccer ball tracking is a challenging task due to occlusion, fast motion and fast direction changes. Many works have been proposed based on ball trajectory. However, this approach requires heavy computational complexity. We propose a ball tracking algorithm with occlusion handling capability. Initial ball location is calculated using the circular hough transform. Then, the ball is tracked using template matching. Occlusion is handled by matching score. In occlusion cases, we generate a set of ball candidates. The ball candidates which exist in the previous frame were removed. On the other hand, the new appearing candidate is determined as the ball. Experiments with several broadcasting soccer video sequences show that the proposed method efficiently handles the occlusion cases.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 2006.06a
• /
• pp.251-257
• /
• 2006

The performance of face recognition methods using subspace projection is directly related to the characteristics of their basis images, especially in the cases of local distortion or partial occlusion. In order for a subspace projection method to be robust to local distortion and partial occlusion, the basis images generated by the method should exhibit a part-based local representation. We propose an effective part-based local representation method named locally salient ICA (LS-ICA) method for face recognition that is robust to local distortion and partial occlusion. The LS-ICA method only employs locally salient information from important facial parts in order to maximize the benefit of applying the idea of 'recognition by parts.' It creates part-based local basis images by imposing additional localization constraint in the process of computing ICA architecture I basis images. We have contrasted the LS-ICA method with other part-based representations such as LNMF (Localized Non-negative Matrix Factorization)and LFA (Local Feature Analysis). Experimental results show that the LS-ICA method performs better than PCA, ICA architecture I, ICA architecture II, LFA, and LNMF methods, especially in the cases of partial occlusions and local distortion

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.6
• /
• pp.23-29
• /
• 2010

Nowadays it is required to design intelligent visual surveillance systems which automatically detect abandoned objects in public places to strengthen the social safety. Already recognized abandoned objects can be occluded partially or fully by surrounding people in public places after the first recognition. To improve an essential recognition performance index PAT, the system should overcome the occlusion problems. In this research, a design scheme is newly proposed to construct the robust detection system which is comprised of multiple stages considering the occlusion problem. To show the feasibilities of the proposed system, the evaluation was tried for the prepared image streams including 6 various situations and the experimental results show 96% and 75% in PAT performance for intrusion and abandoning events, respectively. Finally in spite of full occlusions by multiple persons, the proposed system shows the capability to continuously recognize the abandoned object after complex occlusions disappear.

• The Journal of Korea Robotics Society
• /
• v.18 no.1
• /
• pp.122-126
• /
• 2023

An unexpected occlusion in a real life, not in a laboratory, can be more fatal to neural networks than expected. In addition, it is virtually impossible to create a network that learns all the environmental changes as well as occlusions. Therefore, we propose an alternative approach in which the architecture and number of parameters remain unchanged while adapting to occlusion circumstances. Learning method with the term Conversion Learning classifies them more robustly by converting the weights from various occlusion situations. The experiments on MNIST dataset showed a 3.07 [%p] performance improvement over the baseline CNN model in a situation where most objects are occluded and unknowing what occlusion will appear in advance. The experimental results suggest that Conversion Learning is an efficient method to respond to environmental changes such as occluded images.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.5
• /
• pp.126-134
• /
• 2009

This paper describes the vision-based system to track road signs from within a moving vehicle. The proposed system has the standard architecture with particle filter due to its robust tracking performance in complex environment. In the case of tracking road signs in real environment, it has a great difficulty in predicting time series data by reason of an occlusion due to an obstacle and the rapid change of objects on roads. To overcome this problem and improve the tracking performance, this paper proposes the algorithm using an autoregressive model as an state transition model which has affine parameters as states and using robust statistics for determining occlusion due to obstacles. The experiments of this paper show that the proposed method is efficient for real time tracking of road signs and performs well in road signs under occlusion due to obstacles.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.10
• /
• pp.5112-5128
• /
• 2016

Tracking human body is an important problem in computer vision field. Tracking failures caused by occlusion can lead to wrong rectification of the target position. In this paper, a robust human tracking algorithm is proposed to address the problem of occlusion, rotation and improve the tracking accuracy. It is based on Tracking-Learning-Detection framework. The key auxiliary information is used in the framework which motivated by the fact that a tracking target is usually embedded in the context that provides useful information. First, face localization method is utilized to find key face location information. Second, the relative position relationship is established between the auxiliary information and the target location. With the relevant model, the key face information will get the current target position when a target has disappeared. Thus, the target can be stably tracked even when it is partially or fully occluded. Experiments are conducted in various challenging videos. In conjunction with online update, the results demonstrate that the proposed method outperforms the traditional TLD algorithm, and it has a relatively better tracking performance than other state-of-the-art methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.5
• /
• pp.1711-1725
• /
• 2014

Multi-target tracking is the main purpose of many video surveillance applications. Recently, multi-target tracking based on the particle filter method has achieved robust results by using the data association process. However, this method requires many calculations and it is inadequate for real time applications, because the number of associations exponentially increases with the number of measurements and targets. In this paper, to reduce the computational cost of the data association process, we propose a novel multi-target tracking method that excludes particle samples in the overlapped predictive region between the target to track and marginal targets. Moreover, to resolve the occlusion problem, we define an occlusion mode with the normal dynamic mode. When the targets are occluded, the mode is switched to the occlusion mode and the samples are propagated by Gaussian noise without the sampling process of the particle filter. Experimental results demonstrate the robustness of the proposed multi-target tracking method even in occlusion.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.9
• /
• pp.3196-3210
• /
• 2014

This paper presents a novel video metrology approach based on robust tracking. From videos acquired by an uncalibrated stationary camera, the foreground likelihood map is obtained by using the Codebook background modeling algorithm, and the multiple moving objects are tracked by a combined tracking algorithm. Then, we compute vanishing line of the ground plane and the vertical vanishing point of the scene, and extract the head feature points and the feet feature points in each frame of video sequences. Finally, we apply a single view mensuration algorithm to each of the frames to obtain height measurements and fuse the multi-frame measurements using RANSAC algorithm. Compared with other popular methods, our proposed algorithm does not require calibrating the camera, and can track the multiple moving objects when occlusion occurs. Therefore, it reduces the complexity of calculation and improves the accuracy of measurement simultaneously. The experimental results demonstrate that our method is effective and robust to occlusion.