• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.502-510
• /
• 2016

Considering video copy transform diversity, a multi-feature video copy detection algorithm based on a Speeded-Up Robust Features (SURF) local descriptor is proposed in this paper. Video copy coarse detection is done by an ordinal measure (OM) algorithm after the video is preprocessed. If the matching result is greater than the specified threshold, the video copy fine detection is done based on a SURF descriptor and a box filter is used to extract integral video. In order to improve video copy detection speed, the Hessian matrix trace of the SURF descriptor is used to pre-match, and dimension reduction is done to the traditional SURF feature vector for video matching. Our experimental results indicate that video copy detection precision and recall are greatly improved compared with traditional algorithms, and that our proposed multiple features algorithm has good robustness and discrimination accuracy, as it demonstrated that video detection speed was also improved.

• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.758-768
• /
• 2017

In this paper, we present a novel method to extract face representation based on multi-resolution spatial pyramid. In our method, a face is subdivided into increasingly finer sub-regions (local regions) and represented at multiple levels of histogram representations. To cope with misaligned problem, patch-based local descriptor extraction has been also developed in a novel way. To preserve multiple levels of detail in local characteristics and also encode holistic spatial configuration, histograms from all levels of spatial pyramid are integrated by using dimensionality reduction and feature combination, leading to our spatial-pyramid face feature representation. We incorporate our proposed face features into general face recognition pipeline and achieve state-of-the-art results on challenging face recognition problems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1464-1480
• /
• 2019

Robust tracking of infrared (IR) pedestrian targets with various backgrounds, e.g. appearance changes, illumination variations, and background disturbances, is a great challenge in the infrared image processing field. In the paper, we address a new tracking method for IR pedestrian targets via multi-feature local sparse representation (SR), which consists of three important modules. In the first module, a multi-feature local SR model is constructed. Considering the characterization of infrared pedestrian targets, the gray and edge features are first extracted from all target templates, and then fused into the model learning process. In the second module, an effective tracker is proposed via the learned model. To improve the computational efficiency, a sliding window mechanism with multiple scales is first used to scan the current frame to sample the target candidates. Then, the candidates are recognized via sparse reconstruction residual analysis. In the third module, an adaptive dictionary update approach is designed to further improve the tracking performance. The results demonstrate that our method outperforms several classical methods for infrared pedestrian tracking.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.1
• /
• pp.52-57
• /
• 2007

In this paper we proposed multi-directional matching windows combined by multi-dimensional feature vector matching, which uses not only intensity values but also multiple feature values, such as variance, first and second derivative of pixels. Multi-dimensional feature vector matching has the advantage of compensating the drawbacks of area-based stereo matching using one feature value, such as intensity. We define matching cost of a pixel by the minimum value among eight multi-dimensional feature vector distances of the pixels expanded in eight directions having the interval of 45 degrees. As best stereo matches, we determine the two points with the minimum matching cost within the disparity range. In the experiment we used aerial imagery and IKONOS satellite imagery and obtained more accurate matching results than that of conventional matching method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.151-153
• /
• 2001

Feature Simplification is an essential method for multiple representations of spatial features in GIS. However, spatial features re various, complex and a alrge size. Among spatial features which describe spatial information. linear feature is the msot common. Therefore, an efficient linear feature simplification method is most critical for spatial feature simplification in GIS. This paper propose an original method, by which the problem of linear feature simplification is mapped into the signal processing field. This method avoids conventional geometric computing in existing methods and exploits the advantageous properties of wavelet transform. Experimental results are presented to show that the proposed method outperforms the existing methods and achieves the time complexity of O(n), where n is the number of points of a linear feature. Furthermore, this method is not bound to two-dimension but can be extended to high-dimension space.

• Journal of KIISE:Software and Applications
• /
• v.29 no.11
• /
• pp.818-825
• /
• 2002

Depth information is one of the most important factor for the recognition of a digital face image. Range images are very useful, when comparing one face with other faces, because of implicating depth information. As the processing for the whole fare produces a lot of calculations and data, face images ran be represented in terms of a vector of feature descriptors for a local area. In this paper, depth areas of a 3 dimensional(3D) face image were extracted by the contour line from some depth value. These were resampled and stored in consecutive location in feature vector using multiple feature method. A comparison between two faces was made based on their distance in the feature space, using Euclidian distance. This paper reduced the number of index data in the database and used fewer feature vectors than other methods. Proposed algorithm can be highly recognized for using local depth information and less feature vectors or the face.

• 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.

• Journal of Broadcast Engineering
• /
• v.17 no.4
• /
• pp.634-639
• /
• 2012

In this paper, we propose nonlinear optimization method for feature matching from multiple view image. Typical solution of feature matching is by solving linear equation. However this solution has large error due to nonlinearity of image formation model. If typical nonlinear optimization method is used, complexity grows exponentially over the number of features. To make complexity lower, we use sparse Levenberg-Marquardt nonlinear optimization for matching of features over multiple view image.

• 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.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.6
• /
• pp.345-359
• /
• 2011

In high performance embedded systems, the use of multiple on-chip memories is an essential architectural feature for exploiting inherent parallelism in multimedia applications. This feature allows multiple data accesses to be executed in parallel. However, it remains difficult to effectively exploit of multiple on-chip memories. The successful use of this architecture strongly depends on how to efficiently detect and exploit memory parallelism in target applications. In this paper, we propose a technique based on a linear array access descriptor [1], which is generated from profiled data, to detect and exploit memory parallelism. The proposed technique tackles an array reorganization problem to maximize memory parallelism in multimedia applications. We present preliminary experiments applying the proposed technique onto a representative coarse grained reconfigurable array processor (CGRA) with multimedia kernel codes. Our experimental results demonstrate that our technique optimizes data placement by putting independent data on separate storage. The results exhibit 9.8% higher performance on average compared to the existing method.