Browsing by Author "Ahmad, AMA"

Now showing 1 - 6 of 6

A novel object detection framework in compressed domain
(2004)
Ahmad, BMA
;
Ahmad, AMA
;
Lee, SY
;
資訊工程學系
;
Department of Computer Science
In this paper we propose a novel approach for robust motion vector based object detection in MPEG-2 video streams. By processing the extracted motion vector fields that are directly extracted from MPEG-2 video streams in the compressed domain, through post processing operation, in order to reduce the noise within the motion vector content, obtain more robust object information, and refine this information through our proposed system which composed of a Spatial filter Component, a Temporal filter Component and a Texture filter component. As a result, the object detection algorithm is more capable of accurately detecting objects with more efficient performance in terms of runtime. We compare the performance of our proposed system with other popular and commonly related work and techniques. Based on the experimental results performed over the MPEG7 testing dataset and measuring performance by using the standard recall and precision metrics, object detection using our proposed system is remarkably superior to the alternative techniques. In addition to these results, we describe a user system interface that we developed, where users can maintain the parameters interactively.
Comparison among the Filter Steered robust compressed domain object detection
(2004)
Ahmad, AMA
;
Talat, ST
;
Sheen, WH
;
資訊工程學系
;
Department of Computer Science
Object detection in video images is an interesting subject but often heavy task due to the huge volume of available approaches. The comparisons made in this paper between the different categories of algorithms are attained through literary research and are not based on direct quantitative examination. The focus of this work is on algorithms that are useful in real-time applications, realized in compressed domain and Filter Steered. This paper will provide some illumination into the area of object detection by classifying some of the current and more popular Filter Steered techniques.
Defeating the blocking effect in the filter steered robust compressed domain object detection in MPEG videos
(2004)
Ahmad, AMA
;
Lee, SY
;
資訊工程學系
;
Department of Computer Science
In this paper we propose a novel and an elegant approach for defeating Blocking Effect in MPEG-2 video streams. We first take an MPEG2 video stream, extract the motion vectors from P-frames Meanwhile, we will extract the DCT coefficients from I frames, those coefficient include the DC coefficient, and the AC components as well. Then, we will pass the DCT coefficients into a module to calculate the texture of each frame. Later, we will propagate this texture information into P frame using Inverse Motion Compensation Technique. After that, we will change each motion vector based on its texture value as what will be described later. We compare the performance of our system Based on experimental results over MPEG7 testing dataset, based on the standard recall and precision as metrics, our system performance is remarkable and strongly effective. We develop user system interface, where users can maintain the system parameters interactively.
Efficient object detection technique in MPEG videos
(2004)
Ahmad, AMA
;
Lee, SY
;
資訊工程學系
;
Department of Computer Science
In this paper we propose an efficient approach for Motion Vector (MV) based object detection in MPEG-2 video streams. Rather than processing the whole MV fields that are directly extracted from MPEG-2 video streams in the compressed domain, we perform MV selection process, those MVs have more robust object information, and are know to be more texture. As a result, the object detection algorithm is more capable of accurately detecting objects and efficiently produces the result. We compare the performance of our proposed system with the popular and commonly used object detection techniques in object detection domain. Based on experimental results performed over the MPEG7 testing dataset and measuring performance using the standard recall and precision metrics for perceptual performance, and run time metric for efficiency performance object detection using our texture filter is remarkably superior to the alternative techniques. In addition to these results, we describe a user system interface that we developed, where users can maintain the parameters interactively.
Enhancing the object detection by reference frame's AC components
(2004)
Ahmad, BMA
;
Ahmad, AMA
;
Lee, SY
;
資訊工程學系
;
Department of Computer Science
In this paper we propose a novel approach for Motion Vector (MV) based object detection in MPEG-2 video streams. Rather than processing the extracted MV fields that are directly extracted from MPEG-2 video streams in the compressed domain, we perform MV smoothing, perform MV noise reduction, obtain more robust object information, and refine this information through a texture filter. As a result, the object detection algorithm is more capable of accurately detecting objects. We compare the performance of our proposed system with the popular and commonly used spatial filter processing techniques in object detection domain: median filter, mean filter, Gaussian filter, and no filter Based on experimental results performed over the MPEG7 testing dataset and measuring performance using the standard recall and precision metrics, object detection using our texture filter is remarkably superior to the alternative filtering techniques. In addition to these results, we describe a user system interface that we developed, where users can maintain the filter parameters interactively.
Robust object detection using cascade filter in MPEG videos
(2003)
Ahmad, AMA
;
Chen, DY
;
Lee, SY
;
資訊工程學系
;
Department of Computer Science
In this paper we propose a novel approach for Motion Vector (MV) based object detection in MPEG-2 video streams. Rather than processing the extracted MV fields that are directly extracted from MPEG-2 video streams in the compressed domain, we perform MV smoothing, perform MV noise reduction, obtain more robust object information, and refine this information through a cascaded filter composed of a Gaussian filter and a median filter. As a result, the object detection algorithm is more capable of accurately detecting objects. We compare the performance of our proposed system with the popular and commonly used spatial filter processing techniques: median filter, mean filter, Gaussian filter, and no filter. Based on experimental results performed over the MPEG7 testing dataset and measuring performance using the standard recall and precision metrics, object detection using the cascade filter is remarkably superior to the alternative filtering techniques. In addition to these results, we describe a user system interface that we developed, where users can maintain the filter parameters interactively.