• Journal of KIISE:Software and Applications
• /
• v.33 no.4
• /
• pp.402-410
• /
• 2006

This paper presents a method for feature based block motion estimation that uses multi -resolution image sequences to obtain the panoramic images in the continuous ultrasound image sequences. In the conventional block motion estimation method, the centers of motion estimation blocks are set at the predetermined and equally spaced locations. This requires the large blocks to include at least one feature, which inevitably requires long estimation time. In this paper, we propose an adaptive method which locates the center of the motion estimation blocks at the feature points. This make it possible to reduce the block size while keeping the motion estimation accuracy The Harris-Stephen corner detector is used to get the feature points. The comer points tend to group together, which cause the error in the global motion estimation. In order to distribute the feature points as evenly as Possible, the image is firstly divided into regular subregions, and a strongest corner point is selected as a feature in each subregion. The ultrasound Images contain speckle patterns and noise. In order to reduce the noise artifact and reduce the computational time, the proposed method use the multi-resolution image sequences. The first algorithm estimates the motion in the smoothed low resolution image, and the estimated motion is prolongated to the next higher resolution image. By this way the size of search region can be reduced in the higher resolution image. Experiments were performed on three types of ultrasound image sequences. These were shown that the proposed method reduces both the computational time (from 77ms to 44ms) and the displaced frame difference (from 66.02 to 58.08).

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.2
• /
• pp.143-152
• /
• 2012

It is well-known that image matching is necessary for automatic generation of 3D data such as digital surface data from aerial images. Recently developed aerial digital cameras allow to capture multi-strip images with higher overlaps and less occluded areas than conventional analogue cameras and that much of researches on multi-image matching have been performed, particularly effective methods of measuring a similarity among multi-images using point features as well as linear features. This research aims to investigate similarity measuring methods such as SSD and SNCC incorporated into a area based multi-image matching method based on vertical line locus. In doing this, different similarity measuring entities such as grey value, grey value gradient, and average of grey value and its gradient are implemented and analyzed. Further, both dynamic and pre-fixed adaptive-window size are tested and analyzed in their behaviors in measuring similarity among multi-images. The aerial images used in the experiments were taken by a DMC aerial frame camera in three strips. The over-lap and side-lap are about 80% and 60%, respectively. In the experiment, it was found that the SNCC as similarity measuring method, the average of grey value and its gradient as similarity measuring entity, and dynamic adaptive-window size can be best fit to measuring area-based similarity in area based multi-image matching method based on vertical line locus.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.4
• /
• pp.825-840
• /
• 2015

Adaptive bitrate (ABR) streaming technology has become an important and prevalent feature in many multimedia delivery systems, with content providers such as Netflix and Amazon using ABR streaming to increase bandwidth efficiency and provide the maximum user experience when channel conditions are not ideal. Where such systems could see improvement is in the delivery of live video with a closed loop cognitive control of video encoding. In this paper, we present streaming camera system which provides spatially and temporally adaptive video streams, learning the user's preferences in order to make intelligent scaling decisions. The system employs a hardware based H.264/AVC encoder for video compression. The encoding parameters can be configured by the user or by the cognitive system on behalf of the user when the bandwidth changes. A cognitive video client developed in this study learns the user's preferences(i.e. video size over frame rate) over time and intelligently adapts encoding parameters when the channel conditions change. It has been demonstrated that the cognitive decision system developed has the ability to control video bandwidth by altering the spatial and temporal resolution, as well as the ability to make scaling decisions.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.111-121
• /
• 2011

Intelligent video analysis systems require techniques which can predict accidents and provide alarms to the monitoring personnel. In this paper, we present an abnormal behavior analysis technique based on adaptive background generation. More specifically, abnormal behaviors include fence climbing, abandoned objects, fainting persons, and loitering persons. The proposed video analysis system consists of (i) background generation and (ii) abnormal behavior analysis modules. For robust background generation, the proposed system updates static regions by detecting motion changes at each frame. In addition, noise and shadow removal steps are also were added to improve the accuracy of the object detection. The abnormal behavior analysis module extracts object information, such as centroid, silhouette, size, and trajectory. As the result of the behavior analysis function objects' behavior is configured and analyzed based on the a priori specified scenarios, such as fence climbing, abandoning objects, fainting, and loitering. In the experimental results, the proposed system was able to detect the moving object and analyze the abnormal behavior in complex environments.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.388-396
• /
• 2017

Since there are many variables such as various poses, illuminations and occlusions in a face detection problem, a high performance detection system is required. Although CNN is excellent in image classification, CNN operatioin requires high-performance hardware resources. But low cost low power environments are essential for small and mobile systems. So in this paper, the CPU-FPGA integrated system is designed based on 3-stage cascade CNN architecture using small size FPGA. Adaptive Region of Interest (ROI) is applied to reduce the number of CNN operations using face information of the previous frame. We use a Field Programmable Gate Array(FPGA) to accelerate the CNN computations. The accelerator reads multiple featuremap at once on the FPGA and performs a Multiply-Accumulate (MAC) operation in parallel for convolution operation. The system is implemented on Altera Cyclone V FPGA in which ARM Cortex A-9 and on-chip SRAM are embedded. The system runs at 30FPS with HD resolution input images. The CPU-FPGA integrated system showed 8.5 times of the power efficiency compared to systems using CPU only.

• The Journal of the Acoustical Society of Korea
• /
• v.32 no.1
• /
• pp.71-78
• /
• 2013

This paper describes a multiple audio watermarking using Quantization Index Modulation (QIM) on frequency phase and magnitude response. Proposed embedding procedure is composed of two stage. At the first stage, the watermark is embedded on the frequency phase response using QIM. In the second stage, the watermark is embedded using adaptive QIM with the step-size that is adaptively determined using the maximum value of the frequency magnitude response of every frame. The watermark is extracted by calculating the Euclidean distance as the blind detection. The proposed method is robust against most of attacks of audio watermark benchmarking. For the Fourier attacks, the proposed method shows over 95% recovery rate.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.5
• /
• pp.2430-2436
• /
• 2013

This study suggests a method of detecting the still object, which becomes a cause of danger within the crossroad. The Inverse Perspective Transform was performed in order to make the object size consistent by being inputted the real-time image from CCTV that is installed within the crossroad. It established the detection area in the image with the perspective transform and generated the adaptative background image with the use of the moving information on object. The detection of the stop object was detected the candidate region of the stop object by using the background-image differential method. To grasp the appearance of truth on the detected candidate region, a method is proposed that uses the gradient information on image and EHD(Edge Histogram Descriptor). To examine performance of the suggested algorithm, it experimented by storing the images in the commuting time and the daytime through DVR, which is installed on the cross street. As a result of experiment, it could efficiently detect the stop vehicle within the detection region inside the crossroad. The processing speed is shown in 13~18 frame per second according to the area of the detection region, thereby being judged to likely have no problem about the real-time processing.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.57-64
• /
• 2009

This paper presents the hardware implementation of the pyramidal KLT(Kanade-Lucas-Tomasi) feature tracker. Because of its high computational complexity, it is not easy to implement a real-time KLT feature tracker using general-purpose processors. A hardware implementation of the pyramidal KLT feature tracker using FPGA(Field Programmable Gate Array) is described in this paper with emphasis on 1) adaptive adjustment of threshold in feature extraction under diverse lighting conditions, and 2) modification of the tracking algorithm to accomodate parallel processing and to overcome memory constraints such as capacity and bandwidth limitation. The effectiveness of the implementation was evaluated over ones produced by its software implementation. The throughput of the FPGA-based tracker was 30 frames/sec for video images with size of $720{\times}480$.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.11
• /
• pp.63-77
• /
• 1994

This paper describes the real-time system which, through analyzing a sequence of images, can extract motional information on a moving object and can contol servo equipment to always locate the moving object at the center of an image frame. An image is a vast amount of two-dimensional signal, so it takes a lot of time to analyze the whole quantity of a given image. Especially, the time needed to load pixels from a memory to processor increase exponentially as the size of an image increases. To solve such a problem and track a moving object in real-time, this paper addresses how to selectively search the spatial and time domain. Based on the selective search of spatial and time domain, this paper suggests various types of techniques which are essential in implementing a real-time tracking system. That is, this paper describes how to detect an entrance of a moving object in the field of view of a camera and the direction of the entrance, how to determine the time interval of adjacent images, how to determine nonstationary areas formed by a moving object and calculated velocity and position information of a moving object based on the determined areas, how to control servo equipment to locate the moving object at the center of an image frame, and how to properly adjust time interval(${\Delta}$t) to track an object taking variable speed.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.4
• /
• pp.1-9
• /
• 2012

LCD(Liquid Crystal Display) commonly used as an output device has a drawback of slow response time compared with CRT display. This drawback causes motion blur especially when an abrupt intensity change occurs in an image sequence as time goes on. To overcome the problem of slow response time overdriving technique has been used in TCON of LCD. In this technique, the previous frame data has to be compressed and stored in an external memory. Considering both chip size of TCON and computational complexity, AM-BTC has been applied to the 8bit HD display driver. However, the conventional method is not suitable for 10 bit Full HD because 10 bit Full HD data is much larger than that of 8 bit HD data. Being applied to 10 bit Full HD display driver, the conventional method increase cost by enlarging the external memory size of TCON or deteriorates image quality. In this paper, we propose dual BTC image coding technique for Full HD display driver that is an adaptive coding scheme according to morphological information of each sample block. Through experiments, it is verified that the proposed Dual BTC method performs better than the conventional method not only quantitatively but also qualitatively.