• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.6
• /
• pp.1-8
• /
• 2008

This paper introduces three efficient frame selection schemes to reduce the computation complexity for the multi-reference and variable block size Motion Estimation (ME). The proposed RSP (Reference Selection Pass) scheme can minimize the overhead of frame selection. The MFS (Modified Frame Selection) scheme can reduce the number of search points about 18% compared with existing schemes considering the motion of image during the reference frame selection process. In addition, the TPRFS (Two Pass Reference frame Selection) scheme can minimize the frame selection operation for the variable block size ME in H.264/AVC using the character of selected reference frame according to the block size. The simulation results show the proposed schemes can save up to 50% of the ME computation without degradation of image Qualify. Because the proposed schemes can be separated from the block matching process, they can be used with any existing single reference fast search algorithms.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.8
• /
• pp.109-118
• /
• 1994

We proposed new field/frame mode selection quantization and buffer control strategy for interlaced digital HDTV image coding system. The field/frame mode selection is performed based on the mean square error and number of generated bits for each superblock. The quantization factor for each superblock is determined by the characteristics of human visual system and buffer status. The statistical characteristics of the number of generated bits for basis block and the prediction of buffer status are used for buffer control. Simulation results show that the proposed field/frame mode selection and rate buffer control. Simulation results show that the proposed field/frame mode selection and rate buffer control strategy have good subjective image quality and have stable buffer status.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.11C
• /
• pp.1066-1072
• /
• 2007

In this paper, we propose a fast multiple reference frame selection method for motion estimation and compensation in video coding. Reference frames selected as an optimal reference frame by variable block sizes motion estimation have the statistical characteristic that was based on block size. Using the statistical characteristic, reference frames for smaller block size motion estimation can be selected from reference frame which was decided as an optimal one for the upper layer block size. Simulation results show that the proposal method decreased the computations about 60%. Nevertheless, PSNR and bit rate were almost same as the performances of original H.264 multiple reference motion estimation.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.419-420
• /
• 2006

In the new video coding standard H.264/AVC, motion estimation (ME) is allowed to search multiple reference frames for improve the rate-distortion performance. The complexity of multi-frame motion estimation increases linearly with the number of used reference frame. However, the distortion gain given by each reference frame varies with the video sequence, and it is not efficient to search through all the candidate frames. In this paper, we propose a fast mult-frame selection method using all zero coefficient block (AZCB) prediction and sum of difference (SAD) of neighbor block. Simulation results show that the speed of the proposed algorithm is up to two times faster than exhaustive search of multiple reference frames with similar quality and bit-rate.

• Journal of Korea Multimedia Society
• /
• v.5 no.5
• /
• pp.512-522
• /
• 2002

In this paper, we propose a hybrid method which is mixed with frame selection and weighting model rank method, based on GMM(gaussian mixture model), for real-time text-independent speaker recognition system. In the system, maximum likelihood estimation was used for GMM parameter optimization, and maximum likelihood was used for recognition basically Proposed hybrid method has two steps. First, likelihood score was calculated with speaker models and test data at frame level, and the difference is calculated between the biggest likelihood value and second. And then, the frame is selected if the difference is bigger than threshold. The second, instead of calculated likelihood, weighting value is used for calculating total score at each selected frame. Cepstrum coefficient and regressive coefficient were used as feature parameters, and the database for test and training consists of several data which are collected at different time, and data for experience are selected randomly In experiments, we applied each method to baseline system, and tested. In speaker recognition experiments, proposed hybrid method has an average of 4% higher recognition accuracy than frame selection method and 1% higher than W method, implying the effectiveness of it.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.8
• /
• pp.735-743
• /
• 2002

In this paper, we propose three new text-independent speaker identification methods. At first, to exclude the frames not having enough features of speaker's vocal from calculation of the maximum likelihood, we propose the FS(Frame Selection) method. This approach selects the important frames by evaluating the difference between the biggest likelihood and the second in each frame, and uses only the frames in calculating the score of likelihood. Our secondly proposed, called the Hybrid, is a combined version of the FS and WMR(Weighting Model Rank). This method determines the claimed speaker using exponential function weights, instead of likelihood itself, only on the selected frames obtained from the FS method. The last proposed, called MWMR (Modified WMR), considers both original likelihood itself and its relative position, when the claimed speaker is determined. It is different from the WMR that take into account only the relative position of likelihood. Through the experiments of the speaker identification, we show that the all the proposed have higher identification rates than the ML. In addition, the Hybrid and MWMR have higher identification rate about 2% and about 3% than WMR, respectively.

• Smart Media Journal
• /
• v.9 no.1
• /
• pp.23-29
• /
• 2020

This paper presents an approach for dynamic hand gesture recognition by using algorithm based on 3D Convolutional Neural Network (3D_CNN), which is later extended to 3D Residual Networks (3D_ResNet), and the neural network based key frame selection. Typically, 3D deep neural network is used to classify gestures from the input of image frames, randomly sampled from a video data. In this work, to improve the classification performance, we employ key frames which represent the overall video, as the input of the classification network. The key frames are extracted by SegNet instead of conventional clustering algorithms for video summarization (VSUMM) which require heavy computation. By using a deep neural network, key frame selection can be performed in a real-time system. Experiments are conducted using 3D convolutional kernels such as 3D_CNN, Inflated 3D_CNN (I3D) and 3D_ResNet for gesture classification. Our algorithm achieved up to 97.8% of classification accuracy on the Cambridge gesture dataset. The experimental results show that the proposed approach is efficient and outperforms existing methods.

• ETRI Journal
• /
• v.36 no.1
• /
• pp.179-182
• /
• 2014

This letter presents a very simple yet very effective solution for fast reference frame (RF) selection in H.264/AVC. By efficiently making use of the correlation between the best RF indices in various inter modes, the proposed method significantly reduces the number of RFs to be examined at the expense of a very small miss rate. Simulation results show that the proposed method not only improves upon the coding performance of conventional methods but also reduces the encoding time significantly.

• Journal of Sensor Science and Technology
• /
• v.32 no.5
• /
• pp.313-319
• /
• 2023

In this study, we propose a method to improve the accuracy of acoustic odometry using optimal frame interval selection for Fourier-based image registration. The accuracy of acoustic odometry is related to the phase correlation result of image pairs obtained from the forward-looking sonar (FLS). Phase correlation failure is caused by spurious peaks and high-similarity image pairs that can be prevented by optimal frame interval selection. We proposed a method of selecting the optimal frame interval by analyzing the factors affecting phase correlation. Acoustic odometry error was reduced by selecting the optimal frame interval. The proposed method was verified using field data.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1279-1290
• /
• 2021

As vehicle technology has grown, autonomous driving that does not require driver intervention has developed. Accordingly, CAN security, an network of in-vehicles, has also become important. CAN shows vulnerabilities in hacking attacks, and machine learning-based IDS is introduced to detect these attacks. However, despite its high accuracy, machine learning showed vulnerability against adversarial examples. In this paper, we propose a adversarial CAN frame generation method to avoid IDS by adding noise to feature and proceeding with feature selection and re-packet for physical attack of the vehicle. We check how well the adversarial CAN frame avoids IDS through experiments for each case that adversarial CAN frame generated by all feature modulation, modulation after feature selection, preprocessing after re-packet.