In this letter, a novel method based on Temporal and Spatial Prediction (TSP) to detecl all-zero DC.'T coefficients based on temporal and .spatial prediction between neighboring blocks is proposed. The presented a...In this letter, a novel method based on Temporal and Spatial Prediction (TSP) to detecl all-zero DC.'T coefficients based on temporal and .spatial prediction between neighboring blocks is proposed. The presented algorithm uses the knowledge of all-zero block distribution in the previous frame combined with the Sum of Absolute Difference (S.AD) of the corresponding macroblock as a. criterion. The algorithm almost needs no additional computation, and it. shows an excellent overall detection performance in simulations.展开更多
Deep learning technology is widely used in computer vision.Generally,a large amount of data is used to train the model weights in deep learning,so as to obtain a model with higher accuracy.However,massive data and com...Deep learning technology is widely used in computer vision.Generally,a large amount of data is used to train the model weights in deep learning,so as to obtain a model with higher accuracy.However,massive data and complex model structures require more calculating resources.Since people generally can only carry and use mobile and portable devices in application scenarios,neural networks have limitations in terms of calculating resources,size and power consumption.Therefore,the efficient lightweight model MobileNet is used as the basic network in this study for optimization.First,the accuracy of the MobileNet model is improved by adding methods such as the convolutional block attention module(CBAM)and expansion convolution.Then,the MobileNet model is compressed by using pruning and weight quantization algorithms based on weight size.Afterwards,methods such as Python crawlers and data augmentation are employed to create a garbage classification data set.Based on the above model optimization strategy,the garbage classification mobile terminal application is deployed on mobile phones and raspberry pies,realizing completing the garbage classification task more conveniently.展开更多
A new all-zero block determination rule was used to reduce the complexity of the AVS-M encoder. It reuses the sum of absolute difference of 4x4 block obtained from motion estimation or intra prediction as parameters s...A new all-zero block determination rule was used to reduce the complexity of the AVS-M encoder. It reuses the sum of absolute difference of 4x4 block obtained from motion estimation or intra prediction as parameters so that the determination threshold need to be computed only once when quantization parameter (QP) is invariable for given video sequence. This method avoids a lot of computation for transform, quantization, inverse transform, inverse quantization and block reconstruction. Simulation results showed that it can save about 20%～50% computation without any video quality degradation.展开更多
In this article, we use the general method of quantization by Drinfeld’s twist to quantize explicitly the Lie bialgebra structures on Lie algebras of Block type.
When the saturation degree （SD） of space-borne SAR raw data is high, the performance of conventional block adaptive quantization （BAQ） deteriorates obviously. In order to overcome the drawback, this paper studies ...When the saturation degree （SD） of space-borne SAR raw data is high, the performance of conventional block adaptive quantization （BAQ） deteriorates obviously. In order to overcome the drawback, this paper studies the mapping between the average signal magnitude （ASM） and the standard deviation of the input signal （SDIS） to the A/D from the original reference. Then, it points out the mistake of the mapping and introduces the concept of the standard deviation of the output signal （SDOS） from the A/D. After that, this paper educes the mapping between the ASM and SDOS from the A/D. Monte-Carlo experiment shows that none of the above two mappings is the optimal in the whole set of SD. Thus, this paper proposes the concept of piecewise linear mapping and the searching algorithm in the whole set of SD. According to the linear part, this paper gives the certification and analytical value of k and for nonlinear part, and utilizes the searching algorithm mentioned above to search the corresponding value of k. Experimental results based on simulated data and real data show that the performance of new algorithm is better than conventional BAQ when raw data is in heavy SD.展开更多
文摘In this letter, a novel method based on Temporal and Spatial Prediction (TSP) to detecl all-zero DC.'T coefficients based on temporal and .spatial prediction between neighboring blocks is proposed. The presented algorithm uses the knowledge of all-zero block distribution in the previous frame combined with the Sum of Absolute Difference (S.AD) of the corresponding macroblock as a. criterion. The algorithm almost needs no additional computation, and it. shows an excellent overall detection performance in simulations.
文摘Deep learning technology is widely used in computer vision.Generally,a large amount of data is used to train the model weights in deep learning,so as to obtain a model with higher accuracy.However,massive data and complex model structures require more calculating resources.Since people generally can only carry and use mobile and portable devices in application scenarios,neural networks have limitations in terms of calculating resources,size and power consumption.Therefore,the efficient lightweight model MobileNet is used as the basic network in this study for optimization.First,the accuracy of the MobileNet model is improved by adding methods such as the convolutional block attention module(CBAM)and expansion convolution.Then,the MobileNet model is compressed by using pruning and weight quantization algorithms based on weight size.Afterwards,methods such as Python crawlers and data augmentation are employed to create a garbage classification data set.Based on the above model optimization strategy,the garbage classification mobile terminal application is deployed on mobile phones and raspberry pies,realizing completing the garbage classification task more conveniently.
基金Project (No. 05R214207) supported by the Sustentation Fund Plan for Post Doctor of Shanghai, China
文摘A new all-zero block determination rule was used to reduce the complexity of the AVS-M encoder. It reuses the sum of absolute difference of 4x4 block obtained from motion estimation or intra prediction as parameters so that the determination threshold need to be computed only once when quantization parameter (QP) is invariable for given video sequence. This method avoids a lot of computation for transform, quantization, inverse transform, inverse quantization and block reconstruction. Simulation results showed that it can save about 20%～50% computation without any video quality degradation.
基金supported by the National Science Foundation of China (10825101)"One Hundred Talents Program" from University of Science and Technology of Chinathe China Postdoctoral Science Foundation (20090450810)
文摘In this article, we use the general method of quantization by Drinfeld’s twist to quantize explicitly the Lie bialgebra structures on Lie algebras of Block type.
文摘When the saturation degree （SD） of space-borne SAR raw data is high, the performance of conventional block adaptive quantization （BAQ） deteriorates obviously. In order to overcome the drawback, this paper studies the mapping between the average signal magnitude （ASM） and the standard deviation of the input signal （SDIS） to the A/D from the original reference. Then, it points out the mistake of the mapping and introduces the concept of the standard deviation of the output signal （SDOS） from the A/D. After that, this paper educes the mapping between the ASM and SDOS from the A/D. Monte-Carlo experiment shows that none of the above two mappings is the optimal in the whole set of SD. Thus, this paper proposes the concept of piecewise linear mapping and the searching algorithm in the whole set of SD. According to the linear part, this paper gives the certification and analytical value of k and for nonlinear part, and utilizes the searching algorithm mentioned above to search the corresponding value of k. Experimental results based on simulated data and real data show that the performance of new algorithm is better than conventional BAQ when raw data is in heavy SD.
