Sprite generation, the core of the sprite coding, is a developing technique included in the MPEG-4 standard. It achieves high subjective quality with low bitrates. The affine and perspective GME (Global Motion Estimat...
详细信息
Sprite generation, the core of the sprite coding, is a developing technique included in the MPEG-4 standard. It achieves high subjective quality with low bitrates. The affine and perspective GME (Global Motion Estimation) methods are demonstrated in the MPEG-4 Verification Model (MPEG-4 VM), MPEG-4 Optimization Model (MPEG-4 OM) and many other algorithms. The affine model GME, provides limited image quality, is robust and fast. The perspective model GME generates sprites with better quality, however it suffers from the time-wasting and error propagation problem. A new method to generate sprites in this paper combines the existing affine and perspective GME algorithms to produce high sprites quickly without losing robustness. In order to generate high quality sprites, the proposed "Hybrid Model GME" method uses the affine model GME as an initial search, then switches to the perspective model GME if necessary. To accelerate the speed, a nearest neighborhood (NN) kernel is used to replace the bilinear method for image warping. Experimental results show that the image quality is much improved even when camera movements are more complex and quick. The computation speed is between 10 and 17 times faster than the MPEG-4 VM. If the sprites can be divided into several pieces, the computation speed can be about 1.46 times faster ahead.
Current learning-based single image super-resolution (SISR) algorithms underperform on real data due to the deviation in the assumed degradation process from that in the real-world scenario. Conventional degradation p...
详细信息
As an important application form of immersive multimedia services, free-viewpoint video(FVV) enables users with great immersive experience by strong interaction. However, the computational complexity of virtual view s...
详细信息
In this paper, a unique road contour extraction approach from high resolution satellite image is proposed, in which the road contour was extracted in two steps. Firstly, support vector machines (SVM) was employed mere...
详细信息
In this paper, a unique road contour extraction approach from high resolution satellite image is proposed, in which the road contour was extracted in two steps. Firstly, support vector machines (SVM) was employed merely to classify the image into two groups of categories: a road group and a non-road group. The identified road group images are the discrete and irregularly distributed sampled points, and they are an uncompleted data set for the road. Secondly, the road contour was extracted from the road group images using the tensor voting framework, since the tensor voting technique is superior to the traditional methods in extracting the geometrical structure from the uncompleted data set. The experimental results on the high resolution satellite image demonstrate that the proposed approach worked well with images comprised by both rural and urban area features.
With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers...
详细信息
In this paper, the robust containment control problem of the leader-following multi-agent systems with input saturation and input additive disturbance is addressed, where the followers can be informed by multiple lead...
详细信息
ISBN:
(数字)9789881563903
ISBN:
(纸本)9781728165233
In this paper, the robust containment control problem of the leader-following multi-agent systems with input saturation and input additive disturbance is addressed, where the followers can be informed by multiple leaders. With the help of the lowand-high gain feedback technique and the high-gain observer approach, a distributed control algorithm for each agent is firstly designed by using the observed output information, then sufficient conditions are provided to guarantee the semi-global robust containment of the system. Finally, some numerical simulations are given to verify the correctness of the theoretical results.
3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird’s-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with cam...
详细信息
Automated pavement crack detection and measurement are important road issues. Agencies have to guarantee the improvement of road safety. Conventional crack detection and measurement algorithms can be extremely time-co...
详细信息
Automated pavement crack detection and measurement are important road issues. Agencies have to guarantee the improvement of road safety. Conventional crack detection and measurement algorithms can be extremely time-consuming and low efficiency. Therefore, recently, innovative algorithms have received increased attention from researchers. In this paper, we propose an ensemble of convolutional neural networks (without a pooling layer) based on probability fusion for automated pavement crack detection and measurement. Specifically, an ensemble of convolutional neural networks was employed to identify the structure of small cracks with raw images. Secondly, outputs of the individual convolutional neural network model for the ensemble were averaged to produce the final crack probability value of each pixel, which can obtain a predicted probability map. Finally, the predicted morphological features of the cracks were measured by using the skeleton extraction algorithm. To validate the proposed method, some experiments were performed on two public crack databases (CFD and AigleRN) and the results of the different state-of-the-art methods were compared. To evaluate the efficiency of crack detection methods, three parameters were considered: precision (Pr), recall (Re) and F1 score (F1). For the two public databases of pavement images, the proposed method obtained the highest values of the three evaluation parameters: for the CFD database, Pr = 0.9552, Re = 0.9521 and F1 = 0.9533 (which reach values up to 0.5175 higher than the values obtained on the same database with the other methods), for the AigleRN database, Pr = 0.9302, Re = 0.9166 and F1 = 0.9238 (which reach values up to 0.7313 higher than the values obtained on the same database with the other methods). The experimental results show that the proposed method outperforms the other methods. For crack measurement, the crack length and width can be measure based on different crack types (complex, common, thin, and inter
Unmanned Aerial Vehicles (UAVs) dynamic encirclement is an emerging field with great potential. Researchers often get inspiration from biological systems, either from macro-world like fish schools or bird flocks etc, ...
详细信息
In current society, reliable identification and verification of individuals are becoming more and more necessary tasks for many fields, not only in police environment, but also in civilian applications, such as access...
详细信息
In current society, reliable identification and verification of individuals are becoming more and more necessary tasks for many fields, not only in police environment, but also in civilian applications, such as access control or financial transactions. Biometric systems are used nowadays in these fields, offering greater convenience and several advantages over traditional security methods based on something that you know (password) or something that you have (keys). In this paper, we propose an efficient online personal identification system based on Multi-Spectral Palmprint (MSP) images using Contourlet Transform (CT) and Gabor Filter (GF) response. In this study, the spectrum image is characterized by the contourlet coefficients sub-bands. Then, we use the Hidden Markov Model (HMM) for modeling the observation vector. In addition, the same spectrum is filtered by the Gabor filter. The real and imaginary responses of the filtering image are used to create another observation vector. Subsequently, the two sub-systems are integrated in order to construct an efficient multi-modal identification system based on matching score level fusion. Our experimental results show the effectiveness and reliability of the proposed method, which brings both high identification and accuracy rate.
暂无评论