Volumetric video technology enables an immersive and interactive experience for viewers. However, the point cloud frames composing the video are prohibitively large, imposing significant demands on storage and transmission. The existing inter-frame compression methods perform motion estimation based on a fixed block size, ignoring the inherent motion characteristics of the volumetric content and failing to fully utilize the inter-frame redundancy information. To overcome this limitation, we introduce MP-VVC, a patch-adaptive volumetric video compression framework based on volumetric content and motion analysis. Specifically, MP-VVC involves a two-stage segmentation of volumetric frames, body-part segmentation and patch segmentation. Subsequently, we employ the iterative closest point algorithm to determine rigid movements of body parts and patches. Furthermore, we also take into account the volumetric content of non-rigid movements and compress it. Experiments show that MP-VVC reduces the bitrate by up to$7.58 \times$compared with two baselines, with at most$3.63 \times$improvement in decoding time compared with MP3DG.

Neutral Point Clamped (NPC) three-level inverter has been widely adopted in the industry, but it suffers from the issue of neutral voltage imbalance. This paper uses the FC leg to replace the DC capacitor leg and study the relationship between the switching frequencies of the FC leg and NPC inverter. A prediction method for the flying capacitor voltage ripple is proposed and the variable switching frequency PWM (VSFPWM) based on this prediction is proposed to control the flying capacitor voltage ripple. This utilizes the capacitor voltage ripple to reduce the switching frequency and minimize losses. Simulation and experimental verified the accuracy of the voltage ripple prediction method and the VSFPWM control scheme. Meanwhile, this scheme can reduce the average switching frequency and improve EMI.

The utilization of vector-based deep learning techniques has great prospects in the realm of autonomous driving, particularly in the domains of prediction and planning tasks. However, the application of vector-based backbones for prediction and planning tasks may lead to the occurrence of causal confusion. Previous studies have explored the phenomenon of causal confusion, with a specific emphasis on the context of visual imitation learning. As for the vector-based model, we observe that the states of surrounding vehicles can be a nuisance shortcut. In our work, an off-policy approach is proposed to alleviate the issue by incorporating de-confounding supervision. Additionally, to better capture the environmental cues, such as route and traffic lights, in vectorized representation, a decoder utilizing iterative route fusion is devised. By incorporating auxiliary supervision and employing a dedicated decoder, we demonstrate the effectiveness of our methods in reducing causal confusion and improving performance in planning tasks through reactive and nonreactive closed-loop simulations on the nuPlan dataset.

Land surface temperature (LST) is widely used in the field of time-series remote sensing. However, due to the influence of cloud cover, the large area of LST data observation is missing, which seriously affects the later data analysis. In the past research, various effective interpolation methods have been developed, but they usually cannot effectively interpolate the image data with large observation missing. In this article, a new method for interpolating these missing data called Hilbert tensor rearrangement with Bayesian temporal tensor factorization (HTR-BTTF) is proposed. This method requires tensor rearrangement of remote sensing data, combined with BTTF method for interpolation. In order to evaluate the performance of our method, we select three real study areas with different climates, Wuhan, Harbin, and Kunming LST data during day and night, and add cloud covers with different sizes to the cold and warm season layers each year. BTTF, inverse distance weighted (IDW), harmonic analysis of time series (HANTS), and GapFill are used as comparison methods. Root-mean-square error (RMSE) is a comprehensive evaluation index of interpolation results. Experiments have shown that HTR-BTTF is an effective method for interpolating missing observations, which is better than other methods. In the simulation experiment of the largest cloud cover size, on average, the RMSE of the data filled using the HTR-BTTF method was 17.2% lower than that of BTTF and 54.9% lower than that of the GapFill method, and it shows good robustness and high accuracy.

Although promising results have been achieved in the areas of object detection and classification, few works have provided an end-to-end solution to the perception problems in the autonomous driving field. In this paper, we make two contributions. Firstly, we fully enhanced our previously released TT100K benchmark and provide 16,817 elaborately labeled Tencent Street View panoramas. This newly created benchmark, we call it Tencent Autonomous Driving 16K (TAD16K), not only contains previously labeled traffic-signs (221 types), but also creates annotations for three new objects, which are traffic lights (6 types), vehicles and pedestrians. Secondly, we provide the evaluation results of two state-of-the-art object detection algorithms (SSD and DetectNet) on our benchmark, which can be used as the baseline for future comparison purpose. Finally, we also demonstrate that the network trained on our benchmark can be directly deployed for practical application. The TAD16K, relevant additions and the source codes are publicly available1,2.

How to achieve the balance between exploration and exploitation is a open problem in the field of evolutionary computation. Diversity is used to reflect the balance in practice. In this paper, a scheme that using colony fitness defined by us in selection is proposed to achieve the balance. Such a scheme can be widely used in different evolutionary algorithms. Our experiments are executed based on evolutionary algorithms based on different chromosome representation. Experimental results show that our scheme bring the improvement on diversity. Thus, solutions go significantly better in nine cases out of twenty-five ones, while go statistical worse in only one case.

In the High Speed Internet (HSI) service of the Fiber-To-The-Home (FTTH) networks, there are increasingly various applications, such as browsing, video streaming, large downloads and online games. They are competing for the fixed bandwidth on a best-effort basis, and finally resulting in the network congestion and poor quality of experience (QoE). Users want to improve the quality of certain applications. However, today's network service controller (e.g. Broadband Remote Access Server, BRAS) lacks mechanisms to meet the users' desire to enhance the QoE of specific applications. Moreover, BRAS still lacks mechanisms to allocate the bandwidth resources properly for users' different applications according to their “sweet points”. “Sweet points” is a specific bandwidth value. The QoE gets worse quickly when the bandwidth is smaller than the “sweet point”, and keeps the same approximately when the bandwidth is larger than the “sweet point”. In this paper, we proposed a novel BRAS architecture using Software-Defined Networking (SDN) technology, which can improve the user's QoE by adjusting the bandwidth of a specific application to its “sweet point” according to their requirements. To demonstrate the feasibility of our proposed novel BRAS, we built a prototype using SDN to help the user to adjust the bandwidth for the specific application and improve the users' QoE. The experimental results show that users could enhance the QoE of specific applications according to users' preference.

As a popular type of parallel evolutionary algorithms, distributed evolutionary algorithms (DEAs) are widely used in a variety of fields. To get better solutions of concrete problems, a scheme of subpopulation diversity based accepting immigrant in DEAs is proposed in this paper. In migration with this scheme, an immigrant will be put into its target subpopulation only if its current diversity is lower than a threshold value. Algorithm analysis shows that the extra cost of time for this scheme is acceptable in many DEAs. Experiments are conducted on instances of the Traveling Salesman Problem from the TSPLIB. Results show that the DEA based on the proposed scheme can get better solutions than the one without it.

With the objective of tracing out all craniofacial structures in parallel with landmarking on X-ray images in cephalometry for the first time, a novel approach is proposed to locate 262 feature points composed of 90 landmarks and 172 auxiliary points. Twelve landmarks are identified by classical image processing techniques and a pattern matching algorithm, and then are used to divide the craniofacial shape to ten independent regions according to the anatomical knowledge. For each region, principal component analysis is employed to statistically characterize its shape and the gray profile of every feature point in the training, and a modified active shape model is proposed for localization. We conclude with experiment results and some discussion.

This paper introduces an interactive marker-controlled mesh segmentation algorithm. In many applications, we need to partition a given mesh according to human perception or particular requirements. The algorithm presented in this paper is based on fast marching watersheds. We refer to the experience of image segmentation area and introduce interactive marker selection. Thus we obviously overcome the difficulty in intuitional segmentation control, and improve the quality of segmentation. The output results show the effectiveness and practicability of the algorithm.