For the future cyber-physical system (CPS) society, it is necessary to construct digital twins (DTs) of a real world in realtime using a lot of cameras and sensors. Hence, the energy efficiency of both networks and c...
详细信息
ISBN:
(纸本)9798350399806
For the future cyber-physical system (CPS) society, it is necessary to construct digital twins (DTs) of a real world in realtime using a lot of cameras and sensors. Hence, the energy efficiency of both networks and computers for largescale distributed video analysis is a major challenge for the full-scale spread of CPSs and DTs. Toward this goal, we first propose a model to arbitrarily split and distribute the video analysis task to terminals, edge servers, and cloud servers and dynamically assign appropriate CNN models to them. System-wide optimization of such distributed processing can reduce overall system power consumption by reducing network bandwidth and efficiently utilizing distributed CPU/GPU resources. To realize this optimization in a real system, we also propose a model to estimate the GPU load, processingtime, and power consumption of these devices based on massive experimental measurements. Since such a large-scale optimization is difficult because of the dynamic and multi-objective nature of the problem, we propose a new optimization algorithm composed of Genetic Algorithm and Bayesian Attractor Model. Finally, simulation evaluations are performed to demonstrate that the proposed method can minimize system power consumption and satisfy latency and recognition accuracy requirements of each video analysis, even under changing environmental conditions.
Moire patterns are commonly seen when taking photos of screens. Camera devices usually have limited hardware performance but take high-resolution photos. However, users are sensitive to the photo processingtime, whic...
详细信息
ISBN:
(纸本)9798350349405;9798350349399
Moire patterns are commonly seen when taking photos of screens. Camera devices usually have limited hardware performance but take high-resolution photos. However, users are sensitive to the photo processingtime, which presents a hardly considered challenge of efficiency for demoireing methods. To balance the network speed and quality of results, we propose a Fully Connected enCoder-deCoder based Demoireing Network (FC3DNet). FC3DNet utilizes features with multiple scales in each stage of the decoder for comprehensive information, which contains long-range patterns as well as various local moire styles that both are crucial aspects in demoireing. Besides, to make full use of multiple features, we design a Multi-Feature Multi-Attention Fusion (MFMAF) module to weigh the importance of each feature and compress them for efficiency. These designs enable our network to achieve performance comparable to state-of-the-art (SOTA) methods in real-world datasets while utilizing only a fraction of parameters, FLOPs, and runtime.
video prediction requires efficient models capable of forecasting future frames which is a crucial task in various domains. However, many current methodologies are based on autoregressive mechanism, suffering from low...
详细信息
ISBN:
(纸本)9798350359329;9798350359312
video prediction requires efficient models capable of forecasting future frames which is a crucial task in various domains. However, many current methodologies are based on autoregressive mechanism, suffering from low computing efficiency, error propagation and difficulty in parallel processing of data. With an emphasis on efficiency, we propose the Spatio-Temporal Non-autoregressive Model (STNAM) designed for video prediction tasks. This model aims to achieve superior computational efficiency and reduced error accumulation compared to conventional methodologies. The STNAM is grounded in encoder-prediction-decoder framework with a Spatio-Temporal Attention and a Positional encoding. Experimental evaluations on benchmark video datasets showcase the efficacy of the proposed model. It demonstrates competitive performance in predicting video sequences, establishing its potential for real-timevideo forecasting applications.
This paper proposed a smart parking system that helps drivers in seeking out available parking slots based on imageprocessing. With the increased number of vehicles which leads to the parking congestion, finding an e...
详细信息
In the field of autonomous driving, 3D target detection is an important technology. In view of the shortcomings of existing monocular 3D detection algorithms in terms of accuracy and real-time performance, we propose ...
详细信息
In today's Flight Test Instrumentation (FTI) video telemetry applications, parallel video channels of the same video signal are acquired with the on-board data recorder. One is typically a high-quality video chann...
详细信息
video streaming stands as the cornerstone of telecommunication networks, constituting over 60% of mobile data traffic as of June 2023. The paramount challenge faced by video streaming service providers is ensuring hig...
详细信息
ISBN:
(纸本)9798400704123
video streaming stands as the cornerstone of telecommunication networks, constituting over 60% of mobile data traffic as of June 2023. The paramount challenge faced by video streaming service providers is ensuring high Quality of Experience (QoE) for users. In HTTP Adaptive Streaming (HAS), including DASH and HLS, video content is encoded at multiple quality versions, with an Adaptive Bitrate (ABR) algorithm dynamically selecting versions based on network conditions. Concurrently, Artificial Intelligence (AI) is revolutionizing the industry, particularly in content recommendation and personalization. Leveraging user data and advanced algorithms, AI enhances user engagement, satisfaction, and video quality through super-resolution and denoising techniques. However, challenges persist, such as real-timeprocessing on resource-constrained devices, the need for diverse training datasets, privacy concerns, and model interpretability. Despite these hurdles, the promise of Generative Artificial Intelligence emerges as a transformative force. Generative AI, capable of synthesizing new data based on learned patterns, holds vast potential in the video streaming landscape. In the context of video streaming, it can create realistic and immersive content, adapt in realtime to individual preferences, and optimize video compression for seamless streaming in low-bandwidth conditions This research proposal outlines a comprehensive exploration at the intersection of advanced AI algorithms and digital entertainment, focusing on the potential of generative AI to elevate video quality, user interactivity, and the overall streaming experience. The objective is to integrate generative models into video streaming pipelines, unraveling novel avenues that promise a future of dynamic, personalized, and visually captivating streaming experiences for viewers.
In this paper, we propose a novel chaotic-based encryption scheme for securing real-timevideo data. The proposed encryption algorithm is based on the One-time Pad (OTP) scheme and the unified Lorenz chaotic generator...
详细信息
In this paper, we propose a novel chaotic-based encryption scheme for securing real-timevideo data. The proposed encryption algorithm is based on the One-time Pad (OTP) scheme and the unified Lorenz chaotic generator. The peculiarity of the latter is that it can change the chaotic system's and its behaviour as well as its parameters. This provides the system with an important dynamic reconfiguration dimension, especially for real-time applications, in case the key is under attack. As a result, the attacker is obliged to perform these calculations again and again. The 3D unified chaotic generator can switch between three chaotic systems according to a control parameter. As a result, the cryptosystem will offer several advantages, namely a very large dimension of the secret key, low resource and energy consumption and low latency. An extensive security and differential analysis have been performed, demonstrating the high resistance of the proposed scheme to different attacks. The proposed encryption algorithm is validated for real-timevideo through an experimental implementation of FPGA interfaced with a camera. Experimental results indicate that the proposed hardware architecture is very promising since it provides good performance and can be useful in many embedded applications.
The solution to the problem of road environmental perception is one of the essential prerequisites to realizing the autonomous driving of intelligent vehicles, and road lane detection plays a crucial role in road envi...
详细信息
The solution to the problem of road environmental perception is one of the essential prerequisites to realizing the autonomous driving of intelligent vehicles, and road lane detection plays a crucial role in road environmental per-ception. However, road lane detection in complex road scenes is challenging due to poor illumination conditions, the occlusion of other objects, and the influence of unrelated road markings. It also hinders the commercial appli-cation of autonomous driving technology in various road scenes. In order to minimize the impact of illumination factors on road lane detection tasks, researchers use deep learning (DL) technology to enhance low-light images. In this study, road lane detection is regarded as an image segmentation problem, and road lane detection is studied based on the DL approach to meet the challenge of rapid environmental changes during driving. First, the Zero-DCE++ approach is used to enhance the video frame of the road scene under low-light conditions. Then, based on the bilateral segmentation network (BiSeNet) approach, the approach of associate self-attention with BiSeNet (ASA-BiSeNet) integrating two attention mechanisms is designed to improve the road lane detection ability. Finally, the ASA-BiSeNet approach is trained based on the self-made road lane dataset for the road lane detection task. At the same time, the approach based on the BiSeNet approach is compared with the ASA-BiSeNet approach. The experimental results show that the frames per second (FPS) of the ASA-BiSeNet approach is about 152.5 FPS, and its mean intersection over union is 71.39%, which can meet the requirements of real-time autonomous driving. & COPY;2023 Optica Publishing Group
Imaging through a continuously fluctuating water-air interface (WAI) is challenging. The image obtained in this way will suffer from complex refraction distortions that hinder the observer's accurate identificatio...
详细信息
Imaging through a continuously fluctuating water-air interface (WAI) is challenging. The image obtained in this way will suffer from complex refraction distortions that hinder the observer's accurate identification of the object. Reversing these distortions is an ill-posed problem, and the current restoration methods using high-resolution video streams are difficult to adapt to real-time observation scenarios. This paper proposes a method for restoring instantaneous distorted images based on structured light and local approximate registration. The scheme first uses structured light measurement technology to obtain the fluctuation information of the water surface. Then, the displacement information of the feature points on the distorted structured light image and the standard structured light image is obtained through the feature extraction algorithm and is used to estimate the distortion vector field of the corresponding sampling points in the distorted scene image. On this basis, the local approximate algorithm is used to reconstruct the distortion-free scene image. Experimental results show that the proposed algorithm can not only reduce image distortion and improve image visualization, but also has significantly better computational efficiency than other methods, achieving an "end-to-end" processing effect.
暂无评论