Driven by the tremendous application demands, the Internet-of-Things (IoT) systems are expected to fulfill computation-intensive and latency-sensitive sensing and computational tasks, which pose a significant challenge for the IoT devices with limited computational ability and battery capacity. To address this problem, edge computing is a promising architecture where the IoT devices can offload their tasks to the edge servers. Current works on task offloading often overlook the unique task topologies and schedules from the IoT devices, leading to degraded performance and underutilization of the edge resources. In this paper, we investigate the problem of fine-grained task offloading in edge computing for low-power IoT systems. By explicitly considering 1) the topology/schedules of the IoT tasks, 2) the heterogeneous resources on edge servers and 3) the wireless interference in the multi-access edge networks, we propose a lightweight yet efficient offloading scheme for multi-user Edge systems, which offloads the most appropriate IoT tasks/subtasks to edge servers such that the expected execution time is minimized. To support the multi-user offloading, we also propose a distributed consensus algorithm for low-power IoT devices. We conduct extensive simulation experiments and the results show that the proposed offloading algorithms can effectively reduce the end-to-end task execution time and improve the resource utilization of the edge servers.

In computer vision, the homography estimation of infrared and visible multi-source images based on deep learning is a current research hotspot. Existing homography estimation methods ignore the feature differences of multi-source images, which leads to poor homography performance in infrared and visible image scenes. To address this issue, we designed an infrared and visible image homography estimation method using a Multi-scale Generative Adversarial Network, called HomoMGAN. First, we designed two shallow feature extraction networks to extract fine features of infrared and visible images, respectively, which extract important features in source images from two dimensions: color channel and imaging space. Second, we proposed an unsupervised generative adversarial network to predict the homography matrix directly. In our adversarial network, the generator captures meaningful features for homography estimation at different scales by using an encoder–decoder structure and further predicts the homography matrix. The discriminator recognizes the feature difference between the warped and target image. Through the adversarial game between the generator and the discriminator, the fine features of the warped image in the homography estimation process are closer to the fine features of the target image. Finally, we conduct extensive experiments in the synthetic benchmark dataset to verify the effectiveness of HomoMGAN and its components. We conduct extensive experiments and the results show that HomoMGAN outperforms existing state-of-the-art methods in the synthetic benchmark datasets both qualitatively and quantitatively.

Edge computing is a promising technology to empower the Internet-of-Things (IoT) by providing additional processing ability, where the tasks can be offloaded to the edge servers for efficient computing. To enable easy management and improve the resource utilization of edge computing, Network Function Virtualization (NFV) is often employed to quickly deploy the requested network functions (NFs) for serving front-end devices. Considering that the edge servers are close to the frontend users, the time-varying geographical distribution of users has a significant influence on the NF deployment in the network of edge servers. Based on this observation, we propose a deep reinforcement learning (DRL) based approach for NF deployment, which has the following two salient features. First, we employ DRL to estimate the underlying wireless features affected by user mobility, which has a direct impact on the task performance in the edge-IoT systems. Second, we implicitly utilize the multi-access opportunity to deploy the NFs, considering the estimated features and user requests. Compared to the existing works, the proposed work can significantly improve the resource utilization of edge servers as well as the computational efficiency of IoT tasks. The evaluation results obtained from extensive simulation experiments show that our approach can be well adapted to the time-varying user geo-distributions and achieve improved performance in terms of both resource utilization of edge servers and task executions of the IoT devices.

Homography estimation of infrared and visible images is a highly challenging task in computer vision. Recently, the deep learning homography estimation methods have focused on the plane, while ignoring the details in the image, resulting in the degradation of the homography estimation performance in infrared and visible image scenes. In this work, we propose a detail-aware deep homography estimation network to preserve more detailed information in images. First, we design a shallow feature extraction network to obtain meaningful features for homography estimation from multi-level multi-dimensional features. Second, we propose a Detail Feature Loss (DFL), which utilizes refined features for computation and retains more detailed information while reducing the influence of unimportant features, enabling effective unsupervised learning. Finally, considering that the evaluation indicators of the previous homography estimation tasks are difficult to reflect severe distortion or the workload of manually labelling feature points is too large, we propose an Adaptive Feature Registration Rate (AFRR) to adaptive extraction of image pair feature points to calculate the registration rate. Extensive experiments demonstrate that our method outperforms existing state-of-the-art methods on synthetic benchmark dataset and real dataset.