With the rapid growth of video-based applications, edge-cloud collaboration has become a mainstream paradigm for large-scale visual inference. However, existing edge-cloud systems primarily emphasize task offloading and static resource allocation, often overlooking the dynamic and heterogeneous nature of real-world scenarios. The significant variability in scene complexity across tasks leads to inefficient system performance. In this article, we propose CLAP, a cross-layer adaptive pipelining inference scheduling framework for edge-cloud vision systems. First, CLAP introduces a lightweight multiscale scene-aware module that accurately characterizes the visual complexity of incoming tasks at different granularities with minimal overhead. Based on this complexity profile, we design an adaptive multi-stage pipeline scheduling strategy, which dynamically adjusts processing granularity and selectively activates stages across edge and cloud nodes. Furthermore, we formulate the resource allocation as a multi-agent decision-making problem and employ cross-layer reinforcement learning to optimize task distribution under complex objectives, efficiently balancing accuracy, delay, and energy consumption. Extensive evaluations on public datasets demonstrate that CLAP can improve the throughput by more than 2.1x compared to traditional cloud-only and edge-only solutions while meeting accuracy requirements. Compared to state-of-the-art edge-cloud methods, CLAP achieves a 3% improvement in inference accuracy while simultaneously reducing end-to-end resource overhead, delay, and energy consumption by over 35%, proving its effectiveness in dynamic, large-scale vision applications.

Detecting small objects in large-scale, high-resolution aerial images presents significant challenges. Most existing detectors focus primarily on the design of detection heads and fusion layers, often overlooking information loss in the backbone and the excessive computational resources required, which are particularly constrained in aerial image analysis. To address the aforementioned challenges, we propose the Resolution-Aware Criss-Cross Attention Detector (RACDet), which effectively leverages the contextual information embedded in an innovative backbone RACNet of aerial images. By decomposing the position information into orthogonal horizontal and vertical components, we achieve efficient modeling of spatial dependencies. For each pixel, RACNet gathers contextual information from all other pixels in the same position, establishing position relationships early, which can guide the subsequent processing in convolutional networks across different resolutions. The proposed method not only provides an adaptive representation of feature maps at multi-scale resolutions using normalized position encoding, but also enhances the detection accuracy of small objects by leveraging a regression loss function based on smooth Gaussian Wasserstein distance. We evaluate our method on two challenging aerial image datasets, including VisDrone2019 and UAVDT. Comprehensive experiments show that our approach achieves state-of-the-art performance while significantly decreasing the number of FLOPs.

Vision Transformers ($V$iTs) have made significant progress in achieving performance comparable to traditional convolutional neural networks in computer vision tasks. However, high computational complexity restricts their application to resource-constrained edge devices. Previous methods for pruning redundant tokens have shown that it is possible to balance performance and computational cost by reducing the number of tokens. Unfortunately, simply removing redundant tokens often leads to the loss of crucial information. To address this issue, we propose a novel token compression scheme called TA-ASF. This scheme considers both the global role of low-importance tokens and the redundancy among similar tokens. TA-ASF employs novel approaches for token sampling and fusion, which are directly applicable to$V$iTs without introducing additional trainable parameters. A comprehensive evaluation against several edge devices demonstrates our method effectively reduces model complexity while preserving Top-1 accuracy. Experimental results show that on the ImageNet dataset, the proposed method reduces FLOPs by 37% and increases throughput by 1.48 times on the DeiT-S model, with only a 0.1% decrease in accuracy. Specifically, on the DeiT-B model, the proposed method decreases FLOPs by 35% and increases throughput by 1.52 times while maintaining the same accuracy.

Non-intrusive Appliance Load Monitoring (NALM) aims to recognize individual appliance usage from the main meter without indoor sensors. However, existing systems struggle to balance dataset construction efficiency and event/state recognition accuracy, especially for low-power appliance recognition. This paper introduces Hawk, an efficient and accurate NALM system that operates in two stages: dataset construction and event recognition. In the data construction stage, we efficiently collect a balanced and diverse dataset, HawkDATA, based on balanced Gray code and enable automatic data annotations via a sampling synchronization strategy called shared perceptible time. During the event recognition stage, our algorithm pipeline integrates steady-state differential pre-processing and voting-based post-processing for accurate event recognition from the aggregate current. Experimental results show that HawkDATA takes only 1/71.5 of the collection time to collect 6.34x more appliance state combinations than the baseline. In HawkDATA and a widely used dataset, Hawk achieves an average F1 score of 93.94% for state recognition and 97.07% for event recognition, which is a 47.98% and 11.57% increase over SOTA algorithms. Furthermore, selected appliance subsets and the model trained from HawkDATA are deployed in two real-world scenarios with many unknown background appliances. The average F1 scores of event recognition are 96.02% and 94.76%. Hawk's source code and HawkDATA are accessible at https://github.com/WZiJ/SenSys24-Hawk.

Motivated by the advances in deep learning techniques, the application of unmanned aerial vehicle (UAV)-based object detection has proliferated across a range of fields, including vehicle counting, fire detection, and city monitoring. While most existing research studies only a subset of the challenges inherent to UAV-based object detection, there are few studies that balance various aspects to design a practical system for energy consumption reduction. In response, we present the E3-UAV, an edge-based energy-efficient object detection system for UAVs. The system is designed to dynamically support various UAV devices, edge devices, and detection algorithms, with the aim of minimizing energy consumption by deciding the most energy-efficient flight parameters (including flight altitude, flight speed, detection algorithm, and sampling rate) required to fulfill the detection requirements of the task. We first present an effective evaluation metric for actual tasks and construct a transparent energy consumption model based on hundreds of actual flight data to formalize the relationship between energy consumption and flight parameters. Then, we present a lightweight energy-efficient priority decision algorithm based on a large quantity of actual flight data to assist the system in deciding flight parameters. Finally, we evaluate the performance of the system, and our experimental results demonstrate that it can significantly decrease energy consumption in real-world scenarios. Additionally, we provide four insights that can assist researchers and engineers in their efforts to study UAV-based object detection further.

Deep learning frameworks, such as TensorFlow, PyTorch, MXNet, and Paddle Paddle are widely used and studied by industry. At the same time, AIoT (Artificial Intelligence and Internet of Things) and edge computing have provided more deep learning scenarios on the edge. In order to develop and deploy AIoT applications, we need to evaluate deep learning frameworks from ease-of-use and performance. To describe the full life-cycle performance of deep learning frameworks on the edge, this paper proposed a metric set, PDR, includes three comprehensive submetrics: Programming complexity, Deployment complexity, and Runtime performance. Based on the PDR, this paper designed and implemented a full life-cycle evaluation tool, Flet-Edge, which can automatically collect and present the PDR’s metrics, visually. Finally, to verify the availability of the Flet-Edge, this paper built a heterogeneous edge device cluster and carried out three case studies. With only one configuration file as input, the FletEdge will collect the twelve metrics of training or inference tasks and output them in text or chart. By observing the hierarchical roofline diagram provided by the Flet-Edge, this paper shows that the Flet-edge has the ability to optimize software and hardware of deep learning.

In the last five years, edge computing has attracted tremendous attention from industry and academia due to its promise to reduce latency, save bandwidth, improve availability, and protect data privacy to keep data secure. At the same time, we have witnessed the proliferation of AI algorithms and models which accelerate the successful deployment of intelligence mainly in cloud services. These two trends, combined together, have created a new horizon: Edge Intelligence (EI). The development of EI requires much attention from both the computer systems research community and the AI community to meet these demands. However, existing computing techniques used in the cloud are not applicable to edge computing directly due to the diversity of computing sources and the distribution of data sources. We envision that there missing a framework that can be rapidly deployed on edge and enable edge AI capabilities. To address this challenge, in this paper we first present the definition and a systematic review of EI. Then, we introduce an Open Framework for Edge Intelligence (OpenEI), which is a lightweight software platform to equip edges with intelligent processing and data sharing capability. We analyze four fundamental EI techniques which are used to build OpenEI and identify several open problems based on potential research directions. Finally, four typical application scenarios enabled by OpenEI are presented.

Driven by the visions of Internet of Things and 5G communications, the edge computing systems integrate computing, storage, and network resources at the edge of the network to provide computing infrastructure, enabling developers to quickly develop and deploy edge applications. At present, the edge computing systems have received widespread attention in both industry and academia. To explore new research opportunities and assist users in selecting suitable edge computing systems for specific applications, this survey paper provides a comprehensive overview of the existing edge computing systems and introduces representative projects. A comparison of open-source tools is presented according to their applicability. Finally, we highlight energy efficiency and deep learning optimization of edge computing systems. Open issues for analyzing and designing an edge computing system are also studied in this paper.

In this paper, we envision the future connected and autonomous vehicles (CAVs) as a sophisticated computer on wheels, with substantial on-board sensors as data sources and a variety of services running on top to support autonomous driving or other functions. In general, these services are computationally expensive, especially for the machine learning based applications (e.g., CNN-based object detection). Nevertheless, the on-board computation unit possess limited compute resources, raising a huge challenge to deploy these computation-intensive services on the vehicle. On the contrary, the cloud-based architecture conceptually with unconstrained resources suffers from unexpected extended latency that attributes to the large-scale Internet data transmission; thus, adversely affecting the services' real-time performance, quality of services and user experiences. To address this dilemma, inspired by the promising edge computing paradigm, we propose to build an Open Vehicular Data Analytics Platform (OpenVDAP) for CAVs, which is a full-stack edge based platform including an on-board computing/communication unit, an isolation-supported and security & privacy-preserved vehicle operation system, an edge-aware application library, as well as an optimal workload of?oading and scheduling strategy, allowing CAVs to dynamically detect each service's status, computation overhead and the optimal of?oading destination so that each service could be finished within an acceptable latency and limited bandwidth consumption. Most importantly, contrast to the proprietary platform, OpenVDAP is an open-source platform that offers free APIs and real-?eld vehicle data to the researchers and developers in the community, allowing them to deploy and evaluate applications on the real environment.