Search arXiv⌕ Search

arXiv subjects

Chenshu Wu

Publications and source records attributed to Chenshu Wu.

At least 19 recordsLinked to original sources
arXiv2026

CoraLive: Ultra-Low-Power Underwater Vision for Long-term Coral Reef Monitoring

Effective coral reef protection and restoration demands continuous, long-term underwater monitoring. However, current solutions largely rely on fragmented, manual labor and costly infrastructure, or are severely limited by constrained battery lifespans. In this paper, we present CoraLive, an ultra-low-power underwater camera system for long-term, continuous coral reef monitoring. CoraLive presents a decoupled underwater-shore co-design that minimizes on-board computation and storage, offloading heavy reconstruction and segmentation tasks to offline shore-side processing. To achieve this, CoraLive introduces a dual-rate sensing scheme combining frequent low-resolution frames with sparse high-fidelity samples and a content-adaptive update mechanism that extracts and stores only compact, task-specific data, eliminating the need to save raw video frames. We implement CoraLive on a custom STM32U575-based dual-camera prototype with device-level computation and storage optimization. Compared with raw recording, CoraLive reduces daily storage by $4.51\times$ and average power by $7.78\times$, extending battery lifetime from 20.4 to 159.5~days while retaining high-accuracy segmentation and reconstruction. Further validated in a real-world underwater deployment, we envision CoraLive as a pioneering step for ubiquitous long-term coral reef underwater monitoring.

cs.NI↗
arXiv2026

AmbientFM: A Foundation Model for Ambient Sensing

Ambient intelligence seeks to continuously understand human presence, activity, and physiology in physical spaces, enabling smart environments, health monitoring, and human-computer interaction. WiFi infrastructure offers a ubiquitous, always-on, and privacy-preserving sensing substrate across billions of IoT devices. Yet ambient sensing with WiFi remains largely fragmented, with most systems relying on task-specific models, labeled data collection, and customized training pipelines. We present AmbientFM, a foundation model for ambient sensing through ubiquitous WiFi signals. AmbientFM is pre-trained on 9.2 million unlabeled Channel State Information (CSI) samples collected over 439 days from 20 commercial device types deployed in real homes, the largest real-world WiFi CSI pre-training corpus reported to date. It learns transferable wireless representations through contrastive learning, masked reconstruction, and physics-informed objectives tailored to wireless signals. With lightweight adaptation, a single backbone transfers to 9 downstream tasks, achieving above 0.90 AUROC on all classification benchmarks and supporting dense spatial reconstruction. AmbientFM reduces the need for labeled data and task-specific design, enabling scalable ambient intelligence on existing wireless infrastructure.

cs.LG↗
arXiv2026

StickFigure: Enabling Pose-Only IoT Cameras for Privacy-Preserving Edge Vision

Indoor IoT cameras can support assisted living and activity-aware spaces, but exporting raw RGB frames raises privacy concerns by exposing facial, clothing, and household details that body-motion tasks often do not require. We present StickFigure, a pose-only IoT camera system that, during real-time monitoring, keeps raw frames local and ephemeral while exporting only compact skeleton streams sufficient for downstream human activity recognition (HAR). While pose estimation has matured on GPUs, extracting accurate pose streams on resource-constrained IoT cameras remains difficult. To overcome these challenges and enable on-device pose streams on (almost) any IoT camera, we present two core designs in StickFigure: an activation-aware pose backbone that allocates channel capacity after spatial downsampling and a lightweight hierarchical MLP refiner that selectively corrects elbow and wrist coordinates using intermediate visual features and kinematic context. We fully implement StickFigure and evaluate it on public benchmarks and real-world deployment. Compared with state-of-the-art MCU pose models, StickFigure achieves the highest pose accuracy and downstream HAR utility on both NTU RGB+D and Penn Action, while using 96.5% fewer parameters and 99.3% fewer MACs per frame than RTMPose-S-based baselines, achieving 0.107 s p95 latency on a representative STM32H753 MCU. We believe StickFigure establishes a new operating point for privacy-aware edge vision on massive IoT cameras.

cs.CV↗
arXiv2026

TAP3D: Thermal-Assisted 3D Human Point Clouds

Human body point clouds are a versatile representation for AI-enabled human sensing. However, existing methods using LiDAR, radar, and depth cameras suffer from inherent drawbacks in high cost, sparse reconstruction, and privacy concerns, etc. In this paper, we exploit low-cost thermal arrays and present TAP3D, the first system to reconstruct 3D human point clouds from body heat signatures, offering significant advantages in cost, density, human sensitivity, and privacy. To overcome major challenges in depth estimation, thermal interference, and multi-person separation, we propose a novel physics-informed design, which integrates a forward thermal physics model with two distinct modules: multi-primitive estimation for self-supervised joint recovery of depth and other thermal properties, and geometric perspective fusion for suppressing interference and disentangling multiple people. We implement TAP3D using a single commodity thermal array sensor and build a large-scale dataset (160K samples, 8 environments, 11 users) for evaluation. TAP3D achieves remarkable accuracy for dense point cloud generation, enabling downstream tasks like fall detection (91.46%), indoor tracking (21.86 cm MAE), and human mesh recovery (4.87 cm error). By transforming body heat into point clouds for the first time, TAP3D pioneers a new paradigm for privacy-first, fully passive human sensing for many applications. TAP3D is open-sourced at https://github.com/aiot-lab/TAP3D.

cs.CV↗
arXiv2026

OctoSense: Building a Unified Ecosystem for Open-Source Wireless Sensing

As AI enters the physical world, wireless sensing has emerged as a key modality for enabling non-intrusive physical intelligence. However, unlike the mature ecosystems of vision and language models, wireless sensing research remains highly fragmented. The field faces a growing "reproducibility wall" caused by heterogeneous data formats, non-interoperable processing pipelines, and the lack of standardized benchmarks. To dismantle this barrier, we present OctoSense, a unified platform designed to propel wireless sensing toward an "ImageNet-style" research ecosystem. OctoSense introduces a holistic framework that decouples high-level model logic from ad-hoc data nuances through three distinct components: a unified data abstraction for streamlined dataset access, standardized signal operators for efficient model development, and a rigorous benchmark engine for rapid and fair comparison. To support existing datasets and models, OctoSense integrates a comprehensive suite of widely used datasets and models, reducing the effort required for data and model adaptation to a few lines of declarative code. We demonstrate the efficacy of OctoSense through a set of usage examples that reproduce representative models on popular datasets. By providing a foundational open-source infrastructure, OctoSense enables community efforts to accumulate rather than fragment, paving the way for wireless sensing research that is interoperable, reusable, and reproducible by design.

cs.NI↗
arXiv2026

A Gram-Attention Learning Framework for Spatially Non-Stationary Channel Estimation

As next-generation wireless systems migrate to high-frequency bands, extremely large-scale multiple-input multiple-output (XL-MIMO) is indispensable for combating severe path loss. However, the received path energy along the extremely large array aperture (ELAA) may exhibit spatial non-stationarity, rendering the conventional discrete Fourier transform (DFT) codebook inadequate for channel estimation (CE) due to its full-array angular representation. To address this mismatch, we propose a novel joint angle-subarray (JAS) codebook, where each codeword corresponds to an angular direction and a specific subarray. Spatially non-stationary CE is thus transformed into structured sparse support detection in the JAS domain. However, reliable support recovery remains challenging for conventional model-based methods. We therefore develop a signal processing and deep learning co-design framework, where data-driven JAS parallel support detection is followed by least-squares (LS)-based channel reconstruction. The matched filter response of each JAS grid is embedded into a high-dimensional feature vector. We then propose a Gram-attention module that incorporates the Gram matrix as a physical prior to guide feature purification, enabling the network to suppress leakage-related components while preserving support-relevant information of each grid. The purified features are passed to decoupled heads to infer the hierarchical sparse supports in the JAS domain. Finally, LS is performed over the low-dimensional dictionary constructed from the detected supports to retrieve path gains. Simulation results demonstrate that the proposed framework achieves the highest support detection F1-score and the lowest CE normalized mean square error (NMSE) among all baselines, while ablation studies verify the benefits of integrating the Gram-domain physical prior with data-driven representation learning.

eess.SP↗
arXiv2026

Scaling WiFi Sensing for Ubiquitous Home Monitoring: Lessons from Real-World Deployment on Millions of Devices

WiFi-based home monitoring offers compelling advantages over traditional camera and sensor solutions by leveraging existing wireless infrastructure for contactless, privacy-preserving and through-the-wall detection. This paper presents insights from developing and deploying a WiFi-based human monitoring system across real-world residential environments, addressing the gap between academic research and practical deployment. Through a two-year study involving 280 edge devices across 15 homes in 11 U.S. states, collecting over 4 million motion samples, we identify and address four critical deployment challenges previously underexplored in academic settings: (1) false positives from non-human motion sources (pets, robots) that degrade system reliability, (2) hardware heterogeneity in commercial IoT devices causing inconsistent CSI quality, (3) signal interference in multi-user environments limiting individual tracking capabilities, and (4) computational and bandwidth constraints preventing real-time edge processing. The deployed system integrates a biomechanics-based classifier that reduces non-human false alarms from 63.1\% to 8.4\%, a multi-layer sensing quality metric validating device suitability without environment-specific calibration, proximity-based multi-user detection leveraging distributed IoT devices, and a hybrid edge-cloud architecture with ACF-based compression achieving 99.72\% data reduction. The integrated system achieves 92.61\% human motion detection accuracy across diverse uncontrolled home environments. We have successfully deployed home monitoring technology on millions of WiFi routers nationwide and smart IoT devices (e.g., bulbs, plugs) worldwide, demonstrating its viability for large-scale real-world applications. We share these findings to guide future research toward deployable WiFi sensing systems.

eess.SP↗
arXiv2026

Towards White-Box Deep Wireless Sensing

The empirical success of deep learning has spurred its application to the radio-frequency (RF) domain, leading to significant advances in Deep Wireless Sensing (DWS). However, most existing DWS models remain black boxes, with ad-hoc architectures and learned representations lacking explicit physical and mathematical grounding, which limits their reliability and generalizability in real-world deployments. We present RF-CRATE, an early step towards white-box DWS grounded in the complex sparse rate reduction principle. Using the CR-Calculus framework, we derive a fully complex-valued transformer with mathematically interpretable self-attention and residual modules. To address labeled data scarcity, we introduce subspace regularization to enhance representation diversity, yielding a 19.98% average improvement. We evaluate RF-CRATE across heterogeneous RF modalities and human sensing tasks, including activity, gait, and gesture recognition, pose estimation, and respiration monitoring. Experiments on five datasets show that RF-CRATE remains competitive with strong black-box models while providing mathematically interpretable architectures and representations. Moreover, the complex-valued design achieves a 3.39% gain in classification accuracy and a 10.34% reduction in regression error. Our results demonstrate that mathematically grounded models can achieve strong performance in wireless sensing, offering a promising step towards physically aligned white-box DWS systems.

cs.LG↗
arXiv2026

Networked Tracking of Multiple Moving Targets in 6G Network

This paper considers a networked tracking architecture in 6G integrated sensing and communication (ISAC) systems, where multiple base stations (BSs) cooperatively transmit radio signals and process received echo signals to track multiple moving targets. Compared to the single-BS counterpart, networked tracking allows the moving targets to be associated with different BSs over time such that the wireless resources can be dynamically allocated among BSs based on target locations. However, networked tracking imposes new challenges for algorithm design and resource allocation. In this paper, we first design the networked Kalman Filter (NKF) that is suitable for multi-BS based tracking, then characterize the posterior Cramer-Rao bound (PCRB) under this NKF, and last design the beamforming vectors of all the BSs to minimize the tracking PCRB. Numerical results show that our dynamic beamforming design can properly associate the targets to the suitable BSs at various sensing blocks and reduce the tracking mean-squared error (MSE).

eess.SP↗
arXiv2026

RF-LEGO: Modularized Signal Processing-Deep Learning Co-Design for RF Sensing via Deep Unrolling

Wireless sensing, traditionally relying on signal processing (SP) techniques, has recently shifted toward data-driven deep learning (DL) to achieve performance breakthroughs. However, existing deep wireless sensing models are typically end-to-end and task-specific, lacking reusability and interpretability. We propose RF-LEGO, a modular co-design framework that transforms interpretable SP algorithms into trainable, physics-grounded DL modules through deep unrolling. By replacing hand-tuned parameters with learnable ones while preserving core processing structures and mathematical operators, RF-LEGO ensures modularity, cascadability, and structure-aligned interpretability. Specifically, we introduce three deep-unrolled modules for critical RF sensing tasks: frequency transform, spatial angle estimation, and signal detection. Extensive experiments using real-world data for Wi-Fi, millimeter-wave, UWB, and 6G sensing demonstrate that RF-LEGO significantly outperforms existing SP and DL baselines, both standalone and when integrated into multiple downstream tasks. RF-LEGO pioneers a novel SP-DL co-design paradigm for wireless sensing via deep unrolling, shedding light on efficient and interpretable deep wireless sensing solutions. Our code is available at https://github.com/aiot-lab/RF-LEGO.

cs.DC↗
arXiv2026

"Take Me Home, Wi-Fi Drone": A Drone-based Wireless System for Wilderness Search and Rescue

Wilderness Search and Rescue (WiSAR) represents a longstanding and critical societal challenge, demanding innovative and automatic technological solutions. In this paper, we introduce Wi2SAR, a novel autonomous drone-based wireless system for long-range, through-occlusion WiSAR operations, without relying on existing infrastructure. Our basic insight is to leverage the automatic reconnection behavior of modern Wi-Fi devices to known networks. By mimicking these networks via on-drone Wi-Fi, Wi2SAR uniquely facilitates the discovery and localization of victims through their accompanying mobile devices. Translating this simple idea into a practical system poses substantial technical challenges. Wi2SAR overcomes these challenges via three distinct innovations: (1) a rapid and energy-efficient device discovery mechanism to discover and identify the target victim, (2) a novel RSS-only, long-range direction finding approach using a 3D-printed Luneburg Lens, amplifying the directional signal strength differences and significantly extending the operational range, and (3) an adaptive drone navigation scheme that guides the drone toward the target efficiently. We implement an end-to-end prototype and evaluate Wi2SAR across various mobile devices and real-world wilderness scenarios. Experimental results demonstrate Wi2SAR's high performance, efficiency, and practicality, highlighting its potential to advance autonomous WiSAR solutions. Wi2SAR is open-sourced at https://aiot-lab.github.io/Wi2SAR to facilitate further research and real-world deployment.

cs.NI↗
arXiv2026

TaFall: Balance-Informed Fall Detection via Passive Thermal Sensing

Falls are a major cause of injury and mortality among older adults, yet most incidents occur in private indoor environments where monitoring must balance effectiveness with privacy. Existing privacy-preserving fall detection approaches, particularly those based on radio frequency sensing, often rely on coarse motion cues, which limits reliability in real-world deployments. We introduce TaFall, a balance-informed fall detection system based on low-cost, privacy-preserving thermal array sensing. The key insight is that TaFall models a fall as a process of balance degradation and detects falls by estimating pose-driven biomechanical balance dynamics. To enable this capability from low-resolution thermal array maps, we propose (i) an appearance-motion fusion model for robust pose reconstruction, (ii) physically grounded balance-aware learning, and (iii) pose-bridged pretraining to improve robustness. TaFall achieves a detection rate of 98.26% with a false alarm rate of 0.65% on our dataset with over 3,000 fall instances from 35 participants across diverse indoor environments. In 27 day deployments across four homes, TaFall attains an ultra-low false alarm rate of 0.00126% and a pilot bathroom study confirms robustness under moisture and thermal interference. Together, these results establish TaFall as a reliable and privacy-preserving approach to fall detection in everyday living environments.

cs.CV↗
arXiv2026

Neuro-Wideband WiFi Sensing via Self-Conditioned CSI Extrapolation

WiFi sensing has suffered from the limited bandwidths designated for its original communication purpose, leading to fundamental limits in multipath resolution and thus multi-user sensing. Unfortunately, it is practically prohibitive to obtain large bandwidths on commercial WiFi, considering the conflict between the limited spectrum and the crowded networks. In this paper, we present Neuro-Wideband (NWB), a completely different paradigm that enables wideband WiFi sensing without specialized hardware or extra channel measurements. Our key insight is that any physical measurement of channel state information (CSI) inherently encapsulates multipath parameters, which, while unsolvable in isolation, can be transformed into an expanded form of CSI (eCSI) approximating measurements over a broader bandwidth. To ground this insight, we propose WUKONG to address NWB as a unique self-conditioned learning problem that can be trained by using any existing CSI data as self-labeled samples. WUKONG introduces a novel deep learning framework by integrating Transformer and Diffusion models, which captures sample-specific multipath parameters and transfers this sample-level knowledge to the outcome eCSI. We conduct real-world experiments to evaluate WUKONG on diverse WiFi signals across protocols and bandwidths. The results show the promising effectiveness of NWB, which is further demonstrated through case studies on localization and multi-person breathing monitoring using eCSI. Overall, the proposed NWB promises a practical pathway toward realizing wideband WiFi sensing on commodity hardware, expanding the design space of wireless sensing systems.

eess.SP↗
arXiv2025

CardioLive: Empowering Video Streaming with Online Cardiac Monitoring

Online Cardiac Monitoring (OCM) emerges as a compelling enhancement for the next-generation video streaming platforms. It enables various applications including remote health, online affective computing, and deepfake detection. Yet the physiological information encapsulated in the video streams has been long neglected. In this paper, we present the design and implementation of CardioLive, the first online cardiac monitoring system in video streaming platforms. We leverage the naturally co-existed video and audio streams and devise CardioNet, the first audio-visual network to learn the cardiac series. It incorporates multiple unique designs to extract temporal and spectral features, ensuring robust performance under realistic video streaming conditions. To enable the Service-On-Demand online cardiac monitoring, we implement CardioLive as a plug-and-play middleware service and develop systematic solutions to practical issues including changing FPS and unsynchronized streams. Extensive experiments have been done to demonstrate the effectiveness of our system. We achieve a Mean Square Error (MAE) of 1.79 BPM error, outperforming the video-only and audio-only solutions by 69.2% and 81.2%, respectively. Our CardioLive service achieves average throughputs of 115.97 and 98.16 FPS when implemented in Zoom and YouTube. We believe our work opens up new applications for video stream systems. We will release the code soon.

cs.HC↗
arXiv2025

ASE: Practical Acoustic Speed Estimation Beyond Doppler via Sound Diffusion Field

Passive human speed estimation plays a critical role in acoustic sensing. Despite extensive study, existing systems, however, suffer from various limitations: First, the channel measurement rate proves inadequate to estimate high moving speeds. Second, previous acoustic speed estimation exploits Doppler Frequency Shifts (DFS) created by moving targets and relies on microphone arrays, making them only capable of sensing the radial speed within a constrained distance. To overcome these issues, we present ASE, an accurate and robust Acoustic Speed Estimation system on a single commodity microphone. We propose a novel Orthogonal Time-Delayed Multiplexing (OTDM) scheme for acoustic channel estimation at a high rate that was previously infeasible, making it possible to estimate high speeds. We then model the sound propagation from a unique perspective of the acoustic diffusion field, and infer the speed from the acoustic spatial distribution, a completely different way of thinking about speed estimation beyond prior DFS-based approaches. We further develop novel techniques for motion detection and signal enhancement to deliver a robust and practical system. We implement and evaluate ASE through extensive real-world experiments. Our results show that ASE reliably tracks walking speed, independently of target location and direction, with a mean error of 0.13 m/s, a reduction of 2.5x from DFS, and a detection rate of 97.4% for large coverage, e.g., free walking in a 4m x 4m room. We believe ASE pushes acoustic speed estimation beyond the conventional DFS-based paradigm and inspires exciting research in acoustic sensing. Code is available at https://github.com/aiot-lab/ASE.

cs.HC↗
arXiv2025

Generative AI Meets Wireless Sensing: Towards Wireless Foundation Model

Generative Artificial Intelligence (GenAI) has made significant advancements in fields such as computer vision (CV) and natural language processing (NLP), demonstrating its capability to synthesize high-fidelity data and improve generalization. Recently, there has been growing interest in integrating GenAI into wireless sensing systems. By leveraging generative techniques such as data augmentation, domain adaptation, and denoising, wireless sensing applications, including device localization, human activity recognition, and environmental monitoring, can be significantly improved. This survey investigates the convergence of GenAI and wireless sensing from two complementary perspectives. First, we explore how GenAI can be integrated into wireless sensing pipelines, focusing on two modes of integration: as a plugin to augment task-specific models and as a solver to directly address sensing tasks. Second, we analyze the characteristics of mainstream generative models, such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and diffusion models, and discuss their applicability and unique advantages across various wireless sensing tasks. We further identify key challenges in applying GenAI to wireless sensing and outline a future direction toward a wireless foundation model: a unified, pre-trained design capable of scalable, adaptable, and efficient signal understanding across diverse sensing tasks.

cs.LG↗
arXiv2025

NeurIT: Pushing the Limit of Neural Inertial Tracking for Indoor Robotic IoT

Inertial tracking is vital for robotic IoT and has gained popularity thanks to the ubiquity of low-cost inertial measurement units and deep learning-powered tracking algorithms. Existing works, however, have not fully utilized IMU measurements, particularly magnetometers, nor have they maximized the potential of deep learning to achieve the desired accuracy. To address these limitations, we introduce NeurIT, which elevates tracking accuracy to a new level. NeurIT employs a Time-Frequency Block-recurrent Transformer (TF-BRT) at its core, combining both RNN and Transformer to learn representative features in both time and frequency domains. To fully utilize IMU information, we strategically employ body-frame differentiation of magnetometers, considerably reducing the tracking error. We implement NeurIT on a customized robotic platform and conduct evaluation in various indoor environments. Experimental results demonstrate that NeurIT achieves a mere 1-meter tracking error over a 300-meter distance. Notably, it significantly outperforms state-of-the-art baselines by 48.21% on unseen data. Moreover, NeurIT demonstrates robustness in large urban complexes and performs comparably to the visual-inertial approach (Tango Phone) in vision-favored conditions while surpassing it in feature-sparse settings. We believe NeurIT takes an important step forward toward practical neural inertial tracking for ubiquitous and scalable tracking of robotic things. NeurIT is open-sourced here: https://github.com/aiot-lab/NeurIT.

cs.RO↗
arXiv2025

TAPOR: 3D Hand Pose Reconstruction with Fully Passive Thermal Sensing for Around-Device Interactions

This paper presents the design and implementation of TAPOR, a privacy-preserving, non-contact, and fully passive sensing system for accurate and robust 3D hand pose reconstruction for around-device interaction using a single low-cost thermal array sensor. Thermal sensing using inexpensive and miniature thermal arrays emerges with an excellent utility-privacy balance, offering an imaging resolution significantly lower than cameras but far superior to RF signals like radar or WiFi. The design of TAPOR, however, is challenging, mainly because the captured temperature maps are low-resolution and textureless. To overcome the challenges, we investigate thermo-depth and thermo-pose properties, proposing a novel physics-inspired neural network that learns effective 3D spatial representations of potential hand poses. We then formulate the 3D pose reconstruction problem as a distinct retrieval task, enabling accurate hand pose determination from the input temperature map. To deploy TAPOR on IoT devices, we introduce an effective heterogeneous knowledge distillation method, reducing computation by 377x. TAPOR is fully implemented and tested in real-world scenarios, showing remarkable performance, supported by four gesture control and finger tracking case studies. We envision TAPOR to be a ubiquitous interface for around-device control and have open-sourced it at https://github.com/aiot-lab/TAPOR.

cs.HC↗