Optical motion capture is a foundational technology driving advancements in cutting-edge fields such as virtual reality and film production. However, system performance suffers severely under large-scale marker occlusions common in real-world applications. An in-depth analysis identifies two primary limitations of current models: (i) the lack of training datasets accurately reflecting realistic marker occlusion patterns, and (ii) the absence of training strategies designed to capture long-range dependencies among markers. To tackle these challenges, we introduce the CMU-Occlu dataset, which incorporates ray tracing techniques to realistically simulate practical marker occlusion patterns. Furthermore, we propose OpenMoCap, a novel motion-solving model designed specifically for robust motion capture in environments with significant occlusions. Leveraging a marker-joint chain inference mechanism, OpenMoCap enables simultaneous optimization and construction of deep constraints between markers and joints. Extensive comparative experiments demonstrate that OpenMoCap consistently outperforms competing methods across diverse scenarios, while the CMU-Occlu dataset opens the door for future studies in robust motion solving. The proposed OpenMoCap is integrated into the MoSen MoCap system for practical deployment. The code is released at: https://github.com/qianchen214/OpenMoCap.

Image-level annotations allow to achieve semantic segmentation in a weakly-supervised way. Most advanced approaches utilize class activation map (CAM) from deep classifier to generate pseudo-labels. However, CAM generally only focuses on the most discriminative parts of targets. To explore more pixel-level semantic information and recognize all pixels within the objects for segmentation, we propose a Region-based Pixels Integration Mechanism (RPIM) which discovers the intra-region and inter-region information. Firstly, the foreground regions are formed on the basis of superpixels and the initial responses. Each region is regarded as a subtree, whose nodes are the image pixels within the region. Then, an Intra-region Integration (IRI) Module is designed to explore the nodes relationships inside the subtree. Within each subtree, nodes will vote for the most confident class and share the highest probability. Moreover, an Inter-region Spreading (IRS) Module is proposed to further improve the consistency of CAM. For each class, the most confident unprocessed subtree finds their homologous neighbors, connects with them and shares its probability. By iterative refinement, the training process will integrate the individual nodes into region subtrees, and gradually form the subtrees with similar probabilities to the object semantic trees for each foreground class. To our best knowledge, our approach achieves the state-of-the-art performance on PASCAL VOC 2012 validation set with 71.4% mIoU. The experiments also show that our scheme is plug-and-play and can collaborate with different approaches to improve their performance.

Gait, the walking manner of a person, has been perceived as a physical and behavioral trait for human identification. Compared with cameras and wearable sensors, Wi-Fi-based gait recognition is more attractive because Wi-Fi infrastructure is almost available everywhere and is able to sense passively without the requirement of on-body devices. However, existing Wi-Fi sensing approaches impose strong assumptions of fixed user walking trajectories, sufficient training data, and identification of already known users. In this article, we present GaitSense , a Wi-Fi-based human identification system, to overcome the above unrealistic assumptions. To deal with various walking trajectories and speeds, GaitSense first extracts target specific features that best characterize gait patterns and applies novel normalization algorithms to eliminate gait irrelevant perturbation in signals. On this basis, GaitSense reduces the training efforts in new deployment scenarios by transfer learning and data augmentation techniques. GaitSense also enables a distinct feature of illegal user identification by anomaly detection, making the system readily available for real-world deployment. Our implementation and evaluation with commodity Wi-Fi devices demonstrate a consistent identification accuracy across various deployment scenarios with little training samples, pushing the limit of gait recognition with Wi-Fi signals.

Wi-Fi-based indoor localization gained a lot of attention over recent years due to low cost and open access properties. However, existing schemes might not be applicable in the real environment if their robustness is low. This paper presents CLRS, a novel distributed Indoor Positioning System (IPS) with high robustness which uses Wi-Fi signals to divide the space twice based on Angle of Arrival (AoA) and Effective Channel State Information (ECSI). The proposed scheme trade the redundancy of Access Point (AP) quantity to improve the tolerance of data measurement error. We performed simulations as well as real-world experiments, in which simulation results proved that the theoretical average error is the least when the routers are placed vertically in our localization method while the real-world experiments proved the high accuracy and robustness of CLRS.

Localization and navigation play a key role in many location-based services and have attracted numerous research efforts from both academic and industrial community. In recent years, visual SLAM has been prevailing for robots and autonomous driving cars. However, the ever-growing computation resource demanded by SLAM impedes its application to resource-constrained mobile devices. In this paper we present the design, implementation, and evaluation of edgeSLAM, an edge assisted real-time semantic visual SLAM service running on mobile devices. edgeSLAM leverages the state-of-the-art semantic segmentation algorithm to enhance localization and mapping accuracy, and speeds up the computation-intensive SLAM and semantic segmentation algorithms by computation offloading. The key innovations of edgeSLAM include an efficient computation offloading strategy, an opportunistic data sharing mechanism, and an adaptive task scheduling algorithm. We fully implement edgeSLAM on an edge server and different types of mobile devices (2 types of smartphones and a development board). Extensive experiments are conducted under 3 data sets, and the results show that edgeSLAM is able to run on mobile devices at 35fps frame rate and achieves a 5cm localization accuracy, outperforming existing solutions by more than 15%. We also demonstrate the usability of edgeSLAM through 2 case studies of pedestrian localization and robot navigation. To the best of our knowledge, edgeSLAM is the first real-time semantic visual SLAM for mobile devices.

Passive acoustic localization is an important technique in a wide variety of monitoring applications, ranging from health care over biological survey to structural health monitoring of buildings. However, the method obtains the location of an unknown sound source with low-cost and simple still is lacking. In this paper, we implement a passive sound source location system based on commercial off-the-shelf (COTS) mobile devices, typically a smartphone, are organized as Wireless Sensor Networks (WSNs). We use the Precise Time Protocol (PTP) in WLAN to achieve the time synchronization of mobile devices with a coarse grain, and then uses moving variance and linear interpolation to get the Time of Arrival (TOA) of the sound source signal. We also design and implement a robust Sequence-Based localization algorithm based on Linear Programming, i.e. LPSBL, which transforms the TOA information of the sound source signal arriving at these devices to a nodes sequence and estimate the location of the sound source by the nodes sequence. After plenty of experiments were carried out, it is verified that our system can provide sufficiently reasonable positioning accuracy and good robustness in an indoor environment.