Ying Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ying Chen has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Maria Gorlatova
Electrical and Computer Engineering, Duke University, Durham, North Carolina, USA
4 shared publications - Guohao Lan
Delft University of Technology
2 shared publications - Tianyi Hu
Duke University, Durham, NC, USA
2 shared publications - Tim Scargill
Duke University, Durham, UNITED STATES
2 shared publications - Fan Yang
Duke University, Durham, USA
1 shared publication - Hazer Inaltekin
School of Engineering, Macquarie University, North Ryde, NSW, Australia
1 shared publication
Latest Publications
- Open Access
- 12 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Understanding Retail Planograms through Virtual Reality-based Shopper Shelf Perception Analytics
- 12 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessUnderstanding Retail Planograms through Virtual Reality-based Shopper Shelf Perception Analytics
- Open Access
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 322-335
SEESys: Online Pose Error Estimation System for Visual SLAM
In this work, we introduce SEESys, the first system to provide online pose error estimation for Simultaneous Localization and Mapping (SLAM). Unlike prior offline error estimation approaches, the SEESys framework efficiently collects real-time system features and delivers accurate pose error magnitude estimates with low latency. This enables real-time quality-of-service information for downstream applications. To achieve this goal, we develop a SLAM system run-time status monitor (RTS monitor) that performs feature collection with minimal overhead, along with a multi-modality attention-based Deep SLAM Error Estimator (DeepSEE) for error estimation. We train and evaluate SEESys using both public SLAM benchmarks and a diverse set of synthetic datasets, achieving an RMSE of 0.235 cm of pose error estimation, which is 15.8% lower than the baseline. Additionally, we conduct a case study showcasing SEESys in a real-world scenario, where it is applied to a real-time audio error advisory system for human operators of a SLAM-enabled device. The results demonstrate that SEESys provides error estimates with an average end-to-end latency of 37.3 ms, and the audio error advisory reduces pose tracking error by 25%.
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 322-335
Open AccessSEESys: Online Pose Error Estimation System for Visual SLAM
In this work, we introduce SEESys, the first system to provide online pose error estimation for Simultaneous Localization and Mapping (SLAM). Unlike prior offline error estimation approaches, the SEESys framework efficiently collects real-time system features and delivers accurate pose error magnitude estimates with low latency. This enables real-time quality-of-service information for downstream applications. To achieve this goal, we develop a SLAM system run-time status monitor (RTS monitor) that performs feature collection with minimal overhead, along with a multi-modality attention-based Deep SLAM Error Estimator (DeepSEE) for error estimation. We train and evaluate SEESys using both public SLAM benchmarks and a diverse set of synthetic datasets, achieving an RMSE of 0.235 cm of pose error estimation, which is 15.8% lower than the baseline. Additionally, we conduct a case study showcasing SEESys in a real-world scenario, where it is applied to a real-time audio error advisory system for human operators of a SLAM-enabled device. The results demonstrate that SEESys provides error estimates with an average end-to-end latency of 37.3 ms, and the audio error advisory reduces pose tracking error by 25%.
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (12) , 11466-11482
Quantifying and Exploiting VR Frame Correlations: An Application of a Statistical Model for Viewport Pose
In virtual reality (VR), users’ head pose , that is, the location and the orientation of users’ viewport, determines the view of the virtual world that is shown to the users. The importance of the viewport pose to VR experiences calls for the development of VR viewport pose models. However, no study has obtained a full pose (the position and the orientation) model applicable to modeling the viewport pose in VR experiences. In this paper, informed by our experimental measurements of viewport trajectories across 4 different types of VR interfaces, we first develop a statistical model of viewport poses in VR environments. Based on the developed model, we examine the correlations between pixels in VR frames that correspond to different viewport poses, and obtain an analytical expression for the visibility similarity (ViS) of the pixels across different VR frames. We then propose a lightweight ViS-based algorithm (ALG-ViS) that adaptively splits VR frames into the background and the foreground, reusing the background across different frames. Our implementation of ALG-ViS in two Oculus Quest 2 rendering systems demonstrates ALG-ViS running in real time, supporting the full VR frame rate, and outperforming baselines on measures of frame quality and bandwidth consumption.
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (12) , 11466-11482
Quantifying and Exploiting VR Frame Correlations: An Application of a Statistical Model for Viewport Pose
In virtual reality (VR), users’ head pose , that is, the location and the orientation of users’ viewport, determines the view of the virtual world that is shown to the users. The importance of the viewport pose to VR experiences calls for the development of VR viewport pose models. However, no study has obtained a full pose (the position and the orientation) model applicable to modeling the viewport pose in VR experiences. In this paper, informed by our experimental measurements of viewport trajectories across 4 different types of VR interfaces, we first develop a statistical model of viewport poses in VR environments. Based on the developed model, we examine the correlations between pixels in VR frames that correspond to different viewport poses, and obtain an analytical expression for the visibility similarity (ViS) of the pixels across different VR frames. We then propose a lightweight ViS-based algorithm (ALG-ViS) that adaptively splits VR frames into the background and the foreground, reusing the background across different frames. Our implementation of ALG-ViS in two Oculus Quest 2 rendering systems demonstrates ALG-ViS running in real time, supporting the full VR frame rate, and outperforming baselines on measures of frame quality and bandwidth consumption.
- Open Access
- 2 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
DNN-based SLAM Tracking Error Online Estimation
Simultaneous localization and mapping (SLAM) takes in sensor data, e.g., camera frames, and estimates the user's trajectory while creating a map of the surrounding environment. However, existing SLAM evaluation methods are not reference-free, requiring ground-truth trajectories collected from external systems that are infeasible for most scenarios. In this demo, we present Deep SLAM Error Estimator (DeepSEE), a framework that collects features from a standard visual SLAM pipeline as multivariate time series and uses an attention-based neural network to estimate the tracking error at run time. We evaluate DeepSEE in a game engine-based virtual environment, which generates the visual input for DeepSEE and provides the ground-truth trajectory. Demo participants can navigate the virtual environment to create their own trajectories and view the online pose error estimation. This demo showcases how DeepSEE can act as a quality-of-service indicator for downstream applications.
- 2 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessDNN-based SLAM Tracking Error Online Estimation
Simultaneous localization and mapping (SLAM) takes in sensor data, e.g., camera frames, and estimates the user's trajectory while creating a map of the surrounding environment. However, existing SLAM evaluation methods are not reference-free, requiring ground-truth trajectories collected from external systems that are infeasible for most scenarios. In this demo, we present Deep SLAM Error Estimator (DeepSEE), a framework that collects features from a standard visual SLAM pipeline as multivariate time series and uses an attention-based neural network to estimate the tracking error at run time. We evaluate DeepSEE in a game engine-based virtual environment, which generates the visual input for DeepSEE and provides the ground-truth trajectory. Demo participants can navigate the virtual environment to create their own trajectories and view the online pose error estimation. This demo showcases how DeepSEE can act as a quality-of-service indicator for downstream applications.
- Open Access
- 9 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 368-369
Demo Abstract: BiGuide: A Bi-level Data Acquisition Guidance for Object Detection on Mobile Devices | Proceedings of the 22nd International Conference on Information Processing in Sensor Networks
Real-time object detection (OD) is a key enabling technology for a wide range of emerging mobile system applications. However, deploying an OD model pre-trained on a public dataset (source domain) in a specific local environment (target domain) is known to lead to significant performance degradation because of the so-called domain gap between the dataset and the environment. Collecting local data and fine-tuning the OD model on this data is a commonly used approach for improving the robustness of OD models in real-world deployments. Yet, the question of how to collect this data is currently largely overlooked; unsupported data collection is likely to produce datasets that contain significant proportion of redundant or uninformative data for model training. In this demo, we present BiGuide, a bi-level image data acquisition guidance for OD tasks, to guide users to change their camera locations or angles to different extents (significantly or slightly) to obtain the data which benefits model training via image-level and object instance-level guidance. We showcase an interactive demonstration of collecting data for a lemur species detection application we are developing and deploying at the Duke Lemur Center. Demo participants will take pictures of lemur toys with the mobile phone under the real-time guidance and will observe the real-time display of the metrics that assess the importance of the captured data. They will develop an intuition for how real-time image importance assessment and bi-level guidance improve the quality of collected data.
- 9 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 368-369
Open AccessDemo Abstract: BiGuide: A Bi-level Data Acquisition Guidance for Object Detection on Mobile Devices | Proceedings of the 22nd International Conference on Information Processing in Sensor Networks
Real-time object detection (OD) is a key enabling technology for a wide range of emerging mobile system applications. However, deploying an OD model pre-trained on a public dataset (source domain) in a specific local environment (target domain) is known to lead to significant performance degradation because of the so-called domain gap between the dataset and the environment. Collecting local data and fine-tuning the OD model on this data is a commonly used approach for improving the robustness of OD models in real-world deployments. Yet, the question of how to collect this data is currently largely overlooked; unsupported data collection is likely to produce datasets that contain significant proportion of redundant or uninformative data for model training. In this demo, we present BiGuide, a bi-level image data acquisition guidance for OD tasks, to guide users to change their camera locations or angles to different extents (significantly or slightly) to obtain the data which benefits model training via image-level and object instance-level guidance. We showcase an interactive demonstration of collecting data for a lemur species detection application we are developing and deploying at the Duke Lemur Center. Demo participants will take pictures of lemur toys with the mobile phone under the real-time guidance and will observe the real-time display of the metrics that assess the importance of the captured data. They will develop an intuition for how real-time image importance assessment and bi-level guidance improve the quality of collected data.