skip to main content


Search for: All records

Award ID contains: 1952180

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Free, publicly-accessible full text available July 1, 2024
  2. Split-computing has recently emerged as a paradigm for offloading computation of visual analytics models from low-powered mobile devices to edge or cloud servers, by which the mobiles execute part of the model and compress and send the intermediate features, and the servers complete the remaining model computation. Prior feature compression approaches train different compression models and possibly visual analytics models to reach different target bit rates. We propose a scalable compression model that compresses the intermediate features of the YOLO object detection model into a layered bitstream, which can be easily adapted to meet the rate constraint of a dynamic network. Our approach achieves comparable rate-accuracy performance compared to prior non-scalable compression approaches over a large bitrate range. 
    more » « less
    Free, publicly-accessible full text available May 12, 2024
  3. Vision-based localization approaches now underpin newly emerging navigation pipelines for myriad use cases, from robotics to assistive technologies. Compared to sensor-based solutions, vision-based localization does not require pre-installed sensor infrastructure, which is costly, time-consuming, and/or often infeasible at scale. Herein, we propose a novel vision-based localization pipeline for a specific use case: navigation support for end users with blindness and low vision. Given a query image taken by an end user on a mobile application, the pipeline leverages a visual place recognition (VPR) algorithm to find similar images in a reference image database of the target space. The geolocations of these similar images are utilized in a downstream task that employs a weighted-average method to estimate the end user’s location. Another downstream task utilizes the perspective-n-point (PnP) algorithm to estimate the end user’s direction by exploiting the 2D–3D point correspondences between the query image and the 3D environment, as extracted from matched images in the database. Additionally, this system implements Dijkstra’s algorithm to calculate a shortest path based on a navigable map that includes the trip origin and destination. The topometric map used for localization and navigation is built using a customized graphical user interface that projects a 3D reconstructed sparse map, built from a sequence of images, to the corresponding a priori 2D floor plan. Sequential images used for map construction can be collected in a pre-mapping step or scavenged through public databases/citizen science. The end-to-end system can be installed on any internet-accessible device with a camera that hosts a custom mobile application. For evaluation purposes, mapping and localization were tested in a complex hospital environment. The evaluation results demonstrate that our system can achieve localization with an average error of less than 1 m without knowledge of the camera’s intrinsic parameters, such as focal length. 
    more » « less
  4. Smart health applications have received significant attention in recent years. Novel applications hold significant promise to overcome many of the inconveniences faced by persons with disabilities throughout daily living. For people with blindness and low vision (BLV), environmental perception is compromised, creating myriad difficulties. Precise localization is still a gap in the field and is critical to safe navigation. Conventional GNSS positioning cannot provide satisfactory performance in urban canyons. 3D mapping-aided (3DMA) GNSS may serve as an urban GNSS solution, since the availability of 3D city models has widely increased. As a result, this study developed a real-time 3DMA GNSS-positioning system based on state-of-the-art 3DMA GNSS algorithms. Shadow matching was integrated with likelihood-based ranging 3DMA GNSS, generating positioning hypothesis candidates. To increase robustness, the 3DMA GNSS solution was then optimized with Doppler measurements using factor graph optimization (FGO) in a loosely-coupled fashion. This study also evaluated positioning performance using an advanced wearable system’s recorded data in New York City. The real-time forward-processed FGO can provide a root-mean-square error (RMSE) of about 21 m. The RMSE drops to 16 m when the data is post-processed with FGO in a combined direction. Overall results show that the proposed loosely-coupled 3DMA FGO algorithm can provide a better and more robust positioning performance for the multi-sensor integration approach used by this wearable for persons with BLV. 
    more » « less
  5. Recent advances in computer vision has led to a growth of interest in deploying visual analytics model on mobile devices. However, most mobile devices have limited computing power, which prohibits them from running large scale visual analytics neural networks. An emerging approach to solve this problem is to offload the computation of these neural networks to computing resources at an edge server. Efficient computation offloading requires optimizing the trade-off between multiple objectives including compressed data rate, analytics performance, and computation speed. In this work, we consider a “split computation” system to offload a part of the computation of the YOLO object detection model. We propose a learnable feature compression approach to compress the intermediate YOLO features with lightweight computation. We train the feature compression and decompression module together with the YOLO model to optimize the object detection accuracy under a rate constraint. Compared to baseline methods that apply either standard image compression or learned image compression at the mobile and perform image de-compression and YOLO at the edge, the proposed system achieves higher detection accuracy at the low to medium rate range. Furthermore, the proposed system requires substantially lower computation time on the mobile device with CPU only. 
    more » « less