Advanced wearable devices are increasingly incorporating high-resolution multi-camera systems. As state-of-the-art neural networks for processing the resulting image data are computationally demanding, there has been a growing interest in leveraging fifth generation (5G) wireless connectivity and mobile edge computing for offloading this processing closer to end-users. To assess this possibility, this paper presents a detailed simulation and evaluation of 5G wireless offloading for object detection in the case of a powerful, new smart wearable called VIS 4 ION, for the Blind-and-Visually Impaired (BVI). The current VIS 4 ION system is an instrumented book-bag with high-resolution cameras, vision processing, and haptic and audio feedback. The paper considers uploading the camera data to a mobile edge server to perform real-time object detection and transmitting the detection results back to the wearable. To determine the video requirements, the paper evaluates the impact of video bit rate and resolution on object detection accuracy and range. A new street scene dataset with labeled objects relevant to BVI navigation is leveraged for analysis. The vision evaluation is combined with a full-stack wireless network simulation to determine the distribution of throughputs and delays with real navigation paths and ray-tracing from new high-resolution 3D models in an urban environment. For comparison, the wireless simulation considers both a standard 4G-Long Term Evolution (LTE) sub-6-GHz carrier and high-rate 5G millimeter-wave (mmWave) carrier. The work thus provides a thorough and detailed assessment of edge computing for object detection with mmWave and sub-6-GHz connectivity in an application with both high bandwidth and low latency requirements.
Running deep visual analytics models for real-time applications is challenging for mobile devices. Offloading the computation to edge server can mitigate computation bottleneck at the mobile device, but may decrease the analytics performance due to the necessity of compressing the image data. We consider a “split computing” system to offload a part of the deep learning model's computation and introduce a novel learned feature compression approach with lightweight computation. We demonstrate the effectiveness of the split computing pipeline in performing computation offloading for the problems of object detection and image classification. Compared to compressing the raw images at the mobile, and running the analytics model on the decompressed images at the server, the proposed feature-compression approach can achieve significantly higher analytics performance at the same bit rate, while reducing the complexity at the mobile. We further propose a scalable feature compression approach, which facilitates adaptation to network bandwidth dynamics, while having comparable performance to the non-scalable approach.