English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Depth sensing is a crucial function of unmanned aerial vehicles andautonomous vehicles. Due to the small size and simple structure of monocularcameras, there has been a growing interest in depth estimation from a singleRGB image. However, state-of-the-art monocular CNN-based depth estimationmethods using fairly complex deep neural networks are too slow for real-timeinference on embedded platforms. This paper addresses the problem of real-timedepth estimation on embedded systems. We propose two efficient and lightweightencoder-decoder network architectures, RT-MonoDepth and RT-MonoDepth-S, toreduce computational complexity and latency. Our methodologies demonstrate thatit is possible to achieve similar accuracy as prior state-of-the-art works ondepth estimation at a faster inference speed. Our proposed networks,RT-MonoDepth and RT-MonoDepth-S, runs at 18.4\&30.5 FPS on NVIDIA Jetson Nanoand 253.0\&364.1 FPS on NVIDIA Jetson AGX Orin on a single RGB image ofresolution 640$\times$192, and achieve relative state-of-the-art accuracy onthe KITTI dataset. To the best of the authors' knowledge, this paper achievesthe best accuracy and fastest inference speed compared with existing fastmonocular depth estimation methods.

RT-MonoDepth: Real-time Monocular Depth Estimation on Embedded Systems