Meta tags:
description= ;
Headings (most frequently used words):
fastdepth, fast, monocular, depth, estimation, on, embedded, systems, abstract, video, downloads, bibtex,
Text of the page (most frequently used words):
and (12), the (10), depth (9), estimation (7), #fastdepth (5), embedded (5), #monocular (4), that (4), network (4), fast (3), systems (3), paper (3), accuracy (3), for (3), are (3), this (3), 2019 (2), wofk (2), diana (2), fangchang (2), yang (2), tien (2), karaman (2), sertac (2), sze (2), vivienne (2), single (2), low (2), state (2), art (2), deep (2), neural (2), real (2), time (2), inference (2), platform (2), micro (2), aerial (2), vehicle (2), decoder (2), latency (2), our (2), demonstrates (2), work (2), fps (2), tx2 (2), using (2), with (2), authors (2), accessibility, mit, eems, inproceedings, icra_2019_fastdepth, author, title, booktitle, ieee, international, conference, robotics, automation, icra, year, bibtex, code, poster, downloads, video, impact, optimizations, versus, speed, tradeoff, sensing, critical, function, robotic, tasks, such, localization, mapping, obstacle, detection, there, has, been, significant, growing, interest, from, rgb, image, due, relatively, cost, size, cameras, however, view, algorithms, based, fairly, complex, networks, too, slow, instance, mounted, address, problem, propose, efficient, lightweight, encoder, architecture, apply, pruning, further, reduce, computational, complexity, particular, focus, design, methodology, possible, achieve, similar, prior, but, speeds, order, magnitude, faster, proposed, runs, 178, nvidia, jetson, gpu, when, only, cpu, active, power, consumption, under, achieves, close, nyu, dataset, best, knowledge, highest, throughput, can, carried, abstract, massachusetts, institute, technology, these, contributed, equally,
Text of the page (random words):
fastdepth fastdepth fast monocular depth estimation on embedded systems diana wofk fangchang ma tien ju yang sertac karaman vivienne sze massachusetts institute of technology these authors contributed equally to this work abstract depth sensing is a critical function for robotic tasks such as localization mapping and obstacle detection there has been a significant and growing interest in depth estimation from a single rgb image due to the relatively low cost and size of monocular cameras however state of the art single view depth estimation algorithms are based on fairly complex deep neural networks that are too slow for real time inference on an embedded platform for instance mounted on a micro aerial vehicle in this paper we address the problem of fast depth estimation on embedded systems we propose an efficient and lightweight encoder decoder network architecture and apply network pruning to further reduce computational complexity and latency in particular we focus on the design of a low latency decoder our methodology demonstrates that it is possible to achieve similar accuracy as prior work on depth estimation but at inference speeds that are an order of magnitude faster our proposed network fastdepth runs at 178 fps on an nvidia jetson tx2 gpu and at 27 fps when using only the tx2 cpu with active power consumption under 10 w fastdepth achieves close to state of the art accuracy on the nyu depth v2 dataset to the best of the authors knowledge this paper demonstrates real time monocular depth estimation using a deep neural network with the highest throughput on an embedded platform that can be carried by a micro aerial vehicle accuracy versus speed tradeoff impact of optimizations video downloads paper poster code bibtex inproceedings icra_2019_fastdepth author wofk diana and ma fangchang and yang tien ju and karaman sertac and sze vivienne title fastdepth fast monocular depth estimation on embedded systems booktitle ieee international conference on robotics and automation icra year 2019 mit eems 2019 accessibility
|
