期刊
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017)
卷 -, 期 -, 页码 2850-2859出版社
IEEE
DOI: 10.1109/ICCVW.2017.336
关键词
-
资金
- EPSRC Centre for Doctoral Training in Future Autonomous and Robotic Systems (FARSCOPE) at the Bristol Robotics Laboratory
In this paper, we demonstrate that computer vision pipelines utilising deep neural architectures are well-suited to perform automated Holstein Friesian cattle detection as well as individual identification in agriculturally relevant setups. To the best of our knowledge, this work is the first to apply deep learning to the task of automated visual bovine identification. We show that off-the-shelf networks can perform end-to-end identification of individuals in top-down still imagery acquired from fixed cameras. We then introduce a video processing pipeline composed of standard components to efficiently process dynamic herd footage filmed by Unmanned Aerial Vehicles (UAVs). We report on these setups, as well as the context, training and evaluation of their components. We publish alongside new datasets: FriesianCattle2017 of in-barn top-down imagery, and AerialCattle2017 of outdoor cattle footage filmed by a DJI Inspire MkI UAV. We show that Friesian cattle detection and localisation can be performed robustly with an accuracy of 99.3% on this data. We evaluate individual identification exploiting coat uniqueness on 940 RGB stills taken after milking in-barn (89 individuals, accuracy = 86.1%). We also evaluate identification via a video processing pipeline on 46,430 frames originating from 34 clips (approx. 20 s length each) of UAV footage taken during grazing (23 individuals, accuracy = 98.1%). These tests suggest that, particularly when videoing small herds in uncluttered environments, an application of marker-less Friesian cattle identification is not only feasible using standard deep learning components - it appears robust enough to assist existing tagging methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据