Laboratoire Angevin de Recherche en Ingénierie des Systèmes (LARIS), Université d'Angers, 62 Avenue Notre Dame du Lac, 49035 Angers, France.
UMR 1345 Institut de Recherche en Horticulture et Semences (IRHS), INRAe, 42 Rue Georges Morel, 49071 Beaucouzé, France.
Sensors (Basel). 2020 Jul 27;20(15):4173. doi: 10.3390/s20154173.
Since most computer vision approaches are now driven by machine learning, the current bottleneck is the annotation of images. This time-consuming task is usually performed manually after the acquisition of images. In this article, we assess the value of various egocentric vision approaches in regard to performing joint acquisition and automatic image annotation rather than the conventional two-step process of acquisition followed by manual annotation. This approach is illustrated with apple detection in challenging field conditions. We demonstrate the possibility of high performance in automatic apple segmentation (Dice 0.85), apple counting (88 percent of probability of good detection, and 0.09 true-negative rate), and apple localization (a shift error of fewer than 3 pixels) with eye-tracking systems. This is obtained by simply applying the areas of interest captured by the egocentric devices to standard, non-supervised image segmentation. We especially stress the importance in terms of time of using such eye-tracking devices on head-mounted systems to jointly perform image acquisition and automatic annotation. A gain of time of over 10-fold by comparison with classical image acquisition followed by manual image annotation is demonstrated.
由于大多数计算机视觉方法现在都由机器学习驱动，当前的瓶颈是图像的注释。这项耗时的任务通常在获取图像后手动完成。在本文中，我们评估了各种自我中心视觉方法在执行联合采集和自动图像注释方面的价值，而不是传统的获取后手动注释的两步流程。本文以挑战性田间条件下的苹果检测为例进行了说明。我们通过眼动跟踪系统演示了在自动苹果分割（Dice 0.85）、苹果计数（88%的良好检测概率和 0.09 的真阴性率）和苹果定位（少于 3 个像素的偏移误差）方面实现高性能的可能性。这是通过将自我中心设备捕获的感兴趣区域简单地应用于标准的、非监督的图像分割来实现的。我们特别强调了在头戴式系统上使用这种眼动跟踪设备联合执行图像采集和自动注释的时间方面的重要性。与传统的图像采集后手动图像注释相比，这一过程的时间节省了 10 倍以上。
