基于延时摄像的小昆虫目标检测。

Object Detection of Small Insects in Time-Lapse Camera Recordings.

机构信息

Department of Electrical and Computer Engineering, Aarhus University, 8200 Aarhus N, Denmark.

出版信息

Sensors (Basel). 2023 Aug 18;23(16):7242. doi: 10.3390/s23167242.

DOI:10.3390/s23167242

PMID:37631778

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10459366/

Abstract

As pollinators, insects play a crucial role in ecosystem management and world food production. However, insect populations are declining, necessitating efficient insect monitoring methods. Existing methods analyze video or time-lapse images of insects in nature, but analysis is challenging as insects are small objects in complex and dynamic natural vegetation scenes. In this work, we provide a dataset of primarily honeybees visiting three different plant species during two months of the summer. The dataset consists of 107,387 annotated time-lapse images from multiple cameras, including 9423 annotated insects. We present a method for detecting insects in time-lapse RGB images, which consists of a two-step process. Firstly, the time-lapse RGB images are preprocessed to enhance insects in the images. This motion-informed enhancement technique uses motion and colors to enhance insects in images. Secondly, the enhanced images are subsequently fed into a convolutional neural network (CNN) object detector. The method improves on the deep learning object detectors You Only Look Once (YOLO) and faster region-based CNN (Faster R-CNN). Using motion-informed enhancement, the YOLO detector improves the average micro 1-score from 0.49 to 0.71, and the Faster R-CNN detector improves the average micro 1-score from 0.32 to 0.56. Our dataset and proposed method provide a step forward for automating the time-lapse camera monitoring of flying insects.

摘要

作为传粉媒介，昆虫在生态系统管理和世界粮食生产中起着至关重要的作用。然而，昆虫种群正在减少，因此需要高效的昆虫监测方法。现有的方法分析昆虫在自然界中的视频或延时图像，但由于昆虫是复杂和动态自然植被场景中的小物体，因此分析具有挑战性。在这项工作中，我们提供了一个主要是访问三种不同植物物种的蜜蜂的数据集，该数据集在夏季的两个月内进行拍摄。该数据集由来自多个摄像机的 107,387 张注释延时图像组成，其中包括 9423 张注释昆虫。我们提出了一种用于检测延时 RGB 图像中昆虫的方法，该方法由两步组成。首先，延时 RGB 图像经过预处理，以增强图像中的昆虫。这种运动感知增强技术使用运动和颜色来增强图像中的昆虫。其次，随后将增强后的图像输入到卷积神经网络（CNN）目标检测器中。该方法改进了深度学习目标检测器 You Only Look Once（YOLO）和更快的基于区域的 CNN（Faster R-CNN）。通过运动感知增强，YOLO 检测器将平均微观 1 分数从 0.49 提高到 0.71，而 Faster R-CNN 检测器将平均微观 1 分数从 0.32 提高到 0.56。我们的数据集和提出的方法为自动化飞行昆虫延时摄像机监测迈出了一步。