Understanding External Influences on Target Detection and Classification Using Camera Trap Images and Machine Learning.
Understanding External Influences on Target Detection and Classification Using Camera Trap Images and Machine Learning.
复制标题
DOI：
10.3390/s22145386
复制
发表时间：
2022-07-19
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
使用机器学习（ML）来自动化相机陷阱（CT）图像处理对于时间敏感的应用是有利的。然而，目前对影响这种处理的因素知之甚少。在这里，我们评估的影响闭塞，距离，植被类型，大小类，高度，主题朝向CT，物种，时间的一天，颜色，和分析性能野生动物/人类的检测和分类的CT图像从坦桑尼亚西部。此外，我们还比较了分析师和ML方法的检测和分类性能。我们通过预先存在的CT图像和使用自愿参与者进行CT实验的人类数据获得野生动物数据。我们在检测和分类级别评估了分析师和ML方法。距离和遮挡等因素，加上植被密度的增加，DP和CC的最显着的影响。总体而言，结果表明，与ML相比，分析方法的检测概率（DP）显著更高，为81.1%，正确分类（CC）为76.6%，ML在CT图像中检测到41.1%的野生动物，并对47.5%的野生动物进行分类。然而，当检测到人类时，两种方法对日光CT图像的概率相似，分别为69.4%（ML）和71.8%（分析员），对黄昏CT图像的概率相似，分别为17.6%（ML）和16.2%（分析员）。鉴于用户认真遵循所提供的建议，我们预计DP和CC将增加。反过来，CT图像处理的ML方法将是支持生物多样性保护的时间敏感的威胁监测的一个很好的条件。
Using machine learning (ML) to automate camera trap (CT) image processing is advantageous for time-sensitive applications. However, little is currently known about the factors influencing such processing. Here, we evaluate the influence of occlusion, distance, vegetation type, size class, height, subject orientation towards the CT, species, time-of-day, colour, and analyst performance on wildlife/human detection and classification in CT images from western Tanzania. Additionally, we compared the detection and classification performance of analyst and ML approaches. We obtained wildlife data through pre-existing CT images and human data using voluntary participants for CT experiments. We evaluated the analyst and ML approaches at the detection and classification level. Factors such as distance and occlusion, coupled with increased vegetation density, present the most significant effect on DP and CC. Overall, the results indicate a significantly higher detection probability (DP), 81.1%, and correct classification (CC) of 76.6% for the analyst approach when compared to ML which detected 41.1% and classified 47.5% of wildlife within CT images. However, both methods presented similar probabilities for daylight CT images, 69.4% (ML) and 71.8% (analysts), and dusk CT images, 17.6% (ML) and 16.2% (analysts), when detecting humans. Given that users carefully follow provided recommendations, we expect DP and CC to increase. In turn, the ML approach to CT image processing would be an excellent provision to support time-sensitive threat monitoring for biodiversity conservation.
登录
查看更多内容
DOI：
10.1016/j.patter.2020.100109
发表时间：
2020-10-09
期刊：
Patterns (New York, N.Y.)
影响因子：
--
作者：
McClure EC;Sievers M;Brown CJ;Buelow CA;Ditria EM;Hayes MA;Pearson RM;Tulloch VJD;Unsworth RKF;Connolly RM
通讯作者：
Connolly RM
影响因子：
2.9
作者：
Kim, Jong Hae
通讯作者：
Kim, Jong Hae
DOI：
10.3390/s18051474
发表时间：
2018-05-08
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Kamminga J;Ayele E;Meratnia N;Havinga P
通讯作者：
Havinga P
影响因子：
11.8
作者：
Marin, Javier;Vazquez, David;Kuncheva, Ludmila I.
通讯作者：
Kuncheva, Ludmila I.
影响因子：
5.5
作者：
Hofmeester, Tim R.;Rowcliffe, J. Marcus;Jansen, Patrick A.
通讯作者：
Jansen, Patrick A.