Improving the precision and accuracy of animal population estimates with aerial image object detection
Improving the precision and accuracy of animal population estimates with aerial image object detection
复制标题
DOI：
10.1111/2041-210x.13277
复制
发表时间：
2019-08-29
影响因子：
6.6
通讯作者：
Prins, Herbert H. T.
中科院分区：
文献类型：
--
作者：
Eikelboom, Jasper A. J.;Wind, Johan;Prins, Herbert H. T.
动物种群数量通常是由人类观察者使用航空样本计数来估计的，无论是野生动物还是牲畜。自1970年代以来，相关的统计方法大体上保持不变，但人口估计的精确度和精确度较低。使用具有成本效益的无人机或带有摄像头和自动动物检测算法的微光飞机进行航空计数可能会提高这一精确度和准确度。因此，我们评估了多类卷积神经网络RetinanNet在从两个肯尼亚动物计数的航空图像中检测大象、长颈鹿和斑马的性能。该算法检测到了四层人类标注发现的95%的大象、91%的长颈鹿和90%的斑马，其中正确检测到所有人类漏掉的额外2.8%的大象、3.8%的长颈鹿和4.0%的斑马，而每个真阳性只检测到1.6%到5.0%的假阳性。此外，该算法对动物的探测对视距的敏感度低于人类。在具有如此高的查全率和准确率的情况下，我们假设仅通过人工识别算法选择的图像边界框来取代人工空中动物计数方法(从图像和/或直接)是可行的，然后在计算种群估计时使用等于欠计数偏差的倒数的修正因子。与手工方法相比，这个修正系数会导致人口估计的标准误差略有增加，但当抽样工作量增加23%时，这种增加可以得到补偿。然而，与人工方法相比，在设备和人员费用相同的情况下，使用我们建议的半自动方法可以获得160%到1050%的采样工作量。因此，我们得出的结论是，我们提出的航空计数方法将提高人口估计的精度，并将人口估计的标准误差降低31%至67%。最重要的是，当提供以固定速率拍摄的图像时，这种动物检测算法在从空中检测动物方面具有超越人类的潜力。
Animal population sizes are often estimated using aerial sample counts by human observers, both for wildlife and livestock. The associated methods of counting remained more or less the same since the 1970s, but suffer from low precision and low accuracy of population estimates. Aerial counts using cost-efficient Unmanned Aerial Vehicles or microlight aircrafts with cameras and an automated animal detection algorithm can potentially improve this precision and accuracy. Therefore, we evaluated the performance of the multi-class convolutional neural network RetinaNet in detecting elephants, giraffes and zebras in aerial images from two Kenyan animal counts. The algorithm detected 95% of the number of elephants, 91% of giraffes and 90% of zebras that were found by four layers of human annotation, of which it correctly detected an extra 2.8% of elephants, 3.8% giraffes and 4.0% zebras that were missed by all humans, while detecting only 1.6 to 5.0 false positives per true positive. Furthermore, the animal detections by the algorithm were less sensitive to the sighting distance than humans were. With such a high recall and precision, we posit it is feasible to replace manual aerial animal count methods (from images and/or directly) by only the manual identification of image bounding boxes selected by the algorithm and then use a correction factor equal to the inverse of the undercounting bias in the calculation of the population estimates. This correction factor causes the standard error of the population estimate to increase slightly compared to a manual method, but this increase can be compensated for when the sampling effort would increase by 23%. However, an increase in sampling effort of 160% to 1,050% can be attained with the same expenses for equipment and personnel using our proposed semi-automatic method compared to a manual method. Therefore, we conclude that our proposed aerial count method will improve the accuracy of population estimates and will decrease the standard error of population estimates by 31% to 67%. Most importantly, this animal detection algorithm has the potential to outperform humans in detecting animals from the air when supplied with images taken at a fixed rate.