Abstract
Ant foraging behavior is essential to understanding ecological dynamics and developing effective pest management strategies, but quantifying this behavior is challenging due to the labor-intensive nature of manual counting, especially in densely populated images. This study presents an automated approach using computer vision to count ants and analyze their foraging behavior. Leveraging the YOLOv8 model, the system was calibrated and evaluated on datasets encompassing various imaging scenarios and densities. The study results demonstrate that the system achieves average precision and recall of up to 87.96% and 87,78%, respectively, with only 64 calibration images provided when the both calibration and evaluation images share similar imaging backgrounds. When the background is more complex than the calibration images, the system requires a larger calibration set to generalize effectively, with 1,024 images yielding the precision and recall of up to 83.60% and 78.88, respectively. In more challenging scenarios where more than one thousand ants are present in a single image, the system significantly improves detection accuracy by slicing images into smaller patches, reaching a precision and recall of 77.97% and 71.36%, respectively. The system's ability to generate heatmaps visualizes the spatial distribution of ant activity over time, providing valuable insights into their foraging patterns. This spatial-temporal analysis enables a more comprehensive understanding of ant behavior, which is crucial for ecological studies and improving pest control methods. By automating the counting process and offering detailed behavioral analysis, this study provides an efficient tool for researchers and pest control professionals to develop more effective strategies.
Abstract (translated)
蚂蚁觅食行为对于理解生态动力学和制定有效的害虫管理策略至关重要，但由于人工计数劳动密集型且在图像高度密集的情况下尤为困难，量化这种行为具有挑战性。本研究提出了一种基于计算机视觉的自动化方法来计数蚂蚁并分析其觅食行为。利用YOLOv8模型，该系统在校准和评估包含各种成像场景和密度的数据集上进行了校准和评估。研究表明，在提供仅64张校准图像且校准与评估图像背景相似的情况下，该系统能够达到平均精确度和召回率分别高达87.96%和87.78%。当背景比校准图像更为复杂时，系统需要更大的校准集才能有效泛化，使用1024张图片能达到最高83.60%的精度和78.88%的召回率。在更复杂的场景中，单个图像中有超过一千只蚂蚁时，通过将图像切分为较小块，该系统显著提高了检测准确性，达到了精确度为77.97%，召回率为71.36%。系统的热图生成能力可以可视化随时间变化的蚂蚁活动空间分布，提供了对其觅食模式的重要洞察。这种时空分析有助于更全面地理解蚂蚁行为，对于生态研究和改进害虫控制方法至关重要。通过自动化计数过程并提供详细的行为分析，本研究为研究人员和害虫防治专业人员开发更有效的策略提供了一种高效工具。
URL
https://arxiv.org/abs/2410.20638
