在地下矿山中加强对象检测:UCM-Net和自我监督的预训.
Faguo Zhou1, Junchao Zou1, Rong Xue1
1School of Artificial Intelligence, China University of Mining and Technology-Beijing, Beijing 100083, China.
Sensors (Basel, Switzerland)
|April 12, 2025
概括
本研究介绍了UCM-Net,这是一种有效的AI模型,用于煤矿监测,提高安全和生产. 它使用一种新的骨干和自我监督学习来提高用更少的资源来提高检测准确性.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 采矿工程 采矿工程 采矿工程
背景情况:
- 由于有限的计算资源和恶劣的环境,地下煤矿监测面临着挑战.
- 现有的检测模型在矿井井的识别和计算需求方面扎.
研究的目的:
- 开发一个准确且计算效率高的AI模型,用于实时监控地下煤炭开采操作.
- 为了提高特征捕获稳定性和降低模型复杂性,在具有挑战性的采矿条件下提高性能.
主要方法:
- 拟议的ESFENet骨干具有全球响应规范化 (GRN) 和深度可分离的卷积.
- 开发了基于YOLO架构的UCM-Net检测模型.
- 实施了一种自主监督的预培训方法,使用图像掩盖策略来采集矿井特定的特征.
主要成果:
- 与基线和YOLOv12模型相比,UCM-Net显示出更高的准确性和参数效率.
- 实现了21.5%的参数减少和14.8%的计算负载减少.
- 自主监督的预培训提高了培训效率,在五个数据集中平均产生了94.4%的mAP50.
结论:
- UCM-Net为煤矿安全监测提供了一个强大的解决方案,提高了检测能力.
- 拟议的方法为采矿部门的公共安全提供了重要的技术支持.
- 该研究强调了定制的人工智能模型和在专业环境中的自我监督学习的有效性.
相关概念视频
01:12Non-destructive Tests for Concrete Strength
The rebound hammer test, also known as the Schmidt hammer test, is a non-destructive technique for evaluating the hardness of concrete and, indirectly, the strength of concrete. It operates on the principle that the rebound of a spring-driven mass from a concrete surface correlates to the surface's hardness. The device comprises a mass within a tubular housing, a spring mechanism, and a plunger that strikes the concrete. Upon release, the energy imparted to the mass by the spring causes it to...
01:25Microbial Bioremediation of Uranium
Microorganisms play a critical role in the transformation and immobilization of uranium in contaminated environments through four main pathways: bioreduction, biosorption, bioaccumulation, and biomineralization. These mechanisms reduce uranium’s toxicity and prevent its migration through groundwater systems, offering sustainable approaches for in situ bioremediation.Bioreduction of UraniumBioreduction is driven by anaerobic bacteria such as certain strains of Geobacter and Shewanella, which use...