Pedestrian detection algorithm of coal mine underground
-
摘要: 针对井下光照不均匀、行人特征与背景的相似度高等导致基于计算机视觉的行人检测技术在井下应用面临很大挑战的问题，提出采用Faster区域卷积神经网络（RCNN）进行煤矿井下行人检测。Faster RCNN行人检测算法采用区域建议网络（RPN）生成候选区域，RPN 与Fast RCNN共享卷积层，以提高网络训练和检测速度；在图像特征提取过程中采用动态自适应池化方法对不同池化域进行自适应池化操作，提高了检测准确性。实验结果表明，该算法对于不同环境下图像中的行人均具有较好的检测效果。Abstract: Due to uneven underground illumination and high similarity between pedestrian characteristics and background, pedestrian detection technology based on computer vision is facing great challenges in underground application. Faster region convolutional neural networks(RCNN) was proposed for pedestrians detection of coal mine underground. Faster RCNN pedestrian detection algorithm uses region proposal network(RPN) to generate candidate regions. RPN shares convolutional layer with Fast RCNN, so as to improve network training and detection speed. A dynamic self-adaptive pooling method is adopted to perform self-adaptive pooling operation for different pooling domains in the process of image feature extraction, so as to improve detection accuracy. The experimental results show that the algorithm has better detection effect for pedestrian image in different environments.
-
-
期刊类型引用(7)
1. 陈湘源，饶天荣，潘涛. 基于半监督学习的煤矿井下行人检测模型. 煤炭技术. 2024(02): 231-234 . 
百度学术
2. 邹盛，周李兵，季亮，于政乾. 基于图像融合和改进CornerNet-Squeeze的煤矿井下行人检测方法. 工矿自动化. 2023(02): 77-84 . 本站查看
3. 殷鹏，周保心，殷仕诚，邵卫，徐夫超，王江涛. 低质量成像条件下的副井检修作业人员安全带检测算法研究. 电子元器件与信息技术. 2023(11): 117-121 . 百度学术
4. 杨春雨，张鑫. 煤矿机器人环境感知与路径规划关键技术. 煤炭学报. 2022(07): 2844-2872 . 百度学术
5. 杨春雨，袁晓光. 煤矿井下巷道变形巡检视频异常检测方法. 工矿自动化. 2021(02): 13-17 . 本站查看
6. 党伟超，史云龙，白尚旺，高改梅，刘春霞. 基于条件变分自编码器的井下配电室巡检行为检测. 工矿自动化. 2021(12): 98-105 . 本站查看
7. 袁永，屠世浩，陈忠顺，张村，王沉，王文苗. 薄煤层智能开采技术研究现状与进展. 煤炭科学技术. 2020(05): 1-17 . 百度学术
其他类型引用(6)
计量
- 文章访问数: 57
- HTML全文浏览量: 11
- PDF下载量: 18
- 被引次数: 13
下载:
