基于目标检测与跟踪的轻量化煤矿区域限员算法

  • 打印
  • 收藏
收藏成功


打开文本图片集

中图分类号:TD67 文献标志码:A

Abstract:At present, underground regional personel restriction algorithms based on video monitoring mainlyrelyon multi-object tracking,which has problemssuch ascomplexcomputation that makes low-power embedded deployment dificult and susceptibilityto environmental light interference.To addresstheabove issues, alightweight algorithm for coal mine regional personnel restriction basedon object detectionand tracking was proposed.Multiple binocular structured-light cameras wereused to colect color and depth images at key entrancesand exits.Based on the improved lightweight object detection model GF-YOLOv8,worker image localization wasachieved.An Intersection-Over-Union priority strategy wasadopted to match objectsand trajectories,which reduced the number of matches compared with traditional tracking algorithms and improved thecomputational speedof tracking.Basedontracking trajectories,the total number of people inkey areas was counted through the cros-line counting method with multiple cameras.When the number of people in the area reached thepersonnel limit,alarm information was generated.The experimental resultsshowed that binocular structured-light cameras effectively overcame the influence of illumination. The AP@0.5 and AP@0.5:0.95 of the improved detection model GF-YOLOv8 increased by 0.24% and 3.42% respectively compared with YOLOv8, while the number of parameters and floating point operations per second decreased by 17.29% and 2.58% respectively.The Intersection-Over-Union priority strategy achieved accuracy close to the DeepSort algorithm but with lower matching complexity. Regarding the count of personnel restriction alarms, there were 17 true alarms; the Intersection-Over-Union priority strategy correctly reported 16 and missed 1 alarm.

Key words: coal mine personnel restriction; regional population statistics; object detection and tracking; binocular structured-light camera; GF-YOLOv8; Intersection-Over-Union priority strategy

0引言

煤矿区域限员是考虑井下空间规模、通风状况[]安全设备配置及避灾路径规划[2等因素,对各个区域最大的工作人数进行规定。(剩余12511字)

monitor
客服机器人