Infrared LEDs-Based Pose Estimation With Underground Camera Model for Boom-Type Roadheader in Coal Mining

Abstract

Accurate and reliable pose estimation of a boom-type roadheader is of great importance in order to maintain the efficiency of automatic coal mining. The stability and accuracy of conventional measurement methods are difficult to be guaranteed on account of vibration noise, magnetic disturbance, electrostatic interference, and other factors in an underground environment. In this paper, a vision-based non-contact measurement method for cutting-head pose estimation is presented, which deploy a 16-point infrared LED target on the boom-type roadheader to tackle the low-illumination, high-dust, and complicated background. By establishing a monocular vision measurement system, the cutting-head pose is estimated through processing the LED target images obtained from an explosion-proof industrial camera mounted on the roadheader. After analyzing the measurement mechanism, an underground camera model based on the equivalent focal length is built to eliminate refraction errors caused by the two-layer glasses for explosion-proof and dust removal. Then, the pose estimation processes, including infrared LEDs feature point extraction, spot center location, and an improved P4P method based on dual quaternions, are carried out. The influence factors of cutting-head pose estimation accuracy are further studied by modeling, and the error distribution of the main parameters is investigated and evaluated. The numerical simulation and experimental evaluation are designed to verify the performance of the proposed method. The results show that the pose estimation error is in line with the numerical prediction, achieving the requirements of cuttinghead pose estimation in underground roadway construction in the coal mine.INDEX TERMS Vision measurement, infrared LEDs, pose estimation, underground camera model, total accuracy error, boom-type roadheader.

Bacterial Programming Based Kinematic Chain Estimation of Construction Vehicle

“…All segments are equipped with one randomly placed INS. As such, there are five revolute joints with the joint angles θ i=1.. 5 , where i is the ID of the segment. Coordinate frames are attached to the joints and INS between two links, such that the first transformation is associated with the first joint, the second with the INS and the third is associated with the next link joint.…”

“…Vision-based tool center point (TCP) position estimation methods can directly analyze position as well as orientation information [1] , however these methods are predominantly applied in indoor localization topics [2]. Marker-based vision systems recognize mounted markers and estimate the pose by their geometric relations [3], [4], or project infrared LEDs and analyze the patterns [5]. Markerless pose estimations directly extract image features and estimate pose [6] based on single [7] or multi [8] camera systems.…”

The Use of a Stereovision System in Shape Detection of the Side Surface of the Body of the Mining Machine Working Unit

“…The location of the pick holder base in space is determined by the position of the TCP point of the robot tool positioning the pick holder and the orientation of the coordinate system axis associated with this tool. This work focuses on the issue of identifying (extracting) markers applied to the side surface of the cutting head/cutting drum on recorded images (Yang, Zhang & Zhang, 2019). The applied grid should be as dense as possible and markers as small as possible so that the quantization results of the data contained in the images have a sufficient number of levels of representation, which increases the measurement accuracy (Zorski & Samsel, 2009).…”

A Multi-Sensor Based Roadheader Positioning Model and Arbitrary Tunnel Cross Section Automatic Cutting

“…Similar to the ultra-wide band method, there was difficulty with both deployment and with obtaining a high accuracy. An infrared LED based method was proposed to position the roadheader [9], which was reported to achieve an accuracy of less than 3 cm, but the infrared LED based method suffers from a similar problem to the ultra-wide band method, that is, the error increases with the increasing distance. Therefore, while the aforementioned methods are presented, to the best of our knowledge, none of them have wide-spread applications in a practical tunneling project.…”

“…The critical data that need to be acquired for positioning are the posture angles of the roadheader and the coordinates of a fixed point on the roadheader when taking the roadheader as a rigid body [9]. To efficiently solve the positioning problem and realize high accuracy positioning, the inertial system based method and the total station based method should be combined.…”