Abstract
In this paper, deep learning and image processing technologies are combined, and an automatic sampling robot is proposed that can completely replace the manual method in the three-dimensional space when used for the autonomous location of sampling points. It can also achieve good localization accuracy, which solves the problems of the high labor intensity, low efficiency, and poor scientific accuracy of the manual sampling of mineral powder. To improve localization accuracy and eliminate non-linear image distortion due to wide-angle lenses, distortion correction was applied to the captured images. We solved the problem of low detection accuracy in some scenes of Single Shot MultiBox Detector (SSD) through data augmentation. A visual localization model has been established, and the image coordinates of the sampling point have been determined through color screening, image segmentation, and connected body feature screening, while coordinate conversion has been performed to complete the spatial localization of the sampling point, guiding the robot in performing accurate sampling. Field experiments were conducted to validate the intelligent sampling robot, which showed that the maximum visual positioning error of the robot is 36 mm in the x-direction and 24 mm in the y-direction, both of which meet the error range of less than or equal to 50 mm, and could meet the technical standards and requirements of industrial sampling localization accuracy.
Highlights
In the fiercely competitive environment of the metallurgical industry, the efficiency of ore powder quality inspection is directly related to the costs and benefits of the enterprise
They can be roughly divided into two categories—two-stage algorithms based on the candidate area, such as the R-CNN series, fast R-CNN, faster R-CNN, etc. [14–16], and one-stage algorithms based on the regression method, such as YOLO (You Only Look Once) series and Single Shot MultiBox Detector (SSD) [17–21]
If the prediction frame generated by the SSD algorithm exceeds the actual sampling range, this will cause security probIlfemthse. gIfetnheeragteenderparteeddipctrieodnicftrioanmferaims teoios stomoaslml, aitllw, iitllwniloltncootmcopmlepteleltyelcyocvoevrearlal lslampling sampalrienags.arTehase.reTfhoerree,foIoreU, GIoiUs deisfindeefdinaesdtahsetrhaetiroatoiof tohfethaereaareoafotfhtehienitnetresrescetcitoionnbbeetw- een the tweepnrethdeicptiroednifcrtaiomnefraanmdetahnedrethael frreaaml fer,amdiev,iddievdidbeydtbhyetahreeaaroefatohfethreearlefarlafmraem. eI.oUIoGUis used to is usmedeatosumreeatshueredethteecdtieotnecetfiofenctefofef ctthoefStShDe SaSlgDoariltghomrithinmthine tshaemspalminpglinargeaar.eIaf.tIhfethperediction predfircatimoneferxamceeedexscteheedsstahme psalimngplrinagngraen, gthe,ethseamsapmlipnligngrarnagngeeisisnnoott ddeetteecctteeddoorrIIooUUG< < 0.8, at
Summary
In the fiercely competitive environment of the metallurgical industry, the efficiency of ore powder quality inspection is directly related to the costs and benefits of the enterprise. Two-stage algorithms have high accuracy but slow speed, and are not suitable for the real-time requirements of ore powder target detection. In terms of image segmentation, Wang et al introduced a new automatic Region-based Image Segmentation Algorithm based on k-means clustering (RISA), designed for remote sensing applications This method was shown to have better flexibility and accuracy through case studies [42]. The SSD algorithm based on deep learning is combined with image processing technologies such as color screening and image segmentation to achieve accurate localization and coordinate transformation of sampling points, so as to guide the robot to conduct automatic detection and meet the requirements of the error range of localization. TT2hh.eeTPhPrerooPpprooospseoedsdeSdSyySssyttesetmmem IInn ttIhhniistshssieseccstteiicootnino,,ntt,hhteheeppprrooropppooossseeeddd sssyysstteeemmmiisisseeexxxppplalliaaniienndeeddiniidnneddtaeeiltt.aaTiillh..eTTphhreeopporrosoeppdoossyeesddtesmsyyssitsteemm iiss bbaasseebddasooednn fofoonuufrrosusereccstteiiocotninoss:n:ismi:miamagagegededidsitissottorotritoionnncoccororrrerececttciiotoinno;;nSS;SSSDDSDddeedtteeeccttteiiocontniooonffttohhfeetaahrreeaaaorofefaththoeefccathar-rericaagre-; rtihaegrevi;aisgtuhea;elthvloeiscvuailasiulzaalolticlooanclaizmliazotaidtoieonln;mcmooooddredelli;;nccaootoeorrtddriainnnasatfetoetrrtmarnaasntfisoofrnom,ramatniaodtnig,oaunni,ddaengdduridogebudoidtreolodbcoartloliobzcaoattiliol-oncaanlidzsaatmiozpantliiaonnngd.anTsdahmesapdmleiptnalgiinl.sgT.ahTreehedshdeoetatwailinlssabarereelosswhhoo. wwnnbbeeloloww. . 22..11..2DD.1ii.sstDtooirsrtttioioorntnioCCnooCrrrorerecrcteticiotoninon
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
