Ukutholwa kwento kuyisici esibalulekile se-Computer Vision, lapho inhloso kuwukuhlonza nokuthola izinto ezisesithombeni. Enye yezindlela zokukhombisa indawo yento esithombeni iBhokisi Elibophayo. Ibhokisi elibophayo yibhokisi elingunxande elingenziwa ikhompuyutha ngendlela elula ebandakanya ukuncishiswa kwezibalo okuyisisekelo nomsebenzi wokukhulisa.
Ibhokisi, ngaphezu kwalokho, lingamelwa izixhumanisi ezimbili, i-(x, y) ekhoneni eliphezulu kwesokunxele kanye no-(x, y) ekhoneni elingezansi kwesokudla. Lolu lwazi lubonakala lubalulekile ezinhlelweni zokusebenza ezahlukahlukene zokuphila kwangempela, ukusebenzela ochwepheshe kusukela kulabo abagadayo kuya embonini yezimoto ezizishayelayo.
Isitatimende Senkinga Nesixazululo
Inkinga enkulu esibhekana nayo ekutholweni kwesithombe nokutholwa kwento iwukubona ngokunembile indawo yento esesithombeni. Isixazululo siwukusebenzisa ibhokisi elibophayo, elingabalwa kusetshenziswa indlela elula ehlanganisa imitapo yolwazi ehlukahlukene ye-python.
Python iyisinqumo esihle kakhulu salo msebenzi ngoba unemitapo yolwazi ecebile namathuluzi enza inqubo ibe lula, iyenze isebenze kahle futhi iqonde. Imitapo yolwazi emibili eyinhloko ivame ukusetshenziswa - i-OpenCV ne-Matplotlib.
Indlela ye-OpenCV ne-Matplotlib
I-OpenCV imele umtapo wezincwadi we-Open Source Computer Vision futhi ihlanganisa amakhulu amaningana ama-algorithms ombono wekhompyutha. I-Matplotlib, ngakolunye uhlangothi, ingumtapo wolwazi wokuhlela wolimi lokuhlela lwePython kanye nesandiso sezibalo sezinombolo iNumPy. Inikeza kokubili indlela eshesha kakhulu yokubona idatha evela kuPython kanye nezibalo zekhwalithi yokushicilela ngamafomethi amaningi.
import cv2
import matplotlib.pyplot as plt
# read image
image = cv2.imread('input.jpg')
# our bounding box coordinates
box = (x1, y1, x2, y2)
# Draw rectangle (bounding box)
cv2.rectangle(image, (box[0], box[1]), (box[2], box[3]), (0, 255, 0), 2)
# Display the image with bounding box
plt.imshow(image)
plt.show()
Isithombe silayishwa kusetshenziswa indlela ye-imread esuka ku-cv2, bese zidwetshwa ibhokisi elihlanganisayo kusetshenziswa umsebenzi we-cv2.rectangle othatha isithombe kanye nezixhumanisi ezimbili ezimelwe 'ibhokisi'. Amapharamitha amabili okugcina anombala nogqinsi ngokulandelana. Le khodi izokhombisa izinto ezisesithombeni sakho eziboshwe ngokuphelele ngebhokisi.
Ukusetshenziswa kwamabhokisi okubopha
Sengiphetha, amabhokisi ahlanganisayo adlala indima ebalulekile emisebenzini yokubona ikhompuyutha, okuhlanganisa ukutholwa kwezinto, ukubona kwekhompyutha, nokucubungula izithombe. Banikeza isixazululo esisebenzayo nesisebenzayo sokuthola izinto nolwazi lwemethadatha ngaphakathi kwezithombe. Ukufunda ukusebenzisa ngokunembile amabhokisi abophayo kuPython kungazuzisa kakhulu noma ngubani obambe iqhaza ekuthuthukisweni kwesoftware, ukufunda ngomshini, noma ubuhlakani be-AI emsebenzini. Akukona nje kuphela ukuthi luwusizo ekuvikelekeni nasekugadeni, kodwa futhi lusiza kakhulu ezinhlelweni zokusebenza ezifana nokutholwa kobuso nokubonwa, ukutholwa kwabahamba ngezinyawo, namasistimu okusiza abashayeli (ADAS) ezimotweni ezizishayelayo.
