摘要:一般調(diào)高飽和度會(huì)降低中相對(duì)較低的數(shù)值,凸顯主要顏色的純度。對(duì)當(dāng)前唯一的方法霍夫梯度法,它表示在檢測(cè)階段圓心的累加器閾值。第八個(gè)參數(shù),類型的有默認(rèn)值,表示圓半徑的最小值。
目錄
?
?
?
為什么用HSV空間而不是RGB空間?
因?yàn)?strong>RGB通道并不能很好地反映出物體具體的顏色信息。
而HSV空間能夠非常直觀的表達(dá)色彩的明暗、色調(diào)、以及鮮艷程度,方便進(jìn)行顏色之間的對(duì)比。
(RGB受光線影響很大,所以采取HSV)
這里用HSV的目的:得到合適的二值圖。
Hue(H):色調(diào)、色相(具體的顏色)
Saturation(S):飽和度、色彩純凈度
Value(V):明度
Hue范圍是[0,179],飽和范圍是[0,255],值范圍是[0,255]
(寫(xiě)代碼的時(shí)候,犯了蠢錯(cuò)誤:把3個(gè)都設(shè)成了179,發(fā)現(xiàn)死活調(diào)不對(duì))
Hue:色相(具體的顏色)
明度:色彩的明亮程度,單通道亮度(并不等同于整體發(fā)光量)。
(明度越高越白,越低越黑,一般提高明度會(huì)同時(shí)提高R、G、B三通道的數(shù)值)
Saturation:飽和度、色彩純度(越低越灰,越高越純)??。
(一般調(diào)高飽和度會(huì)降低RGB中相對(duì)較低的數(shù)值,凸顯主要顏色的純度。 )
B站視頻講解:
短動(dòng)畫(huà)慢語(yǔ)速1分鐘講清影視調(diào)色中色彩形成原理基礎(chǔ)——RGB與HSV
這次的初始化,除了電機(jī)、舵機(jī)、窗口等等的初始化,還有滑動(dòng)條的初始設(shè)置。?
在創(chuàng)建滑動(dòng)條之前:
1、需要設(shè)置窗口名稱,不然窗口都沒(méi)有,自然也就無(wú)法設(shè)置滑動(dòng)條了。
2、創(chuàng)建回調(diào)函數(shù)。
def nothing(*arg): pass
def Trackbar_Init(): # 1 create windows cv2.namedWindow("h_binary") cv2.namedWindow("s_binary") cv2.namedWindow("v_binary")
# 2 Create Trackbar cv2.createTrackbar("hmin", "h_binary", 6, 179, nothing) cv2.createTrackbar("hmax", "h_binary", 26, 179, nothing) cv2.createTrackbar("smin", "s_binary", 110, 255, nothing) cv2.createTrackbar("smax", "s_binary", 255, 255, nothing) cv2.createTrackbar("vmin", "v_binary", 140, 255, nothing) cv2.createTrackbar("vmax", "v_binary", 255, 255, nothing) # 創(chuàng)建滑動(dòng)條 滑動(dòng)條值名稱 窗口名稱 滑動(dòng)條值 滑動(dòng)條閾值 回調(diào)函數(shù)
def Motor_Init(): global L_Motor, R_Motor L_Motor= GPIO.PWM(l_motor,100) R_Motor = GPIO.PWM(r_motor,100) L_Motor.start(0) R_Motor.start(0)def Direction_Init(): GPIO.setup(left_back,GPIO.OUT) GPIO.setup(left_front,GPIO.OUT) GPIO.setup(l_motor,GPIO.OUT) GPIO.setup(right_front,GPIO.OUT) GPIO.setup(right_back,GPIO.OUT) GPIO.setup(r_motor,GPIO.OUT)def Servo_Init(): global pwm_servo pwm_servo=Adafruit_PCA9685.PCA9685()def Trackbar_Init(): # 1 create windows cv2.namedWindow("h_binary") cv2.namedWindow("s_binary") cv2.namedWindow("v_binary") # 2 Create Trackbar cv2.createTrackbar("hmin", "h_binary", 6, 179, nothing) cv2.createTrackbar("hmax", "h_binary", 26, 179, nothing) cv2.createTrackbar("smin", "s_binary", 110, 255, nothing) cv2.createTrackbar("smax", "s_binary", 255, 255, nothing) cv2.createTrackbar("vmin", "v_binary", 140, 255, nothing) cv2.createTrackbar("vmax", "v_binary", 255, 255, nothing) # 創(chuàng)建滑動(dòng)條 滑動(dòng)條值名稱 窗口名稱 滑動(dòng)條值 滑動(dòng)條閾值 回調(diào)函數(shù)def Init(): GPIO.setwarnings(False) GPIO.setmode(GPIO.BCM) Direction_Init() Servo_Init() Motor_Init() Trackbar_Init()# 回調(diào)函數(shù)def nothing(*arg): pass
常規(guī)操作:向前、向后、向左、向右、停止。?
def Front(speed): L_Motor.ChangeDutyCycle(speed) GPIO.output(left_front,1) #left_front GPIO.output(left_back,0) #left_back R_Motor.ChangeDutyCycle(speed) GPIO.output(right_front,1) #right_front GPIO.output(right_back,0) #right_back def Back(speed): L_Motor.ChangeDutyCycle(speed) GPIO.output(left_front,0) #left_front GPIO.output(left_back,1) #left_back R_Motor.ChangeDutyCycle(speed) GPIO.output(right_front,0) #right_front GPIO.output(right_back,1) #right_backdef Left(speed): L_Motor.ChangeDutyCycle(speed) GPIO.output(left_front,0) #left_front GPIO.output(left_back,1) #left_back R_Motor.ChangeDutyCycle(speed) GPIO.output(right_front,1) #right_front GPIO.output(right_back,0) #right_backdef Right(speed): L_Motor.ChangeDutyCycle(speed) GPIO.output(left_front,1) #left_front GPIO.output(left_back,0) #left_back R_Motor.ChangeDutyCycle(speed) GPIO.output(right_front,0) #right_front GPIO.output(right_back,1) #right_backdef Stop(): L_Motor.ChangeDutyCycle(0) GPIO.output(left_front,0) #left_front GPIO.output(left_back,0) #left_back R_Motor.ChangeDutyCycle(0) GPIO.output(right_front,0) #right_front GPIO.output(right_back,0) #right_back
def set_servo_angle(channel,angle): angle=4096*((angle*11)+500)/20000 pwm_servo.set_pwm_freq(50) #frequency==50Hz (servo) pwm_servo.set_pwm(channel,0,int(angle))
set_servo_angle(4, 110) #top servo lengthwise #0:back 180:front set_servo_angle(5, 90) #bottom servo crosswise #0:left 180:right
# 1 get trackbar"s value hmin = cv2.getTrackbarPos("hmin", "h_binary") hmax = cv2.getTrackbarPos("hmax", "h_binary") smin = cv2.getTrackbarPos("smin", "s_binary") smax = cv2.getTrackbarPos("smax", "s_binary") vmin = cv2.getTrackbarPos("vmin", "v_binary") vmax = cv2.getTrackbarPos("vmax", "v_binary")
# 2 to HSV hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV) cv2.imshow("hsv", hsv) h, s, v = cv2.split(hsv)
?
分別對(duì)H、S、V三個(gè)道閾值處理:
# 3 set threshold (binary image) # if value in (min, max):white; otherwise:black h_binary = cv2.inRange(np.array(h), np.array(hmin), np.array(hmax)) s_binary = cv2.inRange(np.array(s), np.array(smin), np.array(smax)) v_binary = cv2.inRange(np.array(v), np.array(vmin), np.array(vmax))# 5 Show cv2.imshow("h_binary", h_binary) cv2.imshow("s_binary", s_binary) cv2.imshow("v_binary", v_binary)
對(duì)H、S、V三個(gè)通道與操作。(H&&S&&V)
# 4 get binary binary = cv2.bitwise_and(h_binary, cv2.bitwise_and(s_binary, v_binary))
# 在HSV色彩空間下得到二值圖def Get_HSV(image): # 1 get trackbar"s value hmin = cv2.getTrackbarPos("hmin", "h_binary") hmax = cv2.getTrackbarPos("hmax", "h_binary") smin = cv2.getTrackbarPos("smin", "s_binary") smax = cv2.getTrackbarPos("smax", "s_binary") vmin = cv2.getTrackbarPos("vmin", "v_binary") vmax = cv2.getTrackbarPos("vmax", "v_binary") # 2 to HSV hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV) cv2.imshow("hsv", hsv) h, s, v = cv2.split(hsv) # 3 set threshold (binary image) # if value in (min, max):white; otherwise:black h_binary = cv2.inRange(np.array(h), np.array(hmin), np.array(hmax)) s_binary = cv2.inRange(np.array(s), np.array(smin), np.array(smax)) v_binary = cv2.inRange(np.array(v), np.array(vmin), np.array(vmax)) # 4 get binary(對(duì)H、S、V三個(gè)通道分別與操作) binary = cv2.bitwise_and(h_binary, cv2.bitwise_and(s_binary, v_binary)) # 5 Show cv2.imshow("h_binary", h_binary) cv2.imshow("s_binary", s_binary) cv2.imshow("v_binary", v_binary) cv2.imshow("binary", binary) return binary
# 1 Capture the frames ret, frame = camera.read() image = frame cv2.imshow("frame", frame)
(Get_HSV(frame)其實(shí)就是步驟四的HSV處理)
# 2 get HSV binary = Get_HSV(frame)
# 3 Gausi blur blur = cv2.GaussianBlur(binary,(9,9),0)
# 4 Open kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9,9)) Open = cv2.morphologyEx(blur, cv2.MORPH_OPEN, kernel) cv2.imshow("Open",Open)
# 5 Close Close = cv2.morphologyEx(Open, cv2.MORPH_CLOSE, kernel) cv2.imshow("Close",Close)
?
霍夫變換圓檢測(cè)是基于圖像梯度實(shí)現(xiàn):
圓心檢測(cè)的原理︰圓心是圓周法線的交匯處,設(shè)置一個(gè)閾值,在某點(diǎn)的相交的直線的條數(shù)大于這個(gè)閾值就認(rèn)為該交匯點(diǎn)為圓心。
圓半徑確定原理:圓心到圓周上的距離〔半徑)是相同的,設(shè)置一個(gè)閾值,只要相同距離的數(shù)量大于該閾值,就認(rèn)為該距離是該圓心的半徑。
API
def HoughCircles(image: Any, method: Any, dp: Any, minDist: Any, circles: Any = None, param1: Any = None, param2: Any = None, minRadius: Any = None, maxRadius: Any = None) -> None
參數(shù):?
- 第二個(gè)參數(shù),int類型的method,即使用的檢測(cè)方法,目前OpenCV中就霍夫梯度法一種可以使用,它的標(biāo)識(shí)符為CV_HOUGH_GRADIENT,在此參數(shù)處填這個(gè)標(biāo)識(shí)符即可。
- 第三個(gè)參數(shù),double類型的dp,用來(lái)檢測(cè)圓心的累加器圖像的分辨率于輸入圖像之比的倒數(shù),且此參數(shù)允許創(chuàng)建一個(gè)比輸入圖像分辨率低的累加器。上述文字不好理解的話,來(lái)看例子吧。例如,如果dp= 1時(shí),累加器和輸入圖像具有相同的分辨率。如果dp=2,累加器便有輸入圖像一半那么大的寬度和高度。
- 第四個(gè)參數(shù),double類型的minDist,為霍夫變換檢測(cè)到的圓的圓心之間的最小距離,即讓我們的算法能明顯區(qū)分的兩個(gè)不同圓之間的最小距離。這個(gè)參數(shù)如果太小的話,多個(gè)相鄰的圓可能被錯(cuò)誤地檢測(cè)成了一個(gè)重合的圓。反之,這個(gè)參數(shù)設(shè)置太大的話,某些圓就不能被檢測(cè)出來(lái)了。
- 第五個(gè)參數(shù),InputArray類型的circles,經(jīng)過(guò)調(diào)用HoughCircles函數(shù)后此參數(shù)存儲(chǔ)了檢測(cè)到的圓的輸出矢量,每個(gè)矢量由包含了3個(gè)元素的浮點(diǎn)矢量(x, y, radius)表示。
- 第六個(gè)參數(shù),double類型的param1,有默認(rèn)值100。它是第三個(gè)參數(shù)method設(shè)置的檢測(cè)方法的對(duì)應(yīng)的參數(shù)。對(duì)當(dāng)前唯一的方法霍夫梯度法CV_HOUGH_GRADIENT,它表示傳遞給canny邊緣檢測(cè)算子的高閾值,而低閾值為高閾值的一半。
- 第七個(gè)參數(shù),double類型的param2,也有默認(rèn)值100。它是第三個(gè)參數(shù)method設(shè)置的檢測(cè)方法的對(duì)應(yīng)的參數(shù)。對(duì)當(dāng)前唯一的方法霍夫梯度法CV_HOUGH_GRADIENT,它表示在檢測(cè)階段圓心的累加器閾值。它越小的話,就可以檢測(cè)到更多根本不存在的圓,而它越大的話,能通過(guò)檢測(cè)的圓就更加接近完美的圓形了。
- 第八個(gè)參數(shù),int類型的minRadius,有默認(rèn)值0,表示圓半徑的最小值。
- 第九個(gè)參數(shù),int類型的maxRadius,也有默認(rèn)值0,表示圓半徑的最大值。
# 6 Hough Circle detect circles = cv2.HoughCircles(Close,cv2.HOUGH_GRADIENT,2,120,param1=120,param2=20,minRadius=20,maxRadius=0) # param2:決定圓能否被檢測(cè)到(越少越容易檢測(cè)到圓,但相應(yīng)的也更容易出錯(cuò))
# 1 獲取圓的圓心和半徑 x, y, r = int(circles[0][0][0]),int(circles[0][0][1]),int(circles[0][0][2]) print(x, y, r)
# 2 畫(huà)圓 cv2.circle(image, (x, y), r, (255,0,255),5) cv2.imshow("image", image)
# 圖像處理def Image_Processing(): global h, s, v # 1 Capture the frames ret, frame = camera.read() image = frame cv2.imshow("frame", frame) # 2 get HSV binary = Get_HSV(frame) # 3 Gausi blur blur = cv2.GaussianBlur(binary,(9,9),0) # 4 Open kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9,9)) Open = cv2.morphologyEx(blur, cv2.MORPH_OPEN, kernel) cv2.imshow("Open",Open) # 5 Close Close = cv2.morphologyEx(Open, cv2.MORPH_CLOSE, kernel) cv2.imshow("Close",Close) # 6 Hough Circle detect circles = cv2.HoughCircles(Close,cv2.HOUGH_GRADIENT,2,120,param1=120,param2=20,minRadius=20,maxRadius=0) # param2:決定圓能否被檢測(cè)到(越少越容易檢測(cè)到圓,但相應(yīng)的也更容易出錯(cuò)) # judge if circles is exist if circles is not None: # 1 獲取圓的圓心和半徑 x, y, r = int(circles[0][0][0]),int(circles[0][0][1]),int(circles[0][0][2]) print(x, y, r) # 2 畫(huà)圓 cv2.circle(image, (x, y), r, (255,0,255),5) cv2.imshow("image", image) else: (x,y),r = (0,0), 0 return (x,y), r
根據(jù)檢測(cè)到的圓,獲取到的坐標(biāo)、半徑,進(jìn)行運(yùn)動(dòng)控制。
這里可以做到跟蹤小球,前進(jìn)和后退相配合,“敵進(jìn)我退,敵退我進(jìn)”。
# 運(yùn)動(dòng)控制(這里可以做到跟蹤小球,前景和后退相配合,“敵進(jìn)我退,敵退我進(jìn)”)def Move((x,y), r): low_xlimit = width/4 high_xlimit = 0.75 * width #low_ylimit = 3/4 * height ylimit = 0.75 * height print(high_xlimit, ylimit) # 沒(méi)檢測(cè)到,停止不動(dòng) if x==0: Stop() # 檢測(cè)到在圖片0.75以上的區(qū)域(距離正常) elif x>low_xlimit and xlow_xlimit and x=ylimit: Back(60) # 在左0.25區(qū)域,向左跟蹤 elif xhigh_xlimit: Right(60)
#Ball Tracking(HSV)import RPi.GPIO as GPIOimport timeimport Adafruit_PCA9685import numpy as npimport cv2#set capture windowwidth, height = 320, 240camera = cv2.VideoCapture(0)camera.set(3,width) camera.set(4,height) l_motor = 18left_front = 22left_back = 27r_motor = 23right_front = 25right_back = 24def Motor_Init(): global L_Motor, R_Motor L_Motor= GPIO.PWM(l_motor,100) R_Motor = GPIO.PWM(r_motor,100) L_Motor.start(0) R_Motor.start(0)def Direction_Init(): GPIO.setup(left_back,GPIO.OUT) GPIO.setup(left_front,GPIO.OUT) GPIO.setup(l_motor,GPIO.OUT) GPIO.setup(right_front,GPIO.OUT) GPIO.setup(right_back,GPIO.OUT) GPIO.setup(r_motor,GPIO.OUT)def Servo_Init(): global pwm_servo pwm_servo=Adafruit_PCA9685.PCA9685()def Trackbar_Init(): # 1 create windows cv2.namedWindow("h_binary") cv2.namedWindow("s_binary") cv2.namedWindow("v_binary") # 2 Create Trackbar cv2.createTrackbar("hmin", "h_binary", 6, 179, nothing) cv2.createTrackbar("hmax", "h_binary", 26, 179, nothing) cv2.createTrackbar("smin", "s_binary", 110, 255, nothing) cv2.createTrackbar("smax", "s_binary", 255, 255, nothing) cv2.createTrackbar("vmin", "v_binary", 140, 255, nothing) cv2.createTrackbar("vmax", "v_binary", 255, 255, nothing) # 創(chuàng)建滑動(dòng)條 滑動(dòng)條值名稱 窗口名稱 滑動(dòng)條值 滑動(dòng)條閾值 回調(diào)函數(shù)def Init(): GPIO.setwarnings(False) GPIO.setmode(GPIO.BCM) Direction_Init() Servo_Init() Motor_Init() Trackbar_Init()def Front(speed): L_Motor.ChangeDutyCycle(speed) GPIO.output(left_front,1) #left_front GPIO.output(left_back,0) #left_back R_Motor.ChangeDutyCycle(speed) GPIO.output(right_front,1) #right_front GPIO.output(right_back,0) #right_back def Back(speed): L_Motor.ChangeDutyCycle(speed) GPIO.output(left_front,0) #left_front GPIO.output(left_back,1) #left_back R_Motor.ChangeDutyCycle(speed) GPIO.output(right_front,0) #right_front GPIO.output(right_back,1) #right_backdef Left(speed): L_Motor.ChangeDutyCycle(speed) GPIO.output(left_front,0) #left_front GPIO.output(left_back,1) #left_back R_Motor.ChangeDutyCycle(speed) GPIO.output(right_front,1) #right_front GPIO.output(right_back,0) #right_backdef Right(speed): L_Motor.ChangeDutyCycle(speed) GPIO.output(left_front,1) #left_front GPIO.output(left_back,0) #left_back R_Motor.ChangeDutyCycle(speed) GPIO.output(right_front,0) #right_front GPIO.output(right_back,1) #right_backdef Stop(): L_Motor.ChangeDutyCycle(0) GPIO.output(left_front,0) #left_front GPIO.output(left_back,0) #left_back R_Motor.ChangeDutyCycle(0) GPIO.output(right_front,0) #right_front GPIO.output(right_back,0) #right_backdef set_servo_angle(channel,angle): angle=4096*((angle*11)+500)/20000 pwm_servo.set_pwm_freq(50) #frequency==50Hz (servo) pwm_servo.set_pwm(channel,0,int(angle))# 回調(diào)函數(shù)def nothing(*arg): pass# 在HSV色彩空間下得到二值圖def Get_HSV(image): # 1 get trackbar"s value hmin = cv2.getTrackbarPos("hmin", "h_binary") hmax = cv2.getTrackbarPos("hmax", "h_binary") smin = cv2.getTrackbarPos("smin", "s_binary") smax = cv2.getTrackbarPos("smax", "s_binary") vmin = cv2.getTrackbarPos("vmin", "v_binary") vmax = cv2.getTrackbarPos("vmax", "v_binary") # 2 to HSV hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV) cv2.imshow("hsv", hsv) h, s, v = cv2.split(hsv) # 3 set threshold (binary image) # if value in (min, max):white; otherwise:black h_binary = cv2.inRange(np.array(h), np.array(hmin), np.array(hmax)) s_binary = cv2.inRange(np.array(s), np.array(smin), np.array(smax)) v_binary = cv2.inRange(np.array(v), np.array(vmin), np.array(vmax)) # 4 get binary(對(duì)H、S、V三個(gè)通道分別與操作) binary = cv2.bitwise_and(h_binary, cv2.bitwise_and(s_binary, v_binary)) # 5 Show cv2.imshow("h_binary", h_binary) cv2.imshow("s_binary", s_binary) cv2.imshow("v_binary", v_binary) cv2.imshow("binary", binary) return binary# 圖像處理def Image_Processing(): global h, s, v # 1 Capture the frames ret, frame = camera.read() image = frame cv2.imshow("frame", frame) # 2 get HSV binary = Get_HSV(frame) # 3 Gausi blur blur = cv2.GaussianBlur(binary,(9,9),0) # 4 Open kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9,9)) Open = cv2.morphologyEx(blur, cv2.MORPH_OPEN, kernel) cv2.imshow("Open",Open) # 5 Close Close = cv2.morphologyEx(Open, cv2.MORPH_CLOSE, kernel) cv2.imshow("Close",Close) # 6 Hough Circle detect circles = cv2.HoughCircles(Close,cv2.HOUGH_GRADIENT,2,120,param1=120,param2=20,minRadius=20,maxRadius=0) # param2:決定圓能否被檢測(cè)到(越少越容易檢測(cè)到圓,但相應(yīng)的也更容易出錯(cuò)) # judge if circles is exist if circles is not None: # 1 獲取圓的圓心和半徑 x, y, r = int(circles[0][0][0]),int(circles[0][0][1]),int(circles[0][0][2]) print(x, y, r) # 2 畫(huà)圓 cv2.circle(image, (x, y), r, (255,0,255),5) cv2.imshow("image", image) else: (x,y),r = (0,0), 0 return (x,y), r# 運(yùn)動(dòng)控制(這里可以做到跟蹤小球,前景和后退相配合,“敵進(jìn)我退,敵退我進(jìn)”)def Move((x,y), r): low_xlimit = width/4 high_xlimit = 0.75 * width #low_ylimit = 3/4 * height ylimit = 0.75 * height print(high_xlimit, ylimit) # 沒(méi)檢測(cè)到,停止不動(dòng) if x==0: Stop() # 檢測(cè)到在圖片0.75以上的區(qū)域(距離正常) elif x>low_xlimit and xlow_xlimit and x=ylimit: Back(60) # 在左0.25區(qū)域,向左跟蹤 elif xhigh_xlimit: Right(60) if __name__ == "__main__": Init() set_servo_angle(4, 110) #top servo lengthwise #0:back 180:front set_servo_angle(5, 90) #bottom servo crosswise #0:left 180:right while 1: # 1 Image Process (x,y), r = Image_Processing() # 2 Move Move((x,y), r) # must include this codes(otherwise you can"t open camera successfully) if cv2.waitKey(1) & 0xFF == ord("q"): Stop() GPIO.cleanup() break
這里的HSV是根據(jù)我自己當(dāng)前的情況調(diào)節(jié)的,更改場(chǎng)景以后可能需要重新調(diào)節(jié)H、S、V三通道的閾值(max && min)
基礎(chǔ)的視覺(jué)檢測(cè)+運(yùn)動(dòng),沒(méi)有太多的運(yùn)動(dòng)控制算法(PID等等都沒(méi)有涉及到)。有好的想法和建議歡迎交流討論,Thanks?(?ω?)?
文章版權(quán)歸作者所有,未經(jīng)允許請(qǐng)勿轉(zhuǎn)載,若此文章存在違規(guī)行為,您可以聯(lián)系管理員刪除。
轉(zhuǎn)載請(qǐng)注明本文地址:http://specialneedsforspecialkids.com/yun/119986.html
摘要:在我已經(jīng)制作完成一輛可以運(yùn)行的遙控車(chē)時(shí),公司發(fā)布了一個(gè)自駕車(chē)項(xiàng)目,來(lái)展示自動(dòng)駕駛汽車(chē)的工作原理。需要注意的是,這里用的都是語(yǔ)言而非,其主要原因有兩個(gè)一方面,近來(lái)似乎已成為運(yùn)用機(jī)器學(xué)習(xí)技術(shù)時(shí)實(shí)際使用的語(yǔ)言。 最近,Mapbox 的 Android 工程師 Antonio 使用計(jì)算機(jī)視覺(jué)和機(jī)器學(xué)習(xí)技術(shù),為他的女兒 Violeta 重新制作了一臺(tái)遙控車(chē)。接下來(lái)我們看看 Antonio 是如何...
閱讀 3289·2023-04-26 02:40
閱讀 4638·2021-09-22 15:22
閱讀 1573·2021-09-22 10:02
閱讀 3474·2021-08-11 10:23
閱讀 1387·2019-08-30 15:55
閱讀 2487·2019-08-30 12:48
閱讀 584·2019-08-30 11:04
閱讀 696·2019-08-29 16:29