darknetのyolov3で検出した座標からpythonで計算を行いたい。

前提・実現したいこと

jupyterでdarknetのyolov3を実装し、webカメラでとった2枚のステレオ画像を読み込ませて、物体検知を行い、その検知できた中の人物のみのx座標を、取得して計算を行いたいと考えています。現在は、darknet.pyの内容を書き換えて、ターミナルからpython ./python/darknet.pyで動かして２つの画像共に物体検知、中心座標ともに検出結果が出るまでには行けたのですが、そこからx座標のみを取得して計算をすることがうまく出来ずにいます。プログラミング初心者のため何をすれば良いかわかりません。そのため、こちらのサイトに質問させていただきました。以下のコードで何かおかしな点があればご指摘いただきたく存じます。

エラーメッセージ

class_name= person
confidence= 0.9979870915412903
box1= (757.0997924804688, 574.14208984375, 382.11517333984375, 989.4730224609375)
class_name= chair
confidence= 0.939139187335968
box1= (456.80657958984375, 973.4913330078125, 297.5714111328125, 218.9896697998047)
class_name= diningtable
confidence= 0.867287278175354
box1= (150.55377197265625, 963.4379272460938, 279.58843994140625, 256.3335876464844)
class_name= person
confidence= 0.9986228346824646
box2= (789.9702758789062, 566.0933227539062, 352.4512939453125, 985.2094116210938)
class_name= chair
confidence= 0.9849683046340942
box2= (459.69384765625, 976.21435546875, 317.9201965332031, 218.52052307128906)
class_name= tvmonitor
confidence= 0.8856194019317627
box2= (145.66439819335938, 574.79736328125, 228.37103271484375, 259.6019592285156)
class_name= diningtable
confidence= 0.8115013837814331
box2= (172.94419860839844, 939.2078857421875, 342.9265441894531, 264.38812255859375)
Traceback (most recent call last):
  File "./python/darknet.py", line 181, in <module>
    D = x1 - x2
NameError: name 'x1' is not defined


### 該当のソースコード

from ctypes import *
import math
import random
import numpy as np

def sample(probs):
    s = sum(probs)
    probs = [a/s for a in probs]
    r = random.uniform(0, 1)
    for i in range(len(probs)):
        r = r - probs[i]
        if r <= 0:
            return i
    return len(probs)-1

def c_array(ctype, values):
    arr = (ctype*len(values))()
    arr[:] = values
    return arr

class BOX(Structure):
    _fields_ = [("x", c_float),
                ("y", c_float),
                ("w", c_float),
                ("h", c_float)]

class DETECTION(Structure):
    _fields_ = [("bbox", BOX),
                ("classes", c_int),
                ("prob", POINTER(c_float)),
                ("mask", POINTER(c_float)),
                ("objectness", c_float),
                ("sort_class", c_int)]


class IMAGE(Structure):
    _fields_ = [("w", c_int),
                ("h", c_int),
                ("c", c_int),
                ("data", POINTER(c_float))]

class METADATA(Structure):
    _fields_ = [("classes", c_int),
                ("names", POINTER(c_char_p))]

    

#lib = CDLL("/home/pjreddie/documents/darknet/libdarknet.so", RTLD_GLOBAL)
lib = CDLL("libdarknet.so", RTLD_GLOBAL)
lib.network_width.argtypes = [c_void_p]
lib.network_width.restype = c_int
lib.network_height.argtypes = [c_void_p]
lib.network_height.restype = c_int

predict = lib.network_predict
predict.argtypes = [c_void_p, POINTER(c_float)]
predict.restype = POINTER(c_float)

set_gpu = lib.cuda_set_device
set_gpu.argtypes = [c_int]

make_image = lib.make_image
make_image.argtypes = [c_int, c_int, c_int]
make_image.restype = IMAGE

get_network_boxes = lib.get_network_boxes
get_network_boxes.argtypes = [c_void_p, c_int, c_int, c_float, c_float, POINTER(c_int), c_int, POINTER(c_int)]
get_network_boxes.restype = POINTER(DETECTION)

make_network_boxes = lib.make_network_boxes
make_network_boxes.argtypes = [c_void_p]
make_network_boxes.restype = POINTER(DETECTION)

free_detections = lib.free_detections
free_detections.argtypes = [POINTER(DETECTION), c_int]

free_ptrs = lib.free_ptrs
free_ptrs.argtypes = [POINTER(c_void_p), c_int]

network_predict = lib.network_predict
network_predict.argtypes = [c_void_p, POINTER(c_float)]

reset_rnn = lib.reset_rnn
reset_rnn.argtypes = [c_void_p]

load_net = lib.load_network
load_net.argtypes = [c_char_p, c_char_p, c_int]
load_net.restype = c_void_p

do_nms_obj = lib.do_nms_obj
do_nms_obj.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]

do_nms_sort = lib.do_nms_sort
do_nms_sort.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]

free_image = lib.free_image
free_image.argtypes = [IMAGE]

letterbox_image = lib.letterbox_image
letterbox_image.argtypes = [IMAGE, c_int, c_int]
letterbox_image.restype = IMAGE

load_meta = lib.get_metadata
lib.get_metadata.argtypes = [c_char_p]
lib.get_metadata.restype = METADATA

load_image = lib.load_image_color
load_image.argtypes = [c_char_p, c_int, c_int]
load_image.restype = IMAGE

rgbgr_image = lib.rgbgr_image
rgbgr_image.argtypes = [IMAGE]

predict_image = lib.network_predict_image
predict_image.argtypes = [c_void_p, IMAGE]
predict_image.restype = POINTER(c_float)

def classify(net, meta, im):
    out = predict_image(net, im)
    res = []
    for i in range(meta.classes):
        res.append((meta.names[i], out[i]))
    res = sorted(res, key=lambda x: -x[1])
    return res

def detect(net, meta, image, thresh=.5, hier_thresh=.5, nms=.45):
    im = load_image(image, 0, 0)
    num = c_int(0)
    pnum = pointer(num)
    predict_image(net, im)
    dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, None, 0, pnum)
    num = pnum[0]
    if (nms): do_nms_obj(dets, num, meta.classes, nms);

    res = []
    for j in range(num):
        for i in range(meta.classes):
            if dets[j].prob[i] > 0:
                b = dets[j].bbox
                res.append((meta.names[i], dets[j].prob[i], (b.x, b.y, b.w, b.h)))
    res = sorted(res, key=lambda x: -x[1])
    free_image(im)
    free_detections(dets, num)
    return res
    
if __name__ == "__main__":
    net = load_net("cfg/yolov3.cfg".encode('ascii'),"yolov3.weights".encode('ascii'), 0)
    meta = load_meta("cfg/coco.data".encode('ascii'))
    r1 = detect(net, meta, "path1.jpg".encode('ascii'))
    r2 = detect(net, meta, "path2.jpg".encode('ascii'))
    kekka1 = np.empty((10,3))
    kekka2 = np.empty((10,3))
    for kekka1 in r1:
        print('class_name=', kekka1[0].decode('ascii'))
        print('confidence=', kekka1[1])    
        print('box1=', kekka1[2])  
        
    if kekka1[0].decode('ascii') == "person":
        kekka1[2] = bbox1(0, 1, 2, 3)
        x1 = bbox1(0)
        y1 = bbox1(0)
        
    for kekka2 in r2:
        print('class_name=', kekka2[0].decode('ascii'))
        print('confidence=', kekka2[1])    
        print('box2=', kekka2[2]) 
        
    if kekka1[0].decode('ascii') == "person":
        kekka1[2] = bbox1(0, 1, 2, 3)
        x1 = bbox1(0)
        y1 = bbox1(0)

    if kekka2[0].decode('ascii') == "person":
        kekka2[2] = bbox2(0, 1, 2, 3)
        x2 = bbox2(0)
        y2 = bbox2(0)
        
    F = 123.7
    T = 0.16
    
    D = x1 - x2
    z = F*T/D
    
    print(z)

pythonで実装しています。