def SiamRPN_track(state, im):
p = state['p']
net = state['net']
avg_chans = state['avg_chans']
window = state['window']
target_pos = state['target_pos']
target_sz = state['target_sz']
wc_z = target_sz[1] + p.context_amount * sum(target_sz)
hc_z = target_sz[0] + p.context_amount * sum(target_sz)
s_z = np.sqrt(wc_z * hc_z)
scale_z = p.exemplar_size / s_z
d_search = (p.instance_size - p.exemplar_size) / 2
pad = d_search / scale_z
s_x = s_z + 2 * pad
# extract scaled crops for search region x at previous target position
x_crop = Variable(
get_subwindow_tracking(im, target_pos, p.instance_size, round(s_x),
avg_chans).unsqueeze(0))
target_pos, target_sz, score = tracker_eval(net, x_crop.cpu(), target_pos,
target_sz * scale_z, window,
scale_z, p)
target_pos[0] = max(0, min(state['im_w'], target_pos[0]))
target_pos[1] = max(0, min(state['im_h'], target_pos[1]))
target_sz[0] = max(10, min(state['im_w'], target_sz[0]))
target_sz[1] = max(10, min(state['im_h'], target_sz[1]))
state['target_pos'] = target_pos
state['target_sz'] = target_sz
state['score'] = score
return state
def SiamRPN_track(state, im):
# 接收网络参数
p = state['p']
net = state['net']
avg_chans = state['avg_chans']
window = state['window']
# 主要接收上一帧目标跟踪的位置以及尺寸
target_pos = state['target_pos']
target_sz = state['target_sz']
# 更新搜索区域，决定本帧的搜索区域（根据上一帧的检测结果来设置本帧搜索区域）
wc_z = target_sz[1] + p.context_amount * sum(target_sz)
hc_z = target_sz[0] + p.context_amount * sum(target_sz)
s_z = np.sqrt(wc_z * hc_z)
# 获取尺度变化率
scale_z = p.exemplar_size / s_z
# 调整搜索区域
d_search = (p.instance_size - p.exemplar_size) / 2
pad = d_search / scale_z
s_x = s_z + 2 * pad
# extract scaled crops for search region x at previous target position
x_crop = Variable(
get_subwindow_tracking(im, target_pos, p.instance_size, round(s_x),
avg_chans).unsqueeze(0))
# 获得本帧预测结果，target_pos-目标位置 target_sz-目标尺度 score-置信分数
# Ps: target_sz * scale_z表示本帧的搜索区域大小
if torch.cuda.is_available():
target_pos, target_sz, score = tracker_eval(net, x_crop.cuda(),
target_pos,
target_sz * scale_z,
window, scale_z, p)
else:
target_pos, target_sz, score = tracker_eval(net, x_crop, target_pos,
target_sz * scale_z,
window, scale_z, p)
target_pos[0] = max(0, min(state['im_w'], target_pos[0]))
target_pos[1] = max(0, min(state['im_h'], target_pos[1]))
target_sz[0] = max(10, min(state['im_w'], target_sz[0]))
target_sz[1] = max(10, min(state['im_h'], target_sz[1]))
state['target_pos'] = target_pos
state['target_sz'] = target_sz
state['score'] = score
return state
def SiamRPN_init(im, target_pos, target_sz, net):
state = dict()
p = TrackerConfig()
state['im_h'] = im.shape[0]
state['im_w'] = im.shape[1]
state['ctr'] = 1
if ((target_sz[0] * target_sz[1]) /
float(state['im_h'] * state['im_w'])) < 0.004:
p.instance_size = 287 # small object big search region
else:
p.instance_size = 271
p.score_size = int((p.instance_size - p.exemplar_size) / p.total_stride +
1)
p.anchor = generate_anchor(p.total_stride, p.scales, p.ratios,
p.score_size)
avg_chans = np.mean(im, axis=(0, 1))
wc_z = target_sz[0] + p.context_amount * sum(target_sz)
hc_z = target_sz[1] + p.context_amount * sum(target_sz)
s_z = round(np.sqrt(wc_z * hc_z))
# initialize the exemplar
z_crop = get_subwindow_tracking(im, target_pos, p.exemplar_size, s_z,
avg_chans)
z = Variable(z_crop.unsqueeze(0))
net.temple(z.cuda())
if p.windowing == 'cosine':
window = np.outer(np.hanning(p.score_size), np.hanning(p.score_size))
elif p.windowing == 'uniform':
window = np.ones((p.score_size, p.score_size))
window = np.tile(window.flatten(), p.anchor_num)
state['p'] = p
state['net'] = net
state['avg_chans'] = avg_chans
state['window'] = window
state['target_pos'] = target_pos
state['target_sz'] = target_sz
return state
def SiamRPN_init(im, target_pos, target_sz, net):
# 设置一个空的字典
state = dict()
# 设置跟踪器的相关参数
p = TrackerConfig()
# 将网络的参数加载至跟踪模型中
p.update(net.cfg)
# 将图像的尺寸加载至state中
state['im_h'] = im.shape[0]
state['im_w'] = im.shape[1]
if p.adaptive: # 初始化设置为True
if ((target_sz[0] * target_sz[1]) /
float(state['im_h'] * state['im_w'])) < 0.004:
p.instance_size = 287 # small object big search region
else:
p.instance_size = 271 # 用于设置instance_size，为score_size计算做准备
# 与TrackerConfig类中计算方式一致
p.score_size = (p.instance_size - p.exemplar_size) / p.total_stride + 1
# 生成候选框尺寸锚点
p.anchor = generate_anchor(p.total_stride, p.scales, p.ratios,
int(p.score_size))
# 计算图像均值
avg_chans = np.mean(im, axis=(0, 1))
# context_amount参数已经初始化，默认0.5，
wc_z = target_sz[0] + p.context_amount * sum(
target_sz) # target_sz是模板的横纵尺寸，通过sum函数加在一起
hc_z = target_sz[1] + p.context_amount * sum(target_sz)
# round取整数
s_z = round(np.sqrt(wc_z * hc_z))
# initialize the exemplar 初始化目标模板
z_crop = get_subwindow_tracking(im, target_pos, p.exemplar_size, s_z,
avg_chans)
# 数据降维
z = Variable(z_crop.unsqueeze(0))
# 将网络加载至GPU上运行
if torch.cuda.is_available():
net.temple(z.cuda())
else:
net.temple(z)
if p.windowing == 'cosine':
window = np.outer(np.hanning(p.score_size), np.hanning(p.score_size))
elif p.windowing == 'uniform':
window = np.ones((p.score_size, p.score_size))
window = np.tile(window.flatten(), p.anchor_num)
# 将所有的参数写入字典中，进行保存
state['p'] = p
state['net'] = net
state['avg_chans'] = avg_chans
state['window'] = window
state['target_pos'] = target_pos
state['target_sz'] = target_sz
# 返回网络的初始化设置 以字典形式返回
return state
