def assign_detections_to_tracks(self, detections):
# A. no instances now: initial—>将detection的结果加入instances
# B. we have instances now: (prediction/track<—>detection matching)
# 1. predict/track—> kalman filter
# 2. 找到detection和prediction相互的匹配
# 2.a Munkres Algorithm
# det: b e f // b->b e->f f->f
# pre: a b c f // a->b b->b c->b f->f
# matched: b, f
# 2.b bi-matching: 以predict/track为基准，先匹配det；再由det为基准，匹配pre/track
# 3. 对于正确匹配的物体，进行更新：correction
# 4. 处理未正确匹配的物体
# 4.1 未检测到的物体：a.即时移除(不建议) b.继续更新(单纯pred/track，不考虑detection)
# c.长久未匹配，移除
# 4.2 检测到有新物体：a. 即时加入 b.加入track(试用期)，几帧后(通过适用期后)，加入instances
if len(self.instances) == 0:
for det in detections:
# det: 检测结果
# det: {'tag': [bbox_left, bbox_right, bbox_top, bbox_bottom]}
instance = Instance(self.config, self.video_helper)
tag = list(det.keys())[0]
bbox = det[tag]
# instance.add_to_track(tag, bbox) # 辅助
self.instances.append(instance)
# B.
# B.1
# 算距离：检测框与预测框之间的距离
# costs[i, j]: 每一个预测框与检测框之间的距离
costs = np.zeros(shape=(len(self.instances), len(detections)))
for i, instance in enumerate(self.instances):
# Here, by using Kalman Filter, we predict an bbx for each instance
predicted_bbx = instance.get_predicted_bbx()
for j, det in enumerate(detections):
detected_bbx = list(det.values())[0]
dist = util.dist_btwn_bbx_centroids(predicted_bbx,
detected_bbx)
max_dist = self.config.MAX_PIXELS_DIST_BETWEEN_PREDICTED_AND_DETECTED
if dist > max_dist:
dist = 1000 # sys.maxsize
costs[i, j] = dist
# set all tracked instances as unassigned
for instance in self.instances:
instance.has_match = False
# B.2
# 利用cost矩阵寻找匹配
# Munkres Algorithm
# Instructions and C# version can be found here: http://csclab.murraystate.edu/~bob.pilgrim/445/munkres.html
# while in Python we can solve the problem by using method imported as below.
# Descriptions for Python version can be found in
# https://docs.scipy.org/doc/scipy-0.18.1/reference/generated/scipy.optimize.linear_sum_assignment.html
assigned_instances, assigned_detections = linear_sum_assignment(costs)
# B.3
# 更新assigned bbox
assigned_detection_id = []
for idx, instance_id in enumerate(assigned_instances):
detection_id = assigned_detections[idx]
# if assignment for this instance and detection is sys.maxsize, discard it
if costs[instance_id, detection_id] != 1000: # sys.maxsize:
assigned_detection_id.append(detection_id)
self.instances[instance_id].has_match = True
self.instances[instance_id].correct_track(
detections[detection_id])
self.instances[instance_id].num_misses = 0
# B.4
# keep track of how many times a track has gone unassigned
for instance in self.instances:
if instance.has_match is False:
instance.num_misses += 1
# The function shown below can only remove those instances which has already been
# added to tracks but CAN NOT remove detected bbx which has a huge IOU with
# existed tracks. So we need another remove function to dual with that
self.remove_dead_instances()
# get unassigned detection ids
unassigned_detection_id = list(
set(range(0, len(detections))) - set(assigned_detection_id))
for idx in range(0, len(detections)):
if idx in unassigned_detection_id:
# det: {'tag' : [bbx_left, bbx_right, bbx_up, bbx_bottom]}
tag = list(detections[idx].keys())[0]
bbx = detections[idx][tag]
# then we need to confirm whether the detection is a good one
if self.is_good_detection(bbx):
instance = Instance(self.config, self.video_helper)
# instance.add_to_track(tag, bbx)
self.instances.append(instance)
def assign_detections_to_tracks(self, detections, frame_id, frame):
"""
This function aims to assign detections to their corresponding tracks by minimizing the cost matrix using
Munkres Algorithm.
Args:
param 1. detections: [{'tag1' : [bbx1]}, {'tag2' : [bbx2]}, ..., {'tagn' : [bbxn]}]
where bbx = [bbx_left, bbx_right, bbx_up, bbx_down]
param 2. frame_id: current frame ID starting from 0
"""
""" Step 0: got measurements (detections) """
""" Step 1: get predicted states """
# find distance from all tracked instances to all detected boxes
# if there are no instances, then all detections are new tracks
if (len(self.instances)) == 0:
for det in detections:
# det: {'tag' : [bbx_left, bbx_right, bbx_up, bbx_bottom]}
instance = Instance(self.config, self.video_helper, frame)
tag = list(det.keys())[0]
bbx = det[tag]
instance.add_to_track(tag, bbx, frame)
self.instances.append(instance)
return True
""" Step 2: assign detections to correspondiong instances """
# iou match between detected bboxes and tracked bboxes
track_det_iou, det_track_iou = {}, {}
for t, instance in enumerate(self.instances):
if not track_det_iou.__contains__(t):
track_det_iou[t] = [] # creat key
predicted_bbx = instance.get_predicted_bbx(
frame
) # Here, by using KCF, we predict an bbx for each instance
for d, det in enumerate(detections):
if not det_track_iou.__contains__(d):
det_track_iou[d] = []
detected_bbx = list(det.values())[0]
iou = util.get_iou(
predicted_bbx, detected_bbx
) # get IOU between all detected bboxes and tracked bboxes
track_det_iou[t].append([d, iou])
det_track_iou[d].append([t, iou])
# set all tracked instances as unassigned
for instance in self.instances:
instance.has_match = False
assigned_instances, assigned_detections = [], []
for i, id_iou in track_det_iou.items():
match_detid = util.get_maxiou_id(id_iou)
if match_detid != None:
match_trackid = util.get_maxiou_id(det_track_iou[match_detid])
if match_trackid == i: # match
assigned_instances.append(match_trackid)
assigned_detections.append(match_detid)
""" Step 3: correct an instance if it's matched by correponsding instance and detection """
assigned_detection_id = []
if assigned_instances != None and assigned_detections != None: # sys.maxsize:
for idx, instance_id in enumerate(assigned_instances):
detection_id = assigned_detections[idx]
# if assignment for this instance and detection is sys.maxsize, discard it
# record this detection is assigned
assigned_detection_id.append(detection_id)
# record this tracked instance which is assigned
self.instances[instance_id].has_match = True
# correct states by using kalman filter
self.instances[instance_id].correct_track(
detections[detection_id], frame)
# means this instance is detected
self.instances[instance_id].num_misses = 0
""" Step 4: remove instances which should be """
# keep track of how many times a track has gone unassigned
for instance in self.instances:
if instance.has_match is False:
instance.num_misses += 1
# The function shown below can only remove those instances which has already been
# added to tracks but CAN NOT remove detected bbx which has a huge IOU with
# existed tracks. So we need another remove function to dual with that
self.remove_dead_instances()
""" Step 5: create new instances to track if no detections are matched """
# get unassigned detection ids
unassigned_detection_id = list(
set(range(0, len(detections))) - set(assigned_detection_id))
for idx in range(0, len(detections)):
if idx in unassigned_detection_id:
# det: {'tag' : [bbx_left, bbx_right, bbx_up, bbx_bottom]}
tag = list(detections[idx].keys())[0]
bbx = detections[idx][tag]
# then we need to confirm whether the detection is a good one
if self.is_good_detection(bbx):
instance = Instance(self.config, self.video_helper, frame)
instance.add_to_track(tag, bbx, frame)
self.instances.append(instance)
