基于yolov8实现目标检测功能，结合sort算法赋予id，实现电力目标锁定功能。
部分代码如下：
# aidlux相关
from cvs import *
import aidlite_gpu
from utils import detect_postprocess, preprocess_img, draw_detect_res, scale_boxes
import time
import cv2
import os
import numpy as np
import glob
import argparse
from filterpy.kalman import KalmanFilter
np.random.seed(0)
def linear_assignment(cost_matrix):
try:
import lap
_, x, y = lap.lapjv(cost_matrix, extend_cost=True)
return np.array([[y[i],i] for i in x if i >= 0]) #
except ImportError:
from scipy.optimize import linear_sum_assignment
x, y = linear_sum_assignment(cost_matrix)
return np.array(list(zip(x, y)))
def iou_batch(bb_test, bb_gt):
"""
From SORT: Computes IOU between two bboxes in the form [x1,y1,x2,y2]
"""
bb_gt = np.expand_dims(bb_gt, 0)
bb_test = np.expand_dims(bb_test, 1)
xx1 = np.maximum(bb_test[..., 0], bb_gt[..., 0])
yy1 = np.maximum(bb_test[..., 1], bb_gt[..., 1])
xx2 = np.minimum(bb_test[..., 2], bb_gt[..., 2])
yy2 = np.minimum(bb_test[..., 3], bb_gt[..., 3])
w = np.maximum(0., xx2 - xx1)
h = np.maximum(0., yy2 - yy1)
wh = w * h
o = wh / ((bb_test[..., 2] - bb_test[..., 0]) * (bb_test[..., 3] - bb_test[..., 1])
+ (bb_gt[..., 2] - bb_gt[..., 0]) * (bb_gt[..., 3] - bb_gt[..., 1]) - wh)
return(o)
def convert_bbox_to_z(bbox):
"""
Takes a bounding box in the form [x1,y1,x2,y2] and returns z in the form
[x,y,s,r] where x,y is the centre of the box and s is the scale/area and r is
the aspect ratio
"""
w = bbox[2] - bbox[0]
h = bbox[3] - bbox[1]
x = bbox[0] + w/2.
y = bbox[1] + h/2.
s = w * h #scale is just area
r = w / float(h)
return np.array([x, y, s, r]).reshape((4, 1))
def convert_x_to_bbox(x, score=None):
"""
Takes a bounding box in the centre form [x, y, s, r] and returns it in the form
[x1,y1,x2,y2] where x1, y1 is the top left and x2, y2 is the bottom right
"""
w = np.sqrt(x[2] * x[3])
h = x[2] / w
if(score==None):
return np.array([x[0]-w/2., x[1]-h/2., x[0]+w/2., x[1]+h/2.]).reshape((1,4))
else:
return np.array([x[0]-w/2., x[1]-h/2., x[0]+w/2., x[1]+h/2., score]).reshape((1,5))
class KalmanBoxTracker(object):
"""
This class represents the internal state of individual tracked objects observed as bbox.
"""
count = 0
def __init__(self,bbox):
"""
Initialises a tracker using initial bounding box.
"""
#define constant velocity model
self.kf = KalmanFilter(dim_x=7, dim_z=4)
self.kf.F = np.array([[1,0,0,0,1,0,0],[0,1,0,0,0,1,0],[0,0,1,0,0,0,1],[0,0,0,1,0,0,0], [0,0,0,0,1,0,0],[0,0,0,0,0,1,0],[0,0,0,0,0,0,1]])
self.kf.H = np.array([[1,0,0,0,0,0,0],[0,1,0,0,0,0,0],[0,0,1,0,0,0,0],[0,0,0,1,0,0,0]])
self.kf.R[2:,2:] *= 10.
self.kf.P[4:,4:] *= 1000. #give high uncertainty to the unobservable initial velocities
self.kf.P *= 10.
self.kf.Q[-1,-1] *= 0.01
self.kf.Q[4:,4:] *= 0.01
self.kf.x[:4] = convert_bbox_to_z(bbox)
self.time_since_update = 0
self.id = KalmanBoxTracker.count
KalmanBoxTracker.count += 1
self.history = []
self.hits = 0
self.hit_streak = 0
self.age = 0
def update(self,bbox):
"""
Updates the state vector with observed bbox.
"""
self.time_since_update = 0
self.history = []
self.hits += 1
self.hit_streak += 1
self.kf.update(convert_bbox_to_z(bbox))
def predict(self):
"""
Advances the state vector and returns the predicted bounding box estimate.
"""
if((self.kf.x[6]+self.kf.x[2])<=0):
self.kf.x[6] *= 0.0
self.kf.predict()
self.age += 1
if(self.time_since_update>0):
self.hit_streak = 0
self.time_since_update += 1
self.history.append(convert_x_to_bbox(self.kf.x))
return self.history[-1]
def get_state(self):
"""
Returns the current bounding box estimate.
"""
return convert_x_to_bbox(self.kf.x)
def associate_detections_to_trackers(detections,trackers,iou_threshold = 0.3):
"""
Assigns detections to tracked object (both represented as bounding boxes)
Returns 3 lists of matches, unmatched_detections and unmatched_trackers
"""
if(len(trackers)==0):
return np.empty((0,2),dtype=int), np.arange(len(detections)), np.empty((0,5),dtype=int)
iou_matrix = iou_batch(detections, trackers)
if min(iou_matrix.shape) > 0:
a = (iou_matrix > iou_threshold).astype(np.int32)
if a.sum(1).max() == 1 and a.sum(0).max() == 1:
matched_indices = np.stack(np.where(a), axis=1)
else:
matched_indices = linear_assignment(-iou_matrix)
else:
matched_indices = np.empty(shape=(0,2))
unmatched_detections = []
for d, det in enumerate(detections):
if(d not in matched_indices[:,0]):
unmatched_detections.append(d)
unmatched_trackers = []
for t, trk in enumerate(trackers):
if(t not in matched_indices[:,1]):
unmatched_trackers.append(t)
#filter out matched with low IOU
matches = []
for m in matched_indices:
if(iou_matrix[m[0], m[1]]<iou_threshold):
unmatched_detections.append(m[0])
unmatched_trackers.append(m[1])
else:
matches.append(m.reshape(1,2))
if(len(matches)==0):
matches = np.empty((0,2),dtype=int)
else:
matches = np.concatenate(matches,axis=0)
return matches, np.array(unmatched_detections), np.array(unmatched_trackers)
class Sort(object):
def __init__(self, max_age=1, min_hits=3, iou_threshold=0.3):
"""
Sets key parameters for SORT
"""
self.max_age = max_age # time_since_update > max_age, track被清除
self.min_hits = min_hits
self.iou_threshold = iou_threshold
self.trackers = []
self.frame_count = 0
def update(self, dets=np.empty((0, 5))):
"""
Params:
dets - a numpy array of detections in the format [[x1,y1,x2,y2,score],[x1,y1,x2,y2,score],...]
Requires: this method must be called once for each frame even with empty detections (use np.empty((0, 5)) for frames without detections).
Returns the a similar array, where the last column is the object ID.
NOTE: The number of objects returned may differ from the number of detections provided.
"""
self.frame_count += 1
# get predicted locations from existing trackers.
trks = np.zeros((len(self.trackers), 5))
to_del = []
ret = []
for t, trk in enumerate(trks):
pos = self.trackers[t].predict()[0]
trk[:] = [pos[0], pos[1], pos[2], pos[3], 0]
if np.any(np.isnan(pos)):
to_del.append(t)
trks = np.ma.compress_rows(np.ma.masked_invalid(trks))
for t in reversed(to_del):
self.trackers.pop(t)
matched, unmatched_dets, unmatched_trks = associate_detections_to_trackers(dets, trks, self.iou_threshold)
# update matched trackers with assigned detections
for m in matched:
self.trackers[m[1]].update(dets[m[0], :])
# create and initialize new trackers for unmatched detections
for i in unmatched_dets:
trk = KalmanBoxTracker(dets[i,:])
self.trackers.append(trk)
i = len(self.trackers)
for trk in reversed(self.trackers):
d = trk.get_state()[0]
if (trk.time_since_update < 1) and (trk.hit_streak >= self.min_hits or self.frame_count <= self.min_hits):
ret.append(np.concatenate((d, [trk.id+1])).reshape(1,-1)) # +1 as MOT benchmark requires positive
i -= 1
# remove dead tracklet
if(trk.time_since_update > self.max_age):
self.trackers.pop(i)
if(len(ret)>0):
return np.concatenate(ret)
return np.empty((0,5))
if __name__ == '__main__':
mot_tracker = Sort(max_age = 1, # time_since_update>max_age, 清楚在跟目标
min_hits = 3, # hit_streak>min_hits, 转为确认态
iou_threshold = 0.3) # create instance of the SORT tracker
# tflite模型
model_path = '/home/yolov8/models/8086_best_float32.tflite'
# 定义输入输出shape
in_shape = [1 * 640 * 640 * 3 * 4] # HWC, float32
out_shape = [1 * 8400 * 52 * 4] # 8400: total cells, 52 = 48(num_classes) + 4(xywh), float32
# AidLite初始化
aidlite = aidlite_gpu.aidlite()
# 载入模型
res = aidlite.ANNModel(model_path, in_shape, out_shape, 4, 0)
print(res)
''' 读取手机后置摄像头 '''
cap = cvs.VideoCapture(0)
frame_id = 0
while True:
frame = cap.read()
if frame is None:
continue
frame_id += 1
if frame_id % 3 != 0:
continue
time0 = time.time()
# 预处理
img = preprocess_img(frame, target_shape=(640, 640), div_num=255, means=None, stds=None)
aidlite.setInput_Float32(img, 640, 640)
# 推理
aidlite.invoke()
preds = aidlite.getOutput_Float32(0)
preds = preds.reshape(1, 52, 8400)
preds = detect_postprocess(preds, frame.shape, [640, 640, 3], conf_thres=0.25, iou_thres=0.45)
print('1 batch takes {} s'.format(time.time() - time0))
if len(preds) != 0:
preds[:, :4] = scale_boxes([640, 640], preds[:, :4], frame.shape)
''' SORT锁定 '''
preds_out = preds[:, :5] # 数据切片，得到格式如[x1, y1, x2, y2, conf]的ndarray。
trackers = mot_tracker.update(preds_out) # predict -> associate -> update
''' 绘制结果 '''
for d in trackers:
cv2.putText(frame, str(int(d[4])), (int(d[0]), int(d[1])), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 1)
cv2.rectangle(frame, (int(d[0]), int(d[1])), (int(d[2]), int(d[3])), (0, 0, 255),thickness = 2)
cvs.imshow(frame)
本视频为基于AidLux的演示视频，在安卓端实现yolov8实时检测以及sort电力目标锁定功能。
点击下方演示视频即可观看。
