本文地址：[https://blog.csdn.net/weixin_44936889/article/details/112002152](https://blog.csdn.net/weixin_44936889/article/details/112002152)
# 注意：
本项目使用Yolov5 3.0版本，4.0版本需要替换掉models和utils文件夹
# 项目简介：
使用YOLOv5+Deepsort实现车辆行人追踪和计数，代码封装成一个Detector类，更容易嵌入到自己的项目中。
代码地址（欢迎star）：
[https://github.com/Sharpiless/Yolov5-deepsort-inference](https://github.com/Sharpiless/Yolov5-deepsort-inference)
最终效果：
# YOLOv5检测器：
```python
class Detector(baseDet):
def __init__(self):
super(Detector, self).__init__()
self.init_model()
self.build_config()
def init_model(self):
self.weights = 'weights/yolov5m.pt'
self.device = '0' if torch.cuda.is_available() else 'cpu'
self.device = select_device(self.device)
model = attempt_load(self.weights, map_location=self.device)
model.to(self.device).eval()
model.half()
# torch.save(model, 'test.pt')
self.m = model
self.names = model.module.names if hasattr(
model, 'module') else model.names
def preprocess(self, img):
img0 = img.copy()
img = letterbox(img, new_shape=self.img_size)[0]
img = img[:, :, ::-1].transpose(2, 0, 1)
img = np.ascontiguousarray(img)
img = torch.from_numpy(img).to(self.device)
img = img.half() # 半精度
img /= 255.0 # 图像归一化
if img.ndimension() == 3:
img = img.unsqueeze(0)
return img0, img
def detect(self, im):
im0, img = self.preprocess(im)
pred = self.m(img, augment=False)[0]
pred = pred.float()
pred = non_max_suppression(pred, self.threshold, 0.4)
pred_boxes = []
for det in pred:
if det is not None and len(det):
det[:, :4] = scale_coords(
img.shape[2:], det[:, :4], im0.shape).round()
for *x, conf, cls_id in det:
lbl = self.names[int(cls_id)]
if not lbl in ['person', 'car', 'truck']:
continue
x1, y1 = int(x[0]), int(x[1])
x2, y2 = int(x[2]), int(x[3])
pred_boxes.append(
(x1, y1, x2, y2, lbl, conf))
return im, pred_boxes
```
调用 self.detect 方法返回图像和预测结果
# DeepSort追踪器：
```python
deepsort = DeepSort(cfg.DEEPSORT.REID_CKPT,
max_dist=cfg.DEEPSORT.MAX_DIST, min_confidence=cfg.DEEPSORT.MIN_CONFIDENCE,
nms_max_overlap=cfg.DEEPSORT.NMS_MAX_OVERLAP, max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE,
max_age=cfg.DEEPSORT.MAX_AGE, n_init=cfg.DEEPSORT.N_INIT, nn_budget=cfg.DEEPSORT.NN_BUDGET,
use_cuda=True)
```
调用 self.update 方法更新追踪结果
# 运行demo：
```bash
python demo.py
```
# 训练自己的模型：
参考我的另一篇博客：
[【小白CV】手把手教你用YOLOv5训练自己的数据集（从Windows环境配置到模型部署）](https://blog.csdn.net/weixin_44936889/article/details/110661862)
训练好后放到 weights 文件夹下
# 调用接口：
## 创建检测器：
```python
from AIDetector_pytorch import Detector
det = Detector()
```
## 调用检测接口：
```python
func_status = {}
func_status['headpose'] = None
result = det.feedCap(im, func_status)
```
其中 im 为 BGR 图像
返回的 result 是字典，result['frame'] 返回可视化后的图像
# 关注我的公众号：
感兴趣的同学关注我的公众号——可达鸭的深度学习教程：
# 联系作者：
> B站：[https://space.bilibili.com/470550823](https://space.bilibili.com/470550823)
> CSDN：[https://blog.csdn.net/weixin_44936889](https://blog.csdn.net/weixin_44936889)
> AI Studio：[https://aistudio.baidu.com/aistudio/personalcenter/thirdview/67156](https://aistudio.baidu.com/aistudio/personalcenter/thirdview/67156)
> Github：[https://github.com/Sharpiless](https://github.com/Sharpiless)
遵循 GNU General Public License v3.0 协议，标明目标检测部分来源：https://github.com/ultralytics/yolov5/
Yolov5-deepsort-inference:Yolov5 Deepsort推论，使用YOLOv5 + Deepsort实现车辆行人追踪和计数，代码封装成一个检测器类，更容易嵌入到自己的项目中 （103个子文件） 
.gitkeep 0B
train.jpg 59KB LICENSE 34KB README.md 5KB README.md 65B yolov5m.pt 41.92MB general.py 19KB json_logger.py 11KB yolo.py 10KB torch_utils.py 9KB metrics.py 8KB linear_assignment.py 8KB kalman_filter.py 8KB autoanchor.py 7KB train.py 6KB experimental.py 6KB nn_matching.py 5KB tracker.py 5KB google_utils.py 5KB track.py 5KB io.py 4KB common.py 4KB deep_sort.py 4KB evaluation.py 3KB original_model.py 3KB model.py 3KB iou_matching.py 3KB tracker.py 3KB test.py 2KB activations.py 2KB AIDetector_pytorch.py 2KB preprocessing.py 2KB feature_extractor.py 2KB detection.py 1KB demo.py 1KB draw.py 1KB BaseDetector.py 1KB parser.py 976B tools.py 734B __init__.py 500B log.py 463B asserts.py 316B evaluate.py 293B __init__.py 0B __init__.py 0B __init__.py 0B __init__.py 0B __init__.py 0B datasets.cpython-37.pyc 28KB plots.cpython-37.pyc 14KB general.cpython-36.pyc 14KB general.cpython-37.pyc 14KB torch_utils.cpython-37.pyc 9KB torch_utils.cpython-36.pyc 9KB yolo.cpython-37.pyc 9KB linear_assignment.cpython-37.pyc 7KB linear_assignment.cpython-36.pyc 7KB experimental.cpython-37.pyc 7KB kalman_filter.cpython-36.pyc 7KB metrics.cpython-37.pyc 7KB kalman_filter.cpython-37.pyc 7KB metrics.cpython-36.pyc 7KB nn_matching.cpython-36.pyc 6KB nn_matching.cpython-37.pyc 6KB autoanchor.cpython-37.pyc 6KB common.cpython-37.pyc 6KB loss.cpython-37.pyc 6KB track.cpython-37.pyc 5KB track.cpython-36.pyc 5KB tracker.cpython-37.pyc 5KB tracker.cpython-36.pyc 5KB deep_sort.cpython-37.pyc 4KB deep_sort.cpython-36.pyc 4KB iou_matching.cpython-37.pyc 3KB iou_matching.cpython-36.pyc 3KB google_utils.cpython-37.pyc 3KB model.cpython-37.pyc 3KB model.cpython-36.pyc 3KB google_utils.cpython-36.pyc 3KB feature_extractor.cpython-36.pyc 3KB feature_extractor.cpython-37.pyc 3KB preprocessing.cpython-37.pyc 2KB preprocessing.cpython-36.pyc 2KB detection.cpython-37.pyc 2KB detection.cpython-36.pyc 2KB BaseDetector.cpython-37.pyc 2KB parser.cpython-37.pyc 1KB parser.cpython-36.pyc 1KB __init__.cpython-37.pyc 676B __init__.cpython-36.pyc 672B __init__.cpython-37.pyc 231B __init__.cpython-37.pyc 231B __init__.cpython-36.pyc 227B __init__.cpython-36.pyc 227B __init__.cpython-37.pyc 222B __init__.cpython-37.pyc 221B __init__.cpython-37.pyc 220B __init__.cpython-36.pyc 218B __init__.cpython-36.pyc 127B ckpt.t7 43.9MB共 103 条
- 1
- 2
资源评论
w_wangzi2021-08-18用户下载后在一定时间内未进行评价，系统默认好评。- genos88882021-10-24用户下载后在一定时间内未进行评价，系统默认好评。
刘霏霏
- 粉丝: 35
- 资源: 4717
最新资源
- chromedriver-win64-117.0.5938.0
- 探索NumPy：Python中的多维数组与数值计算
- bsp总结资料合计（2）
- commandline-tools-linux-x64-5.0.3.900.zip.003
- commandline-tools-linux-x64-5.0.3.900.zip.002
- commandline-tools-linux-x64-5.0.3.900.zip.001
- Linkage.msi
- commandline-tools-linux-x64-5.0.3.900.zip.004
- 个人资料-个人资料-个人资料
- Python中Pandas库的数据分析实战指南
资源上传下载、课程学习等过程中有任何疑问或建议，欢迎提出宝贵意见哦~我们会及时处理！
点击此处反馈
