- Notifications
You must be signed in to change notification settings - Fork0
aascer39/smart_classroom
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
课堂专注度及考试作弊系统、课堂动态点名，情绪识别、表情识别和人脸识别结合
相关项目
课堂专注度+表情识别
转头(probe)+低头(peep)+传递物品(passing)
侧面的传递物品识别
1.Halpe dataset (136 keypoints)
| Model | Backbone | Detector | Input Size | AP | Speed | Download | Config | Training Log |
|---|---|---|---|---|---|---|---|---|
| Fast Pose | ResNet50 | YOLOv3 | 256x192 | 69.0 | 3.54 iter/s | GoogleBaidu | cfg | log |
- 放到detection_system/checkpoints
Currently the best performance tracking model. Paper coming soon.
Downloadhuman reid model and place it intoAlphaPose/trackers/weights/.
Then simply run alphapose with additional flag--pose_track
You can try different person reid model by modifingcfg.arch andcfg.loadmodel in./trackers/tracker_cfg.py.
If you want to train your own reid model, please refer to thisproject
Download the object detection model manually:yolov3-spp.weights(Google Drive |Baidu pan). Place it intodetector/yolo/data.
- 放到face_recog/weights文件夹下
百度云 提取码：rwtl
人脸识别：dlib_face_recognition_resnet_model_v1.dat
- detection_system/face_recog/weights
人脸对齐：shape_predictor_68_face_landmarks.dat
- detection_system/face_recog/weights
作弊动作分类器：cheating_detector_rfc_kp.pkl
- detection_system/weights
python setup.py build develop
将detection_system设置为source root
使用摄像头运行程序
python demo_inference.py --vis --webcam 0