https://github.com/lupin1998/adcf_2019
Adaptive Target Tracking Algorithm with Dynamic Weighted Hierarchical Convolutional Neural Network Feature (http://xwxt.sict.ac.cn/CN/abstract/abstract5795.shtml)
https://github.com/lupin1998/adcf_2019
convolutional-neural-networks kcf-tracker pytorch visual-tracking
Last synced: 12 months ago
JSON representation
Adaptive Target Tracking Algorithm with Dynamic Weighted Hierarchical Convolutional Neural Network Feature (http://xwxt.sict.ac.cn/CN/abstract/abstract5795.shtml)
- Host: GitHub
- URL: https://github.com/lupin1998/adcf_2019
- Owner: Lupin1998
- Created: 2019-09-09T03:01:11.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2019-09-09T07:21:18.000Z (over 6 years ago)
- Last Synced: 2025-04-08T09:05:46.916Z (about 1 year ago)
- Topics: convolutional-neural-networks, kcf-tracker, pytorch, visual-tracking
- Language: Python
- Homepage:
- Size: 7.53 MB
- Stars: 3
- Watchers: 1
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# ADCF_2019
code for Adaptive Target Tracking Algorithm with Dynamic Weighted Hierarchical Convolutional Neural Network Feature.
## 1. Intro
- This project includes source code for first experience in our paper based on PyTorch and usage of CNN features.
- For models, inlcuding mainstream models from torchvision [(PyTorch)](https://pytorch.org/docs/stable/torchvision/models.html) in
CNNFeat. Models from tensorflow or caffe should perform better on visual tracking, such as [(pretrained-models)](https://github.com/ZhaoJ9014/face.evoLVe.PyTorch) or [(matconvnet)](https://github.com/vlfeat/matconvnet).
## 2. Install
numpy==1.14.5
torch==0.4.0
torchvision==0.4.0
scipy==1.0.0
opencv_python==3.4.2
matplotlib==2.1.2
numba==0.43.1
pillow==6.1.0
## 3. Usage
- Download seqs [(Visual BenchMark)](http://cvlab.hanyang.ac.kr/tracker_benchmark/datasets.html) and save to Sequence. Change file path before running KCF with CNN features. Choose to run different CNN of single conv-layer or coarse-to-fine features in run.py.
```
python run.py
```
- Visualize different CNN feature maps in CNNfeat. Downloads MobileNet_v3 models in [(mobilenetv3)](https://github.com/xiaolai-sqlai/mobilenetv3).
```
from PIL import Image
from CNN_feat.LightWeight_cnn_feat import LightWeight_feat,LightCNN
net = LightWeight_feat(LightCNN.SqueezeNet.value,'1_1', 1)
# visualize SqueezeNet-1_1 conv1
img = Image.open('Seq/boy/img/0001.jpg')
feat = net.get_cnn_feat(img,True,False,False)
```
- Test old vision of KCF with hog features in 2015-KCF-DSST. Install 'numba' before if using hog features.
```
python run.py
```