Skip to content

Commit e8cb7e4

Browse files
committed
Update readme
1 parent b3f3d8c commit e8cb7e4

File tree

2 files changed

+16
-22
lines changed

2 files changed

+16
-22
lines changed

README.md

Lines changed: 13 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,12 @@ Object detection using deep learning and multi-object tracking
66

77
[![DOI](https://zenodo.org/badge/148338463.svg)](https://zenodo.org/badge/latestdoi/148338463)
88

9+
### Available Trackers
10+
```
11+
SimpleTracker
12+
13+
SimpleTracker2
14+
```
915

1016
#### YOLO
1117
Video Source: [link](https://flic.kr/p/89KYXt)
@@ -39,54 +45,39 @@ pip install -e .
3945

4046
### YOLO
4147

42-
Do the following in the terminal:
48+
Do the following in the terminal to download a pretrained weights of YOLO:
4349
```
4450
cd ./pretrained_models/yolo_weights
4551
sudo chmod +x ./get_yolo.sh
4652
./get_yolo.sh
4753
```
4854

49-
The above commands will download the model and the config files in `./pretrained_models/yolo_weights`.
50-
These weights are to be used in `examples/tracking-yolo-model.ipynb`.
51-
52-
- The video input can be specified in the cell named `Initiate opencv video capture object` in the notebook.
53-
- To make the source as the webcam, use `video_src=0` else provide the path of the video file (example: `video_src="/path/of/videofile.mp4"`).
54-
55-
Example video used in above demo was taken from [here](https://flic.kr/p/L6qyxj)
56-
5755
### TensorFlow model
5856

59-
Do the following in the terminal:
57+
Do the following in the terminal to download a pretrained model:
6058
```
6159
cd ./pretrained_models/tensorflow_weights
6260
sudo chmod +x ./get_ssd_model.sh
6361
./get_ssd_model.sh
6462
```
6563

66-
This will download model and config files in `./pretrained_models/tensorflow_weights`.
67-
These will be used `examples/tracking-tensorflow-ssd_mobilenet_v2_coco_2018_03_29.ipynb`.
68-
6964
**SSD-Mobilenet_v2_coco_2018_03_29** was used for this example.
7065
Other networks can be downloaded and ran: Go through `tracking-tensorflow-ssd_mobilenet_v2_coco_2018_03_29.ipynb` for more details.
7166

72-
- The video input can be specified in the cell named `Initiate opencv video capture object` in the notebook.
73-
- To make the source as the webcam, use `video_src=0` else provide the path of the video file (example: `video_src="/path/of/videofile.mp4"`).
74-
75-
Video used in SSD-Mobilenet multi-object detection and tracking can be found [here](https://flic.kr/p/89KYXt)
76-
7767
### Caffemodel
7868

79-
Do the following in the terminal
69+
Do the following in the terminal to download a pretrained model:
8070
```
8171
cd ./pretrained_models/caffemodel_weights
8272
sudo chmod +x ./get_caffemodel.sh
8373
./get_caffemodel.sh
8474
```
8575

86-
This will download model and config files in `./pretrained_models/caffemodel_weights`.
87-
These will be used `examples/tracking-caffe-model-mobilenetSSD.ipynb`.
76+
This is a MobileNet-SSD caffemodel.
77+
78+
### Examples and How to use:
8879

89-
The caffemodel example provided here also uses MobileNet-SSD model for detection.
80+
For examples and how to use this repository, please refer [examples/](examples/) folder.
9081

9182
### References and Credits
9283
This work is based on the following literature:

examples/readme.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
# multi-object-tracker examples
2+
3+
This folder contains various examples.

0 commit comments

Comments
 (0)