-To train with base weights. It use [./data/train.txt](./data/train.txt) images for training and [./data/val.txt](./data/val.txt) images for validation.
To train with base weights. It use [./data/train.txt](./data/train.txt) images for training and [./data/val.txt](./data/val.txt) images for validation.
```shell
make train_from_base
```
## Detect
\ No newline at end of file
## Detect
```shell
make detect_base_weights # to detect with base weights (adapt the source)
make detect_base_weights_test # to detect with base weights (adapt the source)
make detect_colab_weights_v1 # to detect with colab v1 weights (adapt the source)
make detect_colab_weights_v2 # to detect with colab v2 weights (adapt the source)
make live_cam0 # to detect in real time with colab v2 weights (source 0)
make live_cam2 # to detect in real time with colab v2 weights (source 2)
```
# Next Step
- Estimate the drone position (x,y,z)
-[Dist-YOLO: Fast Object Detection with Distance Estimation](doc/articles/Dist-YOLO_Fast_Object_Detection_with_Distance_Estimation.pdf)
-[Learning Object-Specific Distance From a Monocular Image](doc/articles/Zhu_Learning_Object-Specific_Distance_From_a_Monocular_Image_ICCV_2019_paper.pdf)
``` We present a scheme of how YOLO can be improved in order to predict the absolute distance of objects using only information from a monocular camera.
...
...
@@ -11,7 +11,7 @@ We show that using the KITTI dataset, the proposed scheme yields a mean relative
approaches. Finally, we show that the inference speed is identical to the unmodified YOLO, 45 frames per second.
```
-[Automated Drone Detection Using YOLOv4](doc/articles/Automated_Drone_Detection_Using_YOLOv4.pdf)
-[Automated Drone Detection Using YOLOv4](articles/Automated_Drone_Detection_Using_YOLOv4.pdf)
- abstract:
``` Drones are increasing in popularity and are reaching the public faster than ever before. Consequently, the chances of a drone being misused are multiplying. Automated drone detection is
necessary to prevent unauthorized and unwanted drone interventions. In this research, we designed an automated drone detection system using YOLOv4. The model was trained using drone and
...
...
@@ -21,7 +21,7 @@ better performance than what has been found in previous similar studies, achievi
on the DJI Phantom III and an FPS of 19.0 on the DJI Mavic Pro.
```
-[Learning Object-Specific Distance From a Monocular Image](doc/articles/Zhu_Learning_Object-Specific_Distance_From_a_Monocular_Image_ICCV_2019_paper.pdf)
-[Learning Object-Specific Distance From a Monocular Image](articles/Zhu_Learning_Object-Specific_Distance_From_a_Monocular_Image_ICCV_2019_paper.pdf)
- abstract:
``` Environment perception, including object detection and distance estimation, is one of the most crucial tasks for autonomous driving. Many attentions have been paid on the object detection task, but distance estimation only arouse
few interests in the computer vision community. Observing that the traditional inverse perspective mapping algorithm performs poorly for objects far away from the camera or on the curved road, in this paper, we address the challenging
...
...
@@ -31,7 +31,7 @@ model with a keypoint regressor, where a projection loss is defined to enforce a
road. Moreover, the performance margin implies the effectiveness of our enhanced method
```
-[YOLODrone: Improved YOLO Architecture for Object Detection in Drone Images](doc/articles/YOLODrone_Improved_YOLO_Architecture_for_Object_Detection_in_Drone_Images.pdf)
-[YOLODrone: Improved YOLO Architecture for Object Detection in Drone Images](articles/YOLODrone_Improved_YOLO_Architecture_for_Object_Detection_in_Drone_Images.pdf)
- abstract:
``` Recent advances in robotics and computer vision fields yield emerging new applications for camera equipped drones. One such application is aerial-based object detection. However, despite the recent advances in the relevant literature,
object detection remains as a challenging task in computer vision. Existing object detection algorithms demonstrate even lower performance on drone (or aerial) images since the object detection problem is a more challenging problem in aerial images,
